phylogenetic: Support nextstrain run

Mostly workflow path updates to support `nextstrain run`. This should allow 
the default phylogenetic build to run with 
`nextstrain run mpox phylogenetic <analysis-dir>`. The following commit will 
add support for the other builds.

Author: joverlee521

phylogenetic/Snakefile

@@ -12,7 +12,7 @@ if version.parse(augur_version) < version.parse(min_augur_version):
 
 if not config:
 
-    configfile: "defaults/hmpxv1/config.yaml"
+    configfile: os.path.join(workflow.basedir, "defaults/hmpxv1/config.yaml")
 
 
 build_dir = "results"
@@ -49,7 +49,7 @@ include: "rules/export.smk"
 if "custom_rules" in config:
     for rule_file in config["custom_rules"]:
 
-        include: rule_file
+        include: os.path.join(os.getcwd(), rule_file)
 
 
 rule clean:

phylogenetic/defaults/clade-i/config.yaml

@@ -1,15 +1,15 @@
-reference: "defaults/clade-i/reference.fasta"
-genome_annotation: "defaults/clade-i/genome_annotation.gff3"
-genbank_reference: "defaults/clade-i/reference.gb"
-include: "defaults/clade-i/include.txt"
-exclude: "defaults/exclude.txt"
-clades: "defaults/clades.tsv"
-lat_longs: "defaults/lat_longs.tsv"
-color_ordering: "defaults/color_ordering.tsv"
-color_scheme: "defaults/color_schemes.tsv"
-auspice_config: "defaults/clade-i/auspice_config.json"
-description: "defaults/description.md"
-tree_mask: "defaults/clade-i/tree_mask.tsv"
+reference: "clade-i/reference.fasta"
+genome_annotation: "clade-i/genome_annotation.gff3"
+genbank_reference: "clade-i/reference.gb"
+include: "clade-i/include.txt"
+exclude: "exclude.txt"
+clades: "clades.tsv"
+lat_longs: "lat_longs.tsv"
+color_ordering: "color_ordering.tsv"
+color_scheme: "color_schemes.tsv"
+auspice_config: "clade-i/auspice_config.json"
+description: "description.md"
+tree_mask: "clade-i/tree_mask.tsv"
 
 # Use `accession` as the ID column since `strain` currently contains duplicates¹.
 # ¹ https://github.com/nextstrain/mpox/issues/33
@@ -59,7 +59,7 @@ recency: true
 mask:
   from_beginning: 800
   from_end: 6422
-  maskfile: "defaults/clade-i/mask.bed"
+  maskfile: "clade-i/mask.bed"
 
 colors:
   ignore_categories:

phylogenetic/defaults/hmpxv1/config.yaml

@@ -1,15 +1,15 @@
-reference: "defaults/reference.fasta"
-genome_annotation: "defaults/genome_annotation.gff3"
-genbank_reference: "defaults/reference.gb"
-include: "defaults/hmpxv1/include.txt"
-exclude: "defaults/exclude.txt"
-clades: "defaults/clades.tsv"
-lat_longs: "defaults/lat_longs.tsv"
-color_ordering: "defaults/color_ordering.tsv"
-color_scheme: "defaults/color_schemes.tsv"
-auspice_config: "defaults/hmpxv1/auspice_config.json"
-description: "defaults/description.md"
-tree_mask: "defaults/tree_mask.tsv"
+reference: "reference.fasta"
+genome_annotation: "genome_annotation.gff3"
+genbank_reference: "reference.gb"
+include: "hmpxv1/include.txt"
+exclude: "exclude.txt"
+clades: "clades.tsv"
+lat_longs: "lat_longs.tsv"
+color_ordering: "color_ordering.tsv"
+color_scheme: "color_schemes.tsv"
+auspice_config: "hmpxv1/auspice_config.json"
+description: "description.md"
+tree_mask: "tree_mask.tsv"
 
 # Use `accession` as the ID column since `strain` currently contains duplicates¹.
 # ¹ https://github.com/nextstrain/mpox/issues/33
@@ -101,4 +101,4 @@ recency: true
 mask:
   from_beginning: 800
   from_end: 6422
-  maskfile: "defaults/mask.bed"
+  maskfile: "mask.bed"

phylogenetic/defaults/hmpxv1_big/config.yaml

@@ -1,15 +1,15 @@
-reference: "defaults/reference.fasta"
-genome_annotation: "defaults/genome_annotation.gff3"
-genbank_reference: "defaults/reference.gb"
-include: "defaults/hmpxv1_big/include.txt"
-exclude: "defaults/exclude.txt"
-clades: "defaults/clades.tsv"
-lat_longs: "defaults/lat_longs.tsv"
-color_ordering: "defaults/color_ordering.tsv"
-color_scheme: "defaults/color_schemes.tsv"
-auspice_config: "defaults/hmpxv1_big/auspice_config.json"
-description: "defaults/description.md"
-tree_mask: "defaults/tree_mask.tsv"
+reference: "reference.fasta"
+genome_annotation: "genome_annotation.gff3"
+genbank_reference: "reference.gb"
+include: "hmpxv1_big/include.txt"
+exclude: "exclude.txt"
+clades: "clades.tsv"
+lat_longs: "lat_longs.tsv"
+color_ordering: "color_ordering.tsv"
+color_scheme: "color_schemes.tsv"
+auspice_config: "hmpxv1_big/auspice_config.json"
+description: "description.md"
+tree_mask: "tree_mask.tsv"
 
