diff --git a/.dockstore.yml b/.dockstore.yml index 2b96a35ab1..4be28e7f9c 100644 --- a/.dockstore.yml +++ b/.dockstore.yml @@ -68,6 +68,10 @@ workflows: subclass: WDL primaryDescriptorPath: /pipelines/broad/dna_seq/germline/joint_genotyping/reblocking/ReblockGVCF.wdl + - name: rnaseq_aou + subclass: WDL + primaryDescriptorPath: /all_of_us/rna_seq/rnaseq_aou.wdl + - name: RNAWithUMIsPipeline subclass: WDL primaryDescriptorPath: /pipelines/broad/rna_seq/RNAWithUMIsPipeline.wdl @@ -90,7 +94,7 @@ workflows: - name: SlideTags subclass: WDL - primaryDescriptorPath: /beta-pipelines/skylab/slidetags/SlideTags.wdl + primaryDescriptorPath: /pipelines/skylab/slidetags/SlideTags.wdl - name: snm3C-seq subclass: WDL @@ -144,6 +148,10 @@ workflows: subclass: WDL primaryDescriptorPath: /verification/test-wdls/TestPairedTag.wdl + - name: TestPeakCalling + subclass: WDL + primaryDescriptorPath: /verification/test-wdls/TestPeakCalling.wdl + - name: TestReblockGVCF subclass: WDL primaryDescriptorPath: /verification/test-wdls/TestReblockGVCF.wdl @@ -156,6 +164,10 @@ workflows: subclass: WDL primaryDescriptorPath: /verification/test-wdls/TestSlideSeq.wdl + - name: TestSlideTags + subclass: WDL + primaryDescriptorPath: /verification/test-wdls/TestSlideTags.wdl + - name: Testsnm3C subclass: WDL primaryDescriptorPath: /verification/test-wdls/Testsnm3C.wdl @@ -200,7 +212,7 @@ workflows: subclass: WDL primaryDescriptorPath: /pipelines/broad/dna_seq/germline/variant_calling/VariantCalling.wdl - - name: vds_to_vcf.wdl + - name: vds_to_vcf subclass: WDL primaryDescriptorPath: /all_of_us/ancestry/vds_to_vcf.wdl diff --git a/.github/workflows/test_peakcalling.yml b/.github/workflows/test_peakcalling.yml new file mode 100644 index 0000000000..c4eb3b1080 --- /dev/null +++ b/.github/workflows/test_peakcalling.yml @@ -0,0 +1,65 @@ +name: Test PeakCalling + +# Controls when the workflow will run +on: + pull_request: + branches: [ "develop", "staging", "master" ] + # Only run if files in these paths changed: + #################################### + # SET PIPELINE SPECIFIC PATHS HERE # + #################################### + paths: + # anything in the pipelines folder + - 'pipelines/skylab/peak_calling/**' + # tasks from the pipeline WDL and their dependencies + - 'tasks/broad/Utilities.wdl' + # verification WDL and its dependencies + - 'verification/VerifyPeakCalling.wdl' + - 'verification/VerifyTasks.wdl' + # test WDL and its dependencies + - 'verification/test-wdls/TestPeakCalling.wdl' + - 'tasks/broad/TerraCopyFilesFromCloudToCloud.wdl' + # this file, the subworkflow file, and the firecloud_api script + - '.github/workflows/test_peakcalling.yml' + - '.github/workflows/warp_test_workflow.yml' + - 'scripts/firecloud_api/firecloud_api.py' + + + # Allows you to run this workflow manually from the Actions tab + workflow_dispatch: + inputs: + useCallCache: + description: 'Use call cache (default: true)' + required: false + default: "true" + updateTruth: + description: 'Update truth files (default: false)' + required: false + default: "false" + testType: + description: 'Specify the type of test (Plumbing or Scientific)' + required: false + type: choice + options: + - Plumbing + - Scientific + truthBranch: + description: 'Specify the branch for truth files (default: master)' + required: false + default: "master" + + +jobs: + TestPeakCalling: + uses: ./.github/workflows/warp_test_workflow.yml + with: + pipeline_name: TestPeakCalling + dockstore_pipeline_name: PeakCalling + pipeline_dir: pipelines/skylab/peak_calling + use_call_cache: ${{ github.event.inputs.useCallCache || 'true' }} + update_truth: ${{ github.event.inputs.updateTruth || 'false' }} + test_type: ${{ github.event.inputs.testType }} + truth_branch: ${{ github.event.inputs.truthBranch || 'master' }} + secrets: + PDT_TESTER_SA_B64: ${{ secrets.PDT_TESTER_SA_B64 }} + DOCKSTORE_TOKEN: ${{ secrets.DOCKSTORE_TOKEN }} \ No newline at end of file diff --git a/.github/workflows/test_slidetags.yml b/.github/workflows/test_slidetags.yml new file mode 100644 index 0000000000..49577cd0d5 --- /dev/null +++ b/.github/workflows/test_slidetags.yml @@ -0,0 +1,68 @@ +name: Test Slide Tags + +# Controls when the workflow will run +on: + pull_request: + branches: [ "develop", "staging", "master" ] + # Only run if files in these paths changed: + #################################### + # SET PIPELINE SPECIFIC PATHS HERE # + #################################### + paths: + # anything in the pipelines folder + - 'pipelines/skylab/slidetags/**' + # tasks from the pipeline WDL and their dependencies + - 'tasks/skylab/StarAlign.wdl' + - 'tasks/skylab/Metrics.wdl' + - 'tasks/skylab/H5adUtils.wdl' + - 'tasks/skylab/CheckInputs.wdl' + - 'tasks/skylab/MergeSortBam.wdl' + - 'tasks/broad/Utilities.wdl' + # verification WDL and its dependencies + - 'verification/VerifySlideTags.wdl' + - 'verification/VerifyTasks.wdl' + # test WDL and its dependencies + - 'verification/test-wdls/TestSlideTags.wdl' + - 'tasks/broad/TerraCopyFilesFromCloudToCloud.wdl' + # this file, the subworkflow file, and the firecloud_api script + - '.github/workflows/test_slidetags.yml' + - '.github/workflows/warp_test_workflow.yml' + - 'scripts/firecloud_api/firecloud_api.py' + + # Allows you to run this workflow manually from the Actions tab + workflow_dispatch: + inputs: + useCallCache: + description: 'Use call cache (default: true)' + required: false + default: "true" + updateTruth: + description: 'Update truth files (default: false)' + required: false + default: "false" + testType: + description: 'Specify the type of test (Plumbing or Scientific)' + required: false + type: choice + options: + - Plumbing + - Scientific + truthBranch: + description: 'Specify the branch for truth files (default: master)' + required: false + default: "master" + +jobs: + TestSlideTags: + uses: ./.github/workflows/warp_test_workflow.yml + with: + pipeline_name: TestSlideTags + dockstore_pipeline_name: SlideTags + pipeline_dir: pipelines/skylab/slidetags + use_call_cache: ${{ github.event.inputs.useCallCache || 'true' }} + update_truth: ${{ github.event.inputs.updateTruth || 'false' }} + test_type: ${{ github.event.inputs.testType }} + truth_branch: ${{ github.event.inputs.truthBranch || 'master' }} + secrets: + PDT_TESTER_SA_B64: ${{ secrets.PDT_TESTER_SA_B64 }} + DOCKSTORE_TOKEN: ${{ secrets.DOCKSTORE_TOKEN }} \ No newline at end of file diff --git a/.github/workflows/warp_test_workflow.yml b/.github/workflows/warp_test_workflow.yml index 8821240785..de4de52698 100644 --- a/.github/workflows/warp_test_workflow.yml +++ b/.github/workflows/warp_test_workflow.yml @@ -211,6 +211,7 @@ jobs: done echo "Error: The Dockstore Commit Hash does not match the GitHub Commit Hash after 15 minutes of retries!" + exit 1 env: GITHUB_COMMIT_HASH: ${{ env.GITHUB_COMMIT_HASH }} @@ -249,19 +250,18 @@ jobs: TEST_TYPE="${{ env.testType }}" INPUTS_DIR="${{ inputs.pipeline_dir }}/test_inputs/$TEST_TYPE" echo "Running tests with test type: $TEST_TYPE" - - TRUTH_PATH="gs://broad-gotc-test-storage/${{ inputs.dockstore_pipeline_name }}/truth/$(echo "$TEST_TYPE" | tr '[:upper:]' '[:lower:]')/$TRUTH_BRANCH" - echo "Truth path: $TRUTH_PATH" RESULTS_PATH="gs://pd-test-results/${{ inputs.dockstore_pipeline_name }}/results/$CURRENT_TIME" + # Submit all jobs first and store their submission IDs for input_file in "$INPUTS_DIR"/*.json; do - test_input_file=$(python3 scripts/firecloud_api/UpdateTestInputs.py --truth_path "$TRUTH_PATH" \ + test_input_file=$(python3 scripts/firecloud_api/UpdateTestInputs.py \ --results_path "$RESULTS_PATH" \ --inputs_json "$input_file" \ --update_truth "$UPDATE_TRUTH_BOOL" \ - --branch_name "$BRANCH_NAME" ) + --branch_name "$TRUTH_BRANCH" \ + --dockstore_pipeline_name "${{ inputs.dockstore_pipeline_name }}" ) echo "Uploading the test input file: $test_input_file" # Create the submission_data.json file for this input_file diff --git a/README.md b/README.md index 98bd29b530..820279db1b 100644 --- a/README.md +++ b/README.md @@ -1,7 +1,7 @@ -### WDL Analysis Research Pipelines +### Warp Analysis Research Pipelines -The WDL Analysis Research Pipelines (WARP) repository is a collection of cloud-optimized pipelines for processing biological data from the Broad Institute Data Sciences Platform and collaborators. +The Warp Analysis Research Pipelines (WARP) repository is a collection of cloud-optimized pipelines for processing biological data from the Broad Institute Data Sciences Platform and collaborators. WARP provides robust, standardized data analysis for the Broad Institute Genomics Platform and large consortia like the Human Cell Atlas and the BRAIN Initiative. WARP pipelines are rigorously scientifically validated, high scale, reproducible and open source, released under the [BSD 3-Clause license](https://github.com/broadinstitute/warp/blob/master/LICENSE). diff --git a/all_of_us/ancestry/README.md b/all_of_us/ancestry/README.md index 08481ec79c..ea12b13e79 100644 --- a/all_of_us/ancestry/README.md +++ b/all_of_us/ancestry/README.md @@ -26,7 +26,7 @@ Key characteristics: #### Step 3. Generate Index Files** - Tabix index files (`.tbi`) are created alongside each VCF output. -### Step 4. Create Lists of Outputs (task: `create_fofn`) +#### Step 4. Create Lists of Outputs (task: `create_fofn`) - Two flat text files (`.fofn1.txt`, `.fofn2.txt`) are generated listing all full VCFs and index files. #### Step 5. Output Final Files diff --git a/all_of_us/ancestry/run_ancestry.changelog.md b/all_of_us/ancestry/run_ancestry.changelog.md index 3bbada97c7..4dd91fdba6 100644 --- a/all_of_us/ancestry/run_ancestry.changelog.md +++ b/all_of_us/ancestry/run_ancestry.changelog.md @@ -1,3 +1,9 @@ +# aou-9.0.0 +2025-05-23 (Date of Last Commit) + +* Updated the gnomad metadata tsv from gnomad.genomes.v3.1.hgdp_1kg_subset.sample_meta.tsv.gz to gs://gcp-public-data--gnomad/release/3.1/secondary_analyses/hgdp_1kg_v2/metadata_and_qc/gnomad_meta_updated.tsv +* Updated which column the workflow uses for population labels; it now applies project_meta.project_pop + # aou-8.0.0 2025-04-16 (Date of Last Commit) diff --git a/all_of_us/ancestry/run_ancestry.wdl b/all_of_us/ancestry/run_ancestry.wdl index 2db0a0da8e..f6379b2efe 100644 --- a/all_of_us/ancestry/run_ancestry.wdl +++ b/all_of_us/ancestry/run_ancestry.wdl @@ -34,9 +34,9 @@ workflow run_ancestry { Int num_pcs=16 } - File hgdp_metadata_file = select_first([hgdp_metadata_file_in, "gs://gcp-public-data--gnomad/release/3.1/vcf/genomes/gnomad.genomes.v3.1.hgdp_1kg_subset.sample_meta.tsv.gz"]) + File hgdp_metadata_file = select_first([hgdp_metadata_file_in, "gs://gcp-public-data--gnomad/release/3.1/secondary_analyses/hgdp_1kg_v2/metadata_and_qc/gnomad_meta_updated.tsv"]) Float other_cutoff = select_first([other_cutoff_in, 0.75]) - String pipeline_version = "aou_8.0.0" + String pipeline_version = "aou_9.0.0" # Train the model on the intersection sites (full version that includes the samples) call create_hw_pca_training { @@ -119,8 +119,8 @@ task create_hw_pca_training { eigenvalues_training, scores_training, loadings_training = get_PCA_scores("~{full_bgz}") # Apply any custom processing to the population labels from the training data - pop_label_pd = metadata_pd[['s', 'population_inference.pop']] - pop_label_pd['pop_label'] = metadata_pd['population_inference.pop'].apply(collapse_fin_to_eur) + pop_label_pd = metadata_pd[['s', 'project_meta.project_pop']] + pop_label_pd['pop_label'] = metadata_pd['project_meta.project_pop'].apply(collapse_fin_to_eur) # Join the labels to the training PCA feature set. pop_label_ht = hl.Table.from_pandas(pop_label_pd).key_by('s') diff --git a/all_of_us/phasing/AoU_VCF.py b/all_of_us/phasing/AoU_VCF.py new file mode 100644 index 0000000000..7de5a4c0dc --- /dev/null +++ b/all_of_us/phasing/AoU_VCF.py @@ -0,0 +1,198 @@ +## SET UP THE ENVIRONMENT +from datetime import datetime +import os +import pandas as pd +import numpy as np +import argparse +import subprocess + + +parser = argparse.ArgumentParser() +parser.add_argument('--contig', help='contig to run, in hg38 format (e.g. chr20)') +parser.add_argument('--temp_bucket', help='GCS bucket used for spark.local.dir, likely the cluster temp bucket') +# INPUTS +parser.add_argument('--input_aou_vds_url', help='GCS url to the AoU-only VDS file to process (e.g. gs://bucket/path/to/file.vds)') +# OUTPUTS +parser.add_argument('--output_aou_vcf_url', help='GCS url where the AoU-only VCF output will be copied') +parser.add_argument('--output_aou_vcf_header_url', help='GCS url where the AoU-only VCF header output will be copied') +parser.add_argument('--output_report_url', help='GCS url where the report output will be copied') +args = parser.parse_args() + + +def run_subprocess(cmd, errorMessage): + if isinstance(cmd, list): + cmd = ' '.join(cmd) + try: + # print("running command: " + cmd) + return subprocess.check_output( + cmd, shell=True, universal_newlines=True) + except subprocess.CalledProcessError as e: + print(errorMessage) + print("Exited with " + str(e.returncode) + "-" + e.output) + exit(1) + + +## START THE TIME COUNTER +start = datetime.now() + +## DEFINE BUCKETS +tmp_bucket = args.temp_bucket + +## RIG DETAILS AND COST +# Main: +# CPUs = 32 +# Memory = 208 +# Disk size = 150 +# Workers: +# Workers = 2 +# Preemptibles = 50 +# CPUs = 4 +# Memory = 26 +# Disk size = 150 +rig_cost=7.80 + +## SET UP HAIL ENVIRONMENT (+ PLOTTING) +import hail as hl + +## BOOT UP HAIL +temp_dir = f'{tmp_bucket}/Stage_1/temp' + +spark_conf_more_ram = dict() +spark_conf_more_ram["spark.executor.memory"] = "8g" +spark_conf_more_ram["spark.executor.cores"] = "4" +spark_conf_more_ram["spark.driver.memory"] = "60g" +spark_conf_more_ram["spark.driver.cores"] = "32" +spark_conf_more_ram["spark.local.dir"] = temp_dir + +hl.init(idempotent=True, + tmp_dir=temp_dir, + spark_conf=spark_conf_more_ram) + +hl.default_reference('GRCh38') + +# DEFINE ALL PATHS +CHR_VAR = args.contig # 'chr20' # VARIABLE!!! + +# INPUTS +AOU_VDS_PATH = args.input_aou_vds_url # 'gs://prod-drc-broad/v8/wgs/vds/aou_srwgs_short_variants_v8r1.vds/merged' + +# OUTPUTS +vcf_url = args.output_aou_vcf_url +vcf_header_url = args.output_aou_vcf_header_url +rep_url = args.output_report_url + +## IMPORT AOU DATA +VDS = hl.vds.read_vds(AOU_VDS_PATH) + +## FILTER VDS TO CHROMOSOME (REGIONAL FILTERING) +VDS_FIL = hl.vds.filter_chromosomes(VDS, keep=CHR_VAR) + +## DENSIFY THE VDS FILE TO MT +mt = hl.vds.to_dense_mt(VDS_FIL) + +## FILTER BY THE NUMBER OF ALT ALLELES +ALT_MAX = 31 # VARIABLE!!! +mt = mt.filter_rows(hl.len(mt.alleles) < (ALT_MAX+2)) + +## ANNOTATE ENTRIES +mt = mt.annotate_entries( + GT = hl.vds.lgt_to_gt(mt.LGT, mt.LA), + AD = hl.vds.local_to_global(mt.LAD, + mt.LA, + n_alleles = hl.len(mt.alleles), + fill_value = 0, + number = 'R')) + +mt = mt.annotate_entries( + sumAD = hl.sum(mt.AD)) + +## ANNOTATE ROWS +mt = hl.variant_qc(mt) + +mt = mt.annotate_rows( + infor = hl.struct(AC = mt.variant_qc.AC[1:], + AF = mt.variant_qc.AF[1:], + AN = mt.variant_qc.AN, + homozygote_count = mt.variant_qc.homozygote_count)) + +mt = mt.annotate_rows( + average_variant_sum_AD = hl.agg.sum(mt.sumAD)/hl.agg.count_where(mt.sumAD >= 0), + maximum_variant_AC = hl.max(mt.infor.AC), + defined_AD = hl.agg.count_where(mt.sumAD >= 0)) + +## DROP FIELDS +fields_to_drop = ['LAD', 'truth_sensitivity_snp_threshold', 'truth_sensitivity_indel_threshold', 'as_vets', + 'LGT', 'LA', 'FT', 'PS', 'RGQ', 'LAD', 'sumAD', 'GQ', 'AD'] + +mt = mt.drop(*fields_to_drop) + +## APPLY ROW FILTERS +# Filter the matrixtable +mt_fil = mt.filter_rows( + ((mt.defined_AD >= 1) & (mt.average_variant_sum_AD < 12.0)) | # VARIABLE!!! + (mt.maximum_variant_AC < 2) | # VARIABLE!!! + ((mt.filters.contains('LowQual')) | # VARIABLE!!! Probably a checkbox? + (mt.filters.contains('NO_HQ_GENOTYPES')) | # VARIABLE!!! Probably a checkbox? + (mt.filters.contains('ExcessHet'))) | # VARIABLE!!! Probably a checkbox? + (mt.variant_qc.call_rate < 0.9) | # VARIABLE!!! + (mt.variant_qc.gq_stats.mean < 30.0), # VARIABLE!!! + keep=False) + +## ANNOTATE INFO FIELDS, REMOVE OTHER ETRANEOUS FIELDS +mt_fil = mt_fil.annotate_rows( + info = hl.struct(GQ = mt_fil.variant_qc.gq_stats.mean, + AC = mt_fil.infor.AC, + AF = mt_fil.infor.AF, + AN = mt_fil.infor.AN, + HC = mt_fil.infor.homozygote_count, + AVSAD = mt_fil.average_variant_sum_AD)) + +fields_to_drop = ['filters', 'variant_qc', 'infor', 'maximum_variant_AC', 'defined_AD', 'average_variant_sum_AD'] + +mt_fil = mt_fil.drop(*fields_to_drop) + +## CREATE AND STORE VCF HEADER +vcf_metadata = """##fileformat=VCFv4.2 +##reference=gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.fasta +##INFO= +##INFO= +##INFO= +##INFO= +##INFO= +##INFO= +""" +vcf_metadata += "#CHROM\tPOS\tID\tREF\tALT\tQUAL\tFILTER\tINFO\tFORMAT\t0000000000" + +local_fname = "tmp_vcf_header.txt" +fp = open(local_fname, 'w') +fp.write(vcf_metadata) +fp.flush() +fp.close() + +run_subprocess(f"gcloud storage cp {local_fname} {vcf_header_url}", f"Error copying header - {local_fname} to {vcf_header_url}") + +## WRITE VCF +hl.export_vcf(mt_fil, + vcf_url, + metadata = hl.get_vcf_metadata(vcf_header_url), + tabix = False) + +## WRITE COST REPORT +end = datetime.now() +time_est = (end - start).total_seconds() / 3600 +cost_est = rig_cost * time_est + +export_report = ( + f"Chro:\t{CHR_VAR}\n" + f"Path:\t{vcf_url}\n" # @Franjo - in other scripts you use NAME_BASE instead of the path - does it matter? + f"Time:\t{time_est}\n" + f"Rigs:\t{rig_cost}\n" + f"Cost:\t{cost_est}") + +local_fname2 = "tmp_vcf_report.txt" +fp = open(local_fname2, 'w') +fp.write(export_report) +fp.flush() +fp.close() + +run_subprocess(f"gcloud storage cp {local_fname2} {rep_url}", f"Error copying report - {local_fname2} to {rep_url}") \ No newline at end of file diff --git a/all_of_us/phasing/README.md b/all_of_us/phasing/README.md new file mode 100644 index 0000000000..70dc350735 --- /dev/null +++ b/all_of_us/phasing/README.md @@ -0,0 +1,57 @@ +# Phasing Pipelines +The following pipelines are used to phase WGS data. + +## filter_and_qc_variants +#### Background + +This WDL workflow processes genomic data by filtering and performing quality control (QC) on variants. +It uses Hail and Google Cloud Dataproc to handle large-scale genomic datasets efficiently. The workflow is tailored +for the hg38 reference genome. Each contig handled separately and requires a separate run of the workflow + +Key characteristics: +- Each chromosome is processed independently. +- Output VCFs are not merged. +- Designed for scalability (e.g., 500k AoU WGS VDS). +- Not compatible with requester-pays buckets in Cromwell. +- Input Data: Accepts a Variant Dataset (VDS) and a UCSC BED file to define genomic regions of interest. + +#### Inputs +Analysis Parameters: +- `String input_aou_vds_url` – URL of the input VDS +- `File submission_script` – Python script executed on the Dataproc cluster; defines filter and QC steps +- `String output_bucket` – GCS bucket for storing outputs +- `String contig` – Contig to process (e.g., "chr21") +- `String prefix` – Prefix for output filenames + +Cluster Parameters: +- `String gcs_project` – Google Cloud project ID +- `String region` – Google Cloud region (default: "us-central1") +- `String master_machine_type` – Machine type for the master node (default: "n1-highmem-32") +- `Float master_memory_fraction` – Memory fraction for the master node (default: 0.8) +- `String worker_machine_type` – Machine type for worker nodes (default: "n1-highmem-4") +- `Int num_workers` – Number of worker nodes (default: 2) +- `Int num_preemptible_workers` – Number of preemptible worker nodes (default: 50) +- `Int time_to_live_minutes` – Time to live for the cluster (default: 2880 minutes) +- `String gcs_subnetwork_name` – Subnetwork name for Dataproc + +Runtime Parameters: +- `RuntimeAttr? runtime_attr_override` – Optional runtime attributes for the job +- `String hail_docker` – Docker image with Hail and Google Cloud SDK + +#### Step 1. FilterAndQCVariants +- Input Validation: Ensures required inputs are provided and properly formatted. +- Cluster Setup: Spins up a Dataproc cluster with user-defined configurations. +- Data Processing: + - Filters variants based on the provided BED file. + - Performs QC on the filtered variants. +- Output Generation: Saves filtered VCFs, headers, and QC reports to the specified GCS bucket. +- Cluster Teardown: Deletes the Dataproc cluster after processing. + +#### Outputs + +- `String aou_vcf` – URL for single chromosome output VCF +- `String aou_vcf_header` – URL for single chromosome output VCF header +- `String report` – URL for the report file + + + diff --git a/all_of_us/phasing/filter_and_qc_variants.wdl b/all_of_us/phasing/filter_and_qc_variants.wdl new file mode 100644 index 0000000000..af4eb89baa --- /dev/null +++ b/all_of_us/phasing/filter_and_qc_variants.wdl @@ -0,0 +1,299 @@ +version 1.0 +# +# Given a VDS and a bed file, render a VCF (sharded by chromosome). +# All bed files referenced in this WDL are UCSC bed files (as opposed to PLINK bed files). +# +# This has not been tested on any reference other than hg38. +# Inputs: +# +# ## ANALYSIS PARAMETERS +# # ie, parameters that go to the Hail python code (submission_script below) +# String vds_url +# +# # Genomic region for the output VCFs to cover +# File bed_url +# +# # VCF Header that will be used in the output +# File vcf_header_url +# +# # Contigs of interest. If a contig is present in the bed file, but not in this list, the contig will be ignored. +# # In other words, this is a contig level intersection with the bed file. +# # This list of contigs that must be present in the reference. Each contig will be processed separately (shard) +# # This list should be ordered. Eg, ["chr21", "chr22"] +# Array[String] contigs +# +# # String used in construction of output filename +# # Cannot contain any special characters, ie, characters must be alphanumeric or "_" +# String prefix +# +# ## CLUSTER PARAMETERS +# # Number of workers (per shard) to use in the Hail cluster. +# Int num_workers +# +# # The Google project ID information is necessary when spinning up dataproc. +# # ie, terra- +# # This must match the workspace that this workflow is being run from. +# # eg, "terra-491d5f31" +# String gcs_project +# +# # Set to 'subnetwork' if running in Terra Cromwell +# String gcs_subnetwork_name='subnetwork' +# +# # The script that is run on the cluster +# # See filter_VDS_and_shard_by_contig.py for an example. +# File submission_script +# +# # Set to "us-central1" if running in Terra Cromwell +# String region = "us-central1" +# +# ## VM PARAMETERS +# # Please note that there is a RuntimeAttr struct and a task parameter that can be used to override the defaults +# # of the VM. These are task parameters. +# # However, since this can be a lightweight VM, overriding is unlikely to be necessary. +# +# # The docker to be used on the VM. This will need both Hail and Google Cloud SDK installed. +# String hail_docker="us.gcr.io/broad-dsde-methods/lichtens/hail_dataproc_wdl:1.0" +# +# Important notes: +# - Hail will save the VCFs in the cloud. You will need to provide this storage space. In other words, the runtime +# parameters must have enough storage space to support a single contig +# - This WDL script is still dependent on the python/Hail script that it calls. You will see this when the parameters +# are passed into the script. +# - This WDL is boilerplate, except for input parameters, output parameters, and where marked in the main task. +# - We HIGHLY recommend that the WDL does NOT run on a preemptible VM +# (reminder, this is a single VM that spins up the dataproc cluster and submits jobs -- it is not doing any of the +# actual computation. In other words, it does not need to be a heavy machine.) +# In other words, always set `preemptible_tries` to zero (default). +# +struct RuntimeAttr { + Float? mem_gb + Int? cpu_cores + Int? disk_gb + Int? boot_disk_gb + Int? preemptible_tries + Int? max_retries +} + +workflow RunAoUAnvilMergeFilterAndQc { + ### Change here: You will need to specify all parameters (both analysis and runtime) that need to go to the + # cluster, VM spinning up the cluster, and the script being run on the cluster. + input { + + ## ANALYSIS PARAMETERS + # ie, parameters that go to the Hail python code (submission_script below) + + # Input files/paths + String aou_vds_url + + # Contigs of interest. If a contig is present in the bed file, but not in this list, the contig will be ignored. + # In other words, this is a contig level intersection with the bed file. + # This list of contigs that must be present in the reference. Each contig will be processed separately (shard) + # This list should be ordered. Eg, ["chr21", "chr22"] + Array[String] contigs + + # String used in construction of output filename + # Cannot contain any special characters, ie, characters must be alphanumeric or "_" + String prefix + + ## CLUSTER PARAMETERS + + # The Google project ID information is necessary when spinning up dataproc. + # ie, terra- + # This must match the workspace that this workflow is being run from. + # eg, "terra-491d5f31" + String gcs_project + + # Set to 'subnetwork' if running in Terra Cromwell + String gcs_subnetwork_name = 'subnetwork' + + # The script that is run on the cluster + File submission_script + + # Bucket used to stage input and output files, likely the workspace bucket. + # Include "gs://" prefix and any subdirectory structure, but no trailing "/" + String output_bucket_path + + # Set to "us-central1" if running in Terra Cromwell + String region = "us-central1" + + ## VM PARAMETERS + # Please note that there is a RuntimeAttr struct and a task parameter that can be used to override the defaults + # of the VM. These are task parameters. + # However, since this can be a lightweight VM, overriding is unlikely to be necessary. + + # The docker to be used on the VM. This will need both Hail and Google Cloud SDK installed. + String hail_docker = "gcr.io/broad-dsde-methods/aou-auxiliary/hail_dataproc_wdl:0.2.130" + } + + # Ensure that trailing slash is included in the output bucket path + String output_bucket_path_with_trailing_slash = sub(output_bucket_path, "/$", "") + "/" + + scatter (contig in contigs) { + + call FilterAndQCVariants { + input: + input_aou_vds_url = aou_vds_url, + contig = contig, + prefix = prefix, + gcs_project = gcs_project, + gcs_subnetwork_name = gcs_subnetwork_name, + submission_script = submission_script, + output_bucket = output_bucket_path_with_trailing_slash, + hail_docker = hail_docker, + region = region + } + } + + output { + # Step 1 + Array[String] aou_vcfs = FilterAndQCVariants.aou_vcf + Array[String] aou_vcf_headers = FilterAndQCVariants.aou_vcf_header + Array[String] step1_reports = FilterAndQCVariants.report + } +} + +task FilterAndQCVariants { + input { + # You must treat a VDS as a String, since it is a directory and not a single file + String input_aou_vds_url + + # Cannot make this localization_optional + File submission_script + String output_bucket + + # contig must be in the reference + String contig + String prefix + + # dataproc params + String gcs_project + String region = "us-central1" + String master_machine_type = "n1-highmem-32" + Float master_memory_fraction = 0.8 + String worker_machine_type = "n1-highmem-4" + Int num_workers = 2 + Int num_preemptible_workers = 50 + Int time_to_live_minutes = 2880 # two days + RuntimeAttr? runtime_attr_override + String gcs_subnetwork_name + + String hail_docker + } + + RuntimeAttr runtime_default = object { + mem_gb: 6.5, + disk_gb: 15, + cpu_cores: 1, + preemptible_tries: 0, + max_retries: 0, + boot_disk_gb: 10 + } + RuntimeAttr runtime_override = select_first([runtime_attr_override, runtime_default]) + + # define output file urls with file names + String output_aou_vcf_url = output_bucket + contig + ".step1.aou.vcf.bgz" + String output_aou_vcf_header_url = output_bucket + contig + ".step1.aou.vcf.header" + String output_report_url = output_bucket + contig + ".step1.report" + + command <<< + set -euxo pipefail + + gcloud config list account --format "value(core.account)" 1> account.txt + + #### TEST: Make sure that this docker image is configured for python3 + if which python3 > /dev/null 2>&1; then + pt3="$(which python3)" + echo "** python3 located at $pt3" + echo "** magic: $(file $pt3)" + echo "** Version info:" + echo "$(python3 -V)" + echo "** -c test" + python3 -c "print('hello world')" + else + echo "!! No 'python3' in path." + exit 1 + fi + #### END TEST + + python3 <>> + + output { + String aou_vcf = output_aou_vcf_url + String aou_vcf_header = output_aou_vcf_header_url + String report = output_report_url + } + + runtime { + memory: select_first([runtime_override.mem_gb, runtime_default.mem_gb]) + " GB" + disks: "local-disk " + select_first([runtime_override.disk_gb, runtime_default.disk_gb]) + " HDD" + cpu: select_first([runtime_override.cpu_cores, runtime_default.cpu_cores]) + preemptible: select_first([runtime_override.preemptible_tries, runtime_default.preemptible_tries]) + maxRetries: select_first([runtime_override.max_retries, runtime_default.max_retries]) + docker: hail_docker + bootDiskSizeGb: select_first([runtime_override.boot_disk_gb, runtime_default.boot_disk_gb]) + } +} + diff --git a/all_of_us/rna_seq/LICENSE.txt b/all_of_us/rna_seq/LICENSE.txt new file mode 100644 index 0000000000..73861f00c6 --- /dev/null +++ b/all_of_us/rna_seq/LICENSE.txt @@ -0,0 +1,26 @@ +Copyright (c) 2016-2018, Broad Institute, Inc. All rights reserved. + +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + +* Redistributions of source code must retain the above copyright notice, this + list of conditions and the following disclaimer. + +* Redistributions in binary form must reproduce the above copyright notice, + this list of conditions and the following disclaimer in the documentation + and/or other materials provided with the distribution. + +* Neither the name Broad Institute, Inc. nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE +DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE +FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL +DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR +SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER +CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, +OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE +OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. \ No newline at end of file diff --git a/all_of_us/rna_seq/markduplicates.wdl b/all_of_us/rna_seq/markduplicates.wdl new file mode 100644 index 0000000000..870d92d11b --- /dev/null +++ b/all_of_us/rna_seq/markduplicates.wdl @@ -0,0 +1,47 @@ +task markduplicates { + + File input_bam + String prefix + Int? max_records_in_ram + Float? sorting_collection_size_ratio + + Float memory + Int java_memory = floor(memory - 0.5) + Int disk_space + Int num_threads + Int num_preempt + + String output_bam = sub(basename(input_bam), "\\.bam$", ".md.bam") + + command { + set -euo pipefail + python3 -u /src/run_MarkDuplicates.py ${input_bam} ${prefix} \ + --memory ${java_memory} \ + ${"--max_records_in_ram " + max_records_in_ram} \ + ${"--sorting_collection_size_ratio " + sorting_collection_size_ratio} + samtools index ${output_bam} + } + + output { + File bam_file = "${output_bam}" + File bam_index = "${output_bam}.bai" + File metrics = "${prefix}.marked_dup_metrics.txt" + } + + runtime { + docker: "gcr.io/broad-cga-francois-gtex/gtex_rnaseq:V10" + memory: "${memory}GB" + disks: "local-disk ${disk_space} HDD" + cpu: "${num_threads}" + preemptible: "${num_preempt}" + } + + meta { + author: "Francois Aguet" + } +} + + +workflow markduplicates_workflow { + call markduplicates +} \ No newline at end of file diff --git a/all_of_us/rna_seq/remove_IDS_reads.wdl b/all_of_us/rna_seq/remove_IDS_reads.wdl new file mode 100644 index 0000000000..28a3f54b93 --- /dev/null +++ b/all_of_us/rna_seq/remove_IDS_reads.wdl @@ -0,0 +1,37 @@ +task remove_IDS_reads { + + File transcriptome_bam + String prefix + + Int memory + Int disk_space + Int num_threads + Int num_preempt + + command { + set -euo pipefail + echo $(date +"[%b %d %H:%M:%S] Running remove_IDS_reads") + /src/run_remove_IDS_reads.sh ${transcriptome_bam} ${prefix} + } + + output { + File transcriptome_noIDS_bam = "${prefix}.Aligned.toTranscriptome_noIDS.out.bam" + } + + runtime { + docker: "gcr.io/broad-cga-francois-gtex/gtex_rnaseq:V10" + memory: "${memory}GB" + disks: "local-disk ${disk_space} HDD" + cpu: "${num_threads}" + preemptible: "${num_preempt}" + } + + meta { + author: "Abhishek Choudhary" + } +} + + +workflow rsem_preprocessing_workflow { + call remove_IDS_reads +} \ No newline at end of file diff --git a/all_of_us/rna_seq/rnaseq_aou.changelog.md b/all_of_us/rna_seq/rnaseq_aou.changelog.md new file mode 100644 index 0000000000..509e6eca61 --- /dev/null +++ b/all_of_us/rna_seq/rnaseq_aou.changelog.md @@ -0,0 +1,7 @@ +# aou-9.0.0 +2025-05-20 (Date of Last Commit) + +* First version of the RNAseq AoU pipeline +* Added pipeline_version to inputs +* Updated the STAR task docker from gcr.io/broad-cga-francois-gtex/gtex_rnaseq:V10 to gcr.io/broad-cga-francois-gtex/gtex_rnaseq@sha256:80c2db3cec3c08630237665e2d2f044f065022e0bbf7a62d0765f51f811818e2 to fix a STAR error for an unrecognized parameter +* Added the remove_ids task from the GTEx GitHub repository diff --git a/all_of_us/rna_seq/rnaseq_aou.wdl b/all_of_us/rna_seq/rnaseq_aou.wdl new file mode 100644 index 0000000000..ad88adb943 --- /dev/null +++ b/all_of_us/rna_seq/rnaseq_aou.wdl @@ -0,0 +1,50 @@ +# import "https://api.firecloud.org/ga4gh/v1/tools/broad_drc_aou_aux:samToFastq/versions/1/plain-WDL/descriptor" as samtofastq_wdl +# import "https://api.firecloud.org/ga4gh/v1/tools/gtex_v10_pg:star_align_v10pg/versions/12/plain-WDL/descriptor" as star_align_wdl +# import "https://api.firecloud.org/ga4gh/v1/tools/gtex_v10_pg:pre_RSEM_processing_v10pg/versions/6/plain-WDL/descriptor" as prersem_wdl +# import "https://api.firecloud.org/ga4gh/v1/tools/broadinstitute_gtex:rsem_v1-0_BETA/versions/6/plain-WDL/descriptor" as rsem_wdl +# #import "https://api.firecloud.org/ga4gh/v1/tools/broad_drc_aou_aux:bamsync_v1-0_BETA_041824_WB/versions/5/plain-WDL/descriptor" as bamsync_wdl +# import "https://api.firecloud.org/ga4gh/v1/tools/broadinstitute_gtex:markduplicates_v1-0_BETA/versions/6/plain-WDL/descriptor" as markduplicates_wdl +# import "https://api.firecloud.org/ga4gh/v1/tools/broadinstitute_gtex:rnaseqc2_v1-0_BETA/versions/4/plain-WDL/descriptor" as rnaseqc_wdl + +import "./samtofastq.wdl" as samtofastq_wdl +import "./star.wdl" as star_align_wdl +import "./markduplicates.wdl" as markduplicates_wdl +import "./rsem.wdl" as rsem_wdl +import "./rnaseqc2.wdl" as rnaseqc_wdl +import "./remove_IDS_reads.wdl" as prersem_wdl + + +workflow rnaseq_pipeline_bam_workflow { + + String prefix + + call samtofastq_wdl.samtofastq { + input: prefix=prefix + } + + call star_align_wdl.star { + input: fastq1=samtofastq.fastq1, fastq2=samtofastq.fastq2, prefix=prefix + } + + call prersem_wdl.remove_IDS_reads { + input: transcriptome_bam=star.transcriptome_bam, prefix=prefix + } + + call rsem_wdl.rsem { + input: transcriptome_bam=remove_IDS_reads.transcriptome_noIDS_bam, prefix=prefix + } + +# call bamsync_wdl.bamsync { +# input: target_bam=star.bam_file, target_bam_index=star.bam_index, prefix=prefix +# } + + call markduplicates_wdl.markduplicates { + #input: input_bam=bamsync.patched_bam_file, prefix=prefix + input: input_bam=star.bam_file, prefix=prefix + + } + + call rnaseqc_wdl.rnaseqc2 { + input: bam_file=markduplicates.bam_file, sample_id=prefix + } +} \ No newline at end of file diff --git a/all_of_us/rna_seq/rnaseqc2.wdl b/all_of_us/rna_seq/rnaseqc2.wdl new file mode 100644 index 0000000000..68538940d0 --- /dev/null +++ b/all_of_us/rna_seq/rnaseqc2.wdl @@ -0,0 +1,53 @@ +task rnaseqc2 { + + File bam_file + File genes_gtf + String sample_id + String? strandedness + File? intervals_bed + File? reference_fasta + File? reference_fasta_index + String? flags + + Int memory + Int disk_space + Int num_threads + Int num_preempt + + command { + set -euo pipefail + echo $(date +"[%b %d %H:%M:%S] Running RNA-SeQC 2") + touch ${sample_id}.fragmentSizes.txt + touch ${sample_id}.gc_content.tsv + rnaseqc ${genes_gtf} ${bam_file} . -s ${sample_id} ${"--bed " + intervals_bed} ${"--stranded " + strandedness} ${"--fasta " + reference_fasta} -vv ${flags} + echo " * compressing outputs" + gzip *.gct + echo $(date +"[%b %d %H:%M:%S] done") + } + + output { + File gene_tpm = "${sample_id}.gene_tpm.gct.gz" + File gene_counts = "${sample_id}.gene_reads.gct.gz" + File exon_counts = "${sample_id}.exon_reads.gct.gz" + File metrics = "${sample_id}.metrics.tsv" + File gc_content = "${sample_id}.gc_content.tsv" + File insertsize_distr = "${sample_id}.fragmentSizes.txt" + } + + runtime { + docker: "gcr.io/broad-cga-francois-gtex/gtex_rnaseq:V10" + memory: "${memory}GB" + disks: "local-disk ${disk_space} HDD" + cpu: "${num_threads}" + preemptible: "${num_preempt}" + } + + meta { + author: "Francois Aguet" + } +} + + +workflow rnaseqc2_workflow { + call rnaseqc2 +} \ No newline at end of file diff --git a/all_of_us/rna_seq/rsem.wdl b/all_of_us/rna_seq/rsem.wdl new file mode 100644 index 0000000000..bf09627c6e --- /dev/null +++ b/all_of_us/rna_seq/rsem.wdl @@ -0,0 +1,53 @@ +task rsem { + + File transcriptome_bam + File rsem_reference + String prefix + + Int memory + Int disk_space + Int num_threads + Int num_preempt + + Int? max_frag_len + String? estimate_rspd + String? is_stranded + String? paired_end + + command { + set -euo pipefail + mkdir rsem_reference + tar -xvvf ${rsem_reference} -C rsem_reference --strip-components=1 + + /src/run_RSEM.py \ + ${"--max_frag_len " + max_frag_len} \ + ${"--estimate_rspd " + estimate_rspd} \ + ${"--is_stranded " + is_stranded} \ + ${"--paired_end " + paired_end} \ + --threads ${num_threads} \ + rsem_reference ${transcriptome_bam} ${prefix} + gzip *.results + } + + output { + File genes="${prefix}.rsem.genes.results.gz" + File isoforms="${prefix}.rsem.isoforms.results.gz" + } + + runtime { + docker: "gcr.io/broad-cga-francois-gtex/gtex_rnaseq:V10" + memory: "${memory}GB" + disks: "local-disk ${disk_space} HDD" + cpu: "${num_threads}" + preemptible: "${num_preempt}" + } + + meta { + author: "Francois Aguet" + } +} + + +workflow rsem_workflow { + call rsem +} \ No newline at end of file diff --git a/all_of_us/rna_seq/samtofastq.wdl b/all_of_us/rna_seq/samtofastq.wdl new file mode 100644 index 0000000000..fa4d74f757 --- /dev/null +++ b/all_of_us/rna_seq/samtofastq.wdl @@ -0,0 +1,49 @@ +task samtofastq { + + File input_bam_cram + String prefix + File? reference_fasta + File? reference_fasta_index + + Float memory + Int java_memory = floor(memory - 0.5) + Int disk_space + Int num_threads + Int num_preempt + + command { + set -euo pipefail + + # make sure path is absolute + input_bam_abs=${input_bam_cram} + if [[ $input_bam_abs != /* ]]; then + input_bam_abs=$PWD/$input_bam_abs + fi + + mkdir samtofastq # workaround for named pipes + python3 -u /src/run_SamToFastq.py $input_bam_abs -p ${prefix} ${"--reference_fasta " + reference_fasta} --output_dir samtofastq --memory ${java_memory} + mv samtofastq/${prefix}_*.fastq.gz . + } + + output { + File fastq1="${prefix}_1.fastq.gz" + File fastq2="${prefix}_2.fastq.gz" + } + + runtime { + docker: "gcr.io/broad-cga-francois-gtex/gtex_rnaseq:V10" + memory: "${memory}GB" + disks: "local-disk ${disk_space} HDD" + cpu: "${num_threads}" + preemptible: "${num_preempt}" + } + + meta { + author: "Francois Aguet" + } +} + + +workflow samtofastq_workflow { + call samtofastq +} \ No newline at end of file diff --git a/all_of_us/rna_seq/star.wdl b/all_of_us/rna_seq/star.wdl new file mode 100644 index 0000000000..8368c48197 --- /dev/null +++ b/all_of_us/rna_seq/star.wdl @@ -0,0 +1,147 @@ +# This wdl comes from https://github.com/broadinstitute/gtex-pipeline/blob/v10_pg_update/rnaseq/star.wdl +task star { + + File fastq1 + File? fastq2 + String prefix + File star_index + + # STAR options + Int? outFilterMultimapNmax + Int? alignSJoverhangMin + Int? alignSJDBoverhangMin + Int? outFilterMismatchNmax + Float? outFilterMismatchNoverLmax + Int? alignIntronMin + Int? alignIntronMax + Int? alignMatesGapMax + String? outFilterType + Float? outFilterScoreMinOverLread + Float? outFilterMatchNminOverLread + Int? limitSjdbInsertNsj + String? outSAMstrandField + String? outFilterIntronMotifs + String? alignSoftClipAtReferenceEnds + String? quantMode + String? outSAMattrRGline + String? outSAMattributes + File? varVCFfile + String? waspOutputMode + Int? chimSegmentMin + Int? chimJunctionOverhangMin + String? chimOutType + Int? chimMainSegmentMultNmax + Int? chimOutJunctionFormat + File? sjdbFileChrStartEnd + String? quantTranscriptomeSAMoutput + Int? winAnchorMultimapNmax + String? genomeTransformOutput + + Int memory + Int disk_space + Int num_threads + Int num_preempt + + command { + set -euo pipefail + + if [[ ${fastq1} == *".tar" || ${fastq1} == *".tar.gz" ]]; then + tar -xvvf ${fastq1} + fastq1_abs=$(for f in *_1.fastq*; do echo "$(pwd)/$f"; done | paste -s -d ',') + fastq2_abs=$(for f in *_2.fastq*; do echo "$(pwd)/$f"; done | paste -s -d ',') + if [[ $fastq1_abs == *"*_1.fastq*" ]]; then # no paired-end FASTQs found; check for single-end FASTQ + fastq1_abs=$(for f in *.fastq*; do echo "$(pwd)/$f"; done | paste -s -d ',') + fastq2_abs='' + fi + else + # make sure paths are absolute + fastq1_abs=${fastq1} + fastq2_abs=${fastq2} + if [[ $fastq1_abs != /* ]]; then + fastq1_abs=$PWD/$fastq1_abs + fastq2_abs=$PWD/$fastq2_abs + fi + fi + + echo "FASTQs:" + echo $fastq1_abs + echo $fastq2_abs + + # extract index + echo $(date +"[%b %d %H:%M:%S] Extracting STAR index") + mkdir star_index + tar -xvvf ${star_index} -C star_index --strip-components=1 + + mkdir star_out + # placeholders for optional outputs + touch star_out/${prefix}.Aligned.toTranscriptome.out.bam + touch star_out/${prefix}.Chimeric.out.junction.gz + touch star_out/${prefix}.Chimeric.out.sorted.bam + touch star_out/${prefix}.Chimeric.out.sorted.bam.bai + touch star_out/${prefix}.ReadsPerGene.out.tab # run_STAR.py will gzip + + /src/run_STAR.py \ + star_index $fastq1_abs $fastq2_abs ${prefix} \ + --output_dir star_out \ + ${"--outFilterMultimapNmax " + outFilterMultimapNmax} \ + ${"--alignSJoverhangMin " + alignSJoverhangMin} \ + ${"--alignSJDBoverhangMin " + alignSJDBoverhangMin} \ + ${"--outFilterMismatchNmax " + outFilterMismatchNmax} \ + ${"--outFilterMismatchNoverLmax " + outFilterMismatchNoverLmax} \ + ${"--alignIntronMin " + alignIntronMin} \ + ${"--alignIntronMax " + alignIntronMax} \ + ${"--alignMatesGapMax " + alignMatesGapMax} \ + ${"--outFilterType " + outFilterType} \ + ${"--outFilterScoreMinOverLread " + outFilterScoreMinOverLread} \ + ${"--outFilterMatchNminOverLread " + outFilterMatchNminOverLread} \ + ${"--limitSjdbInsertNsj " + limitSjdbInsertNsj} \ + ${"--outSAMstrandField " + outSAMstrandField} \ + ${"--outFilterIntronMotifs " + outFilterIntronMotifs} \ + ${"--alignSoftClipAtReferenceEnds " + alignSoftClipAtReferenceEnds} \ + ${"--quantMode " + quantMode} \ + ${"--outSAMattrRGline " + outSAMattrRGline} \ + ${"--outSAMattributes " + outSAMattributes} \ + ${"--varVCFfile " + varVCFfile} \ + ${"--waspOutputMode " + waspOutputMode} \ + ${"--chimSegmentMin " + chimSegmentMin} \ + ${"--chimJunctionOverhangMin " + chimJunctionOverhangMin} \ + ${"--chimOutType " + chimOutType} \ + ${"--chimMainSegmentMultNmax " + chimMainSegmentMultNmax} \ + ${"--chimOutJunctionFormat " + chimOutJunctionFormat} \ + ${"--sjdbFileChrStartEnd " + sjdbFileChrStartEnd} \ + ${"--quantTranscriptomeSAMoutput " + quantTranscriptomeSAMoutput} \ + ${"--winAnchorMultimapNmax " + winAnchorMultimapNmax} \ + ${"--genomeTransformOutput " + genomeTransformOutput} \ + --threads ${num_threads} + } + + output { + File bam_file = "star_out/${prefix}.Aligned.sortedByCoord.out.bam" + File bam_index = "star_out/${prefix}.Aligned.sortedByCoord.out.bam.bai" + File transcriptome_bam = "star_out/${prefix}.Aligned.toTranscriptome.out.bam" + File chimeric_junctions = "star_out/${prefix}.Chimeric.out.junction.gz" + File chimeric_bam_file = "star_out/${prefix}.Chimeric.out.sorted.bam" + File chimeric_bam_index = "star_out/${prefix}.Chimeric.out.sorted.bam.bai" + File read_counts = "star_out/${prefix}.ReadsPerGene.out.tab.gz" + File junctions = "star_out/${prefix}.SJ.out.tab.gz" + File junctions_pass1 = "star_out/${prefix}._STARpass1/${prefix}.SJ.pass1.out.tab.gz" + Array[File] logs = ["star_out/${prefix}.Log.final.out", "star_out/${prefix}.Log.out", "star_out/${prefix}.Log.progress.out"] + } + + runtime { + docker: "gcr.io/broad-cga-francois-gtex/gtex_rnaseq@sha256:80c2db3cec3c08630237665e2d2f044f065022e0bbf7a62d0765f51f811818e2" + memory: "${memory}GB" + disks: "local-disk ${disk_space} HDD" + cpu: "${num_threads}" + preemptible: "${num_preempt}" + } + + meta { + author: "Francois Aguet" + } +} + + +workflow star_workflow { + call star +} \ No newline at end of file diff --git a/beta-pipelines/skylab/slidetags/SlideTags.changelog.md b/beta-pipelines/skylab/slidetags/SlideTags.changelog.md new file mode 100644 index 0000000000..e69de29bb2 diff --git a/beta-pipelines/skylab/slidetags/SlideTags.wdl b/beta-pipelines/skylab/slidetags/SlideTags.wdl index 10eaac7c74..e69de29bb2 100644 --- a/beta-pipelines/skylab/slidetags/SlideTags.wdl +++ b/beta-pipelines/skylab/slidetags/SlideTags.wdl @@ -1,89 +0,0 @@ -version 1.0 - -import "scripts/spatial-count.wdl" as SpatialCount -import "scripts/positioning.wdl" as Positioning -import "../../../pipelines/skylab/optimus/Optimus.wdl" as optimus - -workflow SlideTags { - - String pipeline_version = "1.0.0" - - input { - # slide-tags inputs - String id - Array[String] fastq_paths - Array[String] pucks - Array[String] rna_paths - String sb_path - - # Optimus Inputs - String cloud_provider = "gcp" - String input_id - Int expected_cells = 3000 ## copied from Multiome ? - String counting_mode = "sn_rna" - Array[File] gex_r1_fastq - Array[File] gex_r2_fastq - Array[File]? gex_i1_fastq - File tar_star_reference - File annotations_gtf - File? mt_genes - Int tenx_chemistry_version = 3 - Int emptydrops_lower = 100 - Boolean force_no_check = false - Boolean ignore_r1_read_length = false - String star_strand_mode = "Reverse" - Boolean count_exons = false - File gex_whitelist - String? soloMultiMappers - String? gex_nhash_id - - String docker = "us.gcr.io/broad-gotc-prod/slide-tags:1.1.0" - } - - parameter_meta { - fastq_paths: "Array of paths to spatial fastq files" - pucks: "Array of paths to puck files" - docker: "Docker image to use" - } - - # Call the Optimus workflow - call optimus.Optimus as Optimus { - input: - cloud_provider = cloud_provider, - counting_mode = counting_mode, - r1_fastq = gex_r1_fastq, - r2_fastq = gex_r2_fastq, - i1_fastq = gex_i1_fastq, - input_id = input_id + "_gex", - output_bam_basename = input_id + "_gex", - gex_nhash_id = gex_nhash_id, - tar_star_reference = tar_star_reference, - annotations_gtf = annotations_gtf, - mt_genes = mt_genes, - tenx_chemistry_version = tenx_chemistry_version, - whitelist = gex_whitelist, - emptydrops_lower = emptydrops_lower, - force_no_check = force_no_check, - ignore_r1_read_length = ignore_r1_read_length, - star_strand_mode = star_strand_mode, - count_exons = count_exons, - soloMultiMappers = soloMultiMappers, - gex_expected_cells = expected_cells - } - - call SpatialCount.count as spatial_count { - input: - fastq_paths = fastq_paths, - pucks = pucks, - docker = docker - } - - call Positioning.generate_positioning as positioning { - input: - rna_paths = rna_paths, - sb_path = spatial_count.sb_counts, - docker = docker - } - -} - diff --git a/pipeline_versions.txt b/pipeline_versions.txt index 9410b8374f..2c1d77581a 100644 --- a/pipeline_versions.txt +++ b/pipeline_versions.txt @@ -1,26 +1,27 @@ Pipeline Name Version Date of Last Commit -ArrayImputationQuotaConsumed 1.0.2 2025-04-07 -ImputationBeagle 1.0.2 2025-04-07 -Imputation 1.1.18 2025-04-07 +IlluminaGenotypingArray 1.12.24 2024-11-04 WholeGenomeReprocessing 3.3.4 2025-02-21 ExomeReprocessing 3.3.4 2025-02-21 CramToUnmappedBams 1.1.3 2024-08-02 RNAWithUMIsPipeline 1.0.18 2024-11-04 -IlluminaGenotypingArray 1.12.24 2024-11-04 -UltimaGenomicsWholeGenomeCramOnly 1.1.0 2025-03-17 +ArrayImputationQuotaConsumed 1.0.2 2025-04-07 +ImputationBeagle 1.0.2 2025-04-07 +Imputation 1.1.18 2025-04-07 +UltimaGenomicsWholeGenomeCramOnly 1.1.0 2025-03-17 +JointGenotyping 1.7.2 2024-11-04 +UltimaGenomicsJointGenotyping 1.2.2 2024-11-04 +ReblockGVCF 2.4.1 2025-02-21 UltimaGenomicsWholeGenomeGermline 1.2.0 2025-03-17 WholeGenomeGermlineSingleSample 3.3.4 2025-02-12 ExomeGermlineSingleSample 3.2.4 2025-02-21 VariantCalling 2.2.5 2025-02-21 -ReblockGVCF 2.4.1 2025-02-21 -UltimaGenomicsJointGenotyping 1.2.2 2024-11-04 -JointGenotyping 1.7.2 2024-11-04 -BuildIndices 4.0.0 2025-01-17 -SlideSeq 3.6.0 2025-04-02 -PeakCalling 1.0.0 -PairedTag 2.1.1 -MultiSampleSmartSeq2SingleNucleus 2.2.0 2025-04-02 -atac 2.7.2 2025-04-15 -snm3C 4.0.4 2024-08-06 -Optimus 8.0.0 2025-04-02 -Multiome 6.0.2 25-04-16 +atac 2.7.2 2025-04-15 +Multiome 6.0.3 25-05-27 +BuildIndices 4.0.0 2025-01-17 +Optimus 8.0.1 2025-05-27 +MultiSampleSmartSeq2SingleNucleus 2.2.1 2025-05-27 +SlideSeq 3.6.1 2025-05-27 +snm3C 4.0.4 2024-08-06 +PeakCalling 1.0.0 +SlideTags 1.0.0 +PairedTag 2.1.2 2025-05-27 diff --git a/pipelines/broad/arrays/imputation/test_inputs/Plumbing/NA12878_trio.json b/pipelines/broad/arrays/imputation/test_inputs/Plumbing/NA12878_trio.json index 2857a6f576..6830a61534 100644 --- a/pipelines/broad/arrays/imputation/test_inputs/Plumbing/NA12878_trio.json +++ b/pipelines/broad/arrays/imputation/test_inputs/Plumbing/NA12878_trio.json @@ -1,13 +1,13 @@ { "Imputation.single_sample_vcfs": [ - "gs://broad-gotc-test-storage/imputation/plumbing/vcfs/101342370027_R02C01.vcf.gz", - "gs://broad-gotc-test-storage/imputation/plumbing/vcfs/101342370027_R12C02.vcf.gz", - "gs://broad-gotc-test-storage/imputation/plumbing/vcfs/101342370134_R12C02.vcf.gz" + "gs://pd-test-storage-private/Imputation/input/plumbing/NA12878_trio/101342370027_R02C01.vcf.gz", + "gs://pd-test-storage-private/Imputation/input/plumbing/NA12878_trio/101342370027_R12C02.vcf.gz", + "gs://pd-test-storage-private/Imputation/input/plumbing/NA12878_trio/101342370134_R12C02.vcf.gz" ], "Imputation.single_sample_vcf_indices": [ - "gs://broad-gotc-test-storage/imputation/plumbing/vcfs/101342370027_R02C01.vcf.gz.tbi", - "gs://broad-gotc-test-storage/imputation/plumbing/vcfs/101342370027_R12C02.vcf.gz.tbi", - "gs://broad-gotc-test-storage/imputation/plumbing/vcfs/101342370134_R12C02.vcf.gz.tbi" + "gs://pd-test-storage-private/Imputation/input/plumbing/NA12878_trio/101342370027_R02C01.vcf.gz.tbi", + "gs://pd-test-storage-private/Imputation/input/plumbing/NA12878_trio/101342370027_R12C02.vcf.gz.tbi", + "gs://pd-test-storage-private/Imputation/input/plumbing/NA12878_trio/101342370134_R12C02.vcf.gz.tbi" ], "Imputation.ref_dict": "gs://gcp-public-data--broad-references/hg19/v0/Homo_sapiens_assembly19.dict", "Imputation.reference_panel_path": "gs://gcp-public-data--broad-references/hg19/v0/1000G_reference_panel/", diff --git a/pipelines/broad/arrays/imputation/test_inputs/Scientific/NA12878_trio_scientific.json b/pipelines/broad/arrays/imputation/test_inputs/Scientific/NA12878_trio_scientific.json index 0596ac2577..1c844afce5 100644 --- a/pipelines/broad/arrays/imputation/test_inputs/Scientific/NA12878_trio_scientific.json +++ b/pipelines/broad/arrays/imputation/test_inputs/Scientific/NA12878_trio_scientific.json @@ -1,18 +1,18 @@ { "Imputation.single_sample_vcfs": [ - "gs://broad-gotc-test-storage/imputation/scientific/vcfs/101342370027_R02C01.vcf.gz", - "gs://broad-gotc-test-storage/imputation/scientific/vcfs/101342370027_R12C02.vcf.gz", - "gs://broad-gotc-test-storage/imputation/scientific/vcfs/101342370134_R12C02.vcf.gz" + "gs://pd-test-storage-private/Imputation/input/scientific/NA12878_trio_scientific/101342370027_R02C01.vcf.gz", + "gs://pd-test-storage-private/Imputation/input/scientific/NA12878_trio_scientific/101342370027_R12C02.vcf.gz", + "gs://pd-test-storage-private/Imputation/input/scientific/NA12878_trio_scientific/101342370134_R12C02.vcf.gz" ], "Imputation.single_sample_vcf_indices": [ - "gs://broad-gotc-test-storage/imputation/scientific/vcfs/101342370027_R02C01.vcf.gz.tbi", - "gs://broad-gotc-test-storage/imputation/scientific/vcfs/101342370027_R12C02.vcf.gz.tbi", - "gs://broad-gotc-test-storage/imputation/scientific/vcfs/101342370134_R12C02.vcf.gz.tbi" + "gs://pd-test-storage-private/Imputation/input/scientific/NA12878_trio_scientific/101342370027_R02C01.vcf.gz.tbi", + "gs://pd-test-storage-private/Imputation/input/scientific/NA12878_trio_scientific/101342370027_R12C02.vcf.gz.tbi", + "gs://pd-test-storage-private/Imputation/input/scientific/NA12878_trio_scientific/101342370134_R12C02.vcf.gz.tbi" ], "Imputation.ref_dict": "gs://gcp-public-data--broad-references/hg19/v0/Homo_sapiens_assembly19.dict", "Imputation.reference_panel_path": "gs://gcp-public-data--broad-references/hg19/v0/1000G_reference_panel/", "Imputation.contigs": [ "1", "2", "3", "4", "5", "6", "7", "8", "9", "10", "11", "12", "13", "14", "15", "16", "17", "18", "19", "20", "21", "22" ], - "Imputation.genetic_maps_eagle": "gs://broad-gotc-test-storage/imputation/eagle_genetic_map/genetic_map_hg19_withX.txt.gz", + "Imputation.genetic_maps_eagle": "gs://pd-test-storage-private/Imputation/input/scientific/NA12878_trio_scientific/genetic_map_hg19_withX.txt.gz", "Imputation.output_callset_name": "scientific_test", "Imputation.split_output_to_single_sample": false, "Imputation.perform_extra_qc_steps": false, diff --git a/pipelines/broad/arrays/imputation/test_inputs/Scientific/multi_sample_split_test_data_NOT_PUBLIC.json b/pipelines/broad/arrays/imputation/test_inputs/Scientific/multi_sample_split_test_data_NOT_PUBLIC.json index 08f855bfd1..1c3dea1836 100644 --- a/pipelines/broad/arrays/imputation/test_inputs/Scientific/multi_sample_split_test_data_NOT_PUBLIC.json +++ b/pipelines/broad/arrays/imputation/test_inputs/Scientific/multi_sample_split_test_data_NOT_PUBLIC.json @@ -1,6 +1,6 @@ { - "Imputation.multi_sample_vcf": "gs://broad-gotc-test-storage/imputation/scientific/vcfs/merged_input_samples.vcf.gz", - "Imputation.multi_sample_vcf_index": "gs://broad-gotc-test-storage/imputation/scientific/vcfs/merged_input_samples.vcf.gz.tbi", + "Imputation.multi_sample_vcf": "gs://pd-test-storage-private/Imputation/input/scientific/multi_sample_split_test_data_NOT_PUBLIC/merged_input_samples.vcf.gz", + "Imputation.multi_sample_vcf_index": "gs://pd-test-storage-private/Imputation/input/scientific/multi_sample_split_test_data_NOT_PUBLIC/merged_input_samples.vcf.gz.tbi", "Imputation.ref_dict": "gs://gcp-public-data--broad-references/hg19/v0/Homo_sapiens_assembly19.dict", "Imputation.reference_panel_path": "gs://gcp-public-data--broad-references/hg19/v0/1000G_reference_panel/", "Imputation.contigs": [ "21", "22" ], diff --git a/pipelines/broad/arrays/imputation/test_inputs/Scientific/multi_sample_test_data_NOT_PUBLIC.json b/pipelines/broad/arrays/imputation/test_inputs/Scientific/multi_sample_test_data_NOT_PUBLIC.json index ce7aa3e1af..64f6776810 100644 --- a/pipelines/broad/arrays/imputation/test_inputs/Scientific/multi_sample_test_data_NOT_PUBLIC.json +++ b/pipelines/broad/arrays/imputation/test_inputs/Scientific/multi_sample_test_data_NOT_PUBLIC.json @@ -1,6 +1,6 @@ { - "Imputation.multi_sample_vcf": "gs://broad-gotc-test-storage/imputation/scientific/vcfs/merged_input_samples.vcf.gz", - "Imputation.multi_sample_vcf_index": "gs://broad-gotc-test-storage/imputation/scientific/vcfs/merged_input_samples.vcf.gz.tbi", + "Imputation.multi_sample_vcf": "gs://pd-test-storage-private/Imputation/input/scientific/multi_sample_test_data_NOT_PUBLIC/merged_input_samples.vcf.gz", + "Imputation.multi_sample_vcf_index": "gs://pd-test-storage-private/Imputation/input/scientific/multi_sample_test_data_NOT_PUBLIC/merged_input_samples.vcf.gz.tbi", "Imputation.ref_dict": "gs://gcp-public-data--broad-references/hg19/v0/Homo_sapiens_assembly19.dict", "Imputation.reference_panel_path": "gs://gcp-public-data--broad-references/hg19/v0/1000G_reference_panel/", "Imputation.contigs": [ "21", "22" ], diff --git a/pipelines/broad/arrays/imputation_beagle/test_inputs/Plumbing/NA12878_x10_hg38_arrays.json b/pipelines/broad/arrays/imputation_beagle/test_inputs/Plumbing/NA12878_x10_hg38_arrays.json index bdf5a00597..fa9d0eef73 100644 --- a/pipelines/broad/arrays/imputation_beagle/test_inputs/Plumbing/NA12878_x10_hg38_arrays.json +++ b/pipelines/broad/arrays/imputation_beagle/test_inputs/Plumbing/NA12878_x10_hg38_arrays.json @@ -1,8 +1,8 @@ { - "ImputationBeagle.multi_sample_vcf": "gs://broad-gotc-test-storage/imputation_beagle/scientific/vcfs/NA12878_10_duplicate.merged.cleaned.vcf.gz", + "ImputationBeagle.multi_sample_vcf": "gs://pd-test-storage-public/ImputationBeagle/input/plumbing/NA12878_x10_hg38_arrays/NA12878_10_duplicate.merged.cleaned.vcf.gz", "ImputationBeagle.ref_dict": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.dict", - "ImputationBeagle.reference_panel_path_prefix": "gs://broad-gotc-test-storage/imputation_beagle/scientific/1000G_HGDP_no_singletons_reference_panel/hgdp.tgp.gwaspy.AN_added.bcf.ac2", + "ImputationBeagle.reference_panel_path_prefix": "gs://pd-test-storage-public/ImputationBeagle/input/plumbing/NA12878_x10_hg38_arrays/1000G_HGDP_no_singletons_reference_panel/hgdp.tgp.gwaspy.AN_added.bcf.ac2", "ImputationBeagle.contigs": ["chr21","chr22"], - "ImputationBeagle.genetic_maps_path": "gs://broad-gotc-test-storage/imputation_beagle/scientific/plink-genetic-maps/", + "ImputationBeagle.genetic_maps_path": "gs://pd-test-storage-public/ImputationBeagle/input/plumbing/NA12878_x10_hg38_arrays/plink-genetic-maps/", "ImputationBeagle.output_basename": "plumbing_test" } diff --git a/pipelines/broad/arrays/imputation_beagle/test_inputs/Scientific/NA12878_x10_hg38_arrays.json b/pipelines/broad/arrays/imputation_beagle/test_inputs/Scientific/NA12878_x10_hg38_arrays.json index 4263609e29..821b09dcf1 100644 --- a/pipelines/broad/arrays/imputation_beagle/test_inputs/Scientific/NA12878_x10_hg38_arrays.json +++ b/pipelines/broad/arrays/imputation_beagle/test_inputs/Scientific/NA12878_x10_hg38_arrays.json @@ -1,8 +1,8 @@ { - "ImputationBeagle.multi_sample_vcf": "gs://broad-gotc-test-storage/imputation_beagle/scientific/vcfs/NA12878_10_duplicate.merged.cleaned.vcf.gz", + "ImputationBeagle.multi_sample_vcf": "gs://pd-test-storage-public/ImputationBeagle/input/scientific/NA12878_x10_hg38_arrays/NA12878_10_duplicate.merged.cleaned.vcf.gz", "ImputationBeagle.ref_dict": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.dict", - "ImputationBeagle.reference_panel_path_prefix": "gs://broad-gotc-test-storage/imputation_beagle/scientific/1000G_HGDP_no_singletons_reference_panel/hgdp.tgp.gwaspy.AN_added.bcf.ac2", + "ImputationBeagle.reference_panel_path_prefix": "gs://pd-test-storage-public/ImputationBeagle/input/scientific/NA12878_x10_hg38_arrays/1000G_HGDP_no_singletons_reference_panel/hgdp.tgp.gwaspy.AN_added.bcf.ac2", "ImputationBeagle.contigs": ["chr1","chr2","chr3","chr4","chr5","chr6","chr7","chr8","chr9","chr10","chr11","chr12","chr13","chr14","chr15","chr16","chr17","chr18","chr19","chr20","chr21","chr22"], - "ImputationBeagle.genetic_maps_path": "gs://broad-gotc-test-storage/imputation_beagle/scientific/plink-genetic-maps/", + "ImputationBeagle.genetic_maps_path": "gs://pd-test-storage-public/ImputationBeagle/input/scientific/NA12878_x10_hg38_arrays/plink-genetic-maps/", "ImputationBeagle.output_basename": "scientific_test" } diff --git a/pipelines/broad/dna_seq/germline/joint_genotyping/UltimaGenomics/test_inputs/Plumbing/jg_ug_test_sample_map.list b/pipelines/broad/dna_seq/germline/joint_genotyping/UltimaGenomics/test_inputs/Plumbing/jg_ug_test_sample_map.list index c03f86c3f3..5b87b88c59 100644 --- a/pipelines/broad/dna_seq/germline/joint_genotyping/UltimaGenomics/test_inputs/Plumbing/jg_ug_test_sample_map.list +++ b/pipelines/broad/dna_seq/germline/joint_genotyping/UltimaGenomics/test_inputs/Plumbing/jg_ug_test_sample_map.list @@ -1,10 +1,10 @@ -HG02586 gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/plumbing/jg_ug_test_samples/HG02586.annotated.rb.g.vcf.gz -NA24695 gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/plumbing/jg_ug_test_samples/NA24695.annotated.rb.g.vcf.gz -NA12891 gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/plumbing/jg_ug_test_samples/NA12891.annotated.rb.g.vcf.gz -NA24694 gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/plumbing/jg_ug_test_samples/NA24694.annotated.rb.g.vcf.gz -NA24149 gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/plumbing/jg_ug_test_samples/NA24149.annotated.rb.g.vcf.gz -NA12878 gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/plumbing/jg_ug_test_samples/NA12878.annotated.rb.g.vcf.gz -NA24631 gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/plumbing/jg_ug_test_samples/NA24631.annotated.rb.g.vcf.gz -NA24385 gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/plumbing/jg_ug_test_samples/NA24385.annotated.rb.g.vcf.gz -NA24143 gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/plumbing/jg_ug_test_samples/NA24143.annotated.rb.g.vcf.gz -NA12892 gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/plumbing/jg_ug_test_samples/NA12892.annotated.rb.g.vcf.gz \ No newline at end of file +HG02586 gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/plumbing/plumbing.inputs/sample_map/HG02586.annotated.rb.g.vcf.gz +NA24695 gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/plumbing/plumbing.inputs/sample_map/NA24695.annotated.rb.g.vcf.gz +NA12891 gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/plumbing/plumbing.inputs/sample_map/NA12891.annotated.rb.g.vcf.gz +NA24694 gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/plumbing/plumbing.inputs/sample_map/NA24694.annotated.rb.g.vcf.gz +NA24149 gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/plumbing/plumbing.inputs/sample_map/NA24149.annotated.rb.g.vcf.gz +NA12878 gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/plumbing/plumbing.inputs/sample_map/NA12878.annotated.rb.g.vcf.gz +NA24631 gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/plumbing/plumbing.inputs/sample_map/NA24631.annotated.rb.g.vcf.gz +NA24385 gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/plumbing/plumbing.inputs/sample_map/NA24385.annotated.rb.g.vcf.gz +NA24143 gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/plumbing/plumbing.inputs/sample_map/NA24143.annotated.rb.g.vcf.gz +NA12892 gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/plumbing/plumbing.inputs/sample_map/NA12892.annotated.rb.g.vcf.gz \ No newline at end of file diff --git a/pipelines/broad/dna_seq/germline/joint_genotyping/UltimaGenomics/test_inputs/Plumbing/plumbing.inputs.json b/pipelines/broad/dna_seq/germline/joint_genotyping/UltimaGenomics/test_inputs/Plumbing/plumbing.inputs.json index 3dc1a947c6..f212b70659 100644 --- a/pipelines/broad/dna_seq/germline/joint_genotyping/UltimaGenomics/test_inputs/Plumbing/plumbing.inputs.json +++ b/pipelines/broad/dna_seq/germline/joint_genotyping/UltimaGenomics/test_inputs/Plumbing/plumbing.inputs.json @@ -10,19 +10,19 @@ "UltimaGenomicsJointGenotyping.ref_dict":"gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.dict", "UltimaGenomicsJointGenotyping.ref_fasta":"gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.fasta", "UltimaGenomicsJointGenotyping.ref_fasta_index":"gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.fasta.fai", -"UltimaGenomicsJointGenotyping.sample_name_map":"gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/plumbing/jg_ug_test_sample_map.list", +"UltimaGenomicsJointGenotyping.sample_name_map":"gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/plumbing/plumbing.inputs/sample_map/jg_ug_test_sample_map.list", "UltimaGenomicsJointGenotyping.scatter_cross_check_fingerprints":false, "UltimaGenomicsJointGenotyping.unbounded_scatter_count_scale_factor":2.5, "UltimaGenomicsJointGenotyping.unpadded_intervals_file":"gs://gcp-public-data--broad-references/hg38/v0/hg38.even.handcurated.20k.intervals", "UltimaGenomicsJointGenotyping.snp_annotations": ["AS_ReadPosRankSum", "AS_FS", "AS_SOR", "AS_QD", "AVERAGE_TREE_SCORE", "AVERAGE_ASSEMBLED_HAPS", "AVERAGE_FILTERED_HAPS"], "UltimaGenomicsJointGenotyping.indel_annotations": ["AS_MQRankSum", "AS_ReadPosRankSum", "AS_FS", "AS_SOR", "AS_QD", "AVERAGE_TREE_SCORE"], "UltimaGenomicsJointGenotyping.flow_order": "TGCA", -"UltimaGenomicsJointGenotyping.ref_fasta_sdf": "gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/plumbing/reference_sdf.tar", -"UltimaGenomicsJointGenotyping.runs_file": "gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/plumbing/runs.conservative.bed", -"UltimaGenomicsJointGenotyping.annotation_intervals": ["gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/plumbing/LCR-hs38.bed", "gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/plumbing/mappability.0.bed", "gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/plumbing/exome.twist.bed"], -"UltimaGenomicsJointGenotyping.truth_vcf":"gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/plumbing/HG001_GRCh38_GIAB_highconf_CG-IllFB-IllGATKHC-Ion-10X-SOLID_CHROM1-X_v.3.3.2_highconf_PGandRTGphasetransfer.broad-header.vcf.gz", -"UltimaGenomicsJointGenotyping.truth_vcf_index":"gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/plumbing/HG001_GRCh38_GIAB_highconf_CG-IllFB-IllGATKHC-Ion-10X-SOLID_CHROM1-X_v.3.3.2_highconf_PGandRTGphasetransfer.broad-header.vcf.gz", -"UltimaGenomicsJointGenotyping.truth_highconf_intervals": "gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/plumbing/HG001_GRCh38_GIAB_highconf_CG-IllFB-IllGATKHC-Ion-10X-SOLID_CHROM1-X_v.3.3.2_highconf_nosomaticdel_noCENorHET7.bed", +"UltimaGenomicsJointGenotyping.ref_fasta_sdf": "gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/plumbing/plumbing.inputs/reference_sdf.tar", +"UltimaGenomicsJointGenotyping.runs_file": "gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/plumbing/plumbing.inputs/runs.conservative.bed", +"UltimaGenomicsJointGenotyping.annotation_intervals": ["gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/plumbing/plumbing.inputs/LCR-hs38.bed", "gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/plumbing/plumbing.inputs/mappability.0.bed", "gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/plumbing/plumbing.inputs/exome.twist.bed"], +"UltimaGenomicsJointGenotyping.truth_vcf":"gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/plumbing/plumbing.inputs/HG001_GRCh38_GIAB_highconf_CG-IllFB-IllGATKHC-Ion-10X-SOLID_CHROM1-X_v.3.3.2_highconf_PGandRTGphasetransfer.broad-header.vcf.gz", +"UltimaGenomicsJointGenotyping.truth_vcf_index":"gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/plumbing/plumbing.inputs/HG001_GRCh38_GIAB_highconf_CG-IllFB-IllGATKHC-Ion-10X-SOLID_CHROM1-X_v.3.3.2_highconf_PGandRTGphasetransfer.broad-header.vcf.gz", +"UltimaGenomicsJointGenotyping.truth_highconf_intervals": "gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/plumbing/plumbing.inputs/HG001_GRCh38_GIAB_highconf_CG-IllFB-IllGATKHC-Ion-10X-SOLID_CHROM1-X_v.3.3.2_highconf_nosomaticdel_noCENorHET7.bed", "UltimaGenomicsJointGenotyping.call_sample_name": "NA12878", "UltimaGenomicsJointGenotyping.truth_sample_name": "HG001", "UltimaGenomicsJointGenotyping.model_backend": "PYTHON_IFOREST", diff --git a/pipelines/broad/dna_seq/germline/joint_genotyping/UltimaGenomics/test_inputs/Scientific/jg_ug_scientific_test_sample_map.list b/pipelines/broad/dna_seq/germline/joint_genotyping/UltimaGenomics/test_inputs/Scientific/jg_ug_scientific_test_sample_map.list index 320797f62f..33d522a697 100644 --- a/pipelines/broad/dna_seq/germline/joint_genotyping/UltimaGenomics/test_inputs/Scientific/jg_ug_scientific_test_sample_map.list +++ b/pipelines/broad/dna_seq/germline/joint_genotyping/UltimaGenomics/test_inputs/Scientific/jg_ug_scientific_test_sample_map.list @@ -1,70 +1,70 @@ -NA20502 gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/scientific/jg_ug_scientific_samples/002129-X0024.annotated.NA20502.rb.g.vcf.gz -NA18530 gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/scientific/jg_ug_scientific_samples/002129-X0048.annotated.NA18530.rb.g.vcf.gz -NA20509 gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/scientific/jg_ug_scientific_samples/002188-X0039.annotated.NA20509.rb.g.vcf.gz -NA24385 gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/scientific/jg_ug_scientific_samples/002436-X0004.annotated.NA24385.rb.g.vcf.gz -NA24149 gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/scientific/jg_ug_scientific_samples/002436-X0012.annotated.NA24149.rb.g.vcf.gz -NA12892 gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/scientific/jg_ug_scientific_samples/002448-X0001.annotated.NA12892.rb.g.vcf.gz -NA19001 gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/scientific/jg_ug_scientific_samples/002467-X0005.annotated.NA19001.rb.g.vcf.gz -NA18941 gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/scientific/jg_ug_scientific_samples/002467-X0013.annotated.NA18941.rb.g.vcf.gz -NA18499 gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/scientific/jg_ug_scientific_samples/002467-X0020.annotated.NA18499.rb.g.vcf.gz -NA18507 gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/scientific/jg_ug_scientific_samples/002467-X0028.annotated.NA18507.rb.g.vcf.gz -NA19788 gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/scientific/jg_ug_scientific_samples/002483-X0005.annotated.NA19788.rb.g.vcf.gz -NA18539 gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/scientific/jg_ug_scientific_samples/002483-X0020.annotated.NA18539.rb.g.vcf.gz -NA18560 gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/scientific/jg_ug_scientific_samples/002494-X0009.annotated.NA18560.rb.g.vcf.gz -NA21102 gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/scientific/jg_ug_scientific_samples/002494-X0033.annotated.NA21102.rb.g.vcf.gz -NA18995 gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/scientific/jg_ug_scientific_samples/002495-X0006.annotated.NA18995.rb.g.vcf.gz -NA20869 gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/scientific/jg_ug_scientific_samples/002495-X0014.annotated.NA20869.rb.g.vcf.gz -NA19062 gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/scientific/jg_ug_scientific_samples/002495-X0021.annotated.NA19062.rb.g.vcf.gz -NA20802 gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/scientific/jg_ug_scientific_samples/002495-X0029.annotated.NA20802.rb.g.vcf.gz -NA19377 gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/scientific/jg_ug_scientific_samples/004701-X0023.annotated.NA19377.rb.g.vcf.gz -NA20126 gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/scientific/jg_ug_scientific_samples/004701-X0038.annotated.NA20126.rb.g.vcf.gz -NA18930 gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/scientific/jg_ug_scientific_samples/004707-X0005.annotated.NA18930.rb.g.vcf.gz -NA19900 gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/scientific/jg_ug_scientific_samples/004707-X0012.annotated.NA19900.rb.g.vcf.gz -NA19901 gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/scientific/jg_ug_scientific_samples/004707-X0020.annotated.NA19901.rb.g.vcf.gz -NA19035 gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/scientific/jg_ug_scientific_samples/004707-X0036.annotated.NA19035.rb.g.vcf.gz -NA19789 gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/scientific/jg_ug_scientific_samples/004707-X0044.annotated.NA19789.rb.g.vcf.gz -NA20895 gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/scientific/jg_ug_scientific_samples/004710-X0042.annotated.NA20895.rb.g.vcf.gz -NA24631 gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/scientific/jg_ug_scientific_samples/004711-X0039.annotated.NA24631.rb.g.vcf.gz -NA21133 gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/scientific/jg_ug_scientific_samples/004713-X0001.annotated.NA21133.rb.g.vcf.gz -NA19102 gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/scientific/jg_ug_scientific_samples/004716-X0001.annotated.NA19102.rb.g.vcf.gz -NA18549 gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/scientific/jg_ug_scientific_samples/004716-X0002.annotated.NA18549.rb.g.vcf.gz -NA20321 gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/scientific/jg_ug_scientific_samples/004716-X0003.annotated.NA20321.rb.g.vcf.gz -NA18525 gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/scientific/jg_ug_scientific_samples/004726-X0002.annotated.NA18525.rb.g.vcf.gz -NA19240 gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/scientific/jg_ug_scientific_samples/004726-X0018.annotated.NA19240.rb.g.vcf.gz -NA18917 gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/scientific/jg_ug_scientific_samples/004729-X0008.annotated.NA18917.rb.g.vcf.gz -NA21302 gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/scientific/jg_ug_scientific_samples/004729-X0011.annotated.NA21302.rb.g.vcf.gz -NA18916 gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/scientific/jg_ug_scientific_samples/004729-X0012.annotated.NA18916.rb.g.vcf.gz -NA19661 gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/scientific/jg_ug_scientific_samples/004734-X0008.annotated.NA19661.rb.g.vcf.gz -NA19902 gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/scientific/jg_ug_scientific_samples/004734-X0039.annotated.NA19902.rb.g.vcf.gz -NA20346 gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/scientific/jg_ug_scientific_samples/004734-X0040.annotated.NA20346.rb.g.vcf.gz -NA12489 gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/scientific/jg_ug_scientific_samples/004744-X0034.annotated.NA12489.rb.g.vcf.gz -NA21303 gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/scientific/jg_ug_scientific_samples/004745-X0004.annotated.NA21303.rb.g.vcf.gz -NA18923 gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/scientific/jg_ug_scientific_samples/004745-X0019.annotated.NA18923.rb.g.vcf.gz -NA20522 gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/scientific/jg_ug_scientific_samples/004749-X0012.annotated.NA20522.rb.g.vcf.gz -NA12878 gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/scientific/jg_ug_scientific_samples/004749-X0032.annotated.NA12878.rb.g.vcf.gz -NA12891 gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/scientific/jg_ug_scientific_samples/004750-X0028.annotated.NA12891.rb.g.vcf.gz -NA12872 gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/scientific/jg_ug_scientific_samples/004751-X0007.annotated.NA12872.rb.g.vcf.gz -NA18939 gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/scientific/jg_ug_scientific_samples/004754-X0017.annotated.NA18939.rb.g.vcf.gz -NA19790 gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/scientific/jg_ug_scientific_samples/004759-X0011.annotated.NA19790.rb.g.vcf.gz -NA18956 gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/scientific/jg_ug_scientific_samples/004766-X0029.annotated.NA18956.rb.g.vcf.gz -NA19795 gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/scientific/jg_ug_scientific_samples/004766-X0037.annotated.NA19795.rb.g.vcf.gz -NA19746 gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/scientific/jg_ug_scientific_samples/004773-X0037.annotated.NA19746.rb.g.vcf.gz -NA19913 gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/scientific/jg_ug_scientific_samples/004775-X0013.annotated.NA19913.rb.g.vcf.gz -NA19818 gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/scientific/jg_ug_scientific_samples/004778-X0019.annotated.NA19818.rb.g.vcf.gz -NA18945 gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/scientific/jg_ug_scientific_samples/004778-X0022.annotated.NA18945.rb.g.vcf.gz -NA19648 gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/scientific/jg_ug_scientific_samples/004784-X0037.annotated.NA19648.rb.g.vcf.gz -NA24694 gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/scientific/jg_ug_scientific_samples/004788-X0032.annotated.NA24694.rb.g.vcf.gz -NA18638 gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/scientific/jg_ug_scientific_samples/004789-X0007.annotated.NA18638.rb.g.vcf.gz -NA19238 gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/scientific/jg_ug_scientific_samples/004791-X0038.annotated.NA19238.rb.g.vcf.gz -NA20320 gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/scientific/jg_ug_scientific_samples/004797-X0004.annotated.NA20320.rb.g.vcf.gz -NA24143 gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/scientific/jg_ug_scientific_samples/004797-X0043.annotated.NA24143.rb.g.vcf.gz -NA21122 gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/scientific/jg_ug_scientific_samples/005430-X0009.annotated.NA21122.rb.g.vcf.gz -NA20845 gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/scientific/jg_ug_scientific_samples/005430-X0017.annotated.NA20845.rb.g.vcf.gz -NA19443 gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/scientific/jg_ug_scientific_samples/005430-X0033.annotated.NA19443.rb.g.vcf.gz -NA19678 gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/scientific/jg_ug_scientific_samples/005486-X0002.annotated.NA19678.rb.g.vcf.gz -NA19350 gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/scientific/jg_ug_scientific_samples/005486-X0026.annotated.NA19350.rb.g.vcf.gz -NA19143 gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/scientific/jg_ug_scientific_samples/005486-X0034.annotated.NA19143.rb.g.vcf.gz -NA19351 gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/scientific/jg_ug_scientific_samples/005489-X0038.annotated.NA19351.rb.g.vcf.gz -NA24695 gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/scientific/jg_ug_scientific_samples/005499-X0032.annotated.NA24695.rb.g.vcf.gz -NA19625 gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/scientific/jg_ug_scientific_samples/005499-X0033.annotated.NA19625.rb.g.vcf.gz -NA18553 gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/scientific/jg_ug_scientific_samples/005499-X0040.annotated.NA18553.rb.g.vcf.gz \ No newline at end of file +NA20502 gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/scientific/scientific.inputs/sample_map/002129-X0024.annotated.NA20502.rb.g.vcf.gz +NA18530 gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/scientific/scientific.inputs/sample_map/002129-X0048.annotated.NA18530.rb.g.vcf.gz +NA20509 gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/scientific/scientific.inputs/sample_map/002188-X0039.annotated.NA20509.rb.g.vcf.gz +NA24385 gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/scientific/scientific.inputs/sample_map/002436-X0004.annotated.NA24385.rb.g.vcf.gz +NA24149 gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/scientific/scientific.inputs/sample_map/002436-X0012.annotated.NA24149.rb.g.vcf.gz +NA12892 gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/scientific/scientific.inputs/sample_map/002448-X0001.annotated.NA12892.rb.g.vcf.gz +NA19001 gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/scientific/scientific.inputs/sample_map/002467-X0005.annotated.NA19001.rb.g.vcf.gz +NA18941 gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/scientific/scientific.inputs/sample_map/002467-X0013.annotated.NA18941.rb.g.vcf.gz +NA18499 gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/scientific/scientific.inputs/sample_map/002467-X0020.annotated.NA18499.rb.g.vcf.gz +NA18507 gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/scientific/scientific.inputs/sample_map/002467-X0028.annotated.NA18507.rb.g.vcf.gz +NA19788 gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/scientific/scientific.inputs/sample_map/002483-X0005.annotated.NA19788.rb.g.vcf.gz +NA18539 gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/scientific/scientific.inputs/sample_map/002483-X0020.annotated.NA18539.rb.g.vcf.gz +NA18560 gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/scientific/scientific.inputs/sample_map/002494-X0009.annotated.NA18560.rb.g.vcf.gz +NA21102 gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/scientific/scientific.inputs/sample_map/002494-X0033.annotated.NA21102.rb.g.vcf.gz +NA18995 gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/scientific/scientific.inputs/sample_map/002495-X0006.annotated.NA18995.rb.g.vcf.gz +NA20869 gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/scientific/scientific.inputs/sample_map/002495-X0014.annotated.NA20869.rb.g.vcf.gz +NA19062 gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/scientific/scientific.inputs/sample_map/002495-X0021.annotated.NA19062.rb.g.vcf.gz +NA20802 gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/scientific/scientific.inputs/sample_map/002495-X0029.annotated.NA20802.rb.g.vcf.gz +NA19377 gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/scientific/scientific.inputs/sample_map/004701-X0023.annotated.NA19377.rb.g.vcf.gz +NA20126 gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/scientific/scientific.inputs/sample_map/004701-X0038.annotated.NA20126.rb.g.vcf.gz +NA18930 gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/scientific/scientific.inputs/sample_map/004707-X0005.annotated.NA18930.rb.g.vcf.gz +NA19900 gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/scientific/scientific.inputs/sample_map/004707-X0012.annotated.NA19900.rb.g.vcf.gz +NA19901 gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/scientific/scientific.inputs/sample_map/004707-X0020.annotated.NA19901.rb.g.vcf.gz +NA19035 gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/scientific/scientific.inputs/sample_map/004707-X0036.annotated.NA19035.rb.g.vcf.gz +NA19789 gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/scientific/scientific.inputs/sample_map/004707-X0044.annotated.NA19789.rb.g.vcf.gz +NA20895 gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/scientific/scientific.inputs/sample_map/004710-X0042.annotated.NA20895.rb.g.vcf.gz +NA24631 gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/scientific/scientific.inputs/sample_map/004711-X0039.annotated.NA24631.rb.g.vcf.gz +NA21133 gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/scientific/scientific.inputs/sample_map/004713-X0001.annotated.NA21133.rb.g.vcf.gz +NA19102 gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/scientific/scientific.inputs/sample_map/004716-X0001.annotated.NA19102.rb.g.vcf.gz +NA18549 gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/scientific/scientific.inputs/sample_map/004716-X0002.annotated.NA18549.rb.g.vcf.gz +NA20321 gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/scientific/scientific.inputs/sample_map/004716-X0003.annotated.NA20321.rb.g.vcf.gz +NA18525 gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/scientific/scientific.inputs/sample_map/004726-X0002.annotated.NA18525.rb.g.vcf.gz +NA19240 gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/scientific/scientific.inputs/sample_map/004726-X0018.annotated.NA19240.rb.g.vcf.gz +NA18917 gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/scientific/scientific.inputs/sample_map/004729-X0008.annotated.NA18917.rb.g.vcf.gz +NA21302 gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/scientific/scientific.inputs/sample_map/004729-X0011.annotated.NA21302.rb.g.vcf.gz +NA18916 gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/scientific/scientific.inputs/sample_map/004729-X0012.annotated.NA18916.rb.g.vcf.gz +NA19661 gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/scientific/scientific.inputs/sample_map/004734-X0008.annotated.NA19661.rb.g.vcf.gz +NA19902 gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/scientific/scientific.inputs/sample_map/004734-X0039.annotated.NA19902.rb.g.vcf.gz +NA20346 gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/scientific/scientific.inputs/sample_map/004734-X0040.annotated.NA20346.rb.g.vcf.gz +NA12489 gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/scientific/scientific.inputs/sample_map/004744-X0034.annotated.NA12489.rb.g.vcf.gz +NA21303 gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/scientific/scientific.inputs/sample_map/004745-X0004.annotated.NA21303.rb.g.vcf.gz +NA18923 gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/scientific/scientific.inputs/sample_map/004745-X0019.annotated.NA18923.rb.g.vcf.gz +NA20522 gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/scientific/scientific.inputs/sample_map/004749-X0012.annotated.NA20522.rb.g.vcf.gz +NA12878 gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/scientific/scientific.inputs/sample_map/004749-X0032.annotated.NA12878.rb.g.vcf.gz +NA12891 gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/scientific/scientific.inputs/sample_map/004750-X0028.annotated.NA12891.rb.g.vcf.gz +NA12872 gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/scientific/scientific.inputs/sample_map/004751-X0007.annotated.NA12872.rb.g.vcf.gz +NA18939 gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/scientific/scientific.inputs/sample_map/004754-X0017.annotated.NA18939.rb.g.vcf.gz +NA19790 gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/scientific/scientific.inputs/sample_map/004759-X0011.annotated.NA19790.rb.g.vcf.gz +NA18956 gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/scientific/scientific.inputs/sample_map/004766-X0029.annotated.NA18956.rb.g.vcf.gz +NA19795 gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/scientific/scientific.inputs/sample_map/004766-X0037.annotated.NA19795.rb.g.vcf.gz +NA19746 gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/scientific/scientific.inputs/sample_map/004773-X0037.annotated.NA19746.rb.g.vcf.gz +NA19913 gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/scientific/scientific.inputs/sample_map/004775-X0013.annotated.NA19913.rb.g.vcf.gz +NA19818 gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/scientific/scientific.inputs/sample_map/004778-X0019.annotated.NA19818.rb.g.vcf.gz +NA18945 gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/scientific/scientific.inputs/sample_map/004778-X0022.annotated.NA18945.rb.g.vcf.gz +NA19648 gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/scientific/scientific.inputs/sample_map/004784-X0037.annotated.NA19648.rb.g.vcf.gz +NA24694 gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/scientific/scientific.inputs/sample_map/004788-X0032.annotated.NA24694.rb.g.vcf.gz +NA18638 gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/scientific/scientific.inputs/sample_map/004789-X0007.annotated.NA18638.rb.g.vcf.gz +NA19238 gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/scientific/scientific.inputs/sample_map/004791-X0038.annotated.NA19238.rb.g.vcf.gz +NA20320 gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/scientific/scientific.inputs/sample_map/004797-X0004.annotated.NA20320.rb.g.vcf.gz +NA24143 gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/scientific/scientific.inputs/sample_map/004797-X0043.annotated.NA24143.rb.g.vcf.gz +NA21122 gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/scientific/scientific.inputs/sample_map/005430-X0009.annotated.NA21122.rb.g.vcf.gz +NA20845 gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/scientific/scientific.inputs/sample_map/005430-X0017.annotated.NA20845.rb.g.vcf.gz +NA19443 gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/scientific/scientific.inputs/sample_map/005430-X0033.annotated.NA19443.rb.g.vcf.gz +NA19678 gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/scientific/scientific.inputs/sample_map/005486-X0002.annotated.NA19678.rb.g.vcf.gz +NA19350 gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/scientific/scientific.inputs/sample_map/005486-X0026.annotated.NA19350.rb.g.vcf.gz +NA19143 gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/scientific/scientific.inputs/sample_map/005486-X0034.annotated.NA19143.rb.g.vcf.gz +NA19351 gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/scientific/scientific.inputs/sample_map/005489-X0038.annotated.NA19351.rb.g.vcf.gz +NA24695 gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/scientific/scientific.inputs/sample_map/005499-X0032.annotated.NA24695.rb.g.vcf.gz +NA19625 gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/scientific/scientific.inputs/sample_map/005499-X0033.annotated.NA19625.rb.g.vcf.gz +NA18553 gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/scientific/scientific.inputs/sample_map/005499-X0040.annotated.NA18553.rb.g.vcf.gz \ No newline at end of file diff --git a/pipelines/broad/dna_seq/germline/joint_genotyping/UltimaGenomics/test_inputs/Scientific/scientific.inputs.json b/pipelines/broad/dna_seq/germline/joint_genotyping/UltimaGenomics/test_inputs/Scientific/scientific.inputs.json index 9b6270b0b4..d46c22952b 100644 --- a/pipelines/broad/dna_seq/germline/joint_genotyping/UltimaGenomics/test_inputs/Scientific/scientific.inputs.json +++ b/pipelines/broad/dna_seq/germline/joint_genotyping/UltimaGenomics/test_inputs/Scientific/scientific.inputs.json @@ -10,19 +10,19 @@ "UltimaGenomicsJointGenotyping.ref_dict":"gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.dict", "UltimaGenomicsJointGenotyping.ref_fasta":"gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.fasta", "UltimaGenomicsJointGenotyping.ref_fasta_index":"gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.fasta.fai", -"UltimaGenomicsJointGenotyping.sample_name_map":"gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/scientific/jg_ug_scientific_test_sample_map.list", +"UltimaGenomicsJointGenotyping.sample_name_map":"gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/scientific/scientific.inputs/sample_map/jg_ug_scientific_test_sample_map.list", "UltimaGenomicsJointGenotyping.scatter_cross_check_fingerprints":false, "UltimaGenomicsJointGenotyping.unbounded_scatter_count_scale_factor":2.5, "UltimaGenomicsJointGenotyping.unpadded_intervals_file":"gs://gcp-public-data--broad-references/hg38/v0/hg38.even.handcurated.20k.intervals", "UltimaGenomicsJointGenotyping.snp_annotations": ["AS_ReadPosRankSum", "AS_FS", "AS_SOR", "AS_QD", "AVERAGE_TREE_SCORE", "AVERAGE_ASSEMBLED_HAPS", "AVERAGE_FILTERED_HAPS"], "UltimaGenomicsJointGenotyping.indel_annotations": ["AS_MQRankSum", "AS_ReadPosRankSum", "AS_FS", "AS_SOR", "AS_QD", "AVERAGE_TREE_SCORE"], "UltimaGenomicsJointGenotyping.flow_order": "TGCA", -"UltimaGenomicsJointGenotyping.ref_fasta_sdf": "gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/scientific/reference_sdf.tar", -"UltimaGenomicsJointGenotyping.runs_file": "gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/scientific/runs.conservative.bed", -"UltimaGenomicsJointGenotyping.annotation_intervals": ["gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/scientific/LCR-hs38.bed", "gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/scientific/mappability.0.bed", "gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/scientific/exome.twist.bed"], -"UltimaGenomicsJointGenotyping.truth_vcf":"gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/scientific/HG001_GRCh38_GIAB_highconf_CG-IllFB-IllGATKHC-Ion-10X-SOLID_CHROM1-X_v.3.3.2_highconf_PGandRTGphasetransfer.broad-header.vcf.gz", -"UltimaGenomicsJointGenotyping.truth_vcf_index":"gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/scientific/HG001_GRCh38_GIAB_highconf_CG-IllFB-IllGATKHC-Ion-10X-SOLID_CHROM1-X_v.3.3.2_highconf_PGandRTGphasetransfer.broad-header.vcf.gz", -"UltimaGenomicsJointGenotyping.truth_highconf_intervals": "gs://broad-gotc-test-storage/UltimaGenomicsJointGenotyping/wgs/scientific/HG001_GRCh38_GIAB_highconf_CG-IllFB-IllGATKHC-Ion-10X-SOLID_CHROM1-X_v.3.3.2_highconf_nosomaticdel_noCENorHET7.bed", +"UltimaGenomicsJointGenotyping.ref_fasta_sdf": "gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/scientific/scientific.inputs/reference_sdf.tar", +"UltimaGenomicsJointGenotyping.runs_file": "gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/scientific/scientific.inputs/runs.conservative.bed", +"UltimaGenomicsJointGenotyping.annotation_intervals": ["gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/scientific/scientific.inputs/LCR-hs38.bed", "gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/scientific/scientific.inputs/mappability.0.bed", "gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/scientific/scientific.inputs/exome.twist.bed"], +"UltimaGenomicsJointGenotyping.truth_vcf":"gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/scientific/scientific.inputs/HG001_GRCh38_GIAB_highconf_CG-IllFB-IllGATKHC-Ion-10X-SOLID_CHROM1-X_v.3.3.2_highconf_PGandRTGphasetransfer.broad-header.vcf.gz", +"UltimaGenomicsJointGenotyping.truth_vcf_index":"gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/scientific/scientific.inputs/HG001_GRCh38_GIAB_highconf_CG-IllFB-IllGATKHC-Ion-10X-SOLID_CHROM1-X_v.3.3.2_highconf_PGandRTGphasetransfer.broad-header.vcf.gz", +"UltimaGenomicsJointGenotyping.truth_highconf_intervals": "gs://pd-test-storage-private/UltimaGenomicsJointGenotyping/input/scientific/scientific.inputs/HG001_GRCh38_GIAB_highconf_CG-IllFB-IllGATKHC-Ion-10X-SOLID_CHROM1-X_v.3.3.2_highconf_nosomaticdel_noCENorHET7.bed", "UltimaGenomicsJointGenotyping.call_sample_name": "NA12878", "UltimaGenomicsJointGenotyping.truth_sample_name": "HG001", "UltimaGenomicsJointGenotyping.model_backend": "PYTHON_IFOREST", diff --git a/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Plumbing/gather_vcfs_high_memory.json b/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Plumbing/gather_vcfs_high_memory.json index be9aae05ed..6e9853eda8 100644 --- a/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Plumbing/gather_vcfs_high_memory.json +++ b/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Plumbing/gather_vcfs_high_memory.json @@ -28,7 +28,7 @@ "JointGenotyping.haplotype_database": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.haplotype_database.txt", "JointGenotyping.callset_name": "small_callset_low_threshold", - "JointGenotyping.sample_name_map" : "gs://broad-gotc-test-storage/joint_genotyping/exome/plumbing/callset/reblocked_plumbing_sample_map", + "JointGenotyping.sample_name_map" : "gs://pd-test-storage-private/JointGenotyping/input/plumbing/sample_name_maps/exome/reblocked_plumbing_sample_map/reblocked_plumbing_sample_map.txt", "JointGenotyping.small_disk" : 100, "JointGenotyping.medium_disk" : 200, diff --git a/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Plumbing/gather_vcfs_low_memory.json b/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Plumbing/gather_vcfs_low_memory.json index a81631a23d..2d15974893 100644 --- a/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Plumbing/gather_vcfs_low_memory.json +++ b/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Plumbing/gather_vcfs_low_memory.json @@ -28,7 +28,7 @@ "JointGenotyping.haplotype_database": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.haplotype_database.txt", "JointGenotyping.callset_name": "small_callset_high_threshold", - "JointGenotyping.sample_name_map" : "gs://broad-gotc-test-storage/joint_genotyping/exome/plumbing/callset/reblocked_plumbing_sample_map", + "JointGenotyping.sample_name_map" : "gs://pd-test-storage-private/JointGenotyping/input/plumbing/sample_name_maps/exome/reblocked_plumbing_sample_map/reblocked_plumbing_sample_map.txt", "JointGenotyping.small_disk" : 100, "JointGenotyping.medium_disk" : 200, diff --git a/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Plumbing/gnarly.json b/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Plumbing/gnarly.json index 1825ba3822..e4c935221b 100644 --- a/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Plumbing/gnarly.json +++ b/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Plumbing/gnarly.json @@ -28,7 +28,7 @@ "JointGenotyping.haplotype_database": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.haplotype_database.txt", "JointGenotyping.callset_name": "gnarly_callset", - "JointGenotyping.sample_name_map" : "gs://broad-gotc-test-storage/joint_genotyping/exome/plumbing/callset/reblocked_name_sample_map", + "JointGenotyping.sample_name_map" : "gs://pd-test-storage-private/JointGenotyping/input/plumbing/sample_name_maps/exome/reblocked_name_sample_map/reblocked_name_sample_map.txt", "JointGenotyping.small_disk" : 100, "JointGenotyping.medium_disk" : 200, diff --git a/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Plumbing/plumbing.input.json b/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Plumbing/plumbing.input.json index 4827117051..10a23a5bdb 100644 --- a/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Plumbing/plumbing.input.json +++ b/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Plumbing/plumbing.input.json @@ -1,5 +1,5 @@ { - "JointGenotyping.sample_name_map": "gs://broad-gotc-test-storage/JointGenotyping/inputs/plumbing/wgs/sample_name_map", + "JointGenotyping.sample_name_map": "gs://pd-test-storage-private/JointGenotyping/input/plumbing/sample_name_maps/wgs/sample_name_map/sample_name_map.txt", "JointGenotyping.callset_name": "wgs_joint_genotyping_plumbing", "JointGenotyping.unbounded_scatter_count_scale_factor": 2.5, "JointGenotyping.SplitIntervalList.scatter_mode": "INTERVAL_SUBDIVISION", diff --git a/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Plumbing/shard_vcfs_high_memory.json b/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Plumbing/shard_vcfs_high_memory.json index 350afb4ea1..57ec0bbe31 100644 --- a/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Plumbing/shard_vcfs_high_memory.json +++ b/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Plumbing/shard_vcfs_high_memory.json @@ -28,7 +28,7 @@ "JointGenotyping.haplotype_database": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.haplotype_database.txt", "JointGenotyping.callset_name": "large_callset_low_threshold", - "JointGenotyping.sample_name_map" : "gs://broad-gotc-test-storage/joint_genotyping/exome/plumbing/callset/reblocked_plumbing_sample_map", + "JointGenotyping.sample_name_map" : "gs://pd-test-storage-private/JointGenotyping/input/plumbing/sample_name_maps/exome/reblocked_plumbing_sample_map/reblocked_plumbing_sample_map.txt", "JointGenotyping.small_disk" : 100, "JointGenotyping.medium_disk" : 200, diff --git a/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Plumbing/shard_vcfs_low_memory.json b/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Plumbing/shard_vcfs_low_memory.json index 06eeda58ca..900c582cf9 100644 --- a/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Plumbing/shard_vcfs_low_memory.json +++ b/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Plumbing/shard_vcfs_low_memory.json @@ -28,7 +28,7 @@ "JointGenotyping.haplotype_database": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.haplotype_database.txt", "JointGenotyping.callset_name": "large_callset_high_threshold", - "JointGenotyping.sample_name_map" : "gs://broad-gotc-test-storage/joint_genotyping/exome/plumbing/callset/reblocked_plumbing_sample_map", + "JointGenotyping.sample_name_map" : "gs://pd-test-storage-private/JointGenotyping/input/plumbing/sample_name_maps/exome/reblocked_plumbing_sample_map/reblocked_plumbing_sample_map.txt", "JointGenotyping.small_disk" : 100, "JointGenotyping.medium_disk" : 200, diff --git a/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Scientific/bge.json b/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Scientific/bge.json index b74d793cf0..288b2e7ca9 100644 --- a/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Scientific/bge.json +++ b/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Scientific/bge.json @@ -1,5 +1,5 @@ { - "JointGenotyping.sample_name_map": "gs://broad-gotc-test-storage/JointGenotyping/inputs/scientific/bge/BGE_JG_test_sample_map.txt", + "JointGenotyping.sample_name_map": "gs://pd-test-storage-private/JointGenotyping/input/scientific/sample_name_maps/bge/BGE_JG_test_sample_map/BGE_JG_test_sample_map.txt", "JointGenotyping.callset_name": "bge_joint_genotyping", "JointGenotyping.run_vets": true, @@ -7,8 +7,8 @@ "JointGenotyping.ref_fasta": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.fasta", "JointGenotyping.ref_fasta_index": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.fasta.fai", "JointGenotyping.ref_dict": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.dict", - "JointGenotyping.eval_interval_list": "gs://broad-gotc-test-storage/JointGenotyping/inputs/scientific/bge/TwistAllianceClinicalResearchExome_Covered_Targets_hg38.interval_list", - "JointGenotyping.targets_interval_list": "gs://broad-gotc-test-storage/JointGenotyping/inputs/scientific/bge/TwistAllianceClinicalResearchExome_Covered_Targets_hg38.interval_list", + "JointGenotyping.eval_interval_list": "gs://pd-test-storage-private/JointGenotyping/input/scientific/bge/TwistAllianceClinicalResearchExome_Covered_Targets_hg38.interval_list", + "JointGenotyping.targets_interval_list": "gs://pd-test-storage-private/JointGenotyping/input/scientific/bge/TwistAllianceClinicalResearchExome_Covered_Targets_hg38.interval_list", "JointGenotyping.haplotype_database": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.haplotype_database.txt", "JointGenotyping.axiomPoly_resource_vcf": "gs://gcp-public-data--broad-references/hg38/v0/Axiom_Exome_Plus.genotypes.all_populations.poly.hg38.vcf.gz", diff --git a/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Scientific/gather_vcfs_high_memory.json b/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Scientific/gather_vcfs_high_memory.json index 1dfd205112..ef18b355bf 100644 --- a/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Scientific/gather_vcfs_high_memory.json +++ b/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Scientific/gather_vcfs_high_memory.json @@ -28,7 +28,7 @@ "JointGenotyping.haplotype_database": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.haplotype_database.txt", "JointGenotyping.callset_name": "small_callset_low_threshold", - "JointGenotyping.sample_name_map" : "gs://broad-gotc-test-storage/joint_genotyping/exome/scientific/callset/reblocked_name_sample_map", + "JointGenotyping.sample_name_map" : "gs://pd-test-storage-private/JointGenotyping/input/scientific/sample_name_maps/exome/reblocked_name_sample_map/reblocked_name_sample_map.txt", "JointGenotyping.small_disk" : 100, "JointGenotyping.medium_disk" : 200, diff --git a/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Scientific/gather_vcfs_low_memory.json b/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Scientific/gather_vcfs_low_memory.json index efb4a7510e..3992c7a0bf 100644 --- a/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Scientific/gather_vcfs_low_memory.json +++ b/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Scientific/gather_vcfs_low_memory.json @@ -28,7 +28,7 @@ "JointGenotyping.haplotype_database": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.haplotype_database.txt", "JointGenotyping.callset_name": "small_callset_high_threshold", - "JointGenotyping.sample_name_map" : "gs://broad-gotc-test-storage/joint_genotyping/exome/scientific/callset/reblocked_name_sample_map", + "JointGenotyping.sample_name_map" : "gs://pd-test-storage-private/JointGenotyping/input/scientific/sample_name_maps/exome/reblocked_name_sample_map/reblocked_name_sample_map.txt", "JointGenotyping.small_disk" : 100, "JointGenotyping.medium_disk" : 200, diff --git a/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Scientific/gnarly.json b/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Scientific/gnarly.json index 799e8868a8..31501b1530 100644 --- a/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Scientific/gnarly.json +++ b/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Scientific/gnarly.json @@ -28,7 +28,7 @@ "JointGenotyping.haplotype_database": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.haplotype_database.txt", "JointGenotyping.callset_name": "gnarly_callset", - "JointGenotyping.sample_name_map" : "gs://broad-gotc-test-storage/joint_genotyping/exome/scientific/callset/reblocked_name_sample_map", + "JointGenotyping.sample_name_map" : "gs://pd-test-storage-private/JointGenotyping/input/scientific/sample_name_maps/exome/reblocked_name_sample_map/reblocked_name_sample_map.txt", "JointGenotyping.small_disk" : 100, "JointGenotyping.medium_disk" : 200, diff --git a/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Scientific/shard_vcfs_high_memory.json b/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Scientific/shard_vcfs_high_memory.json index 0c4b17b3b2..ba36ddd335 100644 --- a/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Scientific/shard_vcfs_high_memory.json +++ b/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Scientific/shard_vcfs_high_memory.json @@ -28,7 +28,7 @@ "JointGenotyping.haplotype_database": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.haplotype_database.txt", "JointGenotyping.callset_name": "large_callset_low_threshold", - "JointGenotyping.sample_name_map" : "gs://broad-gotc-test-storage/joint_genotyping/exome/scientific/callset/reblocked_name_sample_map", + "JointGenotyping.sample_name_map" : "gs://pd-test-storage-private/JointGenotyping/input/scientific/sample_name_maps/exome/reblocked_name_sample_map/reblocked_name_sample_map.txt", "JointGenotyping.small_disk" : 100, "JointGenotyping.medium_disk" : 200, diff --git a/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Scientific/shard_vcfs_low_memory.json b/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Scientific/shard_vcfs_low_memory.json index af2d0ab568..b45f199991 100644 --- a/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Scientific/shard_vcfs_low_memory.json +++ b/pipelines/broad/dna_seq/germline/joint_genotyping/test_inputs/Scientific/shard_vcfs_low_memory.json @@ -28,7 +28,7 @@ "JointGenotyping.haplotype_database": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.haplotype_database.txt", "JointGenotyping.callset_name": "large_callset_high_threshold", - "JointGenotyping.sample_name_map" : "gs://broad-gotc-test-storage/joint_genotyping/exome/scientific/callset/reblocked_name_sample_map", + "JointGenotyping.sample_name_map" : "gs://pd-test-storage-private/JointGenotyping/input/scientific/sample_name_maps/exome/reblocked_name_sample_map/reblocked_name_sample_map.txt", "JointGenotyping.small_disk" : 100, "JointGenotyping.medium_disk" : 200, diff --git a/pipelines/broad/dna_seq/germline/single_sample/exome/test_inputs/Plumbing/RP-929.NA12878.json b/pipelines/broad/dna_seq/germline/single_sample/exome/test_inputs/Plumbing/RP-929.NA12878.json index 17c06f79b6..be1ca6a3ee 100644 --- a/pipelines/broad/dna_seq/germline/single_sample/exome/test_inputs/Plumbing/RP-929.NA12878.json +++ b/pipelines/broad/dna_seq/germline/single_sample/exome/test_inputs/Plumbing/RP-929.NA12878.json @@ -3,7 +3,7 @@ "sample_name": "NA12878 PLUMBING", "base_file_name": "NA12878_PLUMBING", "flowcell_unmapped_bams": [ - "gs://broad-gotc-test-storage/germline_single_sample/exome/plumbing/bams/RP-929.NA12878/HJ5LVADXX.1.downsampled.unmapped.bam" + "gs://pd-test-storage-public/ExomeGermlineSingleSample/input/plumbing/RP-929.NA12878/HJ5LVADXX.1.downsampled.unmapped.bam" ], "final_gvcf_base_name": "NA12878_PLUMBING", "unmapped_bam_suffix": ".unmapped.bam" @@ -44,8 +44,8 @@ "break_bands_at_multiples_of": 0 }, - "ExomeGermlineSingleSample.fingerprint_genotypes_file": "gs://broad-gotc-test-storage/germline_single_sample/exome/plumbing/bams/RP-929.NA12878/RP-929.NA12878.reference.fingerprint.vcf.gz", - "ExomeGermlineSingleSample.fingerprint_genotypes_index": "gs://broad-gotc-test-storage/germline_single_sample/exome/plumbing/bams/RP-929.NA12878/RP-929.NA12878.reference.fingerprint.vcf.gz.tbi", + "ExomeGermlineSingleSample.fingerprint_genotypes_file": "gs://pd-test-storage-public/ExomeGermlineSingleSample/input/plumbing/RP-929.NA12878/RP-929.NA12878.reference.fingerprint.vcf.gz", + "ExomeGermlineSingleSample.fingerprint_genotypes_index": "gs://pd-test-storage-public/ExomeGermlineSingleSample/input/plumbing/RP-929.NA12878/RP-929.NA12878.reference.fingerprint.vcf.gz.tbi", "ExomeGermlineSingleSample.target_interval_list": "gs://broad-references-private/HybSelOligos/whole_exome_illumina_coding_v1/whole_exome_illumina_coding_v1.Homo_sapiens_assembly38.targets.interval_list", "ExomeGermlineSingleSample.bait_interval_list": "gs://broad-references-private/HybSelOligos/whole_exome_illumina_coding_v1/whole_exome_illumina_coding_v1.Homo_sapiens_assembly38.baits.interval_list", "ExomeGermlineSingleSample.bait_set_name": "whole_exome_illumina_coding_v1", diff --git a/pipelines/broad/dna_seq/germline/single_sample/exome/test_inputs/Scientific/C1963.CHMI_CHMI3_Nex1.json b/pipelines/broad/dna_seq/germline/single_sample/exome/test_inputs/Scientific/C1963.CHMI_CHMI3_Nex1.json index 163e2f8265..9aa3308e42 100644 --- a/pipelines/broad/dna_seq/germline/single_sample/exome/test_inputs/Scientific/C1963.CHMI_CHMI3_Nex1.json +++ b/pipelines/broad/dna_seq/germline/single_sample/exome/test_inputs/Scientific/C1963.CHMI_CHMI3_Nex1.json @@ -3,14 +3,14 @@ "sample_name": "CHMI_CHMI3_Nex1", "base_file_name": "CHMI_CHMI3_Nex1", "flowcell_unmapped_bams": [ - "gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/C1963.CHMI_CHMI3_Nex1/HHM2CCCXX.1.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/C1963.CHMI_CHMI3_Nex1/HHM2CCCXX.2.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/C1963.CHMI_CHMI3_Nex1/HHM2CCCXX.3.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/C1963.CHMI_CHMI3_Nex1/HHM2CCCXX.4.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/C1963.CHMI_CHMI3_Nex1/HHM2CCCXX.5.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/C1963.CHMI_CHMI3_Nex1/HHM2CCCXX.6.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/C1963.CHMI_CHMI3_Nex1/HHM2CCCXX.7.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/C1963.CHMI_CHMI3_Nex1/HHM2CCCXX.8.unmapped.bam" + "gs://pd-test-storage-public/ExomeGermlineSingleSample/input/scientific/C1963.CHMI_CHMI3_Nex1/HHM2CCCXX.1.unmapped.bam", + "gs://pd-test-storage-public/ExomeGermlineSingleSample/input/scientific/C1963.CHMI_CHMI3_Nex1/HHM2CCCXX.2.unmapped.bam", + "gs://pd-test-storage-public/ExomeGermlineSingleSample/input/scientific/C1963.CHMI_CHMI3_Nex1/HHM2CCCXX.3.unmapped.bam", + "gs://pd-test-storage-public/ExomeGermlineSingleSample/input/scientific/C1963.CHMI_CHMI3_Nex1/HHM2CCCXX.4.unmapped.bam", + "gs://pd-test-storage-public/ExomeGermlineSingleSample/input/scientific/C1963.CHMI_CHMI3_Nex1/HHM2CCCXX.5.unmapped.bam", + "gs://pd-test-storage-public/ExomeGermlineSingleSample/input/scientific/C1963.CHMI_CHMI3_Nex1/HHM2CCCXX.6.unmapped.bam", + "gs://pd-test-storage-public/ExomeGermlineSingleSample/input/scientific/C1963.CHMI_CHMI3_Nex1/HHM2CCCXX.7.unmapped.bam", + "gs://pd-test-storage-public/ExomeGermlineSingleSample/input/scientific/C1963.CHMI_CHMI3_Nex1/HHM2CCCXX.8.unmapped.bam" ], "final_gvcf_base_name": "CHMI_CHMI3_Nex1", "unmapped_bam_suffix": ".unmapped.bam" @@ -51,8 +51,8 @@ "break_bands_at_multiples_of": 0 }, - "ExomeGermlineSingleSample.fingerprint_genotypes_file": "gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/C1963.CHMI_CHMI3_Nex1/C1963.CHMI_CHMI3_Nex1.reference.fingerprint.vcf.gz", - "ExomeGermlineSingleSample.fingerprint_genotypes_index": "gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/C1963.CHMI_CHMI3_Nex1/C1963.CHMI_CHMI3_Nex1.reference.fingerprint.vcf.gz.tbi", + "ExomeGermlineSingleSample.fingerprint_genotypes_file": "gs://pd-test-storage-public/ExomeGermlineSingleSample/input/scientific/C1963.CHMI_CHMI3_Nex1/C1963.CHMI_CHMI3_Nex1.reference.fingerprint.vcf.gz", + "ExomeGermlineSingleSample.fingerprint_genotypes_index": "gs://pd-test-storage-public/ExomeGermlineSingleSample/input/scientific/C1963.CHMI_CHMI3_Nex1/C1963.CHMI_CHMI3_Nex1.reference.fingerprint.vcf.gz.tbi", "ExomeGermlineSingleSample.target_interval_list": "gs://broad-references-private/HybSelOligos/whole_exome_illumina_coding_v1/whole_exome_illumina_coding_v1.Homo_sapiens_assembly38.targets.interval_list", "ExomeGermlineSingleSample.bait_interval_list": "gs://broad-references-private/HybSelOligos/whole_exome_illumina_coding_v1/whole_exome_illumina_coding_v1.Homo_sapiens_assembly38.baits.interval_list", "ExomeGermlineSingleSample.bait_set_name": "whole_exome_illumina_coding_v1", diff --git a/pipelines/broad/dna_seq/germline/single_sample/exome/test_inputs/Scientific/C862.NA19238.json b/pipelines/broad/dna_seq/germline/single_sample/exome/test_inputs/Scientific/C862.NA19238.json index c90ddcf59f..e0aa981673 100644 --- a/pipelines/broad/dna_seq/germline/single_sample/exome/test_inputs/Scientific/C862.NA19238.json +++ b/pipelines/broad/dna_seq/germline/single_sample/exome/test_inputs/Scientific/C862.NA19238.json @@ -3,22 +3,22 @@ "sample_name": "NA19238", "base_file_name": "NA19238", "flowcell_unmapped_bams": [ - "gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/C862.NA19238/A1DHK.1.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/C862.NA19238/A1ETR.1.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/C862.NA19238/A1G49.1.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/C862.NA19238/A1G7N.1.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/C862.NA19238/A1G85.1.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/C862.NA19238/A1G9P.1.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/C862.NA19238/A1G9V.1.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/C862.NA19238/A1GAE.1.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/C862.NA19238/A1H1F.1.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/C862.NA19238/A1H1K.1.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/C862.NA19238/A1H3B.1.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/C862.NA19238/A1H3L.1.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/C862.NA19238/A1H88.1.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/C862.NA19238/A1H8B.1.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/C862.NA19238/A1HN8.1.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/C862.NA19238/A1HNG.1.unmapped.bam" + "gs://pd-test-storage-public/ExomeGermlineSingleSample/input/scientific/C862.NA19238/A1DHK.1.unmapped.bam", + "gs://pd-test-storage-public/ExomeGermlineSingleSample/input/scientific/C862.NA19238/A1ETR.1.unmapped.bam", + "gs://pd-test-storage-public/ExomeGermlineSingleSample/input/scientific/C862.NA19238/A1G49.1.unmapped.bam", + "gs://pd-test-storage-public/ExomeGermlineSingleSample/input/scientific/C862.NA19238/A1G7N.1.unmapped.bam", + "gs://pd-test-storage-public/ExomeGermlineSingleSample/input/scientific/C862.NA19238/A1G85.1.unmapped.bam", + "gs://pd-test-storage-public/ExomeGermlineSingleSample/input/scientific/C862.NA19238/A1G9P.1.unmapped.bam", + "gs://pd-test-storage-public/ExomeGermlineSingleSample/input/scientific/C862.NA19238/A1G9V.1.unmapped.bam", + "gs://pd-test-storage-public/ExomeGermlineSingleSample/input/scientific/C862.NA19238/A1GAE.1.unmapped.bam", + "gs://pd-test-storage-public/ExomeGermlineSingleSample/input/scientific/C862.NA19238/A1H1F.1.unmapped.bam", + "gs://pd-test-storage-public/ExomeGermlineSingleSample/input/scientific/C862.NA19238/A1H1K.1.unmapped.bam", + "gs://pd-test-storage-public/ExomeGermlineSingleSample/input/scientific/C862.NA19238/A1H3B.1.unmapped.bam", + "gs://pd-test-storage-public/ExomeGermlineSingleSample/input/scientific/C862.NA19238/A1H3L.1.unmapped.bam", + "gs://pd-test-storage-public/ExomeGermlineSingleSample/input/scientific/C862.NA19238/A1H88.1.unmapped.bam", + "gs://pd-test-storage-public/ExomeGermlineSingleSample/input/scientific/C862.NA19238/A1H8B.1.unmapped.bam", + "gs://pd-test-storage-public/ExomeGermlineSingleSample/input/scientific/C862.NA19238/A1HN8.1.unmapped.bam", + "gs://pd-test-storage-public/ExomeGermlineSingleSample/input/scientific/C862.NA19238/A1HNG.1.unmapped.bam" ], "final_gvcf_base_name": "NA19238", "unmapped_bam_suffix": ".unmapped.bam" @@ -59,8 +59,8 @@ "break_bands_at_multiples_of": 0 }, - "ExomeGermlineSingleSample.fingerprint_genotypes_file": "gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/C862.NA19238/C862.NA19238.reference.fingerprint.vcf.gz", - "ExomeGermlineSingleSample.fingerprint_genotypes_index": "gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/C862.NA19238/C862.NA19238.reference.fingerprint.vcf.gz.tbi", + "ExomeGermlineSingleSample.fingerprint_genotypes_file": "gs://pd-test-storage-public/ExomeGermlineSingleSample/input/scientific/C862.NA19238.reference.fingerprint.vcf.gz", + "ExomeGermlineSingleSample.fingerprint_genotypes_index": "gs://pd-test-storage-public/ExomeGermlineSingleSample/input/scientific/C862.NA19238.reference.fingerprint.vcf.gz.tbi", "ExomeGermlineSingleSample.target_interval_list": "gs://broad-references-private/HybSelOligos/whole_exome_agilent_1.1_refseq_plus_3_boosters/whole_exome_agilent_1.1_refseq_plus_3_boosters.Homo_sapiens_assembly38.targets.interval_list", "ExomeGermlineSingleSample.bait_interval_list": "gs://broad-references-private/HybSelOligos/whole_exome_agilent_1.1_refseq_plus_3_boosters/whole_exome_agilent_1.1_refseq_plus_3_boosters.Homo_sapiens_assembly38.baits.interval_list", "ExomeGermlineSingleSample.bait_set_name": "whole_exome_agilent_1.1_refseq_plus_3_boosters", @@ -73,4 +73,4 @@ "ExomeGermlineSingleSample.AggregatedBamQC.CollectReadgroupBamQualityMetrics.collect_gc_bias_metrics": false, "ExomeGermlineSingleSample.AggregatedBamQC.CollectAggregationMetrics.collect_gc_bias_metrics": false, "ExomeGermlineSingleSample.cloud_provider": "gcp" -} +} \ No newline at end of file diff --git a/pipelines/broad/dna_seq/germline/single_sample/exome/test_inputs/Scientific/D5327.NA12878.json b/pipelines/broad/dna_seq/germline/single_sample/exome/test_inputs/Scientific/D5327.NA12878.json index a302f38a4f..85881de313 100644 --- a/pipelines/broad/dna_seq/germline/single_sample/exome/test_inputs/Scientific/D5327.NA12878.json +++ b/pipelines/broad/dna_seq/germline/single_sample/exome/test_inputs/Scientific/D5327.NA12878.json @@ -3,8 +3,8 @@ "sample_name": "NA12878", "base_file_name": "NA12878", "flowcell_unmapped_bams": [ - "gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/D5327.NA12878/H2GCKCCXX.7.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/D5327.NA12878/H2GCKCCXX.8.unmapped.bam" + "gs://pd-test-storage-public/ExomeGermlineSingleSample/input/scientific/D5327.NA12878/H2GCKCCXX.7.unmapped.bam", + "gs://pd-test-storage-public/ExomeGermlineSingleSample/input/scientific/D5327.NA12878/H2GCKCCXX.8.unmapped.bam" ], "final_gvcf_base_name": "NA12878", "unmapped_bam_suffix": ".unmapped.bam" @@ -44,8 +44,8 @@ "break_bands_at_multiples_of": 0 }, - "ExomeGermlineSingleSample.fingerprint_genotypes_file": "gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/D5327.NA12878/D5327.NA12878.reference.fingerprint.vcf.gz", - "ExomeGermlineSingleSample.fingerprint_genotypes_index": "gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/D5327.NA12878/D5327.NA12878.reference.fingerprint.vcf.gz.tbi", + "ExomeGermlineSingleSample.fingerprint_genotypes_file": "gs://pd-test-storage-public/ExomeGermlineSingleSample/input/scientific/D5327.NA12878/D5327.NA12878.reference.fingerprint.vcf.gz", + "ExomeGermlineSingleSample.fingerprint_genotypes_index": "gs://pd-test-storage-public/ExomeGermlineSingleSample/input/scientific/D5327.NA12878/D5327.NA12878.reference.fingerprint.vcf.gz.tbi", "ExomeGermlineSingleSample.target_interval_list": "gs://broad-references-private/HybSelOligos/whole_exome_illumina_coding_v1/whole_exome_illumina_coding_v1.Homo_sapiens_assembly38.targets.interval_list", "ExomeGermlineSingleSample.bait_interval_list": "gs://broad-references-private/HybSelOligos/whole_exome_illumina_coding_v1/whole_exome_illumina_coding_v1.Homo_sapiens_assembly38.baits.interval_list", "ExomeGermlineSingleSample.bait_set_name": "whole_exome_illumina_coding_v1", diff --git a/pipelines/broad/dna_seq/germline/single_sample/exome/test_inputs/Scientific/D5327.NA12891.json b/pipelines/broad/dna_seq/germline/single_sample/exome/test_inputs/Scientific/D5327.NA12891.json index 945d7bb79c..5b565c5447 100644 --- a/pipelines/broad/dna_seq/germline/single_sample/exome/test_inputs/Scientific/D5327.NA12891.json +++ b/pipelines/broad/dna_seq/germline/single_sample/exome/test_inputs/Scientific/D5327.NA12891.json @@ -3,8 +3,8 @@ "sample_name": "NA12891", "base_file_name": "NA12891", "flowcell_unmapped_bams": [ - "gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/D5327.NA12891/H2GCKCCXX.7.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/D5327.NA12891/H2GCKCCXX.8.unmapped.bam" + "gs://pd-test-storage-public/ExomeGermlineSingleSample/input/scientific/D5327.NA12891/H2GCKCCXX.7.unmapped.bam", + "gs://pd-test-storage-public/ExomeGermlineSingleSample/input/scientific/D5327.NA12891/H2GCKCCXX.8.unmapped.bam" ], "final_gvcf_base_name": "NA12891", "unmapped_bam_suffix": ".unmapped.bam" @@ -44,8 +44,8 @@ "break_bands_at_multiples_of": 0 }, - "ExomeGermlineSingleSample.fingerprint_genotypes_file": "gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/D5327.NA12891/D5327.NA12891.reference.fingerprint.vcf.gz", - "ExomeGermlineSingleSample.fingerprint_genotypes_index": "gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/D5327.NA12891/D5327.NA12891.reference.fingerprint.vcf.gz.tbi", + "ExomeGermlineSingleSample.fingerprint_genotypes_file": "gs://pd-test-storage-public/ExomeGermlineSingleSample/input/scientific/D5327.NA12891/D5327.NA12891.reference.fingerprint.vcf.gz", + "ExomeGermlineSingleSample.fingerprint_genotypes_index": "gs://pd-test-storage-public/ExomeGermlineSingleSample/input/scientific/D5327.NA12891/D5327.NA12891.reference.fingerprint.vcf.gz.tbi", "ExomeGermlineSingleSample.target_interval_list": "gs://broad-references-private/HybSelOligos/whole_exome_illumina_coding_v1/whole_exome_illumina_coding_v1.Homo_sapiens_assembly38.targets.interval_list", "ExomeGermlineSingleSample.bait_interval_list": "gs://broad-references-private/HybSelOligos/whole_exome_illumina_coding_v1/whole_exome_illumina_coding_v1.Homo_sapiens_assembly38.baits.interval_list", "ExomeGermlineSingleSample.bait_set_name": "whole_exome_illumina_coding_v1", diff --git a/pipelines/broad/dna_seq/germline/single_sample/exome/test_inputs/Scientific/D5327.NA12892.json b/pipelines/broad/dna_seq/germline/single_sample/exome/test_inputs/Scientific/D5327.NA12892.json index 67ee0a8bd0..69f22f8dc9 100644 --- a/pipelines/broad/dna_seq/germline/single_sample/exome/test_inputs/Scientific/D5327.NA12892.json +++ b/pipelines/broad/dna_seq/germline/single_sample/exome/test_inputs/Scientific/D5327.NA12892.json @@ -3,8 +3,8 @@ "sample_name": "NA12892", "base_file_name": "NA12892", "flowcell_unmapped_bams": [ - "gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/D5327.NA12892/H2GCKCCXX.7.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/D5327.NA12892/H2GCKCCXX.8.unmapped.bam" + "gs://pd-test-storage-public/ExomeGermlineSingleSample/input/scientific/D5327.NA12892/H2GCKCCXX.7.unmapped.bam", + "gs://pd-test-storage-public/ExomeGermlineSingleSample/input/scientific/D5327.NA12892/H2GCKCCXX.8.unmapped.bam" ], "final_gvcf_base_name": "NA12892", "unmapped_bam_suffix": ".unmapped.bam" @@ -45,8 +45,8 @@ "break_bands_at_multiples_of": 0 }, - "ExomeGermlineSingleSample.fingerprint_genotypes_file": "gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/D5327.NA12892/D5327.NA12892.reference.fingerprint.vcf.gz", - "ExomeGermlineSingleSample.fingerprint_genotypes_index": "gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/D5327.NA12892/D5327.NA12892.reference.fingerprint.vcf.gz.tbi", + "ExomeGermlineSingleSample.fingerprint_genotypes_file": "gs://pd-test-storage-public/ExomeGermlineSingleSample/input/scientific/D5327.NA12892/D5327.NA12892.reference.fingerprint.vcf.gz", + "ExomeGermlineSingleSample.fingerprint_genotypes_index": "gs://pd-test-storage-public/ExomeGermlineSingleSample/input/scientific/D5327.NA12892/D5327.NA12892.reference.fingerprint.vcf.gz.tbi", "ExomeGermlineSingleSample.target_interval_list": "gs://broad-references-private/HybSelOligos/whole_exome_illumina_coding_v1/whole_exome_illumina_coding_v1.Homo_sapiens_assembly38.targets.interval_list", "ExomeGermlineSingleSample.bait_interval_list": "gs://broad-references-private/HybSelOligos/whole_exome_illumina_coding_v1/whole_exome_illumina_coding_v1.Homo_sapiens_assembly38.baits.interval_list", "ExomeGermlineSingleSample.bait_set_name": "whole_exome_illumina_coding_v1", diff --git a/pipelines/broad/dna_seq/germline/single_sample/exome/test_inputs/Scientific/RP-1535.NA17-308.json b/pipelines/broad/dna_seq/germline/single_sample/exome/test_inputs/Scientific/RP-1535.NA17-308.json index 1d8834a98e..01650b3920 100644 --- a/pipelines/broad/dna_seq/germline/single_sample/exome/test_inputs/Scientific/RP-1535.NA17-308.json +++ b/pipelines/broad/dna_seq/germline/single_sample/exome/test_inputs/Scientific/RP-1535.NA17-308.json @@ -3,24 +3,24 @@ "sample_name": "NA17-308", "base_file_name": "NA17-308", "flowcell_unmapped_bams": [ - "gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/RP-1535.NA17-308/HM5NCBBXX.1.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/RP-1535.NA17-308/HM5NCBBXX.3.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/RP-1535.NA17-308/HM5NCBBXX.4.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/RP-1535.NA17-308/HM5NCBBXX.2.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/RP-1535.NA17-308/HMF2NBBXX.5.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/RP-1535.NA17-308/HMF2NBBXX.6.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/RP-1535.NA17-308/HMF2NBBXX.8.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/RP-1535.NA17-308/HMF2NBBXX.7.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/RP-1535.NA17-308/HMF7MBBXX.3.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/RP-1535.NA17-308/HMF7MBBXX.4.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/RP-1535.NA17-308/HMF7MBBXX.5.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/RP-1535.NA17-308/HMF7MBBXX.1.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/RP-1535.NA17-308/HMF7MBBXX.6.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/RP-1535.NA17-308/HMF7MBBXX.8.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/RP-1535.NA17-308/HMF7MBBXX.7.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/RP-1535.NA17-308/HM5LFBBXX.8.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/RP-1535.NA17-308/HMF7MBBXX.2.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/RP-1535.NA17-308/HM5NCBBXX.5.unmapped.bam" + "gs://pd-test-storage-private/ExomeGermlineSingleSample/input/scientific/RP-1535.NA17-308/HM5NCBBXX.1.unmapped.bam", + "gs://pd-test-storage-private/ExomeGermlineSingleSample/input/scientific/RP-1535.NA17-308/HM5NCBBXX.3.unmapped.bam", + "gs://pd-test-storage-private/ExomeGermlineSingleSample/input/scientific/RP-1535.NA17-308/HM5NCBBXX.4.unmapped.bam", + "gs://pd-test-storage-private/ExomeGermlineSingleSample/input/scientific/RP-1535.NA17-308/HM5NCBBXX.2.unmapped.bam", + "gs://pd-test-storage-private/ExomeGermlineSingleSample/input/scientific/RP-1535.NA17-308/HMF2NBBXX.5.unmapped.bam", + "gs://pd-test-storage-private/ExomeGermlineSingleSample/input/scientific/RP-1535.NA17-308/HMF2NBBXX.6.unmapped.bam", + "gs://pd-test-storage-private/ExomeGermlineSingleSample/input/scientific/RP-1535.NA17-308/HMF2NBBXX.8.unmapped.bam", + "gs://pd-test-storage-private/ExomeGermlineSingleSample/input/scientific/RP-1535.NA17-308/HMF2NBBXX.7.unmapped.bam", + "gs://pd-test-storage-private/ExomeGermlineSingleSample/input/scientific/RP-1535.NA17-308/HMF7MBBXX.3.unmapped.bam", + "gs://pd-test-storage-private/ExomeGermlineSingleSample/input/scientific/RP-1535.NA17-308/HMF7MBBXX.4.unmapped.bam", + "gs://pd-test-storage-private/ExomeGermlineSingleSample/input/scientific/RP-1535.NA17-308/HMF7MBBXX.5.unmapped.bam", + "gs://pd-test-storage-private/ExomeGermlineSingleSample/input/scientific/RP-1535.NA17-308/HMF7MBBXX.1.unmapped.bam", + "gs://pd-test-storage-private/ExomeGermlineSingleSample/input/scientific/RP-1535.NA17-308/HMF7MBBXX.6.unmapped.bam", + "gs://pd-test-storage-private/ExomeGermlineSingleSample/input/scientific/RP-1535.NA17-308/HMF7MBBXX.8.unmapped.bam", + "gs://pd-test-storage-private/ExomeGermlineSingleSample/input/scientific/RP-1535.NA17-308/HMF7MBBXX.7.unmapped.bam", + "gs://pd-test-storage-private/ExomeGermlineSingleSample/input/scientific/RP-1535.NA17-308/HM5LFBBXX.8.unmapped.bam", + "gs://pd-test-storage-private/ExomeGermlineSingleSample/input/scientific/RP-1535.NA17-308/HMF7MBBXX.2.unmapped.bam", + "gs://pd-test-storage-private/ExomeGermlineSingleSample/input/scientific/RP-1535.NA17-308/HM5NCBBXX.5.unmapped.bam" ], "final_gvcf_base_name": "NA17-308", "unmapped_bam_suffix": ".unmapped.bam" @@ -61,8 +61,8 @@ "break_bands_at_multiples_of": 0 }, - "ExomeGermlineSingleSample.fingerprint_genotypes_file": "gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/RP-1535.NA17-308/RP-1535.NA17-308.reference.fingerprint.vcf.gz", - "ExomeGermlineSingleSample.fingerprint_genotypes_index": "gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/RP-1535.NA17-308/RP-1535.NA17-308.reference.fingerprint.vcf.gz.tbi", + "ExomeGermlineSingleSample.fingerprint_genotypes_file": "gs://pd-test-storage-private/ExomeGermlineSingleSample/input/scientific/RP-1535.NA17-308/RP-1535.NA17-308.reference.fingerprint.vcf.gz", + "ExomeGermlineSingleSample.fingerprint_genotypes_index": "gs://pd-test-storage-private/ExomeGermlineSingleSample/input/scientific/RP-1535.NA17-308/RP-1535.NA17-308.reference.fingerprint.vcf.gz.tbi", "ExomeGermlineSingleSample.target_interval_list": "gs://broad-references-private/HybSelOligos/whole_exome_illumina_coding_v1/whole_exome_illumina_coding_v1.Homo_sapiens_assembly38.targets.interval_list", "ExomeGermlineSingleSample.bait_interval_list": "gs://broad-references-private/HybSelOligos/whole_exome_illumina_coding_v1/whole_exome_illumina_coding_v1.Homo_sapiens_assembly38.baits.interval_list", "ExomeGermlineSingleSample.bait_set_name": "whole_exome_illumina_coding_v1", diff --git a/pipelines/broad/dna_seq/germline/single_sample/wgs/test_inputs/Plumbing/dragen_mode_best_results.json b/pipelines/broad/dna_seq/germline/single_sample/wgs/test_inputs/Plumbing/dragen_mode_best_results.json index a06a620b6c..6ffd725311 100644 --- a/pipelines/broad/dna_seq/germline/single_sample/wgs/test_inputs/Plumbing/dragen_mode_best_results.json +++ b/pipelines/broad/dna_seq/germline/single_sample/wgs/test_inputs/Plumbing/dragen_mode_best_results.json @@ -52,8 +52,8 @@ "break_bands_at_multiples_of": 100000 }, - "WholeGenomeGermlineSingleSample.fingerprint_genotypes_file": "gs://broad-gotc-test-storage/single_sample/plumbing/bams/G96830.NA12878/G96830.NA12878.hg38.reference.fingerprint.vcf.gz", - "WholeGenomeGermlineSingleSample.fingerprint_genotypes_index": "gs://broad-gotc-test-storage/single_sample/plumbing/bams/G96830.NA12878/G96830.NA12878.hg38.reference.fingerprint.vcf.gz.tbi", + "WholeGenomeGermlineSingleSample.fingerprint_genotypes_file": "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/plumbing/dragen_mode_best_results/G96830.NA12878.hg38.reference.fingerprint.vcf.gz", + "WholeGenomeGermlineSingleSample.fingerprint_genotypes_index": "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/plumbing/dragen_mode_best_results/G96830.NA12878.hg38.reference.fingerprint.vcf.gz.tbi", "WholeGenomeGermlineSingleSample.wgs_coverage_interval_list": "gs://gcp-public-data--broad-references/hg38/v0/wgs_coverage_regions.hg38.interval_list", "WholeGenomeGermlineSingleSample.papi_settings": { diff --git a/pipelines/broad/dna_seq/germline/single_sample/wgs/test_inputs/Plumbing/dragen_mode_functional_equivalence.json b/pipelines/broad/dna_seq/germline/single_sample/wgs/test_inputs/Plumbing/dragen_mode_functional_equivalence.json index 928deacdb5..3441df38d4 100644 --- a/pipelines/broad/dna_seq/germline/single_sample/wgs/test_inputs/Plumbing/dragen_mode_functional_equivalence.json +++ b/pipelines/broad/dna_seq/germline/single_sample/wgs/test_inputs/Plumbing/dragen_mode_functional_equivalence.json @@ -53,8 +53,8 @@ "break_bands_at_multiples_of": 100000 }, - "WholeGenomeGermlineSingleSample.fingerprint_genotypes_file": "gs://broad-gotc-test-storage/single_sample/plumbing/bams/G96830.NA12878/G96830.NA12878.hg38.reference.fingerprint.vcf.gz", - "WholeGenomeGermlineSingleSample.fingerprint_genotypes_index": "gs://broad-gotc-test-storage/single_sample/plumbing/bams/G96830.NA12878/G96830.NA12878.hg38.reference.fingerprint.vcf.gz.tbi", + "WholeGenomeGermlineSingleSample.fingerprint_genotypes_file": "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/plumbing/dragen_mode_functional_equivalence/G96830.NA12878.hg38.reference.fingerprint.vcf.gz", + "WholeGenomeGermlineSingleSample.fingerprint_genotypes_index": "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/plumbing/dragen_mode_functional_equivalence/G96830.NA12878.hg38.reference.fingerprint.vcf.gz.tbi", "WholeGenomeGermlineSingleSample.wgs_coverage_interval_list": "gs://gcp-public-data--broad-references/hg38/v0/wgs_coverage_regions.hg38.interval_list", "WholeGenomeGermlineSingleSample.papi_settings": { diff --git a/pipelines/broad/dna_seq/germline/single_sample/wgs/test_inputs/Scientific/G94794.CHMI_CHMI3_WGS2.json b/pipelines/broad/dna_seq/germline/single_sample/wgs/test_inputs/Scientific/G94794.CHMI_CHMI3_WGS2.json index 33374a597f..84d8ef5c26 100644 --- a/pipelines/broad/dna_seq/germline/single_sample/wgs/test_inputs/Scientific/G94794.CHMI_CHMI3_WGS2.json +++ b/pipelines/broad/dna_seq/germline/single_sample/wgs/test_inputs/Scientific/G94794.CHMI_CHMI3_WGS2.json @@ -3,30 +3,30 @@ "sample_name": "CHMI_CHMI3_WGS2", "base_file_name": "CHMI_CHMI3_WGS2", "flowcell_unmapped_bams": [ - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94794.CHMI_CHMI3_WGS2/HJCMTCCXX.5.Pond-487422.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94794.CHMI_CHMI3_WGS2/HK2WYCCXX.1.Pond-487422.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94794.CHMI_CHMI3_WGS2/HK2WYCCXX.2.Pond-487422.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94794.CHMI_CHMI3_WGS2/HK2WYCCXX.3.Pond-487422.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94794.CHMI_CHMI3_WGS2/HK2WYCCXX.4.Pond-487422.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94794.CHMI_CHMI3_WGS2/HK2WYCCXX.5.Pond-487422.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94794.CHMI_CHMI3_WGS2/HK2WYCCXX.6.Pond-487422.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94794.CHMI_CHMI3_WGS2/HK2WYCCXX.7.Pond-487422.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94794.CHMI_CHMI3_WGS2/HK2WYCCXX.8.Pond-487422.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94794.CHMI_CHMI3_WGS2/HK35WCCXX.1.Pond-487422.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94794.CHMI_CHMI3_WGS2/HK35WCCXX.2.Pond-487422.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94794.CHMI_CHMI3_WGS2/HK35WCCXX.3.Pond-487422.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94794.CHMI_CHMI3_WGS2/HK35WCCXX.4.Pond-487422.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94794.CHMI_CHMI3_WGS2/HK35WCCXX.5.Pond-487422.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94794.CHMI_CHMI3_WGS2/HK35WCCXX.6.Pond-487422.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94794.CHMI_CHMI3_WGS2/HK35WCCXX.7.Pond-487422.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94794.CHMI_CHMI3_WGS2/HK35WCCXX.8.Pond-487422.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94794.CHMI_CHMI3_WGS2/HK3MJCCXX.6.Pond-487422.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94794.CHMI_CHMI3_WGS2/HK3MJCCXX.7.Pond-487422.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94794.CHMI_CHMI3_WGS2/HK3MJCCXX.8.Pond-487422.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94794.CHMI_CHMI3_WGS2/HK3T7CCXX.1.Pond-487422.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94794.CHMI_CHMI3_WGS2/HK3T7CCXX.2.Pond-487422.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94794.CHMI_CHMI3_WGS2/HK3T7CCXX.3.Pond-487422.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94794.CHMI_CHMI3_WGS2/HK3T7CCXX.4.Pond-487422.unmapped.bam" + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94794.CHMI_CHMI3_WGS2/G94794.CHMI_CHMI3_WGS2/HJCMTCCXX.5.Pond-487422.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94794.CHMI_CHMI3_WGS2/G94794.CHMI_CHMI3_WGS2/HK2WYCCXX.1.Pond-487422.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94794.CHMI_CHMI3_WGS2/G94794.CHMI_CHMI3_WGS2/HK2WYCCXX.2.Pond-487422.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94794.CHMI_CHMI3_WGS2/G94794.CHMI_CHMI3_WGS2/HK2WYCCXX.3.Pond-487422.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94794.CHMI_CHMI3_WGS2/G94794.CHMI_CHMI3_WGS2/HK2WYCCXX.4.Pond-487422.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94794.CHMI_CHMI3_WGS2/G94794.CHMI_CHMI3_WGS2/HK2WYCCXX.5.Pond-487422.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94794.CHMI_CHMI3_WGS2/G94794.CHMI_CHMI3_WGS2/HK2WYCCXX.6.Pond-487422.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94794.CHMI_CHMI3_WGS2/G94794.CHMI_CHMI3_WGS2/HK2WYCCXX.7.Pond-487422.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94794.CHMI_CHMI3_WGS2/G94794.CHMI_CHMI3_WGS2/HK2WYCCXX.8.Pond-487422.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94794.CHMI_CHMI3_WGS2/G94794.CHMI_CHMI3_WGS2/HK35WCCXX.1.Pond-487422.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94794.CHMI_CHMI3_WGS2/G94794.CHMI_CHMI3_WGS2/HK35WCCXX.2.Pond-487422.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94794.CHMI_CHMI3_WGS2/G94794.CHMI_CHMI3_WGS2/HK35WCCXX.3.Pond-487422.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94794.CHMI_CHMI3_WGS2/G94794.CHMI_CHMI3_WGS2/HK35WCCXX.4.Pond-487422.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94794.CHMI_CHMI3_WGS2/G94794.CHMI_CHMI3_WGS2/HK35WCCXX.5.Pond-487422.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94794.CHMI_CHMI3_WGS2/G94794.CHMI_CHMI3_WGS2/HK35WCCXX.6.Pond-487422.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94794.CHMI_CHMI3_WGS2/G94794.CHMI_CHMI3_WGS2/HK35WCCXX.7.Pond-487422.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94794.CHMI_CHMI3_WGS2/G94794.CHMI_CHMI3_WGS2/HK35WCCXX.8.Pond-487422.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94794.CHMI_CHMI3_WGS2/G94794.CHMI_CHMI3_WGS2/HK3MJCCXX.6.Pond-487422.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94794.CHMI_CHMI3_WGS2/G94794.CHMI_CHMI3_WGS2/HK3MJCCXX.7.Pond-487422.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94794.CHMI_CHMI3_WGS2/G94794.CHMI_CHMI3_WGS2/HK3MJCCXX.8.Pond-487422.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94794.CHMI_CHMI3_WGS2/G94794.CHMI_CHMI3_WGS2/HK3T7CCXX.1.Pond-487422.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94794.CHMI_CHMI3_WGS2/G94794.CHMI_CHMI3_WGS2/HK3T7CCXX.2.Pond-487422.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94794.CHMI_CHMI3_WGS2/G94794.CHMI_CHMI3_WGS2/HK3T7CCXX.3.Pond-487422.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94794.CHMI_CHMI3_WGS2/G94794.CHMI_CHMI3_WGS2/HK3T7CCXX.4.Pond-487422.unmapped.bam" ], "final_gvcf_base_name": "CHMI_CHMI3_WGS2.f6c39eb5-0716-4f02-9be8-47b343c5830e", "unmapped_bam_suffix": ".unmapped.bam" @@ -67,7 +67,7 @@ "break_bands_at_multiples_of": 1000000 }, - "WholeGenomeGermlineSingleSample.fingerprint_genotypes_file": "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/fingerprint_vcfs/G94794.CHMI_CHMI3_WGS2.reference.fingerprint.vcf", + "WholeGenomeGermlineSingleSample.fingerprint_genotypes_file": "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94794.CHMI_CHMI3_WGS2/G94794.CHMI_CHMI3_WGS2.reference.fingerprint.vcf", "WholeGenomeGermlineSingleSample.wgs_coverage_interval_list": "gs://gcp-public-data--broad-references/hg38/v0/wgs_coverage_regions.hg38.interval_list", "WholeGenomeGermlineSingleSample.papi_settings": { diff --git a/pipelines/broad/dna_seq/germline/single_sample/wgs/test_inputs/Scientific/G94982.NA12878.dragen_mode_best_results.json b/pipelines/broad/dna_seq/germline/single_sample/wgs/test_inputs/Scientific/G94982.NA12878.dragen_mode_best_results.json index c625c8b4c3..4b4bb8aaab 100644 --- a/pipelines/broad/dna_seq/germline/single_sample/wgs/test_inputs/Scientific/G94982.NA12878.dragen_mode_best_results.json +++ b/pipelines/broad/dna_seq/germline/single_sample/wgs/test_inputs/Scientific/G94982.NA12878.dragen_mode_best_results.json @@ -3,30 +3,30 @@ "sample_name": "NA12878", "base_file_name": "NA12878", "flowcell_unmapped_bams": [ - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12878/HJYFJCCXX.4.Pond-492093.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12878/HJYFJCCXX.5.Pond-492093.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12878/HJYFJCCXX.6.Pond-492093.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12878/HJYFJCCXX.7.Pond-492093.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12878/HJYFJCCXX.8.Pond-492093.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12878/HJYN2CCXX.1.Pond-492093.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12878/HK35MCCXX.1.Pond-492093.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12878/HK35MCCXX.2.Pond-492093.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12878/HK35MCCXX.3.Pond-492093.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12878/HK35MCCXX.4.Pond-492093.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12878/HK35MCCXX.5.Pond-492093.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12878/HK35MCCXX.6.Pond-492093.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12878/HK35MCCXX.7.Pond-492093.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12878/HK35MCCXX.8.Pond-492093.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12878/HK35NCCXX.1.Pond-492093.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12878/HK35NCCXX.2.Pond-492093.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12878/HK3T5CCXX.1.Pond-492093.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12878/HK3T5CCXX.2.Pond-492093.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12878/HK3T5CCXX.3.Pond-492093.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12878/HK3T5CCXX.4.Pond-492093.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12878/HK3T5CCXX.5.Pond-492093.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12878/HK3T5CCXX.6.Pond-492093.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12878/HK3T5CCXX.7.Pond-492093.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12878/HK3T5CCXX.8.Pond-492093.unmapped.bam" + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12878.dragen_mode_best_results/HJYFJCCXX.4.Pond-492093.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12878.dragen_mode_best_results/HJYFJCCXX.5.Pond-492093.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12878.dragen_mode_best_results/HJYFJCCXX.6.Pond-492093.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12878.dragen_mode_best_results/HJYFJCCXX.7.Pond-492093.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12878.dragen_mode_best_results/HJYFJCCXX.8.Pond-492093.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12878.dragen_mode_best_results/HJYN2CCXX.1.Pond-492093.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12878.dragen_mode_best_results/HK35MCCXX.1.Pond-492093.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12878.dragen_mode_best_results/HK35MCCXX.2.Pond-492093.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12878.dragen_mode_best_results/HK35MCCXX.3.Pond-492093.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12878.dragen_mode_best_results/HK35MCCXX.4.Pond-492093.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12878.dragen_mode_best_results/HK35MCCXX.5.Pond-492093.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12878.dragen_mode_best_results/HK35MCCXX.6.Pond-492093.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12878.dragen_mode_best_results/HK35MCCXX.7.Pond-492093.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12878.dragen_mode_best_results/HK35MCCXX.8.Pond-492093.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12878.dragen_mode_best_results/HK35NCCXX.1.Pond-492093.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12878.dragen_mode_best_results/HK35NCCXX.2.Pond-492093.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12878.dragen_mode_best_results/HK3T5CCXX.1.Pond-492093.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12878.dragen_mode_best_results/HK3T5CCXX.2.Pond-492093.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12878.dragen_mode_best_results/HK3T5CCXX.3.Pond-492093.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12878.dragen_mode_best_results/HK3T5CCXX.4.Pond-492093.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12878.dragen_mode_best_results/HK3T5CCXX.5.Pond-492093.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12878.dragen_mode_best_results/HK3T5CCXX.6.Pond-492093.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12878.dragen_mode_best_results/HK3T5CCXX.7.Pond-492093.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12878.dragen_mode_best_results/HK3T5CCXX.8.Pond-492093.unmapped.bam" ], "final_gvcf_base_name": "NA12878.2b3dcfd9-5473-4cc8-a3ba-d643f6de3b07", "unmapped_bam_suffix": ".unmapped.bam" @@ -74,7 +74,7 @@ "break_bands_at_multiples_of": 1000000 }, - "WholeGenomeGermlineSingleSample.fingerprint_genotypes_file": "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/fingerprint_vcfs/G94982.NA12878.reference.fingerprint.vcf", + "WholeGenomeGermlineSingleSample.fingerprint_genotypes_file": "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12878.dragen_mode_best_results/G94982.NA12878.reference.fingerprint.vcf", "WholeGenomeGermlineSingleSample.wgs_coverage_interval_list": "gs://gcp-public-data--broad-references/hg38/v0/wgs_coverage_regions.hg38.interval_list", "WholeGenomeGermlineSingleSample.papi_settings": { diff --git a/pipelines/broad/dna_seq/germline/single_sample/wgs/test_inputs/Scientific/G94982.NA12878.dragen_mode_functional_equivalence.json b/pipelines/broad/dna_seq/germline/single_sample/wgs/test_inputs/Scientific/G94982.NA12878.dragen_mode_functional_equivalence.json index 271675b702..ce11c95e07 100644 --- a/pipelines/broad/dna_seq/germline/single_sample/wgs/test_inputs/Scientific/G94982.NA12878.dragen_mode_functional_equivalence.json +++ b/pipelines/broad/dna_seq/germline/single_sample/wgs/test_inputs/Scientific/G94982.NA12878.dragen_mode_functional_equivalence.json @@ -3,30 +3,30 @@ "sample_name": "NA12878", "base_file_name": "NA12878", "flowcell_unmapped_bams": [ - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12878/HJYFJCCXX.4.Pond-492093.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12878/HJYFJCCXX.5.Pond-492093.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12878/HJYFJCCXX.6.Pond-492093.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12878/HJYFJCCXX.7.Pond-492093.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12878/HJYFJCCXX.8.Pond-492093.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12878/HJYN2CCXX.1.Pond-492093.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12878/HK35MCCXX.1.Pond-492093.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12878/HK35MCCXX.2.Pond-492093.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12878/HK35MCCXX.3.Pond-492093.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12878/HK35MCCXX.4.Pond-492093.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12878/HK35MCCXX.5.Pond-492093.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12878/HK35MCCXX.6.Pond-492093.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12878/HK35MCCXX.7.Pond-492093.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12878/HK35MCCXX.8.Pond-492093.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12878/HK35NCCXX.1.Pond-492093.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12878/HK35NCCXX.2.Pond-492093.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12878/HK3T5CCXX.1.Pond-492093.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12878/HK3T5CCXX.2.Pond-492093.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12878/HK3T5CCXX.3.Pond-492093.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12878/HK3T5CCXX.4.Pond-492093.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12878/HK3T5CCXX.5.Pond-492093.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12878/HK3T5CCXX.6.Pond-492093.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12878/HK3T5CCXX.7.Pond-492093.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12878/HK3T5CCXX.8.Pond-492093.unmapped.bam" + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12878.dragen_mode_functional_equivalence/HJYFJCCXX.4.Pond-492093.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12878.dragen_mode_functional_equivalence/HJYFJCCXX.5.Pond-492093.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12878.dragen_mode_functional_equivalence/HJYFJCCXX.6.Pond-492093.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12878.dragen_mode_functional_equivalence/HJYFJCCXX.7.Pond-492093.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12878.dragen_mode_functional_equivalence/HJYFJCCXX.8.Pond-492093.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12878.dragen_mode_functional_equivalence/HJYN2CCXX.1.Pond-492093.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12878.dragen_mode_functional_equivalence/HK35MCCXX.1.Pond-492093.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12878.dragen_mode_functional_equivalence/HK35MCCXX.2.Pond-492093.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12878.dragen_mode_functional_equivalence/HK35MCCXX.3.Pond-492093.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12878.dragen_mode_functional_equivalence/HK35MCCXX.4.Pond-492093.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12878.dragen_mode_functional_equivalence/HK35MCCXX.5.Pond-492093.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12878.dragen_mode_functional_equivalence/HK35MCCXX.6.Pond-492093.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12878.dragen_mode_functional_equivalence/HK35MCCXX.7.Pond-492093.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12878.dragen_mode_functional_equivalence/HK35MCCXX.8.Pond-492093.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12878.dragen_mode_functional_equivalence/HK35NCCXX.1.Pond-492093.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12878.dragen_mode_functional_equivalence/HK35NCCXX.2.Pond-492093.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12878.dragen_mode_functional_equivalence/HK3T5CCXX.1.Pond-492093.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12878.dragen_mode_functional_equivalence/HK3T5CCXX.2.Pond-492093.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12878.dragen_mode_functional_equivalence/HK3T5CCXX.3.Pond-492093.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12878.dragen_mode_functional_equivalence/HK3T5CCXX.4.Pond-492093.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12878.dragen_mode_functional_equivalence/HK3T5CCXX.5.Pond-492093.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12878.dragen_mode_functional_equivalence/HK3T5CCXX.6.Pond-492093.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12878.dragen_mode_functional_equivalence/HK3T5CCXX.7.Pond-492093.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12878.dragen_mode_functional_equivalence/HK3T5CCXX.8.Pond-492093.unmapped.bam" ], "final_gvcf_base_name": "NA12878.2b3dcfd9-5473-4cc8-a3ba-d643f6de3b07", "unmapped_bam_suffix": ".unmapped.bam" @@ -73,7 +73,7 @@ "break_bands_at_multiples_of": 1000000 }, - "WholeGenomeGermlineSingleSample.fingerprint_genotypes_file": "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/fingerprint_vcfs/G94982.NA12878.reference.fingerprint.vcf", + "WholeGenomeGermlineSingleSample.fingerprint_genotypes_file": "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12878.dragen_mode_functional_equivalence/G94982.NA12878.reference.fingerprint.vcf", "WholeGenomeGermlineSingleSample.wgs_coverage_interval_list": "gs://gcp-public-data--broad-references/hg38/v0/wgs_coverage_regions.hg38.interval_list", "WholeGenomeGermlineSingleSample.papi_settings": { diff --git a/pipelines/broad/dna_seq/germline/single_sample/wgs/test_inputs/Scientific/G94982.NA12878.json b/pipelines/broad/dna_seq/germline/single_sample/wgs/test_inputs/Scientific/G94982.NA12878.json index 96cac538de..dd8157f0df 100644 --- a/pipelines/broad/dna_seq/germline/single_sample/wgs/test_inputs/Scientific/G94982.NA12878.json +++ b/pipelines/broad/dna_seq/germline/single_sample/wgs/test_inputs/Scientific/G94982.NA12878.json @@ -3,30 +3,30 @@ "sample_name": "NA12878", "base_file_name": "NA12878", "flowcell_unmapped_bams": [ - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12878/HJYFJCCXX.4.Pond-492093.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12878/HJYFJCCXX.5.Pond-492093.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12878/HJYFJCCXX.6.Pond-492093.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12878/HJYFJCCXX.7.Pond-492093.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12878/HJYFJCCXX.8.Pond-492093.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12878/HJYN2CCXX.1.Pond-492093.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12878/HK35MCCXX.1.Pond-492093.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12878/HK35MCCXX.2.Pond-492093.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12878/HK35MCCXX.3.Pond-492093.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12878/HK35MCCXX.4.Pond-492093.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12878/HK35MCCXX.5.Pond-492093.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12878/HK35MCCXX.6.Pond-492093.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12878/HK35MCCXX.7.Pond-492093.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12878/HK35MCCXX.8.Pond-492093.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12878/HK35NCCXX.1.Pond-492093.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12878/HK35NCCXX.2.Pond-492093.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12878/HK3T5CCXX.1.Pond-492093.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12878/HK3T5CCXX.2.Pond-492093.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12878/HK3T5CCXX.3.Pond-492093.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12878/HK3T5CCXX.4.Pond-492093.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12878/HK3T5CCXX.5.Pond-492093.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12878/HK3T5CCXX.6.Pond-492093.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12878/HK3T5CCXX.7.Pond-492093.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12878/HK3T5CCXX.8.Pond-492093.unmapped.bam" + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12878/HJYFJCCXX.4.Pond-492093.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12878/HJYFJCCXX.5.Pond-492093.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12878/HJYFJCCXX.6.Pond-492093.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12878/HJYFJCCXX.7.Pond-492093.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12878/HJYFJCCXX.8.Pond-492093.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12878/HJYN2CCXX.1.Pond-492093.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12878/HK35MCCXX.1.Pond-492093.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12878/HK35MCCXX.2.Pond-492093.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12878/HK35MCCXX.3.Pond-492093.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12878/HK35MCCXX.4.Pond-492093.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12878/HK35MCCXX.5.Pond-492093.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12878/HK35MCCXX.6.Pond-492093.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12878/HK35MCCXX.7.Pond-492093.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12878/HK35MCCXX.8.Pond-492093.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12878/HK35NCCXX.1.Pond-492093.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12878/HK35NCCXX.2.Pond-492093.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12878/HK3T5CCXX.1.Pond-492093.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12878/HK3T5CCXX.2.Pond-492093.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12878/HK3T5CCXX.3.Pond-492093.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12878/HK3T5CCXX.4.Pond-492093.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12878/HK3T5CCXX.5.Pond-492093.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12878/HK3T5CCXX.6.Pond-492093.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12878/HK3T5CCXX.7.Pond-492093.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12878/HK3T5CCXX.8.Pond-492093.unmapped.bam" ], "final_gvcf_base_name": "NA12878.2b3dcfd9-5473-4cc8-a3ba-d643f6de3b07", "unmapped_bam_suffix": ".unmapped.bam" @@ -67,7 +67,7 @@ "break_bands_at_multiples_of": 1000000 }, - "WholeGenomeGermlineSingleSample.fingerprint_genotypes_file": "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/fingerprint_vcfs/G94982.NA12878.reference.fingerprint.vcf", + "WholeGenomeGermlineSingleSample.fingerprint_genotypes_file": "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12878/G94982.NA12878.reference.fingerprint.vcf", "WholeGenomeGermlineSingleSample.wgs_coverage_interval_list": "gs://gcp-public-data--broad-references/hg38/v0/wgs_coverage_regions.hg38.interval_list", "WholeGenomeGermlineSingleSample.papi_settings": { diff --git a/pipelines/broad/dna_seq/germline/single_sample/wgs/test_inputs/Scientific/G94982.NA12891.json b/pipelines/broad/dna_seq/germline/single_sample/wgs/test_inputs/Scientific/G94982.NA12891.json index eeccd9275b..e66a454999 100644 --- a/pipelines/broad/dna_seq/germline/single_sample/wgs/test_inputs/Scientific/G94982.NA12891.json +++ b/pipelines/broad/dna_seq/germline/single_sample/wgs/test_inputs/Scientific/G94982.NA12891.json @@ -3,33 +3,33 @@ "sample_name": "NA12891", "base_file_name": "NA12891", "flowcell_unmapped_bams": [ - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12891/HJYFJCCXX.4.Pond-492101.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12891/HJYFJCCXX.5.Pond-492101.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12891/HJYFJCCXX.6.Pond-492101.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12891/HJYFJCCXX.7.Pond-492101.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12891/HJYFJCCXX.8.Pond-492101.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12891/HJYN2CCXX.1.Pond-492101.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12891/HK35MCCXX.1.Pond-492101.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12891/HK35MCCXX.2.Pond-492101.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12891/HK35MCCXX.3.Pond-492101.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12891/HK35MCCXX.4.Pond-492101.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12891/HK35MCCXX.5.Pond-492101.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12891/HK35MCCXX.6.Pond-492101.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12891/HK35MCCXX.7.Pond-492101.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12891/HK35MCCXX.8.Pond-492101.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12891/HK35NCCXX.1.Pond-492101.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12891/HK35NCCXX.2.Pond-492101.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12891/HK3T5CCXX.1.Pond-492101.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12891/HK3T5CCXX.2.Pond-492101.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12891/HK3T5CCXX.3.Pond-492101.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12891/HK3T5CCXX.4.Pond-492101.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12891/HK3T5CCXX.5.Pond-492101.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12891/HK3T5CCXX.6.Pond-492101.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12891/HK3T5CCXX.7.Pond-492101.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12891/HK3T5CCXX.8.Pond-492101.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12891/HM3G2CCXX.2.Pond-492101.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12891/HTL2KCCXX.5.Pond-492101.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12891/HTL2KCCXX.6.Pond-492101.unmapped.bam" + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12891/HJYFJCCXX.4.Pond-492101.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12891/HJYFJCCXX.5.Pond-492101.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12891/HJYFJCCXX.6.Pond-492101.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12891/HJYFJCCXX.7.Pond-492101.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12891/HJYFJCCXX.8.Pond-492101.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12891/HJYN2CCXX.1.Pond-492101.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12891/HK35MCCXX.1.Pond-492101.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12891/HK35MCCXX.2.Pond-492101.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12891/HK35MCCXX.3.Pond-492101.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12891/HK35MCCXX.4.Pond-492101.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12891/HK35MCCXX.5.Pond-492101.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12891/HK35MCCXX.6.Pond-492101.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12891/HK35MCCXX.7.Pond-492101.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12891/HK35MCCXX.8.Pond-492101.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12891/HK35NCCXX.1.Pond-492101.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12891/HK35NCCXX.2.Pond-492101.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12891/HK3T5CCXX.1.Pond-492101.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12891/HK3T5CCXX.2.Pond-492101.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12891/HK3T5CCXX.3.Pond-492101.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12891/HK3T5CCXX.4.Pond-492101.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12891/HK3T5CCXX.5.Pond-492101.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12891/HK3T5CCXX.6.Pond-492101.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12891/HK3T5CCXX.7.Pond-492101.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12891/HK3T5CCXX.8.Pond-492101.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12891/HM3G2CCXX.2.Pond-492101.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12891/HTL2KCCXX.5.Pond-492101.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12891/HTL2KCCXX.6.Pond-492101.unmapped.bam" ], "final_gvcf_base_name": "NA12891.0526ac75-aec1-4acf-9574-2c88878f4529", "unmapped_bam_suffix": ".unmapped.bam" @@ -70,7 +70,7 @@ "break_bands_at_multiples_of": 1000000 }, - "WholeGenomeGermlineSingleSample.fingerprint_genotypes_file": "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/fingerprint_vcfs/G94982.NA12891.FunctionalEqTest.reference.fingerprint.vcf", + "WholeGenomeGermlineSingleSample.fingerprint_genotypes_file": "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12891/G94982.NA12891.FunctionalEqTest.reference.fingerprint.vcf", "WholeGenomeGermlineSingleSample.wgs_coverage_interval_list": "gs://gcp-public-data--broad-references/hg38/v0/wgs_coverage_regions.hg38.interval_list", "WholeGenomeGermlineSingleSample.papi_settings": { diff --git a/pipelines/broad/dna_seq/germline/single_sample/wgs/test_inputs/Scientific/G94982.NA12892.json b/pipelines/broad/dna_seq/germline/single_sample/wgs/test_inputs/Scientific/G94982.NA12892.json index 5558036b60..f5def586de 100644 --- a/pipelines/broad/dna_seq/germline/single_sample/wgs/test_inputs/Scientific/G94982.NA12892.json +++ b/pipelines/broad/dna_seq/germline/single_sample/wgs/test_inputs/Scientific/G94982.NA12892.json @@ -3,31 +3,31 @@ "sample_name": "NA12892", "base_file_name": "NA12892", "flowcell_unmapped_bams": [ - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12892/HJYFJCCXX.4.Pond-492081.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12892/HJYFJCCXX.5.Pond-492081.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12892/HJYFJCCXX.6.Pond-492081.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12892/HJYFJCCXX.7.Pond-492081.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12892/HJYFJCCXX.8.Pond-492081.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12892/HJYN2CCXX.1.Pond-492081.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12892/HK35MCCXX.1.Pond-492081.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12892/HK35MCCXX.2.Pond-492081.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12892/HK35MCCXX.3.Pond-492081.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12892/HK35MCCXX.4.Pond-492081.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12892/HK35MCCXX.5.Pond-492081.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12892/HK35MCCXX.6.Pond-492081.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12892/HK35MCCXX.7.Pond-492081.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12892/HK35MCCXX.8.Pond-492081.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12892/HK35NCCXX.1.Pond-492081.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12892/HK35NCCXX.2.Pond-492081.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12892/HK3T5CCXX.1.Pond-492081.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12892/HK3T5CCXX.2.Pond-492081.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12892/HK3T5CCXX.3.Pond-492081.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12892/HK3T5CCXX.4.Pond-492081.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12892/HK3T5CCXX.5.Pond-492081.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12892/HK3T5CCXX.6.Pond-492081.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12892/HK3T5CCXX.7.Pond-492081.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12892/HK3T5CCXX.8.Pond-492081.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12892/HT23WCCXX.3.Pond-492081.unmapped.bam" + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12892/HJYFJCCXX.4.Pond-492081.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12892/HJYFJCCXX.5.Pond-492081.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12892/HJYFJCCXX.6.Pond-492081.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12892/HJYFJCCXX.7.Pond-492081.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12892/HJYFJCCXX.8.Pond-492081.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12892/HJYN2CCXX.1.Pond-492081.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12892/HK35MCCXX.1.Pond-492081.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12892/HK35MCCXX.2.Pond-492081.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12892/HK35MCCXX.3.Pond-492081.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12892/HK35MCCXX.4.Pond-492081.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12892/HK35MCCXX.5.Pond-492081.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12892/HK35MCCXX.6.Pond-492081.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12892/HK35MCCXX.7.Pond-492081.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12892/HK35MCCXX.8.Pond-492081.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12892/HK35NCCXX.1.Pond-492081.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12892/HK35NCCXX.2.Pond-492081.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12892/HK3T5CCXX.1.Pond-492081.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12892/HK3T5CCXX.2.Pond-492081.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12892/HK3T5CCXX.3.Pond-492081.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12892/HK3T5CCXX.4.Pond-492081.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12892/HK3T5CCXX.5.Pond-492081.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12892/HK3T5CCXX.6.Pond-492081.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12892/HK3T5CCXX.7.Pond-492081.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12892/HK3T5CCXX.8.Pond-492081.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12892/HT23WCCXX.3.Pond-492081.unmapped.bam" ], "final_gvcf_base_name": "NA12892.f175671b-f657-4077-9856-732c96b586ad", "unmapped_bam_suffix": ".unmapped.bam" @@ -68,7 +68,7 @@ "break_bands_at_multiples_of": 1000000 }, - "WholeGenomeGermlineSingleSample.fingerprint_genotypes_file": "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/fingerprint_vcfs/G94982.NA12892.FunctionalEqTest.reference.fingerprint.vcf", + "WholeGenomeGermlineSingleSample.fingerprint_genotypes_file": "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G94982.NA12892/G94982.NA12892.FunctionalEqTest.reference.fingerprint.vcf", "WholeGenomeGermlineSingleSample.wgs_coverage_interval_list": "gs://gcp-public-data--broad-references/hg38/v0/wgs_coverage_regions.hg38.interval_list", "WholeGenomeGermlineSingleSample.papi_settings": { diff --git a/pipelines/broad/dna_seq/germline/single_sample/wgs/test_inputs/Scientific/G96830.NA12878.json b/pipelines/broad/dna_seq/germline/single_sample/wgs/test_inputs/Scientific/G96830.NA12878.json index b4e3b1574a..83a179a6ed 100644 --- a/pipelines/broad/dna_seq/germline/single_sample/wgs/test_inputs/Scientific/G96830.NA12878.json +++ b/pipelines/broad/dna_seq/germline/single_sample/wgs/test_inputs/Scientific/G96830.NA12878.json @@ -3,30 +3,30 @@ "sample_name": "NA12878", "base_file_name": "NA12878", "flowcell_unmapped_bams": [ - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G96830.NA12878/HJYFJCCXX.4.Pond-492100.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G96830.NA12878/HJYFJCCXX.5.Pond-492100.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G96830.NA12878/HJYFJCCXX.6.Pond-492100.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G96830.NA12878/HJYFJCCXX.7.Pond-492100.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G96830.NA12878/HJYFJCCXX.8.Pond-492100.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G96830.NA12878/HJYN2CCXX.1.Pond-492100.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G96830.NA12878/HK35MCCXX.1.Pond-492100.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G96830.NA12878/HK35MCCXX.2.Pond-492100.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G96830.NA12878/HK35MCCXX.3.Pond-492100.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G96830.NA12878/HK35MCCXX.4.Pond-492100.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G96830.NA12878/HK35MCCXX.5.Pond-492100.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G96830.NA12878/HK35MCCXX.6.Pond-492100.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G96830.NA12878/HK35MCCXX.7.Pond-492100.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G96830.NA12878/HK35MCCXX.8.Pond-492100.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G96830.NA12878/HK35NCCXX.1.Pond-492100.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G96830.NA12878/HK35NCCXX.2.Pond-492100.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G96830.NA12878/HK3T5CCXX.1.Pond-492100.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G96830.NA12878/HK3T5CCXX.2.Pond-492100.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G96830.NA12878/HK3T5CCXX.3.Pond-492100.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G96830.NA12878/HK3T5CCXX.4.Pond-492100.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G96830.NA12878/HK3T5CCXX.5.Pond-492100.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G96830.NA12878/HK3T5CCXX.6.Pond-492100.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G96830.NA12878/HK3T5CCXX.7.Pond-492100.unmapped.bam", - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G96830.NA12878/HK3T5CCXX.8.Pond-492100.unmapped.bam" + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G96830.NA12878/HJYFJCCXX.4.Pond-492100.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G96830.NA12878/HJYFJCCXX.5.Pond-492100.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G96830.NA12878/HJYFJCCXX.6.Pond-492100.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G96830.NA12878/HJYFJCCXX.7.Pond-492100.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G96830.NA12878/HJYFJCCXX.8.Pond-492100.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G96830.NA12878/HJYN2CCXX.1.Pond-492100.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G96830.NA12878/HK35MCCXX.1.Pond-492100.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G96830.NA12878/HK35MCCXX.2.Pond-492100.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G96830.NA12878/HK35MCCXX.3.Pond-492100.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G96830.NA12878/HK35MCCXX.4.Pond-492100.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G96830.NA12878/HK35MCCXX.5.Pond-492100.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G96830.NA12878/HK35MCCXX.6.Pond-492100.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G96830.NA12878/HK35MCCXX.7.Pond-492100.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G96830.NA12878/HK35MCCXX.8.Pond-492100.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G96830.NA12878/HK35NCCXX.1.Pond-492100.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G96830.NA12878/HK35NCCXX.2.Pond-492100.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G96830.NA12878/HK3T5CCXX.1.Pond-492100.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G96830.NA12878/HK3T5CCXX.2.Pond-492100.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G96830.NA12878/HK3T5CCXX.3.Pond-492100.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G96830.NA12878/HK3T5CCXX.4.Pond-492100.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G96830.NA12878/HK3T5CCXX.5.Pond-492100.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G96830.NA12878/HK3T5CCXX.6.Pond-492100.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G96830.NA12878/HK3T5CCXX.7.Pond-492100.unmapped.bam", + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G96830.NA12878/HK3T5CCXX.8.Pond-492100.unmapped.bam" ], "final_gvcf_base_name": "NA12878", "unmapped_bam_suffix": ".unmapped.bam" @@ -67,7 +67,7 @@ "break_bands_at_multiples_of": 1000000 }, - "WholeGenomeGermlineSingleSample.fingerprint_genotypes_file": "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/fingerprint_vcfs/G96830.NA12878.FunctionalEqTest.reference.fingerprint.vcf", + "WholeGenomeGermlineSingleSample.fingerprint_genotypes_file": "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/G96830.NA12878/G96830.NA12878.FunctionalEqTest.reference.fingerprint.vcf", "WholeGenomeGermlineSingleSample.wgs_coverage_interval_list": "gs://gcp-public-data--broad-references/hg38/v0/wgs_coverage_regions.hg38.interval_list", "WholeGenomeGermlineSingleSample.papi_settings": { diff --git a/pipelines/broad/dna_seq/germline/single_sample/wgs/test_inputs/Scientific/RP-518.NA12878.json b/pipelines/broad/dna_seq/germline/single_sample/wgs/test_inputs/Scientific/RP-518.NA12878.json index 035b62a322..ea022322a8 100644 --- a/pipelines/broad/dna_seq/germline/single_sample/wgs/test_inputs/Scientific/RP-518.NA12878.json +++ b/pipelines/broad/dna_seq/germline/single_sample/wgs/test_inputs/Scientific/RP-518.NA12878.json @@ -3,7 +3,7 @@ "sample_name": "NA12878", "base_file_name": "NA12878.huge-ubam", "flowcell_unmapped_bams": [ - "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/RP-518.NA12878/H0164ALXX.2.Solexa-272222.unmapped.bam" + "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/RP-518.NA12878/H0164ALXX.2.Solexa-272222.unmapped.bam" ], "final_gvcf_base_name": "NA12878.huge-ubam", "unmapped_bam_suffix": ".unmapped.bam" @@ -44,7 +44,7 @@ "break_bands_at_multiples_of": 1000000 }, - "WholeGenomeGermlineSingleSample.fingerprint_genotypes_file": "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/fingerprint_vcfs/RP-518.NA12878.reference.fingerprint.vcf", + "WholeGenomeGermlineSingleSample.fingerprint_genotypes_file": "gs://pd-test-storage-public/WholeGenomeGermlineSingleSample/input/scientific/RP-518.NA12878/RP-518.NA12878.reference.fingerprint.vcf", "WholeGenomeGermlineSingleSample.wgs_coverage_interval_list": "gs://gcp-public-data--broad-references/hg38/v0/wgs_coverage_regions.hg38.interval_list", "WholeGenomeGermlineSingleSample.papi_settings": { @@ -52,4 +52,4 @@ "agg_preemptible_tries": 3 }, "WholeGenomeGermlineSingleSample.cloud_provider": "gcp" -} +} \ No newline at end of file diff --git a/pipelines/broad/dna_seq/somatic/single_sample/ugwgs/test_inputs/Plumbing/NA12878.downsampled.json b/pipelines/broad/dna_seq/somatic/single_sample/ugwgs/test_inputs/Plumbing/NA12878.downsampled.json index 04c8e8e39d..8614cd5b3f 100644 --- a/pipelines/broad/dna_seq/somatic/single_sample/ugwgs/test_inputs/Plumbing/NA12878.downsampled.json +++ b/pipelines/broad/dna_seq/somatic/single_sample/ugwgs/test_inputs/Plumbing/NA12878.downsampled.json @@ -1,5 +1,5 @@ { - "UltimaGenomicsWholeGenomeCramOnly.input_cram_list": ["gs://broad-gotc-test-storage/somatic_single_sample/ugwgs/plumbing/crams/downsampled_NA12878.cram"], + "UltimaGenomicsWholeGenomeCramOnly.input_cram_list": ["gs://pd-test-storage-public/UltimaGenomicsWholeGenomeCramOnly/input/plumbing/NA12878.downsampled/downsampled_NA12878.cram"], "UltimaGenomicsWholeGenomeCramOnly.base_file_name": "downsampled_NA12878", "UltimaGenomicsWholeGenomeCramOnly.contamination_sites": { "contamination_sites_vcf": "gs://gcp-public-data--broad-references/hg38/v0/ultima_genomics/verify_bam_id/Homo_sapiens_assembly38.contam_fixed.vcf", diff --git a/pipelines/broad/dna_seq/somatic/single_sample/ugwgs/test_inputs/Scientific/HCC1187.json b/pipelines/broad/dna_seq/somatic/single_sample/ugwgs/test_inputs/Scientific/HCC1187.json index 340a82d66e..3faff51a20 100644 --- a/pipelines/broad/dna_seq/somatic/single_sample/ugwgs/test_inputs/Scientific/HCC1187.json +++ b/pipelines/broad/dna_seq/somatic/single_sample/ugwgs/test_inputs/Scientific/HCC1187.json @@ -1,5 +1,5 @@ { - "UltimaGenomicsWholeGenomeCramOnly.input_cram_list": ["gs://broad-gotc-test-storage/somatic_single_sample/ugwgs/scientific/crams/012505-HCC1187-Lodeyonono-CTTAGCTGTGATGAT.cram"], + "UltimaGenomicsWholeGenomeCramOnly.input_cram_list": ["gs://pd-test-storage-private/UltimaGenomicsWholeGenomeCramOnly/input/scientific/HCC1187/012505-HCC1187-Lodeyonono-CTTAGCTGTGATGAT.cram"], "UltimaGenomicsWholeGenomeCramOnly.base_file_name": "HCC1187", "UltimaGenomicsWholeGenomeCramOnly.contamination_sites": { "contamination_sites_vcf": "gs://gcp-public-data--broad-references/hg38/v0/ultima_genomics/verify_bam_id/Homo_sapiens_assembly38.contam_fixed.vcf", diff --git a/pipelines/broad/reprocessing/cram_to_unmapped_bams/test_inputs/Plumbing/G96830.NA12878.WGS.json b/pipelines/broad/reprocessing/cram_to_unmapped_bams/test_inputs/Plumbing/G96830.NA12878.WGS.json index 896592d9b6..c034cebf62 100644 --- a/pipelines/broad/reprocessing/cram_to_unmapped_bams/test_inputs/Plumbing/G96830.NA12878.WGS.json +++ b/pipelines/broad/reprocessing/cram_to_unmapped_bams/test_inputs/Plumbing/G96830.NA12878.WGS.json @@ -1,6 +1,6 @@ { - "CramToUnmappedBams.input_cram": "gs://broad-gotc-test-storage/single_sample/plumbing/truth/master/20k/NA12878_PLUMBING.cram", - "CramToUnmappedBams.output_map": "gs://broad-gotc-test-storage/germline_single_sample/wgs/plumbing/bams/G96830.NA12878/readgroupid_to_bamfilename_map.txt", + "CramToUnmappedBams.input_cram": "gs://pd-test-storage-public/CramToUnmappedBams/input/plumbing/G96830.NA12878.WGS/NA12878_PLUMBING.cram", + "CramToUnmappedBams.output_map": "gs://pd-test-storage-public/CramToUnmappedBams/input/plumbing/G96830.NA12878.WGS/readgroupid_to_bamfilename_map.txt", "CramToUnmappedBams.base_file_name": "G96830.NA12878.WGS", "CramToUnmappedBams.unmapped_bam_suffix": ".unmapped.bam", "CramToUnmappedBams.ref_fasta": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.fasta", diff --git a/pipelines/broad/reprocessing/cram_to_unmapped_bams/test_inputs/Plumbing/RP-929.NA12878.Exome.json b/pipelines/broad/reprocessing/cram_to_unmapped_bams/test_inputs/Plumbing/RP-929.NA12878.Exome.json index b2a4bbf4ec..f128ef6690 100644 --- a/pipelines/broad/reprocessing/cram_to_unmapped_bams/test_inputs/Plumbing/RP-929.NA12878.Exome.json +++ b/pipelines/broad/reprocessing/cram_to_unmapped_bams/test_inputs/Plumbing/RP-929.NA12878.Exome.json @@ -1,6 +1,6 @@ { - "CramToUnmappedBams.input_cram": "gs://broad-gotc-test-storage/ExomeGermlineSingleSample/truth/plumbing/master/RP-929.NA12878/NA12878_PLUMBING.cram", - "CramToUnmappedBams.output_map": "gs://broad-gotc-test-storage/germline_single_sample/exome/plumbing/bams/RP-929.NA12878/readgroupid_to_bamfilename_map.txt", + "CramToUnmappedBams.input_cram": "gs://pd-test-storage-public/CramToUnmappedBams/input/plumbing/exome/RP-929.NA12878.Exome/NA12878_PLUMBING.cram", + "CramToUnmappedBams.output_map": "gs://pd-test-storage-public/CramToUnmappedBams/input/plumbing/exome/RP-929.NA12878.Exome/readgroupid_to_bamfilename_map.txt", "CramToUnmappedBams.base_file_name": "RP-929.NA12878.Exome", "CramToUnmappedBams.unmapped_bam_suffix": ".unmapped.bam", "CramToUnmappedBams.ref_fasta": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.fasta", diff --git a/pipelines/broad/reprocessing/cram_to_unmapped_bams/test_inputs/Scientific/C1963.CHMI_CHMI3_Nex1.Exome.json b/pipelines/broad/reprocessing/cram_to_unmapped_bams/test_inputs/Scientific/C1963.CHMI_CHMI3_Nex1.Exome.json index d3c5601544..80072712d2 100644 --- a/pipelines/broad/reprocessing/cram_to_unmapped_bams/test_inputs/Scientific/C1963.CHMI_CHMI3_Nex1.Exome.json +++ b/pipelines/broad/reprocessing/cram_to_unmapped_bams/test_inputs/Scientific/C1963.CHMI_CHMI3_Nex1.Exome.json @@ -1,6 +1,6 @@ { - "CramToUnmappedBams.input_cram": "gs://broad-gotc-test-storage/ExomeGermlineSingleSample/truth/scientific/master/C1963.CHMI_CHMI3_Nex1/CHMI_CHMI3_Nex1.cram", - "CramToUnmappedBams.output_map": "gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/C1963.CHMI_CHMI3_Nex1/readgroupid_to_bamfilename_map.txt", + "CramToUnmappedBams.input_cram": "gs://pd-test-storage-public/CramToUnmappedBams/input/scientific/C1963.CHMI_CHMI3_Nex1.Exome/CHMI_CHMI3_Nex1.cram", + "CramToUnmappedBams.output_map": "gs://pd-test-storage-public/CramToUnmappedBams/input/scientific/C1963.CHMI_CHMI3_Nex1.Exome/readgroupid_to_bamfilename_map.txt", "CramToUnmappedBams.base_file_name": "C1963.CHMI_CHMI3_Nex1.Exome", "CramToUnmappedBams.unmapped_bam_suffix": ".unmapped.bam", "CramToUnmappedBams.ref_fasta": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.fasta", diff --git a/pipelines/broad/reprocessing/cram_to_unmapped_bams/test_inputs/Scientific/D5327.NA12878.Exome.json b/pipelines/broad/reprocessing/cram_to_unmapped_bams/test_inputs/Scientific/D5327.NA12878.Exome.json index 12586c7028..a4d87b38e0 100644 --- a/pipelines/broad/reprocessing/cram_to_unmapped_bams/test_inputs/Scientific/D5327.NA12878.Exome.json +++ b/pipelines/broad/reprocessing/cram_to_unmapped_bams/test_inputs/Scientific/D5327.NA12878.Exome.json @@ -1,6 +1,6 @@ { - "CramToUnmappedBams.input_cram": "gs://broad-gotc-test-storage/ExomeGermlineSingleSample/truth/scientific/master/D5327.NA12878/NA12878.cram", - "CramToUnmappedBams.output_map": "gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/D5327.NA12878/readgroupid_to_bamfilename_map.txt", + "CramToUnmappedBams.input_cram": "gs://pd-test-storage-public/CramToUnmappedBams/input/scientific/D5327.NA12878.Exome/NA12878.cram", + "CramToUnmappedBams.output_map": "gs://pd-test-storage-public/CramToUnmappedBams/input/scientific/D5327.NA12878.Exome/readgroupid_to_bamfilename_map.txt", "CramToUnmappedBams.base_file_name": "D5327.NA12878.Exome", "CramToUnmappedBams.unmapped_bam_suffix": ".unmapped.bam", "CramToUnmappedBams.ref_fasta": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.fasta", diff --git a/pipelines/broad/reprocessing/cram_to_unmapped_bams/test_inputs/Scientific/G94794.CHMI_CHMI3_WGS2.json b/pipelines/broad/reprocessing/cram_to_unmapped_bams/test_inputs/Scientific/G94794.CHMI_CHMI3_WGS2.json index 2a9cf46342..d4ebb4459e 100644 --- a/pipelines/broad/reprocessing/cram_to_unmapped_bams/test_inputs/Scientific/G94794.CHMI_CHMI3_WGS2.json +++ b/pipelines/broad/reprocessing/cram_to_unmapped_bams/test_inputs/Scientific/G94794.CHMI_CHMI3_WGS2.json @@ -1,6 +1,6 @@ { - "CramToUnmappedBams.input_cram": "gs://broad-gotc-test-storage/WholeGenomeGermlineSingleSample/truth/scientific/master/G94794.CHMI_CHMI3_WGS2/CHMI_CHMI3_WGS2.cram", - "CramToUnmappedBams.output_map": "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94794.CHMI_CHMI3_WGS2/readgroupid_to_bamfilename_map.txt", + "CramToUnmappedBams.input_cram": "gs://pd-test-storage-public/CramToUnmappedBams/input/scientific/G94794.CHMI_CHMI3_WGS2/CHMI_CHMI3_WGS2.cram", + "CramToUnmappedBams.output_map": "gs://pd-test-storage-public/CramToUnmappedBams/input/scientific/G94794.CHMI_CHMI3_WGS2/readgroupid_to_bamfilename_map.txt", "CramToUnmappedBams.base_file_name": "G94794.CHMI_CHMI3_WGS2", "CramToUnmappedBams.unmapped_bam_suffix": ".unmapped.bam", diff --git a/pipelines/broad/reprocessing/cram_to_unmapped_bams/test_inputs/Scientific/G94982.NA12878.WGS.json b/pipelines/broad/reprocessing/cram_to_unmapped_bams/test_inputs/Scientific/G94982.NA12878.WGS.json index bb14cc9544..0e47a25968 100644 --- a/pipelines/broad/reprocessing/cram_to_unmapped_bams/test_inputs/Scientific/G94982.NA12878.WGS.json +++ b/pipelines/broad/reprocessing/cram_to_unmapped_bams/test_inputs/Scientific/G94982.NA12878.WGS.json @@ -1,6 +1,6 @@ { - "CramToUnmappedBams.input_cram": "gs://broad-gotc-test-storage/WholeGenomeGermlineSingleSample/truth/scientific/master/G94982.NA12878/NA12878.cram", - "CramToUnmappedBams.output_map": "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G94982.NA12878/readgroupid_to_bamfilename_map.txt", + "CramToUnmappedBams.input_cram": "gs://pd-test-storage-public/CramToUnmappedBams/input/scientific/G94982.NA12878.WGS/NA12878.cram", + "CramToUnmappedBams.output_map": "gs://pd-test-storage-public/CramToUnmappedBams/input/scientific/G94982.NA12878.WGS/readgroupid_to_bamfilename_map.txt", "CramToUnmappedBams.base_file_name": "G94982.NA12878.WGS", "CramToUnmappedBams.unmapped_bam_suffix": ".unmapped.bam", "CramToUnmappedBams.ref_fasta": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.fasta", diff --git a/pipelines/broad/reprocessing/cram_to_unmapped_bams/test_inputs/Scientific/G96830.NA12878.WGS.json b/pipelines/broad/reprocessing/cram_to_unmapped_bams/test_inputs/Scientific/G96830.NA12878.WGS.json index b1f7f6e02e..10b52aaa85 100644 --- a/pipelines/broad/reprocessing/cram_to_unmapped_bams/test_inputs/Scientific/G96830.NA12878.WGS.json +++ b/pipelines/broad/reprocessing/cram_to_unmapped_bams/test_inputs/Scientific/G96830.NA12878.WGS.json @@ -1,6 +1,6 @@ { - "CramToUnmappedBams.input_cram": "gs://broad-gotc-test-storage/WholeGenomeGermlineSingleSample/truth/scientific/master/G96830.NA12878/NA12878.cram", - "CramToUnmappedBams.output_map": "gs://broad-gotc-test-storage/germline_single_sample/wgs/scientific/bams/G96830.NA12878/readgroupid_to_bamfilename_map.txt", + "CramToUnmappedBams.input_cram": "gs://pd-test-storage-public/CramToUnmappedBams/input/scientific/G96830.NA12878.WGS/NA12878.cram", + "CramToUnmappedBams.output_map": "gs://pd-test-storage-public/CramToUnmappedBams/input/scientific/G96830.NA12878.WGS/readgroupid_to_bamfilename_map.txt", "CramToUnmappedBams.base_file_name": "G96830.NA12878.WGS", "CramToUnmappedBams.unmapped_bam_suffix": ".unmapped.bam", "CramToUnmappedBams.ref_fasta": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.fasta", diff --git a/pipelines/broad/reprocessing/cram_to_unmapped_bams/test_inputs/Scientific/RP-1535.NA17-308.Exome.json b/pipelines/broad/reprocessing/cram_to_unmapped_bams/test_inputs/Scientific/RP-1535.NA17-308.Exome.json index 953f45c135..9e44767505 100644 --- a/pipelines/broad/reprocessing/cram_to_unmapped_bams/test_inputs/Scientific/RP-1535.NA17-308.Exome.json +++ b/pipelines/broad/reprocessing/cram_to_unmapped_bams/test_inputs/Scientific/RP-1535.NA17-308.Exome.json @@ -1,6 +1,6 @@ { - "CramToUnmappedBams.input_cram": "gs://broad-gotc-test-storage/ExomeGermlineSingleSample/truth/scientific/master/RP-1535.NA17-308/NA17-308.cram", - "CramToUnmappedBams.output_map": "gs://broad-gotc-test-storage/germline_single_sample/exome/scientific/bams/RP-1535.NA17-308/readgroupid_to_bamfilename_map.txt", + "CramToUnmappedBams.input_cram": "gs://pd-test-storage-private/CramToUnmappedBams/input/scientific/RP-1535.NA17-308.Exome/NA17-308.cram", + "CramToUnmappedBams.output_map": "gs://pd-test-storage-private/CramToUnmappedBams/input/scientific/RP-1535.NA17-308.Exome/readgroupid_to_bamfilename_map.txt", "CramToUnmappedBams.base_file_name": "RP-1535.NA17-308.Exome", "CramToUnmappedBams.unmapped_bam_suffix": ".unmapped.bam", "CramToUnmappedBams.ref_fasta": "gs://gcp-public-data--broad-references/hg38/v0/Homo_sapiens_assembly38.fasta", diff --git a/pipelines/broad/reprocessing/exome/test_inputs/Plumbing/RP-929.NA12878.json b/pipelines/broad/reprocessing/exome/test_inputs/Plumbing/RP-929.NA12878.json index 7c80bb5fdd..8763e4df9e 100644 --- a/pipelines/broad/reprocessing/exome/test_inputs/Plumbing/RP-929.NA12878.json +++ b/pipelines/broad/reprocessing/exome/test_inputs/Plumbing/RP-929.NA12878.json @@ -1,6 +1,6 @@ { - "ExomeReprocessing.input_cram": "gs://broad-gotc-test-storage/ExomeGermlineSingleSample/truth/plumbing/master/RP-929.NA12878/NA12878_PLUMBING.cram", - "ExomeReprocessing.output_map": "gs://broad-gotc-test-storage/germline_single_sample/exome/plumbing/bams/RP-929.NA12878/readgroupid_to_bamfilename_map.txt", + "ExomeReprocessing.input_cram": "gs://pd-test-storage-public/ExomeReprocessing/input/plumbing/RP-929.NA12878/NA12878_PLUMBING.cram", + "ExomeReprocessing.output_map": "gs://pd-test-storage-public/ExomeReprocessing/input/plumbing/RP-929.NA12878/readgroupid_to_bamfilename_map.txt", "ExomeReprocessing.sample_name": "NA12878 PLUMBING", "ExomeReprocessing.base_file_name": "RP-929.NA12878", @@ -42,8 +42,8 @@ "break_bands_at_multiples_of": 0 }, - "ExomeReprocessing.fingerprint_genotypes_file": "gs://broad-gotc-test-storage/germline_single_sample/exome/plumbing/bams/RP-929.NA12878/RP-929.NA12878.reference.fingerprint.vcf.gz", - "ExomeReprocessing.fingerprint_genotypes_index": "gs://broad-gotc-test-storage/germline_single_sample/exome/plumbing/bams/RP-929.NA12878/RP-929.NA12878.reference.fingerprint.vcf.gz.tbi", + "ExomeReprocessing.fingerprint_genotypes_file": "gs://pd-test-storage-public/ExomeReprocessing/input/plumbing/RP-929.NA12878/RP-929.NA12878.reference.fingerprint.vcf.gz", + "ExomeReprocessing.fingerprint_genotypes_index": "gs://pd-test-storage-public/ExomeReprocessing/input/plumbing/RP-929.NA12878/RP-929.NA12878.reference.fingerprint.vcf.gz.tbi", "ExomeReprocessing.target_interval_list": "gs://broad-references-private/HybSelOligos/whole_exome_illumina_coding_v1/whole_exome_illumina_coding_v1.Homo_sapiens_assembly38.targets.interval_list", "ExomeReprocessing.bait_interval_list": "gs://broad-references-private/HybSelOligos/whole_exome_illumina_coding_v1/whole_exome_illumina_coding_v1.Homo_sapiens_assembly38.baits.interval_list", diff --git a/pipelines/broad/reprocessing/wgs/test_inputs/Plumbing/G96830.NA12878.json b/pipelines/broad/reprocessing/wgs/test_inputs/Plumbing/G96830.NA12878.json index da81415881..1c41b9e5d3 100644 --- a/pipelines/broad/reprocessing/wgs/test_inputs/Plumbing/G96830.NA12878.json +++ b/pipelines/broad/reprocessing/wgs/test_inputs/Plumbing/G96830.NA12878.json @@ -1,6 +1,6 @@ { - "WholeGenomeReprocessing.input_cram": "gs://broad-gotc-test-storage/single_sample/plumbing/truth/master/20k/NA12878_PLUMBING.cram", - "WholeGenomeReprocessing.output_map": "gs://broad-gotc-test-storage/germline_single_sample/wgs/plumbing/bams/G96830.NA12878/readgroupid_to_bamfilename_map.txt", + "WholeGenomeReprocessing.input_cram": "gs://pd-test-storage-public/WholeGenomeReprocessing/input/plumbing/G96830.NA12878/NA12878_PLUMBING.cram", + "WholeGenomeReprocessing.output_map": "gs://pd-test-storage-public/WholeGenomeReprocessing/input/plumbing/G96830.NA12878/readgroupid_to_bamfilename_map.txt", "WholeGenomeReprocessing.sample_name": "NA12878 PLUMBING", "WholeGenomeReprocessing.base_file_name": "G96830.NA12878", @@ -43,8 +43,8 @@ "break_bands_at_multiples_of": 100000 }, - "WholeGenomeReprocessing.fingerprint_genotypes_file": "gs://broad-gotc-test-storage/single_sample/plumbing/bams/G96830.NA12878/G96830.NA12878.hg38.reference.fingerprint.vcf.gz", - "WholeGenomeReprocessing.fingerprint_genotypes_index": "gs://broad-gotc-test-storage/single_sample/plumbing/bams/G96830.NA12878/G96830.NA12878.hg38.reference.fingerprint.vcf.gz.tbi", + "WholeGenomeReprocessing.fingerprint_genotypes_file": "gs://pd-test-storage-public/WholeGenomeReprocessing/input/plumbing/G96830.NA12878/G96830.NA12878.hg38.reference.fingerprint.vcf.gz", + "WholeGenomeReprocessing.fingerprint_genotypes_index": "gs://pd-test-storage-public/WholeGenomeReprocessing/input/plumbing/G96830.NA12878/G96830.NA12878.hg38.reference.fingerprint.vcf.gz.tbi", "WholeGenomeReprocessing.wgs_coverage_interval_list": "gs://gcp-public-data--broad-references/hg38/v0/wgs_coverage_regions.hg38.interval_list", "WholeGenomeReprocessing.WholeGenomeGermlineSingleSample.UnmappedBamToAlignedBam.CheckContamination.disable_sanity_check": true, diff --git a/pipelines/skylab/atac/test_inputs/Plumbing/10k_pbmc_downsampled.json b/pipelines/skylab/atac/test_inputs/Plumbing/10k_pbmc_downsampled.json index 71be349541..f28014aef2 100644 --- a/pipelines/skylab/atac/test_inputs/Plumbing/10k_pbmc_downsampled.json +++ b/pipelines/skylab/atac/test_inputs/Plumbing/10k_pbmc_downsampled.json @@ -2,13 +2,13 @@ "ATAC.input_id":"10k_PBMC_downsampled", "ATAC.cloud_provider":"gcp", "ATAC.read1_fastq_gzipped":[ - "gs://pd-test-storage-public/Multiome/input/plumbing/fastq_R1_atac.fastq.gz" + "gs://pd-test-storage-public/atac/input/plumbing/10k_pbmc_downsampled/fastq_R1_atac.fastq.gz" ], "ATAC.read2_fastq_gzipped":[ - "gs://pd-test-storage-public/Multiome/input/plumbing/fastq_R2_atac.fastq.gz" + "gs://pd-test-storage-public/atac/input/plumbing/10k_pbmc_downsampled/fastq_R2_atac.fastq.gz" ], "ATAC.read3_fastq_gzipped":[ - "gs://pd-test-storage-public/Multiome/input/plumbing/fastq_R3_atac.fastq.gz" + "gs://pd-test-storage-public/atac/input/plumbing/10k_pbmc_downsampled/fastq_R3_atac.fastq.gz" ], "ATAC.tar_bwa_reference":"gs://gcp-public-data--broad-references/hg38/v0/bwa/v2_2_1/bwa-mem2-2.2.1-Human-GENCODE-build-GRCh38.tar", "ATAC.chrom_sizes":"gs://pd-test-storage-public/Multiome/input/hg38.chrom.sizes", diff --git a/pipelines/skylab/atac/test_inputs/Plumbing/8k_cortex.json b/pipelines/skylab/atac/test_inputs/Plumbing/8k_cortex.json index d4a1858e72..cdf9e24394 100644 --- a/pipelines/skylab/atac/test_inputs/Plumbing/8k_cortex.json +++ b/pipelines/skylab/atac/test_inputs/Plumbing/8k_cortex.json @@ -2,13 +2,13 @@ "ATAC.input_id":"10x_8k_cortex_downsampled", "ATAC.cloud_provider":"gcp", "ATAC.read1_fastq_gzipped":[ - "gs://pd-test-storage-public/atac/input/plumbing/fastq_R1_0.fastq.gz" + "gs://pd-test-storage-public/atac/input/plumbing/8k_cortex/fastq_R1_0.fastq.gz" ], "ATAC.read2_fastq_gzipped":[ - "gs://pd-test-storage-public/atac/input/plumbing/fastq_R2_0.fastq.gz" + "gs://pd-test-storage-public/atac/input/plumbing/8k_cortex/fastq_R2_0.fastq.gz" ], "ATAC.read3_fastq_gzipped":[ - "gs://pd-test-storage-public/atac/input/plumbing/fastq_R3_0.fastq.gz" + "gs://pd-test-storage-public/atac/input/plumbing/8k_cortex/fastq_R3_0.fastq.gz" ], "ATAC.tar_bwa_reference":"gs://gcp-public-data--broad-references/GRCm39/bwa/v2_2_1/bwa-mem2-2.2.1-Mouse-GENCODE-build-GRCm39.tar", "ATAC.chrom_sizes":"gs://gcp-public-data--broad-references/GRCm39/bwa/v2_2_1/chrom.sizes", @@ -17,7 +17,7 @@ "ATAC.mem_size_bwa":"64", "ATAC.atac_nhash_id":"example_1234", "ATAC.annotations_gtf":" gs://gcp-public-data--broad-references/GRCm39/star/v2_7_10a/modified_vM32.annotation.gtf", - "ATAC.whitelist":"gs://pd-test-storage-public/atac/input/plumbing/737K-cratac-v1.txt", + "ATAC.whitelist":"gs://pd-test-storage-public/atac/input/plumbing/8k_cortex/737K-cratac-v1.txt", "ATAC.vm_size":"Standard_M128s", "ATAC.peak_calling":true, "ATAC.PeakCalling.probability_threshold":"1.0", diff --git a/pipelines/skylab/multiome/Multiome.changelog.md b/pipelines/skylab/multiome/Multiome.changelog.md index e793687f97..b71c6de66f 100644 --- a/pipelines/skylab/multiome/Multiome.changelog.md +++ b/pipelines/skylab/multiome/Multiome.changelog.md @@ -1,3 +1,8 @@ +# 6.0.3 +25-05-27 (Date of Last Commit) + +* Increased the ulimit in the STARsoloFastq task in the StarAlign.wdl to 10000; this does not affect the outputs of the pipeline + # 6.0.2 25-04-16 (Date of Last Commit) diff --git a/pipelines/skylab/multiome/Multiome.wdl b/pipelines/skylab/multiome/Multiome.wdl index 170fa51255..17d76e8420 100644 --- a/pipelines/skylab/multiome/Multiome.wdl +++ b/pipelines/skylab/multiome/Multiome.wdl @@ -9,7 +9,7 @@ import "../../../tasks/broad/Utilities.wdl" as utils workflow Multiome { - String pipeline_version = "6.0.2" + String pipeline_version = "6.0.3" input { String cloud_provider diff --git a/pipelines/skylab/multiome/test_inputs/Plumbing/macaque_CK03.json b/pipelines/skylab/multiome/test_inputs/Plumbing/macaque_CK03.json new file mode 100644 index 0000000000..9b07beb41d --- /dev/null +++ b/pipelines/skylab/multiome/test_inputs/Plumbing/macaque_CK03.json @@ -0,0 +1,30 @@ +{ + "Multiome.annotations_gtf":"gs://gcp-public-data--broad-references/M.mulatta/Mmul_10/star/v2_7_10a/10x_filtered/mt_v103_modified.annotation.gtf", + "Multiome.input_id":"macaque_CK03", + "Multiome.cloud_provider":"gcp", + "Multiome.gex_r1_fastq":[ + "gs://pd-test-storage-private/Multiome/input/plumbing/macaque_CK03/subsampled_CK03_GEX_S3_L001_R1_001.fastq.gz" + ], + "Multiome.gex_r2_fastq":[ + "gs://pd-test-storage-private/Multiome/input/plumbing/macaque_CK03/subsampled_CK03_GEX_S3_L001_R2_001.fastq.gz" + ], + "Multiome.atac_r1_fastq":[ + "gs://pd-test-storage-private/Multiome/input/plumbing/macaque_CK03/subsampled_CK03_ATAC_S3_L001_R1_001.fastq.gz" + ], + "Multiome.atac_r2_fastq":[ + "gs://pd-test-storage-private/Multiome/input/plumbing/macaque_CK03/subsampled_CK03_ATAC_S3_L001_R2_001.fastq.gz" + ], + "Multiome.atac_r3_fastq":[ + "gs://pd-test-storage-private/Multiome/input/plumbing/macaque_CK03/subsampled_CK03_ATAC_S3_L001_R3_001.fastq.gz" + ], + "Multiome.tar_bwa_reference":"gs://gcp-public-data--broad-references/M.mulatta/Mmul_10/bwa/v2_2_1/bwa-mem2-2.2.1-Macaque-NCBI-build-GCF_003339765.1.tar", + "Multiome.tar_star_reference":"gs://gcp-public-data--broad-references/M.mulatta/Mmul_10/star/v2_7_10a/10x_filtered/modified_star2.7.10a-Macaque-NCBI-build-GCF_003339765.1-103.tar", + "Multiome.chrom_sizes":"gs://gcp-public-data--broad-references/M.mulatta/Mmul_10/bwa/v2_2_1/chrom.sizes", + "Multiome.run_cellbender":"false", + "Multiome.Atac.cpu_platform_bwa":"Intel Cascade Lake", + "Multiome.Atac.num_threads_bwa":"16", + "Multiome.Atac.mem_size_bwa":"64", + "Multiome.soloMultiMappers":"Uniform", + "Multiome.gex_nhash_id":"example_1234", + "Multiome.atac_nhash_id":"example_1234" +} diff --git a/pipelines/skylab/optimus/Optimus.changelog.md b/pipelines/skylab/optimus/Optimus.changelog.md index 339c5ac9cd..11ce814fbb 100644 --- a/pipelines/skylab/optimus/Optimus.changelog.md +++ b/pipelines/skylab/optimus/Optimus.changelog.md @@ -1,3 +1,8 @@ +# 8.0.1 +2025-05-27 (Date of Last Commit) + +* Increased the ulimit in the STARsoloFastq task in the StarAlign.wdl to 10000; this does not affect the outputs of the pipeline + # 8.0.0 2025-04-02 (Date of Last Commit) diff --git a/pipelines/skylab/optimus/Optimus.wdl b/pipelines/skylab/optimus/Optimus.wdl index 22e7945aba..7b654041d6 100644 --- a/pipelines/skylab/optimus/Optimus.wdl +++ b/pipelines/skylab/optimus/Optimus.wdl @@ -78,7 +78,7 @@ workflow Optimus { } # Version of this pipeline - String pipeline_version = "8.0.0" + String pipeline_version = "8.0.1" # this is used to scatter matched [r1_fastq, r2_fastq, i1_fastq] arrays Array[Int] indices = range(length(r1_fastq)) diff --git a/pipelines/skylab/optimus/test_inputs/Scientific/inputs_8k_pbmc.json b/pipelines/skylab/optimus/test_inputs/Scientific/inputs_8k_pbmc.json index 466716fdf8..628988194b 100644 --- a/pipelines/skylab/optimus/test_inputs/Scientific/inputs_8k_pbmc.json +++ b/pipelines/skylab/optimus/test_inputs/Scientific/inputs_8k_pbmc.json @@ -1,15 +1,15 @@ { "Optimus.r1_fastq": [ -"gs://broad-gotc-test-storage/Optimus/input/scientific/chemistry_X10_V2/8k_pbmc/fastqs/pbmc8k_S1_L007_R1_001.fastq.gz", -"gs://broad-gotc-test-storage/Optimus/input/scientific/chemistry_X10_V2/8k_pbmc/fastqs/pbmc8k_S1_L008_R1_001.fastq.gz" +"gs://pd-test-storage-private/Optimus/input/scientific/chemistry_X10_V2/8k_pbmc/fastqs/pbmc8k_S1_L007_R1_001.fastq.gz", +"gs://pd-test-storage-private/Optimus/input/scientific/chemistry_X10_V2/8k_pbmc/fastqs/pbmc8k_S1_L008_R1_001.fastq.gz" ], "Optimus.r2_fastq": [ -"gs://broad-gotc-test-storage/Optimus/input/scientific/chemistry_X10_V2/8k_pbmc/fastqs/pbmc8k_S1_L007_R2_001.fastq.gz", -"gs://broad-gotc-test-storage/Optimus/input/scientific/chemistry_X10_V2/8k_pbmc/fastqs/pbmc8k_S1_L008_R2_001.fastq.gz" +"gs://pd-test-storage-private/Optimus/input/scientific/chemistry_X10_V2/8k_pbmc/fastqs/pbmc8k_S1_L007_R2_001.fastq.gz", +"gs://pd-test-storage-private/Optimus/input/scientific/chemistry_X10_V2/8k_pbmc/fastqs/pbmc8k_S1_L008_R2_001.fastq.gz" ], "Optimus.i1_fastq": [ -"gs://broad-gotc-test-storage/Optimus/input/scientific/chemistry_X10_V2/8k_pbmc/fastqs/pbmc8k_S1_L007_I1_001.fastq.gz", -"gs://broad-gotc-test-storage/Optimus/input/scientific/chemistry_X10_V2/8k_pbmc/fastqs/pbmc8k_S1_L008_I1_001.fastq.gz" +"gs://pd-test-storage-private/Optimus/input/scientific/chemistry_X10_V2/8k_pbmc/fastqs/pbmc8k_S1_L007_I1_001.fastq.gz", +"gs://pd-test-storage-private/Optimus/input/scientific/chemistry_X10_V2/8k_pbmc/fastqs/pbmc8k_S1_L008_I1_001.fastq.gz" ], "Optimus.tar_star_reference": "gs://gcp-public-data--broad-references/hg38/v0/star/v2_7_10a/modified_star2.7.10a-Human-GENCODE-build-GRCh38-43.tar", "Optimus.input_id": "8k_pbmc", diff --git a/pipelines/skylab/optimus/test_inputs/Scientific/inputs_8k_pbmc_stranded.json b/pipelines/skylab/optimus/test_inputs/Scientific/inputs_8k_pbmc_stranded.json index 0a9ee3adc2..de2e17b569 100644 --- a/pipelines/skylab/optimus/test_inputs/Scientific/inputs_8k_pbmc_stranded.json +++ b/pipelines/skylab/optimus/test_inputs/Scientific/inputs_8k_pbmc_stranded.json @@ -1,15 +1,15 @@ { "Optimus.r1_fastq": [ -"gs://broad-gotc-test-storage/Optimus/input/scientific/chemistry_X10_V2/8k_pbmc/fastqs/pbmc8k_S1_L007_R1_001.fastq.gz", -"gs://broad-gotc-test-storage/Optimus/input/scientific/chemistry_X10_V2/8k_pbmc/fastqs/pbmc8k_S1_L008_R1_001.fastq.gz" +"gs://pd-test-storage-private/Optimus/input/scientific/chemistry_X10_V2/8k_pbmc/fastqs/pbmc8k_S1_L007_R1_001.fastq.gz", +"gs://pd-test-storage-private/Optimus/input/scientific/chemistry_X10_V2/8k_pbmc/fastqs/pbmc8k_S1_L008_R1_001.fastq.gz" ], "Optimus.r2_fastq": [ -"gs://broad-gotc-test-storage/Optimus/input/scientific/chemistry_X10_V2/8k_pbmc/fastqs/pbmc8k_S1_L007_R2_001.fastq.gz", -"gs://broad-gotc-test-storage/Optimus/input/scientific/chemistry_X10_V2/8k_pbmc/fastqs/pbmc8k_S1_L008_R2_001.fastq.gz" +"gs://pd-test-storage-private/Optimus/input/scientific/chemistry_X10_V2/8k_pbmc/fastqs/pbmc8k_S1_L007_R2_001.fastq.gz", +"gs://pd-test-storage-private/Optimus/input/scientific/chemistry_X10_V2/8k_pbmc/fastqs/pbmc8k_S1_L008_R2_001.fastq.gz" ], "Optimus.i1_fastq": [ -"gs://broad-gotc-test-storage/Optimus/input/scientific/chemistry_X10_V2/8k_pbmc/fastqs/pbmc8k_S1_L007_I1_001.fastq.gz", -"gs://broad-gotc-test-storage/Optimus/input/scientific/chemistry_X10_V2/8k_pbmc/fastqs/pbmc8k_S1_L008_I1_001.fastq.gz" +"gs://pd-test-storage-private/Optimus/input/scientific/chemistry_X10_V2/8k_pbmc/fastqs/pbmc8k_S1_L007_I1_001.fastq.gz", +"gs://pd-test-storage-private/Optimus/input/scientific/chemistry_X10_V2/8k_pbmc/fastqs/pbmc8k_S1_L008_I1_001.fastq.gz" ], "Optimus.tar_star_reference": "gs://gcp-public-data--broad-references/hg38/v0/star/star_2.7.9a_primary_gencode_human_v27.tar", "Optimus.input_id": "8k_pbmc", diff --git a/pipelines/skylab/paired_tag/PairedTag.changelog.md b/pipelines/skylab/paired_tag/PairedTag.changelog.md index e924b7075f..a5547d69e8 100644 --- a/pipelines/skylab/paired_tag/PairedTag.changelog.md +++ b/pipelines/skylab/paired_tag/PairedTag.changelog.md @@ -1,3 +1,9 @@ +# 2.1.2 +2025-05-27 (Date of Last Commit) + +* Increased the ulimit in the STARsoloFastq task in the StarAlign.wdl to 10000; this does not affect the outputs of the pipeline + + # 2.1.1 2025-04-15 (Date of Last Commit) diff --git a/pipelines/skylab/paired_tag/PairedTag.wdl b/pipelines/skylab/paired_tag/PairedTag.wdl index b0193cb339..6e9ad1e95c 100644 --- a/pipelines/skylab/paired_tag/PairedTag.wdl +++ b/pipelines/skylab/paired_tag/PairedTag.wdl @@ -9,7 +9,7 @@ import "../../../tasks/broad/Utilities.wdl" as utils workflow PairedTag { - String pipeline_version = "2.1.1" + String pipeline_version = "2.1.2" input { String input_id diff --git a/pipelines/skylab/paired_tag/test_inputs/Plumbing/10k_pbmc_downsampled.json b/pipelines/skylab/paired_tag/test_inputs/Plumbing/10k_pbmc_downsampled.json index cc083e1d9a..d58ae44f9e 100644 --- a/pipelines/skylab/paired_tag/test_inputs/Plumbing/10k_pbmc_downsampled.json +++ b/pipelines/skylab/paired_tag/test_inputs/Plumbing/10k_pbmc_downsampled.json @@ -2,23 +2,23 @@ "PairedTag.annotations_gtf":"gs://gcp-public-data--broad-references/hg38/v0/star/v2_7_10a/modified_v43.annotation.gtf", "PairedTag.input_id":"10k_PBMC_downsampled", "PairedTag.gex_r1_fastq":[ - "gs://pd-test-storage-public/Multiome/input/plumbing/fastq_R1_gex.fastq.gz" + "gs://pd-test-storage-public/PairedTag/input/plumbing/10k_PBMC_downsampled/fastq_R1_gex.fastq.gz" ], "PairedTag.gex_r2_fastq":[ - "gs://pd-test-storage-public/Multiome/input/plumbing/fastq_R2_gex.fastq.gz" + "gs://pd-test-storage-public/PairedTag/input/plumbing/10k_PBMC_downsampled/fastq_R2_gex.fastq.gz" ], "PairedTag.atac_r1_fastq":[ - "gs://pd-test-storage-public/Multiome/input/plumbing/fastq_R1_atac.fastq.gz" + "gs://pd-test-storage-public/PairedTag/input/plumbing/10k_PBMC_downsampled/fastq_R1_atac.fastq.gz" ], "PairedTag.atac_r2_fastq":[ - "gs://pd-test-storage-public/Multiome/input/plumbing/fastq_R2_atac.fastq.gz" + "gs://pd-test-storage-public/PairedTag/input/plumbing/10k_PBMC_downsampled/fastq_R2_atac.fastq.gz" ], "PairedTag.atac_r3_fastq":[ - "gs://pd-test-storage-public/Multiome/input/plumbing/fastq_R3_atac.fastq.gz" + "gs://pd-test-storage-public/PairedTag/input/plumbing/10k_PBMC_downsampled/fastq_R3_atac.fastq.gz" ], "PairedTag.tar_bwa_reference":"gs://gcp-public-data--broad-references/hg38/v0/bwa/v2_2_1/bwa-mem2-2.2.1-Human-GENCODE-build-GRCh38.tar", "PairedTag.tar_star_reference":"gs://gcp-public-data--broad-references/hg38/v0/star/v2_7_10a/modified_star2.7.10a-Human-GENCODE-build-GRCh38-43.tar", - "PairedTag.chrom_sizes":"gs://pd-test-storage-public/Multiome/input/hg38.chrom.sizes", + "PairedTag.chrom_sizes":"gs://pd-test-storage-public/PairedTag/input/hg38.chrom.sizes", "PairedTag.preindex":"false", "PairedTag.Atac_preindex.cpu_platform_bwa":"Intel Cascade Lake", "PairedTag.Atac_preindex.num_threads_bwa":"16", diff --git a/pipelines/skylab/paired_tag/test_inputs/Scientific/BC011_10kPBMC.json b/pipelines/skylab/paired_tag/test_inputs/Scientific/BC011_10kPBMC.json index fd0183b5c5..90bfeae64e 100644 --- a/pipelines/skylab/paired_tag/test_inputs/Scientific/BC011_10kPBMC.json +++ b/pipelines/skylab/paired_tag/test_inputs/Scientific/BC011_10kPBMC.json @@ -14,13 +14,13 @@ "gs://pd-test-storage-public/Multiome/input/scientific/10k_PBMC_Multiome/10k_PBMC_Multiome_nextgem_Chromium_Controller_gex_S1_L002_R2_001.fastq.gz" ], "PairedTag.atac_r1_fastq":[ - "gs://pd-test-storage-public/PairedTag/input/scientific/BC011_S1_L001_R1_001.fastq.gz" + "gs://pd-test-storage-public/PairedTag/input/scientific/BC011_10kPBMC/BC011_S1_L001_R1_001.fastq.gz" ], "PairedTag.atac_r2_fastq":[ - "gs://pd-test-storage-public/PairedTag/input/scientific/BC011_S1_L001_R2_001.fastq.gz" + "gs://pd-test-storage-public/PairedTag/input/scientific/BC011_10kPBMC/BC011_S1_L001_R2_001.fastq.gz" ], "PairedTag.atac_r3_fastq":[ - "gs://pd-test-storage-public/PairedTag/input/scientific/BC011_S1_L001_R3_001.fastq.gz" + "gs://pd-test-storage-public/PairedTag/input/scientific/BC011_10kPBMC/BC011_S1_L001_R3_001.fastq.gz" ], "PairedTag.chrom_sizes":"gs://pd-test-storage-public/Multiome/input/hg38.chrom.sizes", "PairedTag.preindex":"true", diff --git a/pipelines/skylab/peak_calling/test_inputs/Plumbing/10k_PBMC_downsampled.json b/pipelines/skylab/peak_calling/test_inputs/Plumbing/10k_PBMC_downsampled.json new file mode 100644 index 0000000000..09122f7361 --- /dev/null +++ b/pipelines/skylab/peak_calling/test_inputs/Plumbing/10k_PBMC_downsampled.json @@ -0,0 +1,7 @@ +{ + "PeakCalling.annotations_gtf":"gs://gcp-public-data--broad-references/hg38/v0/star/v2_7_10a/modified_v43.annotation.gtf", + "PeakCalling.metrics_h5ad":"gs://broad-gotc-test-storage/PeakCalling/input/plumbing/10k_PBMC_downsampled/10k_PBMC_downsampled_atac.metrics.h5ad", + "PeakCalling.cloud_provider":"gcp", + "PeakCalling.output_base_name":"10k_PBMC_downsampled", + "PeakCalling.chrom_sizes":"gs://pd-test-storage-public/Multiome/input/hg38.chrom.sizes" +} diff --git a/pipelines/skylab/peak_calling/test_inputs/Scientific/10k_PBMC.json b/pipelines/skylab/peak_calling/test_inputs/Scientific/10k_PBMC.json new file mode 100644 index 0000000000..7d207893a8 --- /dev/null +++ b/pipelines/skylab/peak_calling/test_inputs/Scientific/10k_PBMC.json @@ -0,0 +1,7 @@ +{ + "PeakCalling.annotations_gtf":"gs://gcp-public-data--broad-references/hg38/v0/star/v2_7_10a/modified_v43.annotation.gtf", + "PeakCalling.metrics_h5ad":"gs://broad-gotc-test-storage/PeakCalling/input/scientific/10k_PBMC/10k_PBMC_atac.metrics.h5ad", + "PeakCalling.cloud_provider":"gcp", + "PeakCalling.output_base_name":"10k_PBMC", + "PeakCalling.chrom_sizes":"gs://pd-test-storage-public/Multiome/input/hg38.chrom.sizes" +} diff --git a/pipelines/skylab/slideseq/SlideSeq.changelog.md b/pipelines/skylab/slideseq/SlideSeq.changelog.md index 0d7172fbb7..5c6659da8b 100644 --- a/pipelines/skylab/slideseq/SlideSeq.changelog.md +++ b/pipelines/skylab/slideseq/SlideSeq.changelog.md @@ -1,3 +1,7 @@ +# 3.6.1 +2025-05-27 (Date of Last Commit) +* Increased the ulimit in the STARsoloFastq task in the StarAlign.wdl to 10000; this does not affect the outputs of the pipeline + # 3.6.0 2025-04-02 (Date of Last Commit) * Removed MergeStarOutput task and updated docker image in alignemnt step (STARsoloFastq) in Optimus; this does not affect the outputs of the pipeline diff --git a/pipelines/skylab/slideseq/SlideSeq.wdl b/pipelines/skylab/slideseq/SlideSeq.wdl index bbca00180d..c2c3aaae5a 100644 --- a/pipelines/skylab/slideseq/SlideSeq.wdl +++ b/pipelines/skylab/slideseq/SlideSeq.wdl @@ -25,7 +25,7 @@ import "../../../tasks/broad/Utilities.wdl" as utils workflow SlideSeq { - String pipeline_version = "3.6.0" + String pipeline_version = "3.6.1" input { Array[File] r1_fastq diff --git a/pipelines/skylab/slideseq/test_inputs/Plumbing/Puck_210817_11.mm10.json b/pipelines/skylab/slideseq/test_inputs/Plumbing/Puck_210817_11.mm10.json index 035b22c58e..0263c76edf 100644 --- a/pipelines/skylab/slideseq/test_inputs/Plumbing/Puck_210817_11.mm10.json +++ b/pipelines/skylab/slideseq/test_inputs/Plumbing/Puck_210817_11.mm10.json @@ -1,18 +1,18 @@ { - "SlideSeq.r1_fastq": ["gs://broad-gotc-test-storage/slide_seq/plumbing/truth/master/210817_Puck_210817_11.L001_sampled_down.R1", - "gs://broad-gotc-test-storage/slide_seq/plumbing/truth/master/210817_Puck_210817_11.L002_sampled_down.R1", - "gs://broad-gotc-test-storage/slide_seq/plumbing/truth/master/210817_Puck_210817_11.L003_sampled_down.R1", - "gs://broad-gotc-test-storage/slide_seq/plumbing/truth/master/210817_Puck_210817_11.L004_sampled_down.R1"], - "SlideSeq.r2_fastq": ["gs://broad-gotc-test-storage/slide_seq/plumbing/truth/master/210817_Puck_210817_11.L001_sampled_down.R2", - "gs://broad-gotc-test-storage/slide_seq/plumbing/truth/master/210817_Puck_210817_11.L002_sampled_down.R2", - "gs://broad-gotc-test-storage/slide_seq/plumbing/truth/master/210817_Puck_210817_11.L003_sampled_down.R2", - "gs://broad-gotc-test-storage/slide_seq/plumbing/truth/master/210817_Puck_210817_11.L004_sampled_down.R2"], + "SlideSeq.r1_fastq": ["gs://pd-test-storage-public/SlideSeq/input/plumbing/Puck_210817_11/210817_Puck_210817_11.L001_sampled_down.R1", + "gs://pd-test-storage-public/SlideSeq/input/plumbing/Puck_210817_11/210817_Puck_210817_11.L002_sampled_down.R1", + "gs://pd-test-storage-public/SlideSeq/input/plumbing/Puck_210817_11/210817_Puck_210817_11.L003_sampled_down.R1", + "gs://pd-test-storage-public/SlideSeq/input/plumbing/Puck_210817_11/210817_Puck_210817_11.L004_sampled_down.R1"], + "SlideSeq.r2_fastq": ["gs://pd-test-storage-public/SlideSeq/input/plumbing/Puck_210817_11/210817_Puck_210817_11.L001_sampled_down.R2", + "gs://pd-test-storage-public/SlideSeq/input/plumbing/Puck_210817_11/210817_Puck_210817_11.L002_sampled_down.R2", + "gs://pd-test-storage-public/SlideSeq/input/plumbing/Puck_210817_11/210817_Puck_210817_11.L003_sampled_down.R2", + "gs://pd-test-storage-public/SlideSeq/input/plumbing/Puck_210817_11/210817_Puck_210817_11.L004_sampled_down.R2"], "SlideSeq.read_structure": "8C18X6C9M1X", "SlideSeq.input_id": "Puck_210817_11", "SlideSeq.output_bam_basename": "Puck_210817_11", "SlideSeq.tar_star_reference": "gs://gcp-public-data--broad-references/mm10/v0/single_nucleus/star/modified_star_2.7.9a_primary_gencode_mouse_vM23.tar", "SlideSeq.annotations_gtf": "gs://gcp-public-data--broad-references/mm10/v0/single_nucleus/modified_gencode.vM23.primary_assembly.annotation.gtf", "SlideSeq.count_exons": true, - "SlideSeq.bead_locations": " gs://broad-gotc-test-storage/SlideSeq/inputs/plumbing/Puck_210817_11/Puck_210817_11.tsv", + "SlideSeq.bead_locations": "gs://pd-test-storage-public/SlideSeq/input/plumbing/Puck_210817_11/Puck_210817_11.tsv", "SlideSeq.cloud_provider": "gcp" } \ No newline at end of file diff --git a/pipelines/skylab/slideseq/test_inputs/Scientific/Puck_210817_11.mm10.json b/pipelines/skylab/slideseq/test_inputs/Scientific/Puck_210817_11.mm10.json index 458c4412ed..bf0bde8f34 100644 --- a/pipelines/skylab/slideseq/test_inputs/Scientific/Puck_210817_11.mm10.json +++ b/pipelines/skylab/slideseq/test_inputs/Scientific/Puck_210817_11.mm10.json @@ -1,20 +1,20 @@ { "SlideSeq.r1_fastq": [ -"gs://broad-gotc-test-storage/SlideSeq/inputs/scientific/Puck_210817_11/Puck_210817_11_L01_R1.fastq.gz", -"gs://broad-gotc-test-storage/SlideSeq/inputs/scientific/Puck_210817_11/Puck_210817_11_L02_R1.fastq.gz", -"gs://broad-gotc-test-storage/SlideSeq/inputs/scientific/Puck_210817_11/Puck_210817_11_L03_R1.fastq.gz", -"gs://broad-gotc-test-storage/SlideSeq/inputs/scientific/Puck_210817_11/Puck_210817_11_L04_R1.fastq.gz"], +"gs://pd-test-storage-public/SlideSeq/input/scientific/Puck_210817_11/Puck_210817_11_L01_R1.fastq.gz", +"gs://pd-test-storage-public/SlideSeq/input/scientific/Puck_210817_11/Puck_210817_11_L02_R1.fastq.gz", +"gs://pd-test-storage-public/SlideSeq/input/scientific/Puck_210817_11/Puck_210817_11_L03_R1.fastq.gz", +"gs://pd-test-storage-public/SlideSeq/input/scientific/Puck_210817_11/Puck_210817_11_L04_R1.fastq.gz"], "SlideSeq.r2_fastq": [ -"gs://broad-gotc-test-storage/SlideSeq/inputs/scientific/Puck_210817_11/Puck_210817_11_L01_R2.fastq.gz", -"gs://broad-gotc-test-storage/SlideSeq/inputs/scientific/Puck_210817_11/Puck_210817_11_L02_R2.fastq.gz", -"gs://broad-gotc-test-storage/SlideSeq/inputs/scientific/Puck_210817_11/Puck_210817_11_L03_R2.fastq.gz", -"gs://broad-gotc-test-storage/SlideSeq/inputs/scientific/Puck_210817_11/Puck_210817_11_L04_R2.fastq.gz"], +"gs://pd-test-storage-public/SlideSeq/input/scientific/Puck_210817_11/Puck_210817_11_L01_R2.fastq.gz", +"gs://pd-test-storage-public/SlideSeq/input/scientific/Puck_210817_11/Puck_210817_11_L02_R2.fastq.gz", +"gs://pd-test-storage-public/SlideSeq/input/scientific/Puck_210817_11/Puck_210817_11_L03_R2.fastq.gz", +"gs://pd-test-storage-public/SlideSeq/input/scientific/Puck_210817_11/Puck_210817_11_L04_R2.fastq.gz"], "SlideSeq.read_structure": "8C18X6C9M1X", "SlideSeq.input_id": "210817_Puck_210817_11", "SlideSeq.output_bam_basename": "210817_Puck_210817_11", "SlideSeq.tar_star_reference": "gs://gcp-public-data--broad-references/mm10/v0/single_nucleus/star/modified_star_2.7.9a_primary_gencode_mouse_vM23.tar", "SlideSeq.annotations_gtf": "gs://gcp-public-data--broad-references/mm10/v0/single_nucleus/modified_gencode.vM23.primary_assembly.annotation.gtf", "SlideSeq.count_exons": true, - "SlideSeq.bead_locations": "gs://broad-gotc-test-storage/SlideSeq/inputs/scientific/Puck_210817_11/Puck_210817_11.tsv", + "SlideSeq.bead_locations": "gs://pd-test-storage-public/SlideSeq/input/scientific/Puck_210817_11/Puck_210817_11.tsv", "SlideSeq.cloud_provider": "gcp" } diff --git a/pipelines/skylab/slidetags/SlideTags.changelog.md b/pipelines/skylab/slidetags/SlideTags.changelog.md new file mode 100644 index 0000000000..e15148e463 --- /dev/null +++ b/pipelines/skylab/slidetags/SlideTags.changelog.md @@ -0,0 +1,5 @@ +# 1.0.0 + +2025-06-02 (Date of Last Commit) + +* The first major version release for the Slide-Tags pipeline. \ No newline at end of file diff --git a/pipelines/skylab/slidetags/SlideTags.wdl b/pipelines/skylab/slidetags/SlideTags.wdl new file mode 100644 index 0000000000..00841b572b --- /dev/null +++ b/pipelines/skylab/slidetags/SlideTags.wdl @@ -0,0 +1,136 @@ +version 1.0 + +import "../../../tasks/skylab/slidetags_utils/spatial-count.wdl" as SpatialCount +import "../../../tasks/skylab/slidetags_utils/positioning.wdl" as Positioning +import "../../../pipelines/skylab/optimus/Optimus.wdl" as optimus + +workflow SlideTags { + + String pipeline_version = "1.0.0" + + input { + # slide-tags inputs + Array[String] spatial_fastq + Array[String] pucks + + # Optimus inputs + Array[File] gex_r1_fastq + Array[File] gex_r2_fastq + Array[File]? gex_i1_fastq + File tar_star_reference + File annotations_gtf + File gex_whitelist + String cloud_provider = "gcp" + String input_id + Int expected_cells = 3000 + String counting_mode = "sn_rna" + Int tenx_chemistry_version = 3 + Int emptydrops_lower = 100 + Boolean force_no_check = false + Boolean ignore_r1_read_length = false + String star_strand_mode = "Reverse" + Boolean count_exons = false + String? soloMultiMappers + String? gex_nhash_id + File? mt_genes + + String docker = "us.gcr.io/broad-gotc-prod/slide-tags:1.1.0" + } + + parameter_meta { + spatial_fastq: "Array of paths to spatial fastq files" + pucks: "Array of paths to puck files" + docker: "Docker image to use" + } + + # Call the optimus workflow + call optimus.Optimus as Optimus { + input: + cloud_provider = cloud_provider, + counting_mode = counting_mode, + r1_fastq = gex_r1_fastq, + r2_fastq = gex_r2_fastq, + i1_fastq = gex_i1_fastq, + input_id = input_id + "_gex", + output_bam_basename = input_id + "_gex", + gex_nhash_id = gex_nhash_id, + tar_star_reference = tar_star_reference, + annotations_gtf = annotations_gtf, + mt_genes = mt_genes, + tenx_chemistry_version = tenx_chemistry_version, + whitelist = gex_whitelist, + emptydrops_lower = emptydrops_lower, + force_no_check = force_no_check, + ignore_r1_read_length = ignore_r1_read_length, + star_strand_mode = star_strand_mode, + count_exons = count_exons, + soloMultiMappers = soloMultiMappers, + gex_expected_cells = expected_cells + } + + call SpatialCount.count as spatial_count { + input: + fastq_paths = spatial_fastq, + pucks = pucks, + docker = docker, + input_id = input_id + } + + call Positioning.generate_positioning as positioning { + input: + rna_paths = [Optimus.h5ad_output_file, Optimus.library_metrics], + sb_path = spatial_count.sb_counts, + docker = docker, + input_id = input_id + } + + output { + # Version of Optimus pipeline + String optimus_pipeline_version_out = Optimus.pipeline_version_out + File optimus_genomic_reference_version = Optimus.genomic_reference_version + + # Optimus Metrics outputs + File optimus_cell_metrics = Optimus.cell_metrics + File optimus_gene_metrics = Optimus.gene_metrics + File? optimus_cell_calls = Optimus.cell_calls + + # Optimus Star outputs + File optimus_library_metrics = Optimus.library_metrics + File optimus_bam = Optimus.bam + File optimus_matrix = Optimus.matrix + File optimus_matrix_row_index = Optimus.matrix_row_index + File optimus_matrix_col_index = Optimus.matrix_col_index + File? optimus_aligner_metrics = Optimus.aligner_metrics + File? optimus_mtx_files = Optimus.mtx_files + File? optimus_filtered_mtx_files = Optimus.filtered_mtx_files + File? optimus_multimappers_EM_matrix = Optimus.multimappers_EM_matrix + File? optimus_multimappers_Uniform_matrix = Optimus.multimappers_Uniform_matrix + File? optimus_multimappers_Rescue_matrix = Optimus.multimappers_Rescue_matrix + File? optimus_multimappers_PropUnique_matrix = Optimus.multimappers_PropUnique_matrix + + # Optimus H5ad + File optimus_h5ad_output_file = Optimus.h5ad_output_file + + # Optimus Cellbender outputs + File? cb_cell_barcodes_csv = Optimus.cell_barcodes_csv + File? cb_checkpoint_file = Optimus.checkpoint_file + Array[File]? cb_h5_array = Optimus.h5_array + Array[File]? cb_html_report_array = Optimus.html_report_array + File? cb_log = Optimus.log + Array[File]? cb_metrics_csv_array = Optimus.metrics_csv_array + String? cb_output_directory = Optimus.output_directory + File? cb_summary_pdf = Optimus.summary_pdf + + # Spatial/Positioning outputs + File spatial_output_h5 = spatial_count.sb_counts + File spatial_output_log = spatial_count.spatial_log + File positioning_seurat_qs = positioning.seurat_qs + File positioning_coords_csv = positioning.coords_csv + File positioning_coords2_csv = positioning.coords2_csv + File positioning_summary_pdf = positioning.summary_pdf + File positioning_intermediates = positioning.intermediates_file + File positioning_positioning_log = positioning.positioning_log + } + +} + diff --git a/pipelines/skylab/slidetags/test_inputs/Plumbing/example.json b/pipelines/skylab/slidetags/test_inputs/Plumbing/example.json new file mode 100644 index 0000000000..a7899826ab --- /dev/null +++ b/pipelines/skylab/slidetags/test_inputs/Plumbing/example.json @@ -0,0 +1,11 @@ +{ + "SlideTags.spatial_fastq": ["gs://pd-test-storage-private/SlideTags/input/plumbing/example/SI-TT-B10_S2_L001_R1_001.fastq.gz", "gs://pd-test-storage-private/SlideTags/input/plumbing/example/SI-TT-B10_S2_L001_R2_001.fastq.gz"], + "SlideTags.pucks": ["gs://pd-test-storage-private/SlideTags/input/plumbing/example/Puck_240314_04.csv"], + "SlideTags.gex_r1_fastq": ["gs://warp-testing-public/slide-tag/5p_dataset/fastqs/SI-TT-B9_S1_L001_R1_001.fastq.gz", "gs://warp-testing-public/slide-tag/5p_dataset/fastqs/SI-TT-B9_S1_L002_R1_001.fastq.gz"], + "SlideTags.gex_r2_fastq": ["gs://warp-testing-public/slide-tag/5p_dataset/fastqs/SI-TT-B9_S1_L001_R2_001.fastq.gz", "gs://warp-testing-public/slide-tag/5p_dataset/fastqs/SI-TT-B9_S1_L002_R2_001.fastq.gz"], + "SlideTags.gex_whitelist": "gs://pd-test-storage-private/SlideTags/input/plumbing/example/3M-5pgex-jan-2023.txt", + "SlideTags.tar_star_reference": "gs://pd-test-storage-private/SlideTags/input/plumbing/example/modified_star2.7.10a-Human-GENCODE-build-GRCh38-44.tar", + "SlideTags.input_id": "plumbing", + "SlideTags.annotations_gtf": "gs://pd-test-storage-private/SlideTags/input/plumbing/example/gencode.v44.primary_assembly.annotation.gtf.filtered" +} + \ No newline at end of file diff --git a/pipelines/skylab/smartseq2_single_nucleus_multisample/MultiSampleSmartSeq2SingleNucleus.changelog.md b/pipelines/skylab/smartseq2_single_nucleus_multisample/MultiSampleSmartSeq2SingleNucleus.changelog.md index c83e09ac7c..75a950e90e 100644 --- a/pipelines/skylab/smartseq2_single_nucleus_multisample/MultiSampleSmartSeq2SingleNucleus.changelog.md +++ b/pipelines/skylab/smartseq2_single_nucleus_multisample/MultiSampleSmartSeq2SingleNucleus.changelog.md @@ -1,3 +1,8 @@ +# 2.2.1 +2025-05-27 (Date of Last Commit) + +* Increased the ulimit in the STARsoloFastq task in the StarAlign.wdl to 10000; this does not affect the outputs of the pipeline + # 2.2.0 2025-04-02 (Date of Last Commit) diff --git a/pipelines/skylab/smartseq2_single_nucleus_multisample/MultiSampleSmartSeq2SingleNucleus.wdl b/pipelines/skylab/smartseq2_single_nucleus_multisample/MultiSampleSmartSeq2SingleNucleus.wdl index f4cfa41545..258bbb1e67 100644 --- a/pipelines/skylab/smartseq2_single_nucleus_multisample/MultiSampleSmartSeq2SingleNucleus.wdl +++ b/pipelines/skylab/smartseq2_single_nucleus_multisample/MultiSampleSmartSeq2SingleNucleus.wdl @@ -57,7 +57,7 @@ workflow MultiSampleSmartSeq2SingleNucleus { } # Version of this pipeline - String pipeline_version = "2.2.0" + String pipeline_version = "2.2.1" if (false) { String? none = "None" diff --git a/pipelines/skylab/smartseq2_single_nucleus_multisample/test_inputs/Plumbing/mouse_example.json b/pipelines/skylab/smartseq2_single_nucleus_multisample/test_inputs/Plumbing/mouse_example.json