 # Use `accession` as the ID column since `strain` currently contains duplicates¹.
 # ¹ https://github.com/nextstrain/mpox/issues/33
@@ -64,4 +64,4 @@ recency: true
 mask:
   from_beginning: 800
   from_end: 6422
-  maskfile: "defaults/mask.bed"
+  maskfile: "mask.bed"

phylogenetic/defaults/mpxv/config.yaml

@@ -1,15 +1,15 @@
-auspice_config: "defaults/mpxv/auspice_config.json"
-include: "defaults/mpxv/include.txt"
-exclude: "defaults/exclude.txt"
-reference: "defaults/reference.fasta"
-genome_annotation: "defaults/genome_annotation.gff3"
-genbank_reference: "defaults/reference.gb"
-lat_longs: "defaults/lat_longs.tsv"
-color_ordering: "defaults/color_ordering.tsv"
-color_scheme: "defaults/color_schemes.tsv"
-description: "defaults/description.md"
-clades: "defaults/clades.tsv"
-tree_mask: "defaults/tree_mask.tsv"
+auspice_config: "mpxv/auspice_config.json"
+include: "mpxv/include.txt"
+exclude: "exclude.txt"
+reference: "reference.fasta"
+genome_annotation: "genome_annotation.gff3"
+genbank_reference: "reference.gb"
+lat_longs: "lat_longs.tsv"
+color_ordering: "color_ordering.tsv"
+color_scheme: "color_schemes.tsv"
+description: "description.md"
+clades: "clades.tsv"
+tree_mask: "tree_mask.tsv"
 
 # Use `accession` as the ID column since `strain` currently contains duplicates¹.
 # ¹ https://github.com/nextstrain/mpox/issues/33
@@ -94,4 +94,4 @@ recency: true
 mask:
   from_beginning: 1350
   from_end: 6422
-  maskfile: "defaults/mask_overview.bed"
+  maskfile: "mask_overview.bed"

phylogenetic/rules/annotate_phylogeny.smk

@@ -60,7 +60,7 @@ rule translate:
     input:
         tree=build_dir + "/{build_name}/tree.nwk",
         node_data=build_dir + "/{build_name}/nt_muts.json",
-        genome_annotation=config["genome_annotation"],
+        genome_annotation=resolve_config_path(config["genome_annotation"]),
     output:
         node_data=build_dir + "/{build_name}/aa_muts.json",
     log:
@@ -120,7 +120,7 @@ rule clades:
         tree=build_dir + "/{build_name}/tree.nwk",
         aa_muts=build_dir + "/{build_name}/aa_muts.json",
         nuc_muts=build_dir + "/{build_name}/nt_muts.json",
-        clades=config["clades"],
+        clades=resolve_config_path(config["clades"]),
     output:
         node_data=build_dir + "/{build_name}/clades_raw.json",
     log:
@@ -154,7 +154,7 @@ rule rename_clades:
         r"""
         exec &> >(tee {log:q})
 
-        python scripts/clades_renaming.py \
+        python {workflow.basedir}/scripts/clades_renaming.py \
             --input-node-data {input:q} \
             --output-node-data {output.node_data:q}
         """
@@ -180,7 +180,7 @@ rule assign_clades_via_metadata:
         r"""
         exec &> >(tee {log:q})
 
-        python scripts/assign-clades-via-metadata.py \
+        python {workflow.basedir}/scripts/assign-clades-via-metadata.py \
             --metadata {input.metadata:q} \
             --tree {input.tree:q} \
             --output-node-data {output.node_data:q}
@@ -201,7 +201,7 @@ rule mutation_context:
         r"""
         exec &> >(tee {log:q})
 
-        python3 scripts/mutation_context.py \
+        python3 {workflow.basedir}/scripts/mutation_context.py \
             --tree {input.tree:q} \
             --mutations {input.node_data:q} \
             --output {output.node_data:q}
@@ -226,7 +226,7 @@ rule recency:
         r"""
         exec &> >(tee {log:q})
 