index 587a4aa5e4..bff802dd22 100644 --- a/pipelines/skylab/smartseq2_single_nucleus_multisample/test_inputs/Plumbing/mouse_example.json +++ b/pipelines/skylab/smartseq2_single_nucleus_multisample/test_inputs/Plumbing/mouse_example.json @@ -2,16 +2,16 @@ "MultiSampleSmartSeq2SingleNucleus.genome_ref_fasta": "gs://gcp-public-data--broad-references/mm10/v0/single_nucleus/modified_mm10.primary_assembly.genome.fa", "MultiSampleSmartSeq2SingleNucleus.tar_star_reference": "gs://gcp-public-data--broad-references/mm10/v0/single_nucleus/star/modified_star_2.7.9a_primary_gencode_mouse_vM23.tar", "MultiSampleSmartSeq2SingleNucleus.annotations_gtf": "gs://gcp-public-data--broad-references/mm10/v0/single_nucleus/modified_gencode.vM23.primary_assembly.annotation.gtf", - "MultiSampleSmartSeq2SingleNucleus.adapter_list": "gs://broad-gotc-test-storage/MultiSampleSmartSeq2SingleNucleus/adapters/Illumina_adapters_list.fa", + "MultiSampleSmartSeq2SingleNucleus.adapter_list": "gs://pd-test-storage-public/Smartseq2_Single_Nucleus_Multisample/input/plumbing/SM-GE644/adapters/Illumina_adapters_list.fa", "MultiSampleSmartSeq2SingleNucleus.fastq1_input_files": [ - "gs://broad-gotc-test-storage/Smartseq2_Single_Nucleus_Multisample/truth/plumbing/master/pr_test_truth/SM-GE644_S110_E1-50_GGAGCTAC-CTAAGCCT_R1.fastq.gz", - "gs://broad-gotc-test-storage/Smartseq2_Single_Nucleus_Multisample/truth/plumbing/master/pr_test_truth/SM-GE644_S117_E1-50_GCGTAGTA-AAGGAGTA_R1.fastq.gz", - "gs://broad-gotc-test-storage/Smartseq2_Single_Nucleus_Multisample/truth/plumbing/master/pr_test_truth/SM-GE644_S118_E1-50_GCGTAGTA-CTAAGCCT_R1.fastq.gz" + "gs://pd-test-storage-public/Smartseq2_Single_Nucleus_Multisample/input/plumbing/SM-GE644/SM-GE644_S110_E1-50_GGAGCTAC-CTAAGCCT_R1.fastq.gz", + "gs://pd-test-storage-public/Smartseq2_Single_Nucleus_Multisample/input/plumbing/SM-GE644/SM-GE644_S117_E1-50_GCGTAGTA-AAGGAGTA_R1.fastq.gz", + "gs://pd-test-storage-public/Smartseq2_Single_Nucleus_Multisample/input/plumbing/SM-GE644/SM-GE644_S118_E1-50_GCGTAGTA-CTAAGCCT_R1.fastq.gz" ], "MultiSampleSmartSeq2SingleNucleus.fastq2_input_files": [ - "gs://broad-gotc-test-storage/Smartseq2_Single_Nucleus_Multisample/truth/plumbing/master/pr_test_truth/SM-GE644_S110_E1-50_GGAGCTAC-CTAAGCCT_R2.fastq.gz", - "gs://broad-gotc-test-storage/Smartseq2_Single_Nucleus_Multisample/truth/plumbing/master/pr_test_truth/SM-GE644_S117_E1-50_GCGTAGTA-AAGGAGTA_R2.fastq.gz", - "gs://broad-gotc-test-storage/Smartseq2_Single_Nucleus_Multisample/truth/plumbing/master/pr_test_truth/SM-GE644_S118_E1-50_GCGTAGTA-CTAAGCCT_R2.fastq.gz" + "gs://pd-test-storage-public/Smartseq2_Single_Nucleus_Multisample/input/plumbing/SM-GE644/SM-GE644_S110_E1-50_GGAGCTAC-CTAAGCCT_R2.fastq.gz", + "gs://pd-test-storage-public/Smartseq2_Single_Nucleus_Multisample/input/plumbing/SM-GE644/SM-GE644_S117_E1-50_GCGTAGTA-AAGGAGTA_R2.fastq.gz", + "gs://pd-test-storage-public/Smartseq2_Single_Nucleus_Multisample/input/plumbing/SM-GE644/SM-GE644_S118_E1-50_GCGTAGTA-CTAAGCCT_R2.fastq.gz" ], "MultiSampleSmartSeq2SingleNucleus.input_ids": [ "SM-GE644_S110_E1-50_GGAGCTAC-CTAAGCCT", diff --git a/pipelines/skylab/snm3C/test_inputs/Plumbing/miseq_M16_G13.json b/pipelines/skylab/snm3C/test_inputs/Plumbing/miseq_M16_G13.json index 047314bea1..a35c153044 100644 --- a/pipelines/skylab/snm3C/test_inputs/Plumbing/miseq_M16_G13.json +++ b/pipelines/skylab/snm3C/test_inputs/Plumbing/miseq_M16_G13.json @@ -1,21 +1,21 @@ { "snm3C.fastq_input_read1": [ - "gs://broad-gotc-test-storage/snM3C/inputs/plumbing/230117-AD3C-hs-snm3C_seq-NovaSeq-pe-150-PB-AD3C_BA17_2027_P1-1-B11_S1_L001_R1_001_fastq_R1_0.fastq.gz", - "gs://broad-gotc-test-storage/snM3C/inputs/plumbing/230117-AD3C-hs-snm3C_seq-NovaSeq-pe-150-PB-AD3C_BA17_2027_P1-1-B11_S1_L002_R1_001_fastq_R1_0.fastq.gz", - "gs://broad-gotc-test-storage/snM3C/inputs/plumbing/230117-AD3C-hs-snm3C_seq-NovaSeq-pe-150-PB-AD3C_BA17_2027_P1-1-B11_S1_L003_R1_001_fastq_R1_0.fastq.gz", - "gs://broad-gotc-test-storage/snM3C/inputs/plumbing/230117-AD3C-hs-snm3C_seq-NovaSeq-pe-150-PB-AD3C_BA17_2027_P1-1-B11_S1_L004_R1_001_fastq_R1_0.fastq.gz" + "gs://pd-test-storage-public/snm3C-seq/input/plumbing/miseq_M16_G13/230117-AD3C-hs-snm3C_seq-NovaSeq-pe-150-PB-AD3C_BA17_2027_P1-1-B11_S1_L001_R1_001_fastq_R1_0.fastq.gz", + "gs://pd-test-storage-public/snm3C-seq/input/plumbing/miseq_M16_G13/230117-AD3C-hs-snm3C_seq-NovaSeq-pe-150-PB-AD3C_BA17_2027_P1-1-B11_S1_L002_R1_001_fastq_R1_0.fastq.gz", + "gs://pd-test-storage-public/snm3C-seq/input/plumbing/miseq_M16_G13/230117-AD3C-hs-snm3C_seq-NovaSeq-pe-150-PB-AD3C_BA17_2027_P1-1-B11_S1_L003_R1_001_fastq_R1_0.fastq.gz", + "gs://pd-test-storage-public/snm3C-seq/input/plumbing/miseq_M16_G13/230117-AD3C-hs-snm3C_seq-NovaSeq-pe-150-PB-AD3C_BA17_2027_P1-1-B11_S1_L004_R1_001_fastq_R1_0.fastq.gz" ], "snm3C.fastq_input_read2": [ - "gs://broad-gotc-test-storage/snM3C/inputs/plumbing/230117-AD3C-hs-snm3C_seq-NovaSeq-pe-150-PB-AD3C_BA17_2027_P1-1-B11_S1_L001_R1_001_fastq_R2_0.fastq.gz", - "gs://broad-gotc-test-storage/snM3C/inputs/plumbing/230117-AD3C-hs-snm3C_seq-NovaSeq-pe-150-PB-AD3C_BA17_2027_P1-1-B11_S1_L002_R1_001_fastq_R2_0.fastq.gz", - "gs://broad-gotc-test-storage/snM3C/inputs/plumbing/230117-AD3C-hs-snm3C_seq-NovaSeq-pe-150-PB-AD3C_BA17_2027_P1-1-B11_S1_L003_R1_001_fastq_R2_0.fastq.gz", - "gs://broad-gotc-test-storage/snM3C/inputs/plumbing/230117-AD3C-hs-snm3C_seq-NovaSeq-pe-150-PB-AD3C_BA17_2027_P1-1-B11_S1_L004_R1_001_fastq_R2_0.fastq.gz" + "gs://pd-test-storage-public/snm3C-seq/input/plumbing/miseq_M16_G13/230117-AD3C-hs-snm3C_seq-NovaSeq-pe-150-PB-AD3C_BA17_2027_P1-1-B11_S1_L001_R1_001_fastq_R2_0.fastq.gz", + "gs://pd-test-storage-public/snm3C-seq/input/plumbing/miseq_M16_G13/230117-AD3C-hs-snm3C_seq-NovaSeq-pe-150-PB-AD3C_BA17_2027_P1-1-B11_S1_L002_R1_001_fastq_R2_0.fastq.gz", + "gs://pd-test-storage-public/snm3C-seq/input/plumbing/miseq_M16_G13/230117-AD3C-hs-snm3C_seq-NovaSeq-pe-150-PB-AD3C_BA17_2027_P1-1-B11_S1_L003_R1_001_fastq_R2_0.fastq.gz", + "gs://pd-test-storage-public/snm3C-seq/input/plumbing/miseq_M16_G13/230117-AD3C-hs-snm3C_seq-NovaSeq-pe-150-PB-AD3C_BA17_2027_P1-1-B11_S1_L004_R1_001_fastq_R2_0.fastq.gz" ], - "snm3C.random_primer_indexes": "gs://broad-gotc-test-storage/snM3C/inputs/plumbing/random_index_M16_G13.fa", + "snm3C.random_primer_indexes": "gs://pd-test-storage-public/snm3C-seq/input/plumbing/miseq_M16_G13/random_index_M16_G13.fa", "snm3C.plate_id": "AD3C_BA17_2027_P1-1-B11", - "snm3C.tarred_index_files":"gs://broad-gotc-test-storage/methylome/input/plumbing/index_files/hg38_index_files.tar.gz", - "snm3C.chromosome_sizes": "gs://broad-gotc-test-storage/methylome/input/plumbing/index_files/hg38.chrom.sizes", - "snm3C.genome_fa": "gs://broad-gotc-test-storage/methylome/input/plumbing/index_files/hg38.fa", + "snm3C.tarred_index_files":"gs://pd-test-storage-public/snm3C-seq/input/plumbing/miseq_M16_G13/index_files/hg38_index_files.tar.gz", + "snm3C.chromosome_sizes": "gs://pd-test-storage-public/snm3C-seq/input/plumbing/miseq_M16_G13/index_files/hg38.chrom.sizes", + "snm3C.genome_fa": "gs://pd-test-storage-public/snm3C-seq/input/plumbing/miseq_M16_G13/index_files/hg38.fa", "snm3C.Hisat_paired_end.cpu_platform" : "Intel Cascade Lake", "snm3C.Hisat_single_end.cpu_platform" : "Intel Cascade Lake", "snm3C.Merge_sort_analyze.cpu_platform" : "Intel Cascade Lake", diff --git a/pipelines/skylab/snm3C/test_inputs/Scientific/novaseq_M16_G13.json b/pipelines/skylab/snm3C/test_inputs/Scientific/novaseq_M16_G13.json index 14441d35ae..ca590c16b6 100644 --- a/pipelines/skylab/snm3C/test_inputs/Scientific/novaseq_M16_G13.json +++ b/pipelines/skylab/snm3C/test_inputs/Scientific/novaseq_M16_G13.json @@ -1,21 +1,21 @@ { "snm3C.fastq_input_read1": [ - "gs://broad-gotc-test-storage/snM3C/inputs/scientific/230419-iN-hs-snm3C_seq-NovaSeq-pe-150-BW-iN230412_Entorhinal_Cortex_Adult_2115_R1_1-1-I3_S1_L001_R1_001_fastq_R1_0.fastq.gz", - "gs://broad-gotc-test-storage/snM3C/inputs/scientific/230419-iN-hs-snm3C_seq-NovaSeq-pe-150-BW-iN230412_Entorhinal_Cortex_Adult_2115_R1_1-1-I3_S1_L002_R1_001_fastq_R1_0.fastq.gz", - "gs://broad-gotc-test-storage/snM3C/inputs/scientific/230419-iN-hs-snm3C_seq-NovaSeq-pe-150-BW-iN230412_Entorhinal_Cortex_Adult_2115_R1_1-1-I3_S1_L003_R1_001_fastq_R1_0.fastq.gz", - "gs://broad-gotc-test-storage/snM3C/inputs/scientific/230419-iN-hs-snm3C_seq-NovaSeq-pe-150-BW-iN230412_Entorhinal_Cortex_Adult_2115_R1_1-1-I3_S1_L004_R1_001_fastq_R1_0.fastq.gz" + "gs://pd-test-storage-private/snm3C-seq/input/scientific/novaseq_M16_G13/230419-iN-hs-snm3C_seq-NovaSeq-pe-150-BW-iN230412_Entorhinal_Cortex_Adult_2115_R1_1-1-I3_S1_L001_R1_001_fastq_R1_0.fastq.gz", + "gs://pd-test-storage-private/snm3C-seq/input/scientific/novaseq_M16_G13/230419-iN-hs-snm3C_seq-NovaSeq-pe-150-BW-iN230412_Entorhinal_Cortex_Adult_2115_R1_1-1-I3_S1_L002_R1_001_fastq_R1_0.fastq.gz", + "gs://pd-test-storage-private/snm3C-seq/input/scientific/novaseq_M16_G13/230419-iN-hs-snm3C_seq-NovaSeq-pe-150-BW-iN230412_Entorhinal_Cortex_Adult_2115_R1_1-1-I3_S1_L003_R1_001_fastq_R1_0.fastq.gz", + "gs://pd-test-storage-private/snm3C-seq/input/scientific/novaseq_M16_G13/230419-iN-hs-snm3C_seq-NovaSeq-pe-150-BW-iN230412_Entorhinal_Cortex_Adult_2115_R1_1-1-I3_S1_L004_R1_001_fastq_R1_0.fastq.gz" ], "snm3C.fastq_input_read2": [ - "gs://broad-gotc-test-storage/snM3C/inputs/scientific/230419-iN-hs-snm3C_seq-NovaSeq-pe-150-BW-iN230412_Entorhinal_Cortex_Adult_2115_R1_1-1-I3_S1_L001_R1_001_fastq_R2_0.fastq.gz", - "gs://broad-gotc-test-storage/snM3C/inputs/scientific/230419-iN-hs-snm3C_seq-NovaSeq-pe-150-BW-iN230412_Entorhinal_Cortex_Adult_2115_R1_1-1-I3_S1_L002_R1_001_fastq_R2_0.fastq.gz", - "gs://broad-gotc-test-storage/snM3C/inputs/scientific/230419-iN-hs-snm3C_seq-NovaSeq-pe-150-BW-iN230412_Entorhinal_Cortex_Adult_2115_R1_1-1-I3_S1_L003_R1_001_fastq_R2_0.fastq.gz", - "gs://broad-gotc-test-storage/snM3C/inputs/scientific/230419-iN-hs-snm3C_seq-NovaSeq-pe-150-BW-iN230412_Entorhinal_Cortex_Adult_2115_R1_1-1-I3_S1_L004_R1_001_fastq_R2_0.fastq.gz" + "gs://pd-test-storage-private/snm3C-seq/input/scientific/novaseq_M16_G13/230419-iN-hs-snm3C_seq-NovaSeq-pe-150-BW-iN230412_Entorhinal_Cortex_Adult_2115_R1_1-1-I3_S1_L001_R1_001_fastq_R2_0.fastq.gz", + "gs://pd-test-storage-private/snm3C-seq/input/scientific/novaseq_M16_G13/230419-iN-hs-snm3C_seq-NovaSeq-pe-150-BW-iN230412_Entorhinal_Cortex_Adult_2115_R1_1-1-I3_S1_L002_R1_001_fastq_R2_0.fastq.gz", + "gs://pd-test-storage-private/snm3C-seq/input/scientific/novaseq_M16_G13/230419-iN-hs-snm3C_seq-NovaSeq-pe-150-BW-iN230412_Entorhinal_Cortex_Adult_2115_R1_1-1-I3_S1_L003_R1_001_fastq_R2_0.fastq.gz", + "gs://pd-test-storage-private/snm3C-seq/input/scientific/novaseq_M16_G13/230419-iN-hs-snm3C_seq-NovaSeq-pe-150-BW-iN230412_Entorhinal_Cortex_Adult_2115_R1_1-1-I3_S1_L004_R1_001_fastq_R2_0.fastq.gz" ], - "snm3C.random_primer_indexes": "gs://broad-gotc-test-storage/snM3C/inputs/plumbing/random_index_M16_G13.fa", + "snm3C.random_primer_indexes": "gs://pd-test-storage-private/snm3C-seq/input/scientific/novaseq_M16_G13/random_index_M16_G13.fa", "snm3C.plate_id": "230419-iN-hs-snm3C_seq-NovaSeq-pe-150-BW-iN230412_Entorhinal_Cortex_Adult_2115_R1_1-1-I3", - "snm3C.tarred_index_files":"gs://broad-gotc-test-storage/methylome/input/plumbing/index_files/hg38_index_files.tar.gz", - "snm3C.chromosome_sizes": "gs://broad-gotc-test-storage/methylome/input/plumbing/index_files/hg38.chrom.sizes", - "snm3C.genome_fa": "gs://broad-gotc-test-storage/methylome/input/plumbing/index_files/hg38.fa", + "snm3C.tarred_index_files":"gs://pd-test-storage-private/snm3C-seq/input/scientific/novaseq_M16_G13/index_files/hg38_index_files.tar.gz", + "snm3C.chromosome_sizes": "gs://pd-test-storage-private/snm3C-seq/input/scientific/novaseq_M16_G13/index_files/hg38.chrom.sizes", + "snm3C.genome_fa": "gs://pd-test-storage-private/snm3C-seq/input/scientific/novaseq_M16_G13/index_files/hg38.fa", "snm3C.Hisat_paired_end.cpu_platform" : "Intel Cascade Lake", "snm3C.Hisat_single_end.cpu_platform" : "Intel Cascade Lake", "snm3C.Merge_sort_analyze.cpu_platform" : "Intel Cascade Lake", diff --git a/scripts/firecloud_api/UpdateTestInputs.py b/scripts/firecloud_api/UpdateTestInputs.py index 1eb45d85e9..a65d21679a 100644 --- a/scripts/firecloud_api/UpdateTestInputs.py +++ b/scripts/firecloud_api/UpdateTestInputs.py @@ -3,6 +3,10 @@ import os import ast from decimal import Decimal +import logging + +logging.basicConfig(level=logging.INFO) + def format_float(value): """Format float to avoid scientific notation for small numbers.""" @@ -11,7 +15,51 @@ def format_float(value): return str(Decimal(str(value))) return value -def update_test_inputs(inputs_json, truth_path, results_path, update_truth, branch_name): +def determine_bucket_from_inputs(test_inputs): + """ + Determine whether inputs are from public or private bucket by examining the values. + If private is explicitly found, return private. + If known public buckets are found AND no unrecognized gs:// buckets exist, return public. + Otherwise, default to private. + """ + private_bucket = "gs://pd-test-storage-private" + public_bucket = "gs://pd-test-storage-public" + public_identifiers = [ + "gs://pd-test-storage-public", + "gs://broad-public-datasets", + "gs://gcp-public-data--broad-references", + "gs://gatk-best-practices" + ] + + inputs_str = json.dumps(test_inputs).lower() + logging.info(f"Here is the input string: {inputs_str}") + + if private_bucket in inputs_str: + logging.info("Detected private bucket reference.") + return private_bucket + + # Detect any gs://... that is NOT known to be public + import re + found_gs_paths = re.findall(r"gs://[a-zA-Z0-9\-_./]+", inputs_str) + + unknown_buckets = [ + path for path in found_gs_paths + if not any(pub in path for pub in public_identifiers) + ] + + if unknown_buckets: + logging.info(f"Detected unknown gs:// buckets (possibly private): {unknown_buckets}") + return private_bucket + + if any(pub in inputs_str for pub in public_identifiers): + logging.info("Detected public bucket reference only.") + return public_bucket + + logging.info("No known bucket found, defaulting to private.") + return private_bucket + + +def update_test_inputs(inputs_json, results_path, update_truth, branch_name, dockstore_pipeline_name): with open(inputs_json, 'r') as file: test_inputs = json.load(file) @@ -19,10 +67,34 @@ def update_test_inputs(inputs_json, truth_path, results_path, update_truth, bran sample_name = os.path.splitext(os.path.basename(inputs_json))[0] # Get the pipeline name from the test inputs JSON - pipeline_name = next(iter(test_inputs)).split('.')[0] + pipeline_name_from_test_inputs = next(iter(test_inputs)).split('.')[0] # Append "Test" in front of the pipeline name - test_name = f"Test{pipeline_name}" + test_name = f"Test{pipeline_name_from_test_inputs}" + + # Determine the correct bucket based on the input data + bucket_path = determine_bucket_from_inputs(test_inputs) + + # Get the test type from the sample name or infer from the inputs + if "plumbing" in sample_name.lower(): + test_type = "plumbing" + elif "scientific" in sample_name.lower(): + test_type = "scientific" + else: + # Try to infer from the inputs + inputs_str = json.dumps(test_inputs).lower() + if "plumbing" in inputs_str: + test_type = "plumbing" + elif "scientific" in inputs_str: + test_type = "scientific" + else: + # Default to plumbing if we can't determine + test_type = "plumbing" + + # Create the truth and results paths based on the determined bucket + # Extract the pipeline name from the input JSON for creating the bucket path + dockstore_pipeline_name = dockstore_pipeline_name + truth_path = f"{bucket_path}/{dockstore_pipeline_name}/truth/{test_type}/{branch_name}" # Update all keys and ensure nested inputs are handled correctly updated_inputs = {} @@ -35,7 +107,7 @@ def update_test_inputs(inputs_json, truth_path, results_path, update_truth, bran # For nested keys (more than two parts), append the original pipeline name with a `.` if len(key_parts) > 2: - key_parts[1] = f"{pipeline_name}.{key_parts[1]}" + key_parts[1] = f"{pipeline_name_from_test_inputs}.{key_parts[1]}" # Reconstruct the updated key new_key = '.'.join(key_parts) @@ -77,22 +149,17 @@ def update_test_inputs(inputs_json, truth_path, results_path, update_truth, bran def main(): description = """This script updates the test inputs JSON to work with the test wrapper WDL, - which runs the pipeline and verification""" + which runs the pipeline and verification. It now determines the appropriate bucket (public or private) + based on the input data locations.""" parser = argparse.ArgumentParser(description=description) - parser.add_argument( - "--truth_path", - dest="truth_path", - required=True, - help="The base path where the truth data is stored", - ) - parser.add_argument( "--results_path", dest="results_path", - required=True, - help="The base path where the test data will be stored", + required=False, + default="gs://pd-test-results", + help="The base path where the test data will be stored (now determined dynamically based on input data)", ) parser.add_argument( @@ -117,12 +184,18 @@ def main(): required=True, help="Branch name of the current pipeline run") + parser.add_argument( + "--dockstore_pipeline_name", + required=True, + help="The pipeline name from Dockstore", + ) + args = parser.parse_args() # convert the update_truth flag to a boolean update_truth_bool = args.update_truth.lower() == "true" # Update the test inputs to work with the test wrapper WDL - update_test_inputs(args.inputs_json, args.truth_path, args.results_path, update_truth_bool, args.branch_name) + update_test_inputs(args.inputs_json, args.results_path, update_truth_bool, args.branch_name, args.dockstore_pipeline_name) if __name__ == "__main__": main() \ No newline at end of file diff --git a/tasks/broad/Qc.wdl b/tasks/broad/Qc.wdl index b1561407a5..9d6a71c8fb 100644 --- a/tasks/broad/Qc.wdl +++ b/tasks/broad/Qc.wdl @@ -179,7 +179,7 @@ task CollectAggregationMetrics { } runtime { docker: "us.gcr.io/broad-gotc-prod/picard-cloud:2.26.10" - memory: "7000 MiB" + memory: "18000 MiB" disks: "local-disk " + disk_size + " HDD" preemptible: preemptible_tries } diff --git a/tasks/broad/TerraCopyFilesFromCloudToCloud.wdl b/tasks/broad/TerraCopyFilesFromCloudToCloud.wdl index 66b6eb69a4..1860151bff 100644 --- a/tasks/broad/TerraCopyFilesFromCloudToCloud.wdl +++ b/tasks/broad/TerraCopyFilesFromCloudToCloud.wdl @@ -30,9 +30,9 @@ task TerraCopyFilesFromCloudToCloud { echo ~{default='no_contamination' contamination} > contamination if ! grep -q no_contamination contamination; then - gcloud storage cp -L cp.log contamination ~{destination_cloud_path}.contamination + gcloud storage cp --project=warp-pipeline-dev --billing-project=terra-f8e3de20 -L cp.log contamination ~{destination_cloud_path}.contamination fi - gcloud storage cp ~{sep=' ' files_to_copy} ~{destination_cloud_path} + gcloud storage cp --project=warp-pipeline-dev --billing-project=terra-f8e3de20 ~{sep=' ' files_to_copy} ~{destination_cloud_path} } output { diff --git a/tasks/skylab/StarAlign.wdl b/tasks/skylab/StarAlign.wdl index 363d8226d5..21182edc51 100644 --- a/tasks/skylab/StarAlign.wdl +++ b/tasks/skylab/StarAlign.wdl @@ -266,6 +266,8 @@ task STARsoloFastq { set -euo pipefail set -x + ulimit -n 10000 + UMILen=10 CBLen=16 if [ "~{chemistry}" == 2 ] diff --git a/beta-pipelines/skylab/slidetags/scripts/CREDITS.md b/tasks/skylab/slidetags_utils/CREDITS.md similarity index 100% rename from beta-pipelines/skylab/slidetags/scripts/CREDITS.md rename to tasks/skylab/slidetags_utils/CREDITS.md diff --git a/beta-pipelines/skylab/slidetags/scripts/positioning.wdl b/tasks/skylab/slidetags_utils/positioning.wdl similarity index 60% rename from beta-pipelines/skylab/slidetags/scripts/positioning.wdl rename to tasks/skylab/slidetags_utils/positioning.wdl index c51dacb8c4..7d31fffd83 100644 --- a/beta-pipelines/skylab/slidetags/scripts/positioning.wdl +++ b/tasks/skylab/slidetags_utils/positioning.wdl @@ -4,6 +4,7 @@ task generate_positioning { input { Array[String] rna_paths String sb_path + String input_id Int mem_GiB = 128 Int disk_GiB = 128 Int nthreads = 16 @@ -13,15 +14,17 @@ task generate_positioning { set -euo pipefail set -x echo "<< starting spatial-count >>" + + Rscript -e "install.packages(c('optparse', 'BiocManager'), repos='https://cloud.r-project.org'); BiocManager::install('IRanges')" gcloud config set storage/process_count 16 # is this set by user? gcloud config set storage/thread_count 2 # is this set by user? - # Download the scripts -- these need to be changed -- also need to add to docker - wget https://raw.githubusercontent.com/MacoskoLab/Macosko-Pipelines/ee005109446f58764509ee47ff51c212ce8dabe3/positioning/positioning.R - wget https://raw.githubusercontent.com/MacoskoLab/Macosko-Pipelines/6a78716aa08a9f2506c06844f7e3fd491b03aa8b/positioning/load_matrix.R - wget https://raw.githubusercontent.com/MacoskoLab/Macosko-Pipelines/a7fc86abbdd3d46461c500e7d024315d88a97e9a/positioning/run-positioning.R - + # Download the scripts -- these need to be changed -- also need to add to docker + wget https://raw.githubusercontent.com/MacoskoLab/Macosko-Pipelines/d89176cf21e072fe8b5aad3a1454ad194fca7c9a/slide-tags/run-positioning.R + wget https://raw.githubusercontent.com/MacoskoLab/Macosko-Pipelines/d89176cf21e072fe8b5aad3a1454ad194fca7c9a/slide-tags/positioning.R + wget https://raw.githubusercontent.com/MacoskoLab/Macosko-Pipelines/d89176cf21e072fe8b5aad3a1454ad194fca7c9a/slide-tags/helpers.R + echo "RNA: ~{sep=' ' rna_paths}" echo "SB: ~{sb_path}" @@ -47,12 +50,12 @@ task generate_positioning { # Download the SB echo "Downloading SB:" - mkdir SB - gcloud storage cp ~{sb_path} SB + gcloud storage cp ~{sb_path} . + baseSB=`basename ~{sb_path}` # Run the script echo ; echo "Running run-positioning.R" - Rscript run-positioning.R RNA SB output + Rscript run-positioning.R RNA $baseSB output # Upload the results ls output/* @@ -65,19 +68,34 @@ task generate_positioning { echo; echo "Writing logs:" echo; echo "RNA size:"; du -sh RNA - echo; echo "SB size:"; du -sh SB + echo; echo "SB size:"; du -sh $baseSB echo; echo "output size:"; du -sh output echo; echo "FREE SPACE:"; df -h echo "tar files/logs" cat stdout stderr > positioning.log - tar -zcvf output.tar.gz output + + # Rename and move files + mv output/* . + mv summary.pdf ~{input_id}_summary.pdf + mv seurat.qs ~{input_id}_seurat.qs + mv coords.csv ~{input_id}_coords.csv + mv coords2.csv ~{input_id}_coords2.csv + + ls + tar -zcvf output.tar.gz matrix.csv.gz cb_whitelist.txt spatial_metadata.json + mv output.tar.gz ~{input_id}_intermediates.tar.gz + mv positioning.log ~{input_id}_positioning.log echo "<< completed positioning >>" >>> output { - File output_file = "output.tar.gz" - File positioning_log = "positioning.log" + File seurat_qs = "~{input_id}_seurat.qs" + File coords_csv = "~{input_id}_coords.csv" + File coords2_csv = "~{input_id}_coords2.csv" + File summary_pdf = "~{input_id}_summary.pdf" + File intermediates_file = "~{input_id}_intermediates.tar.gz" + File positioning_log = "~{input_id}_positioning.log" } runtime { diff --git a/beta-pipelines/skylab/slidetags/scripts/spatial-count.wdl b/tasks/skylab/slidetags_utils/spatial-count.wdl similarity index 82% rename from beta-pipelines/skylab/slidetags/scripts/spatial-count.wdl rename to tasks/skylab/slidetags_utils/spatial-count.wdl index 409a983de0..f24fb3eb2f 100644 --- a/beta-pipelines/skylab/slidetags/scripts/spatial-count.wdl +++ b/tasks/skylab/slidetags_utils/spatial-count.wdl @@ -4,6 +4,7 @@ task count { input { Array[String] fastq_paths Array[String] pucks + String input_id Int mem_GiB = 64 Int disk_GiB = 128 Int nthreads = 1 @@ -18,8 +19,9 @@ task count { gcloud config set storage/process_count 16 gcloud config set storage/thread_count 2 - # Download the script -- put this script into a docker - wget https://raw.githubusercontent.com/MacoskoLab/Macosko-Pipelines/5c74e9e6148102081827625b9ce91ec2b7ba3541/spatial-count/spatial-count.jl + # Download the script -- put this script into a docker + # This needs to be changed when Matthew finalizes changes to these scripts + wget https://raw.githubusercontent.com/MacoskoLab/Macosko-Pipelines/d89176cf21e072fe8b5aad3a1454ad194fca7c9a/slide-tags/spatial-count.jl echo "FASTQs: ~{length(fastq_paths)} paths provided" echo "Pucks: ~{length(pucks)} puck(s) provided" @@ -69,16 +71,18 @@ task count { echo; echo "pucks size:"; du -sh pucks echo; echo "output size:"; du -sh SBcounts.h5 echo; echo "FREE SPACE:"; df -h - - cat stdout stderr > spatial-count.log + + mv SBcounts.h5 ~{input_id}_SBcounts.h5 + cat stdout stderr > ~{input_id}_spatial-count.log echo "<< completed spatial-count >>" + >>> output { - File sb_counts = "SBcounts.h5" - File spatial_log = "spatial-count.log" - + File sb_counts = "~{input_id}_SBcounts.h5" + File spatial_log = "~{input_id}_spatial-count.log" } + runtime { docker: docker memory: "~{mem_GiB} GB" diff --git a/verification/VerifyNA12878.wdl b/verification/VerifyNA12878.wdl index 3d5720df4d..d65c96df57 100644 --- a/verification/VerifyNA12878.wdl +++ b/verification/VerifyNA12878.wdl @@ -7,9 +7,9 @@ workflow VerifyNA12878 { Array[File] vcf_file_indexes Array[String] vcf_names - File truth_vcf = "gs://broad-gotc-test-storage/VerifyNA12878/nist_na12878_giab_hg38_sd_fix.vcf.gz" - File truth_vcf_index = "gs://broad-gotc-test-storage/VerifyNA12878/nist_na12878_giab_hg38_sd_fix.vcf.gz.tbi" - File truth_intervals = "gs://broad-gotc-test-storage/VerifyNA12878/HG001_NA12878_GRCh38_GIAB_highconf.exome.interval_list" + File truth_vcf = "gs://pd-test-storage-private/VerifyNA12878/input/nist_na12878_giab_hg38_sd_fix.vcf.gz" + File truth_vcf_index = "gs://pd-test-storage-private/VerifyNA12878/input/nist_na12878_giab_hg38_sd_fix.vcf.gz.tbi" + File truth_intervals = "gs://pd-test-storage-private/VerifyNA12878/input/HG001_NA12878_GRCh38_GIAB_highconf.exome.interval_list" String sample_name = "NA12878" Int? preemptible_attempts diff --git a/verification/VerifyPeakCalling.wdl b/verification/VerifyPeakCalling.wdl new file mode 100644 index 0000000000..32c06d7c3b --- /dev/null +++ b/verification/VerifyPeakCalling.wdl @@ -0,0 +1,27 @@ +version 1.0 + +import "../verification/VerifyTasks.wdl" as VerifyTasks + +workflow VerifyPeakCalling { + + input { + File test_cellbybin_h5ad + File truth_cellbybin_h5ad + + File test_cellbypeak_h5ad + File truth_cellbypeak_h5ad + + Boolean? done + } + + call VerifyTasks.CompareH5adFilesATAC as CompareH5adFilesCellByBin { + input: + test_h5ad = test_cellbybin_h5ad, + truth_h5ad = truth_cellbybin_h5ad + } + call VerifyTasks.CompareH5adFilesATAC as CompareH5adFilesCellByPeak { + input: + test_h5ad = test_cellbypeak_h5ad, + truth_h5ad = truth_cellbypeak_h5ad + } +} \ No newline at end of file diff --git a/verification/VerifySlideTags.wdl b/verification/VerifySlideTags.wdl new file mode 100644 index 0000000000..88d223ff7d --- /dev/null +++ b/verification/VerifySlideTags.wdl @@ -0,0 +1,227 @@ +version 1.0 + +import "../verification/VerifyTasks.wdl" as VerifyTasks + +workflow VerifySlideTags { + + input { + File test_h5ad + File truth_h5ad + + File test_bam + File truth_bam + + File test_gene_metrics + File truth_gene_metrics + + File test_cell_metrics + File truth_cell_metrics + + File test_library_metrics + File truth_library_metrics + + # spatial and positioning outputs + File test_spatial_output_h5 + File truth_spatial_output_h5 + + File test_seurat_qs + File truth_seurat_qs + + File test_coords_csv + File truth_coords_csv + + File test_coords2_csv + File truth_coords2_csv + + File test_intermediates_file + File truth_intermediates_file + + Boolean? done + } + + call VerifyTasks.CompareBams as CompareOptimusBams { + input: + test_bam = test_bam, + truth_bam = truth_bam, + lenient_header = true + } + + call VerifyTasks.CompareCompressedTextFiles as CompareGeneMetrics { + input: + test_zip = test_gene_metrics, + truth_zip = truth_gene_metrics + } + + call VerifyTasks.CompareCompressedTextFiles as CompareCellMetrics { + input: + test_zip = test_cell_metrics, + truth_zip = truth_cell_metrics + } + + call VerifyTasks.CompareH5adFilesGEX as CompareH5adFilesOptimus { + input: + test_h5ad = test_h5ad, + truth_h5ad = truth_h5ad + } + + call VerifyTasks.CompareLibraryFiles as CompareLibraryMetrics { + input: + test_text_file = test_library_metrics, + truth_text_file = truth_library_metrics + } + + call VerifyTasks.CompareH5Files as CompareSpatialOutputH5 { + input: + test_h5 = test_spatial_output_h5, + truth_h5 = truth_spatial_output_h5 + } + + call compare_slidetags_csv as CompareCSV { + input: + test_csv = test_coords_csv, + truth_csv = truth_coords_csv + } + + call compare_slidetags_csv as CompareCSV2 { + input: + test_csv = test_coords2_csv, + truth_csv = truth_coords2_csv + } + + call CompareSlideTagsTarballContents as CompareTarballContents { + input: + test_tar = test_intermediates_file, + truth_tar = truth_intermediates_file + } + +} + +task CompareSlideTagsTarballContents { + input { + File test_tar + File truth_tar + } + + Float file_size = size(test_tar, "GiB") + size(truth_tar, "GiB") + Int disk_size = ceil(file_size * 4) + 20 + + command <<< + set -e + + mkdir test_dir truth_dir + + # Extract tarballs + tar -xzf ~{test_tar} -C test_dir + tar -xzf ~{truth_tar} -C truth_dir + + # Prepare log file + touch comparison_errors.log + + # Compare matrix.csv.gz + echo "Comparing matrix.csv.gz..." + gunzip -c test_dir/matrix.csv.gz | sort > sorted_test_matrix.txt + gunzip -c truth_dir/matrix.csv.gz | sort > sorted_truth_matrix.txt + if ! diff sorted_test_matrix.txt sorted_truth_matrix.txt > /dev/null; then + echo "matrix.csv.gz files differ." >> comparison_errors.log + else + echo "matrix.csv.gz files are identical." + fi + + # Compare cb_whitelist.txt + echo "Comparing cb_whitelist.txt..." + sort test_dir/cb_whitelist.txt > sorted_test_cb.txt + sort truth_dir/cb_whitelist.txt > sorted_truth_cb.txt + if ! diff sorted_test_cb.txt sorted_truth_cb.txt > /dev/null; then + echo "cb_whitelist.txt files differ." >> comparison_errors.log + else + echo "cb_whitelist.txt files are identical." + fi + + # Final check for errors + if [ -s comparison_errors.log ]; then + sed -i '1iNOTE: These differences may be due to non-deterministic behavior in the pipeline, but should still be investigated.' comparison_errors.log + echo "Comparison failed. See comparison_errors.log for details:" + cat comparison_errors.log + exit 1 + else + echo "All comparisons succeeded." + fi + >>> + + runtime { + docker: "gcr.io/gcp-runtimes/ubuntu_16_0_4@sha256:025124e2f1cf4d29149958f17270596bffe13fc6acca6252977c572dd5ba01bf" + disks: "local-disk ~{disk_size} HDD" + memory: "20 GiB" + preemptible: 3 + } +} + + +task compare_slidetags_csv { + input { + File truth_csv + File test_csv + } + + command <<< +python3 < Mismatch: {val1} != {val2}") + mismatches.append((row_num, colname, val1, val2)) + +if mismatches: + print("\\nSummary of mismatches (exact match expected):") + for row_num, col, v1, v2 in mismatches: + print(f"- Row {row_num}, Column {col}: {v1} != {v2}") + print("Comparison failed.") + sys.exit(1) +else: + print("Files match exactly for columns:", ", ".join(columns_to_compare)) +CODE + >>> + + runtime { + docker: "python:3.9" + } +} + + diff --git a/verification/VerifyTasks.wdl b/verification/VerifyTasks.wdl index 46ed24373c..7001faab71 100644 --- a/verification/VerifyTasks.wdl +++ b/verification/VerifyTasks.wdl @@ -810,4 +810,43 @@ task CompareLibraryFiles { memory: "50 GiB" preemptible: 3 } -} \ No newline at end of file +} + +task CompareH5Files { + input { + File test_h5 + File truth_h5 + } + + command { + set -eo pipefail + exit_code=0 + + apt update + apt install -y hdf5-tools + + h5diff ~{test_h5} ~{truth_h5} > diff_output.txt + + echo "H5diff output:" + # Print the diff output to the console + cat diff_output.txt + + if [ $? -ne 0 ]; then + echo "H5 files differ." + exit_code=2 + else + echo "H5 files are identical." + fi + echo "Exiting with code $exit_code" + } + + runtime { + docker: "ubuntu:20.04" + disks: "local-disk 100 HDD" + memory: "50 GiB" + preemptible: 3 + } +} + + + diff --git a/verification/test-wdls/TestPeakCalling.wdl b/verification/test-wdls/TestPeakCalling.wdl new file mode 100644 index 0000000000..c1ecbf528d --- /dev/null +++ b/verification/test-wdls/TestPeakCalling.wdl @@ -0,0 +1,102 @@ +version 1.0 + + +import "../../pipelines/skylab/peak_calling/PeakCalling.wdl" as PeakCalling +import "../../verification/VerifyPeakCalling.wdl" as VerifyPeakCalling +import "../../tasks/broad/Utilities.wdl" as Utilities +import "../../tasks/broad/TerraCopyFilesFromCloudToCloud.wdl" as Copy + +workflow TestPeakCalling { + + input { + File annotations_gtf + File metrics_h5ad + File chrom_sizes + String output_base_name + Int min_counts = 5000 + Int min_tsse = 10 + Int max_counts = 100000 + Float probability_threshold = 0.5 + Int disk_size = 500 + Int mem_size = 64 + Int nthreads = 4 + String cloud_provider + + # These values will be determined and injected into the inputs by the scala test framework + String truth_path + String results_path + Boolean update_truth + } + + meta { + allowNestedInputs: true + } + + call PeakCalling.PeakCalling { + input: + annotations_gtf = annotations_gtf, + metrics_h5ad = metrics_h5ad, + chrom_sizes = chrom_sizes, + output_base_name = output_base_name, + min_counts = min_counts, + min_tsse = min_tsse, + max_counts = max_counts, + probability_threshold = probability_threshold, + disk_size = disk_size, + mem_size = mem_size, + nthreads = nthreads, + cloud_provider = cloud_provider + + } + + + # Collect all of the pipeline outputs into single Array[String] + Array[String] pipeline_outputs = flatten([ + [ # File outputs + PeakCalling.cellbypeak_h5ad, + PeakCalling.cellbybin_h5ad, + ], + + ]) + + # Copy results of pipeline to test results bucket + call Copy.TerraCopyFilesFromCloudToCloud as CopyToTestResults { + input: + files_to_copy = flatten([pipeline_outputs]), + destination_cloud_path = results_path + } + + # If updating truth then copy output to truth bucket + if (update_truth){ + call Copy.TerraCopyFilesFromCloudToCloud as CopyToTruth { + input: + files_to_copy = flatten([pipeline_outputs]), + destination_cloud_path = truth_path + } + } + + # This is achieved by passing each desired file/array[files] to GetValidationInputs + if (!update_truth){ + call Utilities.GetValidationInputs as GetCellbybinH5ad { + input: + input_file = PeakCalling.cellbybin_h5ad, + results_path = results_path, + truth_path = truth_path + } + call Utilities.GetValidationInputs as GetCellbypeakH5ad { + input: + input_file = PeakCalling.cellbypeak_h5ad, + results_path = results_path, + truth_path = truth_path + } + + call VerifyPeakCalling.VerifyPeakCalling as Verify { + input: + truth_cellbybin_h5ad = GetCellbybinH5ad.truth_file, + test_cellbybin_h5ad = GetCellbybinH5ad.results_file, + truth_cellbypeak_h5ad = GetCellbypeakH5ad.truth_file, + test_cellbypeak_h5ad = GetCellbypeakH5ad.results_file, + done = CopyToTestResults.done + } + } +} \ No newline at end of file diff --git a/verification/test-wdls/TestSlideTags.wdl b/verification/test-wdls/TestSlideTags.wdl new file mode 100644 index 0000000000..319690be82 --- /dev/null +++ b/verification/test-wdls/TestSlideTags.wdl @@ -0,0 +1,226 @@ +version 1.0 + +import "../../tasks/broad/Utilities.wdl" as Utilities +import "../../pipelines/skylab/slidetags/SlideTags.wdl" as SlideTags +import "../../verification/VerifySlideTags.wdl" as VerifySlideTags +import "../../tasks/broad/TerraCopyFilesFromCloudToCloud.wdl" as Copy + +workflow TestSlideTags { + + input { + + #String id + Array[String] spatial_fastq + Array[String] pucks + + # Optimus Inputs + Array[File] gex_r1_fastq + Array[File] gex_r2_fastq + Array[File]? gex_i1_fastq + File tar_star_reference + File annotations_gtf + File gex_whitelist + String cloud_provider = "gcp" + String input_id + Int expected_cells = 3000 + String counting_mode = "sn_rna" + Int tenx_chemistry_version = 3 + Int emptydrops_lower = 100 + Boolean force_no_check = false + Boolean ignore_r1_read_length = false + String star_strand_mode = "Reverse" + Boolean count_exons = false + String? soloMultiMappers + String? gex_nhash_id + File? mt_genes + String docker = "us.gcr.io/broad-gotc-prod/slide-tags:1.1.0" + + String truth_path + String results_path + Boolean update_truth + + } + + meta { + allowNestedInputs: true + } + + call SlideTags.SlideTags { + input: + # id = id, + spatial_fastq = spatial_fastq, + pucks = pucks, + gex_r1_fastq = gex_r1_fastq, + gex_r2_fastq = gex_r2_fastq, + gex_i1_fastq = gex_i1_fastq, + tar_star_reference = tar_star_reference, + annotations_gtf = annotations_gtf, + gex_whitelist = gex_whitelist, + cloud_provider = cloud_provider, + input_id = input_id, + expected_cells = expected_cells, + counting_mode = counting_mode, + tenx_chemistry_version = tenx_chemistry_version, + emptydrops_lower = emptydrops_lower, + force_no_check = force_no_check, + ignore_r1_read_length = ignore_r1_read_length, + star_strand_mode = star_strand_mode, + count_exons = count_exons, + soloMultiMappers = soloMultiMappers, + gex_nhash_id = gex_nhash_id, + mt_genes = mt_genes, + docker = docker + } + +# collect all of the pipeline outputs into single Array[String] +Array[String] pipeline_outputs = flatten([ + [ # File outputs + SlideTags.optimus_h5ad_output_file, + SlideTags.optimus_matrix_col_index, + SlideTags.optimus_matrix_row_index, + SlideTags.optimus_matrix, + SlideTags.optimus_bam, + SlideTags.optimus_genomic_reference_version, + SlideTags.spatial_output_h5, + SlideTags.positioning_seurat_qs, + SlideTags.positioning_coords_csv, + SlideTags.positioning_coords2_csv, + SlideTags.positioning_intermediates, + ], + # File? outputs + select_all([SlideTags.optimus_mtx_files]), + select_all([SlideTags.optimus_cell_calls]), + ]) + + + # Collect all of the pipeline metrics into single Array[String] + Array[String] pipeline_metrics = flatten([ + [ # File outputs + SlideTags.optimus_gene_metrics, + SlideTags.optimus_cell_metrics, + ], + # File? outputs + select_all([SlideTags.optimus_library_metrics]), + select_all([SlideTags.optimus_aligner_metrics]), + ]) + + # Copy results of pipeline to test results bucket + call Copy.TerraCopyFilesFromCloudToCloud as CopyToTestResults { + input: + files_to_copy = flatten([pipeline_outputs, pipeline_metrics]), + destination_cloud_path = results_path + } + + # If updating truth then copy pipeline results to truth bucket + if (update_truth){ + call Copy.TerraCopyFilesFromCloudToCloud as CopyToTruth { + input: + files_to_copy = flatten([pipeline_outputs, pipeline_metrics]), + destination_cloud_path = truth_path + } + } + + # If not updating truth then gather the inputs and call verification wdl + if (!update_truth) { + call Utilities.GetValidationInputs as GetH5adInputs { + input: + input_file = SlideTags.optimus_h5ad_output_file, + results_path = results_path, + truth_path = truth_path + } + + call Utilities.GetValidationInputs as GetBamInputs { + input: + input_file = SlideTags.optimus_bam, + results_path = results_path, + truth_path = truth_path, + } + + call Utilities.GetValidationInputs as GetGeneMetrics { + input: + input_file = SlideTags.optimus_gene_metrics, + results_path = results_path, + truth_path = truth_path + } + + call Utilities.GetValidationInputs as GetCellMetrics { + input: + input_file = SlideTags.optimus_cell_metrics, + results_path = results_path, + truth_path = truth_path + } + + call Utilities.GetValidationInputs as GetSpatialOutput { + input: + input_file = SlideTags.spatial_output_h5, + results_path = results_path, + truth_path = truth_path + } + + call Utilities.GetValidationInputs as GetSeuratQs { + input: + input_file = SlideTags.positioning_seurat_qs, + results_path = results_path, + truth_path = truth_path + } + + call Utilities.GetValidationInputs as GetCoordsCsv { + input: + input_file = SlideTags.positioning_coords_csv, + results_path = results_path, + truth_path = truth_path + } + + call Utilities.GetValidationInputs as GetCoords2Csv { + input: + input_file = SlideTags.positioning_coords2_csv, + results_path = results_path, + truth_path = truth_path + } + call Utilities.GetValidationInputs as GetIntermediates { + input: + input_file = SlideTags.positioning_intermediates, + results_path = results_path, + truth_path = truth_path + } + + if(defined(SlideTags.optimus_library_metrics)){ + call Utilities.GetValidationInputs as GetLibraryMetrics { + input: + input_file = SlideTags.optimus_library_metrics, + results_path = results_path, + truth_path = truth_path + } +} + + call VerifySlideTags.VerifySlideTags as Verify { + input: + test_h5ad = GetH5adInputs.results_file, + test_bam = GetBamInputs.results_file, + test_gene_metrics = GetGeneMetrics.results_file, + test_cell_metrics = GetCellMetrics.results_file, + truth_h5ad = GetH5adInputs.truth_file, + truth_bam = GetBamInputs.truth_file, + truth_gene_metrics = GetGeneMetrics.truth_file, + truth_cell_metrics = GetCellMetrics.truth_file, + test_library_metrics = select_first([GetLibraryMetrics.results_file, ""]), + truth_library_metrics = select_first([GetLibraryMetrics.truth_file, ""]), + test_spatial_output_h5 = GetSpatialOutput.results_file, + truth_spatial_output_h5 = GetSpatialOutput.truth_file, + test_seurat_qs = GetSeuratQs.results_file, + truth_seurat_qs = GetSeuratQs.truth_file, + test_coords_csv = GetCoordsCsv.results_file, + truth_coords_csv = GetCoordsCsv.truth_file, + test_coords2_csv = GetCoords2Csv.results_file, + truth_coords2_csv = GetCoords2Csv.truth_file, + test_intermediates_file = GetIntermediates.results_file, + truth_intermediates_file = GetIntermediates.truth_file, + done = CopyToTestResults.done + } + } + + output { + + } + +} diff --git a/website/docs/About_WARP/BestPractices.md b/website/docs/About_WARP/BestPractices.md index 067996ae68..3b19892add 100644 --- a/website/docs/About_WARP/BestPractices.md +++ b/website/docs/About_WARP/BestPractices.md @@ -128,6 +128,26 @@ We recommend using standard file formats and interfaces. In computational biolog - _Do_: When using containerization technologies, follow best practices to assure associated images do not update without explicit updates. - _Do_: Make both the images and the build files (Dockerfile) available to document the environment. [More on Dockerfiles](https://docs.docker.com/develop/develop-images/dockerfile_best-practices/). +## Cross-Platform Compatibility +This section offers resources to help you adapt WDLs for use across various environments. The links below point to key tools and platforms that support WDL execution and provide guidance for modifying workflows to fit specific contexts. + + + **1. Cromwell Documentation** + +Cromwell is a popular WDL execution engine that supports running workflows in various environments. Refer to the official [Cromwell documentation](https://cromwell.readthedocs.io/en/stable/) for guidance on adapting WDLs for use in local, cloud, or hybrid environments. + + **2. MiniWDL** + +MiniWDL is a lightweight version of WDL designed for local or smaller-scale workflows. It can help in environments where a full Cromwell installation may not be necessary. Refer to the official [MiniWDL documentation](https://miniwdl.readthedocs.io/en/latest/) for more details. + + **3. Seven Bridges Genomics (Velsera)** + +[Seven Bridges Genomics](https://www.sevenbridges.com/), now known as Velsera, provides a cloud platform for bioinformatics workflows. The platform supports WDL and provides tools for modifying workflows to run on their infrastructure. + + **4. Manifold** + +[Manifold](https://www.manifold.ai/) is a cloud-native platform that supports WDL, CWL, and Nextflow, enabling scalable and reproducible bioinformatics workflows. It offers tools and documentation to help adapt WDLs for efficient execution across cloud and hybrid environments. + ## Versioning Versioning pipelines and associated Docker images allows you to determine when and how data is created (provenance). As you make improvements and changes to your pipeline, it is important to know which version of the pipeline and software you used to create a given dataset so that it can be easily reproduced. This not only facilitates scientific reproducibility for the greater community, it also allows you to verify that new pipeline changes produce consistent results. We recommend choosing a consistent versioning system (for example, the [semantic system](https://semver.org/)) and tracking pipeline changes in a [changelog](https://keepachangelog.com/en/1.0.0/). diff --git a/website/docs/About_WARP/ForkingWARP.md b/website/docs/About_WARP/ForkingWARP.md new file mode 100644 index 0000000000..b74231a160 --- /dev/null +++ b/website/docs/About_WARP/ForkingWARP.md @@ -0,0 +1,73 @@ +--- +sidebar_position: 5 +--- +# Forking WARP + +The best way to make pipelines your own is to fork WARP. Forking is also a great way to create new pipelines or to suggest improvements to existing pipelines. Here we take you through all the steps needed to fork WARP using Github, and what the best options are for how to deploy your forked code to run in the cloud. + + * Start Forking. To start a fork, find the WARP repo on github and select the fork button. You can also choose which branch you want to fork, in this case we will fork the develop branch but you may also wish to fork the released `master` branch. Note you will need to be logged into a github account: + + ![forking01](../images/forking01.png) + * Configure Fork. From the “Create…” dialog, you can choose a new owner such as yourself and update the description with the purpose of your fork. You can uncheck the lower option if you want to fork all branches rather than the specific one. + + ![forking02](../images/forking02.png) + * Clone Repo. Now you are almost ready to start modifying your code. This can be managed on github and git as normal. For very small changes, you can edit code directly on github with the edit dialog and submit them directly. For larger changes you might want to use an IDE and git to synchronize your changes with the repo. To do this use the CODE button in github and copy the clone repo line. Then create a local copy of your repo either using your IDE, the github desktop client, or running the `git clone` command (e.g. `git clone git@github.com:rsc3/warp.git`) in your preferred local directory. + + ![forking03](../images/forking03.png) + + * Edit code. Note that you will be on the same branch that you forked from. Here we will stay on this branch though you may want to create a new branch for your code changes. Let’s change the code of the `StarAlign.wdl` workflow so that the task STARsoloFastq can run on a different cloud backend, such as AWS or Azure rather than only GCP. This is the alignment and metric calculation task for single-cell RNA-Seq, and since it is a costly step we might want to change the cloud platform it runs on. So we can add a cloud_provider input to the task, and decide which values are allowed and how they will change the execution. Note that every workflow dependent on `StarAlign.wdl` will also have to be updated to pass the `cloud_provider` input. Commit and push your modifications back to your repository. + + ![forking04](../images/forking04.png) + + * Now that you have modified your fork of WARP, you have several options to deploy your WDL workflows to a backend execution environment. We recommend GA4GH Dockstore for this purpose as a flexible hosting solution which you can use to deploy your code to a variety of execution options. One of those options is Broad Terra, for complete instructions on deploying to Dockstore and then to Terra see [this document on Terra deployment](https://support.terra.bio/hc/en-us/articles/8888504224283-How-to-set-up-a-WDL-on-Github-Dockstore). Continue following this guide to synchronize your code to Dockstore and choose how to deploy it from there. + + * Make an account on [Dockstore](https://dockstore.org/) and link your account to your Github account. This will allow you to find your WARP fork branch on Dockstore. Connect your Warp fork to Dockstore. + + ![forking05](../images/forking05.png) + + * Register your workflow to Dockstore: From the workflows tab in Dockstore, select “Register a Workflow”. This will bring up a panel. Select “Register using GitHub Apps”, then “Next”. + + ![forking06](../images/forking06.png) + + * Select “Manage Dockstore installations on GitHub”. This will take you to GitHub with a view of your organizations. + + ![forking07](../images/forking07.png) + + * Select the organization with your fork. + + ![forking08](../images/forking08.png) + + * This will open a new view. You can choose to install Dockstore for all repositories or select just your fork. Select “Install”. + + ![forking09](../images/forking09.png) + + * Find your workflow in Dockstore: In the workflows tab in Dockstore, you will see your organization. Expand it and scroll down to find your workflow of interest. + + ![forking10](../images/forking10.png) + ![forking11](../images/forking11.png) + + * NOTE: you may need to push another commit to your branch to get this to show up. + * NOTE: you will need a .dockstore.yml file in the root of your branch in the forked repository. Warp includes this file which will be included in your fork. + * NOTE: If for some reason your workflow of interest is not in the .dockstore.yml file on the commit you checked out you will need to add it. + * Publish your workflow in Dockstore: On the page for your workflow, select the “Versions” tab. Find and select the version for your branch (there may be many versions). Click the “Actions” dropdown and select “Set as Default Version” (it will not be greyed out if it has not already been set as the default version). + + ![forking12](../images/forking12.png) + + * Back at the top of the page, click “Publish”. This will change the “Publish” button to an “Unpublish” button and add a link to “View public page”. Click “View public page”. + + ![forking13](../images/forking13.png) + + * Your new workflow is now published to Dockstore! GA4GH Dockstore provides documentation on deploying your WDL workflows into containers on Dockerhub, Quay, Amazon ECR, and running them on several choices for cloud services. + + ![forking14](../images/forking14.png) + + * See the [Best Practices for Building Pipelines](https://broadinstitute.github.io/warp/docs/About_WARP/BestPractices) page for information on how to execute WDL Workflows. Also see the [cromwell docs](https://cromwell.readthedocs.io/en/latest/backends/Backends/#backends) for some options for backend execution, and [this document describing other options for deploying workflows from Dockstore](https://docs.dockstore.org/en/stable/advanced-topics/tools-vs-workflows.html). + + + + + + + + + diff --git a/website/docs/Pipelines/SlideTags_Pipeline/README.md b/website/docs/Pipelines/SlideTags_Pipeline/README.md new file mode 100644 index 0000000000..cbd0beacaf --- /dev/null +++ b/website/docs/Pipelines/SlideTags_Pipeline/README.md @@ -0,0 +1,176 @@ +--- +sidebar_position: 1 +slug: /Pipelines/SlideTags_Pipeline/README +--- + +# Slide-tags Overview + +| Pipeline Version | Date Updated | Documentation Author | Questions or Feedback | +| :----: | :---: | :----: | :--------------: | +| v1.0.0 | May, 2025 | WARP Pipelines | Please [file an issue in WARP](https://github.com/broadinstitute/warp/issues) | + +![Slide-tags_diagram](./Slide-tags.png) + +## Introduction to the Slide-tags Pipeline + +The **Slide-tags Pipeline** is an open-source, cloud-optimized workflow for processing spatial transcriptomics data. It supports data derived from spatially barcoded sequencing technologies, including Slide-tags-based single-molecule profiling. The pipeline processes raw sequencing data into spatially resolved gene expression matrices, ensuring accurate alignment, spatial positioning, and quantification. + +This pipeline integrates multiple processing steps, including barcode extraction, spatial alignment, transcript counting, and output generation in formats compatible with community tools. The pipeline calls three subworkflows: the Optimus workflow for gene expression data, the SpatialCount workflow for spatial barcode processing, and the Positioning workflow for integrating both data types. + +The Optimus workflow (GEX) corrects cell barcodes and Unique Molecular Identifiers (UMIs), aligns reads to the genome, calculates per-barcode and per-gene quality metrics, and produces a cell-by-gene count matrix. + +The SpatialCount workflow processes spatial barcoding data from FASTQ files to generate spatial barcode counts that represent transcript locations within the tissue. + +The Positioning workflow integrates the gene expression data with spatial information to generate coordinate files and visualizations, producing a Seurat object for downstream spatial analysis. + + +## Quickstart Table +| Pipeline Features | Description | Source | +|--- | --- | --- | +| Assay type | Spatial transcriptomics using Slide-tags | [Macosko Lab](https://macoskolab.com/) | +| Overall workflow | Barcode extraction, spatial positioning, transcript quantification | Original code available from [GitHub](https://github.com/MacoskoLab/Macosko-Pipelines/tree/main/slide-tags); WDL workflow available in WARP. | +| Workflow language | WDL | [openWDL](https://github.com/openwdl/wdl) | +| Sub-workflows | Optimus (gene expression), SpatialCount (spatial barcoding), Positioning (integration) | Imported from separate WDL scripts | +| Genomic Reference Sequence | STAR reference genome provided as tar file | Referenced as input parameter | +| Gene annotation reference | GTF file containing gene annotations | Referenced as input parameter | +| Aligners | STARsolo | [STAR aligner](https://github.com/alexdobin/STAR) | +| Data input file format | File format in which sequencing data is provided | [FASTQ](https://academic.oup.com/nar/article/38/6/1767/3112533) and [CSV](https://www.loc.gov/preservation/digital/formats/fdd/fdd000323.shtml)| +| Data output file format | Output formats for downstream analysis | [HDF5](https://www.hdfgroup.org/), [Seurat](https://satijalab.org/seurat/) and [CSV](https://www.loc.gov/preservation/digital/formats/fdd/fdd000323.shtml)| + + +## Set-up + +### Installation + +To download the latest Slide-tags release, see the release tags prefixed with "Slide-tags" on the WARP [releases page](https://github.com/broadinstitute/warp/releases). All Slide-tags pipeline releases are documented in the [Slide-tags changelog](https://github.com/broadinstitute/warp/blob/master/pipelines/skylab/slidetags/SlideTags.changelog.md). + +The pipeline can be deployed using [Cromwell](https://cromwell.readthedocs.io/en/stable/), a GA4GH-compliant workflow manager. Additionally, it can be run in cloud-based analysis platforms such as [Terra](https://app.terra.bio). + +### Inputs + +The pipeline requires JSON-formatted configuration files detailing input parameters. Required inputs include: + +- **Raw paired-end GEX FASTQ files** containing sequencing GEX reads +- **Raw paired-end Spatial FASTQ files** containing spatial reads +- **Pucks files** contains spatial coordinates of bead centroids + +***General input variables used by both the Optimus and spatial/positioning components of the pipeline.*** + +| Input Variables | Description | Format | +|-------------------------|--------------------------------------------------|------------------| +| input_id | Unique input identifier | String | +| docker | Docker image used for the workflow | String | + +***Input variables for the spatial and positioning components of the Slide-Tags pipeline can be found below.*** + +| Input Variables | Description | Format | +|-------------------------|--------------------------------------------------|------------------| +| spatial_fastq | Array of paths to spatial FASTQ files. Requires at least one complete R1 and R2 pair. Each filename must include _R1_ or _R2_ to distinguish read pairs. The full directory is scanned, matching R1 and R2 files; an error is raised if any pair is incomplete | Array[String] | +| pucks | Array of paths to puck files | Array[String] | + +***Optimus input variables can be found below.*** + +| Input Variables | Description | Format | +|-------------------------|--------------------------------------------------|------------------| +| gex_r1_fastq | Array of FASTQ files for R1 reads | Array[File] | +| gex_r2_fastq | Array of FASTQ files for R2 reads | Array[File] | +| gex_i1_fastq | Optional FASTQ files for I1 index reads | Array[File]? | +| tar_star_reference | Reference genome in a TAR format for STAR align | File | +| annotations_gtf | Gene annotation file in GTF format | File | +| gex_whitelist | Whitelist file for cell barcodes | File | +| cloud_provider | Cloud provider for computing resources | String | +| expected_cells | Expected number of cells in the dataset | Int | +| counting_mode | Counting mode (e.g., snRNA) | String | +| tenx_chemistry_version | Version of 10X chemistry used | Int | +| emptydrops_lower | Lower threshold for EmptyDrops filtering | Int | +| force_no_check | Flag to disable sanity checks | Boolean | +| ignore_r1_read_length | Ignore length check for R1 reads | Boolean | +| star_strand_mode | Strand mode setting for STAR alignment | String | +| count_exons | Flag to enable exon counting | Boolean | +| soloMultiMappers | Optional setting for handling multi-mapped reads | String? | +| gex_nhash_id | Optional NHash identifier for gene expression | String? | +| mt_genes | Optional file listing mitochondrial genes | File? | + +Example input configurations can be found in the `test_inputs` folder of the GitHub repository. + +## Slide-tags Pipeline Tasks and Tools + +The workflow is composed of several key steps, implemented in separate WDL tasks: + +| Task | Tool | Description | +| --- | --- | --- | +| [Optimus](https://github.com/broadinstitute/warp/blob/master/pipelines/skylab/optimus/Optimus.wdl) | STARsolo | Gene quantification subworkflow that aligns reads to a reference genome and produces a count matrix. Read more in the [Optimus Overview](../Optimus_Pipeline/README.md). | +| spatial_count | [Custom Julia script](https://raw.githubusercontent.com/MacoskoLab/Macosko-Pipelines/d89176cf21e072fe8b5aad3a1454ad194fca7c9a/slide-tags/spatial-count.jl) developed by the Macosko lab | Extracts spatial barcodes, performs barcode sequencing error correction, maps reads to spatial barcodes and stores unique (cell, UMI, barcode) triplets in a count matrix, and calculates quality control metrics. Produces an h5 output. | +| positioning | Custom R scripts for developed by the Macosko lab; includes [positioning.R](https://raw.githubusercontent.com/MacoskoLab/Macosko-Pipelines/d89176cf21e072fe8b5aad3a1454ad194fca7c9a/slide-tags/positioning.R), [helpers.R](https://raw.githubusercontent.com/MacoskoLab/Macosko-Pipelines/d89176cf21e072fe8b5aad3a1454ad194fca7c9a/slide-tags/helpers.R), and [run-positioning.R](https://raw.githubusercontent.com/MacoskoLab/Macosko-Pipelines/d89176cf21e072fe8b5aad3a1454ad194fca7c9a/slide-tags/run-positioning.R) | Takes in the rna_paths (path to the filtered cell by gene count matrix, UMI counts, and the intronic metrics) to extract cell barcodes, calculates log-transformed UMI counts, and determines mitochondrial gene percentages. Performs data normalization, PCA, clustering, and UMAP embedding for visualization and produces quality metrics and graphs. Assigns cell barcodes to spatial barcode coordinates. | + +Each of these tasks utilizes scripts from the [Macosko Lab Pipelines](https://github.com/MacoskoLab/Macosko-Pipelines/tree/main/slide-tags) repository, modified for streamlined output handling. Dockers for running these scripts are maintained in the warp-tools repository under [slide-tags](https://github.com/broadinstitute/warp-tools/tree/develop/3rd-party-tools/slide-tags). + +## Outputs + +### Optimus outputs + +| Output Variable | File Name | Description | Format | +| ---- | --- | ------ | -- | +| optimus_genomic_reference_version | `.txt` | File containing the Genome build, source and GTF annotation version. | TXT | +| optimus_bam | `.bam` | BAM file containing aligned reads from Optimus workflow. | BAM | +| optimus_matrix | `_gex_sparse_counts.npz` | NPZ file containing raw gene by cell counts. | NPZ | +| optimus_matrix_row_index | `_gex_sparse_counts_row_index.npy` | NPY file containing the row indices. | NPY | +| optimus_matrix_col_index | `_gex_sparse_counts_col_index.npy` | NPY file containing the column indices. | NPY | +| optimus_cell_metrics | `_gex.cell_metrics.csv.gz` | CSV file containing the per-cell (barcode) metrics. | Compressed CSV | +| optimus_gene_metrics | `.gene_metrics.csv.gz` | CSV file containing the per-gene metrics. | Compressed CSV | +| optimus_cell_calls | `.emptyDrops.csv` | TSV file containing the EmptyDrops results when the Optimus workflow is run in sc_rna mode. | CSV | +| optimus_h5ad_output_file | `.h5ad` | h5ad (Anndata) file containing the raw cell-by-gene count matrix, gene metrics, cell metrics, and global attributes. See the [Optimus Count Matrix Overview](../Optimus_Pipeline/Loom_schema.md) for more details. | H5AD | +| optimus_multimappers_EM_matrix | `UniqueAndMult-EM.mtx` | Optional output produced when `soloMultiMappers` is "EM"; see STARsolo [documentation](https://github.com/alexdobin/STAR/blob/master/docs/STARsolo.md#multi-gene-reads) for more information.| MTX | +| optimus_multimappers_Uniform_matrix | `UniqueAndMult-Uniform.mtx` | Optional output produced when `soloMultiMappers` is "Uniform"; see STARsolo [documentation](https://github.com/alexdobin/STAR/blob/master/docs/STARsolo.md#multi-gene-reads) for more information.| MTX | +| optimus_multimappers_Rescue_matrix | `UniqueAndMult-Rescue.mtx` | Optional output produced when `soloMultiMappers` is "Rescue"; see STARsolo [documentation](https://github.com/alexdobin/STAR/blob/master/docs/STARsolo.md#multi-gene-reads) for more information. | MTX | +| optimus_multimappers_PropUnique_matrix | `UniqueAndMult-PropUnique.mtx` | Optional output produced when `soloMultiMappers` is "PropUnique"; see STARsolo [documentation](https://github.com/alexdobin/STAR/blob/master/docs/STARsolo.md#multi-gene-reads) for more information.| +| optimus_aligner_metrics | `.star_metrics.tar` | Text file containing per barcode metrics (`CellReads.stats`) produced by the GEX pipeline STARsolo aligner. | TAR | +| optimus_library_metrics | `_gex__library_metrics.csv` | Optional CSV file containing all library-level metrics calculated with STARsolo for gene expression data. | CSV | +| optimus_mtx_files | `_gex.mtx_files.tar` | TAR file with STARsolo matrix market files (barcodes.tsv, features.tsv, and matrix.mtx) | TAR | +| cb_cell_barcodes_csv | `` | Optional output produced when `run_cellbender` is "true"; see CellBender [documentation](https://cellbender.readthedocs.io/en/latest/usage/index.html) and [GitHub repository](https://github.com/broadinstitute/CellBender/tree/master) for more information.| +| cb_checkpoint_file | `` | Optional output produced when `run_cellbender` is "true"; see CellBender [documentation](https://cellbender.readthedocs.io/en/latest/usage/index.html) and [GitHub repository](https://github.com/broadinstitute/CellBender/tree/master) for more information. | +| cb_h5_array | `` | Optional output produced when `run_cellbender` is "true"; see CellBender [documentation](https://cellbender.readthedocs.io/en/latest/usage/index.html) and [GitHub repository](https://github.com/broadinstitute/CellBender/tree/master) for more information. | +| cb_html_report_array | `` | Optional output produced when `run_cellbender` is "true"; see CellBender [documentation](https://cellbender.readthedocs.io/en/latest/usage/index.html) and [GitHub repository](https://github.com/broadinstitute/CellBender/tree/master) for more information. | +| cb_log | `` | Optional output produced when `run_cellbender` is "true"; see CellBender [documentation](https://cellbender.readthedocs.io/en/latest/usage/index.html) and [GitHub repository](https://github.com/broadinstitute/CellBender/tree/master) for more information. | +| cb_metrics_csv_array | `` | Optional output produced when `run_cellbender` is "true"; see CellBender [documentation](https://cellbender.readthedocs.io/en/latest/usage/index.html) and [GitHub repository](https://github.com/broadinstitute/CellBender/tree/master) for more information. | +| cb_output_directory | `` | Optional output produced when `run_cellbender` is "true"; see CellBender [documentation](https://cellbender.readthedocs.io/en/latest/usage/index.html) and [GitHub repository](https://github.com/broadinstitute/CellBender/tree/master) for more information. | +| cb_summary_pdf | `` | Optional output produced when `run_cellbender` is "true"; see CellBender [documentation](https://cellbender.readthedocs.io/en/latest/usage/index.html) and [GitHub repository](https://github.com/broadinstitute/CellBender/tree/master) for more information. | + + +### Output variables for the spatial and positioning components of the Slide-Tags pipeline + +For more details regarding the output variables, please refer to the [README](https://github.com/MacoskoLab/Macosko-Pipelines/tree/main/slide-tags) in the Slide-Tags directoty in the Macosko Lab repository. + +| Output Variable | File Name | Description | Format | +| ------ | --- | ------ | ------ | +| spatial_output_h5 | `_SBcounts.h5` | h5 file containing cell by bead matrix and spatial barcode information. | H5 | +| spatial_output_log | `_spatial-count.log` | Standard output of the spatial barcodes task. | TXT | +| positioning_seurat_qs | `_seurat.qs` | Seurat object with processed spatial transcriptomics data. | SEURAT | +| positioning_coords_csv | `_coords.csv` | Spatial coordinates for called cells. | CSV | +| positioning_coords2_csv | `_coords2.csv` | Alternate or refined spatial coordinates. | CSV | +| positioning_summary_pdf | `_summary.pdf` | QC summary report with plots and metrics. | PDF | +| positioning_intermediates | `_intermediates.tar.gz` | Contains spatial barcodes matrix, cell barcode whitelist, and spatial metadata. | TAR | +| positioning_log | `_positioning.log` | Standard output of the positioning task. | TXT | + +## Versioning + +All releases of the pipeline are documented in the repository’s changelog. + +## Citing the Slide-tags Pipeline + +If you use the Slide-tags Pipeline in your research, please cite the original sources: + +- **Macosko Lab Pipelines:** https://github.com/MacoskoLab/Macosko-Pipelines/tree/main/slide-tags + +Please also consider citing our preprint: + +Degatano, K.; Awdeh, A.; Dingman, W.; Grant, G.; Khajouei, F.; Kiernan, E.; Konwar, K.; Mathews, K.; Palis, K.; Petrillo, N.; Van der Auwera, G.; Wang, C.; Way, J.; Pipelines, W. WDL Analysis Research Pipelines: Cloud-Optimized Workflows for Biological Data Processing and Reproducible Analysis. Preprints 2024, 2024012131. https://doi.org/10.20944/preprints202401.2131.v1 + +## Acknowledgements + +We are immensely grateful Matthew Shabet and the Macosko Lab for development of these analsyes, for their generous time making these scripts FAIR, and for the many hours working with the WARP team to incoporate the scripts into WDL. + +## Feedback + +Please help us make our tools better by [filing an issue in WARP](https://github.com/broadinstitute/warp/issues); we welcome pipeline-related suggestions or questions. + diff --git a/website/docs/Pipelines/SlideTags_Pipeline/Slide-tags.png b/website/docs/Pipelines/SlideTags_Pipeline/Slide-tags.png new file mode 100644 index 0000000000..78a1a28379 Binary files /dev/null and b/website/docs/Pipelines/SlideTags_Pipeline/Slide-tags.png differ diff --git a/website/docs/Pipelines/SlideTags_Pipeline/Slide-tags_old.png b/website/docs/Pipelines/SlideTags_Pipeline/Slide-tags_old.png new file mode 100644 index 0000000000..3bae7dd770 Binary files /dev/null and b/website/docs/Pipelines/SlideTags_Pipeline/Slide-tags_old.png differ diff --git a/website/docs/Pipelines/SlideTags_Pipeline/_category_.json b/website/docs/Pipelines/SlideTags_Pipeline/_category_.json new file mode 100644 index 0000000000..31a12b6138 --- /dev/null +++ b/website/docs/Pipelines/SlideTags_Pipeline/_category_.json @@ -0,0 +1,4 @@ +{ + "label": "Slide-tags", + "position": 15 +} \ No newline at end of file diff --git a/website/docs/get-started.md b/website/docs/get-started.md index 3b3b56f378..7c60720a45 100755 --- a/website/docs/get-started.md +++ b/website/docs/get-started.md @@ -4,10 +4,15 @@ sidebar_position: 1 # Welcome to WARP -WARP (WDL Analysis Research Pipelines) repository is a collection of cloud-optimized pipelines for processing biological data from the Broad Institute Data Sciences Platform and collaborators. +The Warp Analysis Research Pipelines repository is a collection of cloud-optimized pipelines for processing biological data from the Broad Institute Data Sciences Platform and collaborators. The contents of this repository are open source and released under the [BSD 3-Clause license](https://github.com/broadinstitute/warp/blob/master/LICENSE). +## WARP Philosophy + +Our mission is to develop production-grade, cloud-optimized pipelines that serve the needs of large-scale research consortia and the broader scientific community. Since many of these consortia have adopted Terra as their primary computing environment, most WARP pipelines are written in WDL and tuned for optimal performance on Terra. As community needs evolve, WARP will adapt accordingly to support those environments. + +We do not position WDL as inherently superior to workflow languages like Nextflow or Snakemake. Rather, we focus on addressing the specific needs of scientific consortia and research communities that prioritize reproducibility, scalability, and seamless integration with the Terra platform. ## WARP Overview @@ -33,7 +38,7 @@ Try our pipelines in [Terra](https://app.terra.bio/#workspaces?tagsFilter%5B0%5D All versioned and released pipelines are in one of the three [pipelines](https://github.com/broadinstitute/warp/tree/master/pipelines) subdirectories: broad (pipelines for the Broad Institute’s Genomics Platform), cemba (pipelines for the BRAIN Initiative) or skylab (pipelines for the BRAIN Initiative and Human Cell Atlas Project). -Each pipeline directory hosts a main workflow WDL that includes a pipeline version number and a corresponding changelog file. +Each pipeline directory hosts a main workflow (WDL) that includes a pipeline version number and a corresponding changelog file. Workflows may call additional WDLs, referred to as tasks, that are located in the [tasks](https://github.com/broadinstitute/warp/tree/master/tasks) directory. diff --git a/website/docs/images/forking01.png b/website/docs/images/forking01.png new file mode 100644 index 0000000000..3bea044ed6 Binary files /dev/null and b/website/docs/images/forking01.png differ diff --git a/website/docs/images/forking02.png b/website/docs/images/forking02.png new file mode 100644 index 0000000000..cc92dc9fef Binary files /dev/null and b/website/docs/images/forking02.png differ diff --git a/website/docs/images/forking03.png b/website/docs/images/forking03.png new file mode 100644 index 0000000000..675bfa5652 Binary files /dev/null and b/website/docs/images/forking03.png differ diff --git a/website/docs/images/forking04.png b/website/docs/images/forking04.png new file mode 100644 index 0000000000..93621a23fc Binary files /dev/null and b/website/docs/images/forking04.png differ diff --git a/website/docs/images/forking05.png b/website/docs/images/forking05.png new file mode 100644 index 0000000000..6bb5a2d14e Binary files /dev/null and b/website/docs/images/forking05.png differ diff --git a/website/docs/images/forking06.png b/website/docs/images/forking06.png new file mode 100644 index 0000000000..ce5285ca1c Binary files /dev/null and b/website/docs/images/forking06.png differ diff --git a/website/docs/images/forking07.png b/website/docs/images/forking07.png new file mode 100644 index 0000000000..d5927a22ab Binary files /dev/null and b/website/docs/images/forking07.png differ diff --git a/website/docs/images/forking08.png b/website/docs/images/forking08.png new file mode 100644 index 0000000000..7d2f9ec143 Binary files /dev/null and b/website/docs/images/forking08.png differ diff --git a/website/docs/images/forking09.png b/website/docs/images/forking09.png new file mode 100644 index 0000000000..c9004917bb Binary files /dev/null and b/website/docs/images/forking09.png differ diff --git a/website/docs/images/forking10.png b/website/docs/images/forking10.png new file mode 100644 index 0000000000..557ebeb353 Binary files /dev/null and b/website/docs/images/forking10.png differ diff --git a/website/docs/images/forking11.png b/website/docs/images/forking11.png new file mode 100644 index 0000000000..cb27cc1ad4 Binary files /dev/null and b/website/docs/images/forking11.png differ diff --git a/website/docs/images/forking12.png b/website/docs/images/forking12.png new file mode 100644 index 0000000000..ec08d89705 Binary files /dev/null and b/website/docs/images/forking12.png differ diff --git a/website/docs/images/forking13.png b/website/docs/images/forking13.png new file mode 100644 index 0000000000..86f7dec760 Binary files /dev/null and b/website/docs/images/forking13.png differ diff --git a/website/docs/images/forking14.png b/website/docs/images/forking14.png new file mode 100644 index 0000000000..a00280a66a Binary files /dev/null and b/website/docs/images/forking14.png differ diff --git a/website/yarn.lock b/website/yarn.lock index 9f4409df3f..2760965f66 100644 --- a/website/yarn.lock +++ b/website/yarn.lock @@ -8073,16 +8073,6 @@ regenerate@^1.4.0, regenerate@^1.4.2: resolved "https://registry.yarnpkg.com/regenerate/-/regenerate-1.4.2.tgz#b9346d8827e8f5a32f7ba29637d398b69014848a" integrity sha512-zrceR/XhGYU/d/opr2EKO7aRHUeiBI8qjtfHqADTwZd6Szfy16la6kqD0MIUs5z5hx6AaKa+PixpPrR289+I0A== -regenerator-runtime@^0.13.11: - version "0.13.11" - resolved "https://registry.yarnpkg.com/regenerator-runtime/-/regenerator-runtime-0.13.11.tgz#f6dca3e7ceec20590d07ada785636a90cdca17f9" - integrity sha512-kY1AZVr2Ra+t+piVaJ4gxaFaReZVH40AKNo7UCX6W+dEwBo/2oZJzqfuN1qLq1oL45o56cPaTXELwrTh8Fpggg== - -regenerator-runtime@^0.14.0: - version "0.14.1" - resolved "https://registry.yarnpkg.com/regenerator-runtime/-/regenerator-runtime-0.14.1.tgz#356ade10263f685dda125100cd862c1db895327f" - integrity sha512-dYnhHh0nJoMfnkZs6GmmhFknAGRrLznOu5nc9ML+EJxGvrx6H7teuevqVqCuPcPK//3eDrrjQhehXVx9cnkGdw== - regenerator-runtime@^0.14.0: version "0.14.1" resolved "https://registry.yarnpkg.com/regenerator-runtime/-/regenerator-runtime-0.14.1.tgz#356ade10263f685dda125100cd862c1db895327f"