-        python3 scripts/construct-recency-from-submission-date.py \
+        python3 {workflow.basedir}/scripts/construct-recency-from-submission-date.py \
             --metadata {input.metadata:q} \
             --metadata-id-columns {params.strain_id:q} \
             --output {output:q} 2>&1

phylogenetic/rules/config.smk

@@ -7,6 +7,9 @@ from textwrap import dedent, indent
 from typing import Union
 
 
+include: "../../shared/vendored/snakemake/config.smk"
+
+
 def as_list(config_param: Union[list,str]) -> list:
     if isinstance(config_param, list):
         return config_param

phylogenetic/rules/construct_phylogeny.smk

@@ -21,7 +21,7 @@ rule tree:
     """
     input:
         alignment=build_dir + "/{build_name}/masked.fasta",
-        tree_mask=config["tree_mask"],
+        tree_mask=resolve_config_path(config["tree_mask"]),
     output:
         tree=build_dir + "/{build_name}/tree_raw.nwk",
     threads: workflow.cores
@@ -64,7 +64,7 @@ rule fix_tree:
         r"""
         exec &> >(tee {log:q})
 
-        python3 scripts/fix_tree.py \
+        python3 {workflow.basedir}/scripts/fix_tree.py \
             --alignment {input.alignment:q} \
             --input-tree {input.tree:q} \
             {params.root} \

phylogenetic/rules/export.smk

@@ -43,16 +43,16 @@ rule remove_time:
         r"""
         exec &> >(tee {log:q})
 
-        python3 scripts/remove_timeinfo.py \
+        python3 {workflow.basedir}/scripts/remove_timeinfo.py \
             --input-node-data {input:q} \
             --output-node-data {output:q}
         """
 
 
 rule colors:
     input:
-        ordering=config["color_ordering"],
-        color_schemes=config["color_scheme"],
+        ordering=resolve_config_path(config["color_ordering"]),
+        color_schemes=resolve_config_path(config["color_scheme"]),
         metadata=build_dir + "/{build_name}/metadata.tsv",
     output:
         colors=build_dir + "/{build_name}/colors.tsv",
@@ -66,7 +66,7 @@ rule colors:
         r"""
         exec &> >(tee {log:q})
 
-        python3 scripts/assign-colors.py \
+        python3 {workflow.basedir}/scripts/assign-colors.py \
             --ordering {input.ordering:q} \
             --color-schemes {input.color_schemes:q} \
             --output {output.colors:q} \
@@ -102,9 +102,9 @@ rule export:
             else []
         ),
         colors=build_dir + "/{build_name}/colors.tsv",
-        lat_longs=config["lat_longs"],
-        description=config["description"],
-        auspice_config=config["auspice_config"],
+        lat_longs=resolve_config_path(config["lat_longs"]),
+        description=resolve_config_path(config["description"]),
+        auspice_config=resolve_config_path(config["auspice_config"]),
     output:
         auspice_json=build_dir + "/{build_name}/tree.json",
         root_sequence=build_dir + "/{build_name}/tree_root-sequence.json",

phylogenetic/rules/prepare_sequences.smk

@@ -69,7 +69,7 @@ rule filter:
     input:
         sequences="data/sequences.fasta",
         metadata="data/metadata.tsv",
-        exclude=config["exclude"],
+        exclude=resolve_config_path(config["exclude"]),
     output:
         sequences=build_dir + "/{build_name}/good_sequences.fasta",
         metadata=build_dir + "/{build_name}/good_metadata.tsv",
@@ -128,7 +128,7 @@ rule add_private_data:
         r"""
         exec &> >(tee {log:q})
 
-        python3 scripts/combine_data_sources.py \
+        python3 {workflow.basedir}/scripts/combine_data_sources.py \
             --metadata nextstrain={input.metadata:q} private={input.private_metadata:q} \
             --sequences {input.sequences:q} {input.private_sequences:q} \
             --output-metadata {output.metadata:q} \
@@ -182,7 +182,7 @@ rule combine_samples:
             if config.get("private_metadata", False)
             else build_dir + "/{build_name}/good_metadata.tsv"
         ),
-        include=config["include"],
+        include=resolve_config_path(config["include"]),
     output:
         sequences=build_dir + "/{build_name}/filtered.fasta",
         metadata=build_dir + "/{build_name}/metadata.tsv",
@@ -221,7 +221,7 @@ rule reverse_reverse_complements:
         r"""
         exec &> >(tee {log:q})
 
-        python3 scripts/reverse_reversed_sequences.py \
+        python3 {workflow.basedir}/scripts/reverse_reversed_sequences.py \
             --metadata {input.metadata:q} \
             --sequences {input.sequences:q} \
             --output {output:q}
@@ -234,8 +234,8 @@ rule align:
     """
     input:
         sequences=build_dir + "/{build_name}/reversed.fasta",
-        reference=config["reference"],
-        genome_annotation=config["genome_annotation"],
+        reference=resolve_config_path(config["reference"]),
+        genome_annotation=resolve_config_path(config["genome_annotation"]),
     output:
         alignment=build_dir + "/{build_name}/aligned.fasta",
     params:
@@ -279,7 +279,7 @@ rule mask:
     """
     input:
         sequences=build_dir + "/{build_name}/aligned.fasta",
-        mask=config["mask"]["maskfile"],
+        mask=resolve_config_path(config["mask"]["maskfile"]),
     output:
         build_dir + "/{build_name}/masked.fasta",
     params: