commandline options changed

Author: ShujiaHuang

README.md

@@ -110,11 +110,11 @@ To review each of the parameters, you can type `basevar caller -h` in the Linux/
 $ /path/to/basevar caller -h
 
 About: Call variants and estimate allele frequency by BaseVar.
-Usage: basevar caller [options] <-R Fasta> <--output-vcf> [-L bam.list] in1.bam [in2.bam ...] ...
+Usage: basevar caller [options] <-f Fasta> <--output-vcf output_file> [-L bam.list] in1.bam [in2.bam ...] ...
 
 Required arguments:
-  -R, --reference FILE         Input reference fasta file.
-  --output-vcf FILE            Output VCF file.
+  -f, --reference FILE         Input reference fasta file.
+  -o, --output    FILE         Output VCF file.
 
 Optional options:
   -L, --align-file-list=FILE   BAM/CRAM files list, one file per row.
@@ -127,10 +127,10 @@ Optional options:
                                represents the number of input BAM files min(0.001000, 100/x). In most
                                cases, users need not be overly concerned about this parameter, as it
                                is generally handled automatically by the program.
-  -Q, --min-BQ INT             Skip bases with base quality < INT [5]
-  -q, --mapq=INT               Skip reads with mapping quality < INT [10]
-  -B, --batch-count=INT        INT simples per batchfile. [200]
-  -t, --thread=INT             Number of threads. [hardware-concurrency]
+  -Q, --min-BQ INT             Skip bases with base quality < INT [10]
+  -q, --mapq=INT               Skip reads with mapping quality < INT [5]
+  -B, --batch-count=INT        INT simples per batchfile. [500]
+  -t, --thread=INT             Number of threads. [14]
 
   --filename-has-samplename    If the name of bamfile is something like 'SampleID.xxxx.bam', set this
                                argrument could save a lot of time during get the sample id from BAMfile.
@@ -145,30 +145,30 @@ This command will provide detailed information about parameters of `basevar`.
 ### Call variants from several bamfiles
 
 ```bash
-basevar caller -R reference.fasta \
+basevar caller -f reference.fasta \
     -q 10 -Q 20 -B 500 -t 24 \
     --pop-group=sample_group.info \
     --regions=chr11:5246595-5248428,chr17:41197764-41276135 \
-    --output-vcf test.vcf.gz 00alzqq6jw.bam 09t3r9n2rg.bam 0fkpl1p55b.bam ...
+    --output test.vcf.gz 00alzqq6jw.bam 09t3r9n2rg.bam 0fkpl1p55b.bam ...
 ```
 
 The format of `sample_group.info` could be found [here](https://github.com/ShujiaHuang/BaseVar2/blob/main/tests/data/sample_group.info).
 
 ### Or call variants from bamlist
 
 ```bash
-basevar caller -R reference.fasta \
+basevar caller -f reference.fasta \
     -q 10 -Q 20 -B 500 -t 24 \
     -L bamfile.list \ 
     --regions=chr11:5246595-5248428,chr17:41197764-41276135 \
     --pop-group=sample_group.info \
-    --output-vcf test.vcf.gz 
+    --output test.vcf.gz 
 ```
 
 For stramlinened variant calling across the entire genome, you can use the pipeline generator [**create_pipeline.py**](https://github.com/ShujiaHuang/BaseVar2/blob/main/scripts/create_pipeline.py), which distributes the computational tasks based on the --delta parameter across a specific chromosome defined by the -c parameter.
 
 ```bash
-python create_pipeline.py -Q 20 -q 10 -R reference.fa --ref_fai reference_fa.fai -c chr20 --delta 5000000 -t 24 -L bamfile.list -o outdir > basevar.chr20.sh
+python create_pipeline.py -Q 20 -q 10 -f reference.fa --ref_fai reference_fa.fai -c chr20 --delta 5000000 -t 24 -L bamfile.list -o outdir > basevar.chr20.sh
 ```
 
 **BaseVar** is under active development. Obtain the newest version by pulling the newest version and compilling again.

scripts/create_pipeline.py

@@ -82,13 +82,13 @@ def creat_basetype_pipe():
             if opt.pop_group:
                 print(f'time {exe_prog} -t {opt.n_thread} -f {opt.reference} -L {opt.infilelist} '
                       f'-G {opt.pop_group} -r {reg} --min-af={opt.min_af} -q {opt.mapq} -Q {opt.min_bq} '
-                      f'--output-vcf {opt.outdir}/{outfile_prefix}.vcf.gz --smart-rerun '
+                      f'--output {opt.outdir}/{outfile_prefix}.vcf.gz --smart-rerun '
                       f'> {opt.outdir}/{outfile_prefix}.log && '
                       f'echo "** {outfile_prefix} done **"')
             else:    
                 print(f'time {exe_prog} -t {opt.n_thread} -f {opt.reference} -L {opt.infilelist} '
                       f'-r {reg} --min-af={opt.min_af} -q {opt.mapq} -Q {opt.min_bq} '
-                      f'--output-vcf {opt.outdir}/{outfile_prefix}.vcf.gz --smart-rerun '
+                      f'--output {opt.outdir}/{outfile_prefix}.vcf.gz --smart-rerun '
                       f'> {opt.outdir}/{outfile_prefix}.log && '
                       f'echo "** {outfile_prefix} done **"')
 

src/basetype_caller.cpp

@@ -11,11 +11,11 @@
 const std::string BaseTypeRunner::usage() const {
     static const std::string BASETYPE_CALLER_USAGE = 
         "About: Call variants and estimate allele frequency by BaseVar.\n" 
-        "Usage: basevar caller [options] <-R Fasta> <--output-vcf> [-L bam.list] in1.bam [in2.bam ...] ...\n\n" 
+        "Usage: basevar caller [options] <-f Fasta> <--output-vcf output_file> [-L bam.list] in1.bam [in2.bam ...] ...\n\n" 
 
         "Required arguments:\n" 
-        "  -R, --reference FILE         Input reference fasta file.\n"
-        "  -O, --output-vcf FILE        Output VCF file.\n\n"
+        "  -f, --reference FILE         Input reference fasta file.\n"
+        "  -o, --output    FILE         Output VCF file.\n\n"
 
         "Optional options:\n"
         "  -L, --align-file-list=FILE   BAM/CRAM files list, one file per row.\n"
@@ -54,8 +54,8 @@ BaseTypeRunner::BaseTypeRunner(int cmd_argc, char *cmd_argv[]) {
     static const struct option BASETYPE_CMDLINE_LOPTS[] = {
         // Optional arguments to long style command line parameters require 'equals sign' (=). 
         // https://stackoverflow.com/questions/1052746/getopt-does-not-parse-optional-arguments-to-parameters
-        {"reference",         required_argument, NULL, 'R'},
-        {"output-vcf",        required_argument, NULL, 'O'},
+        {"reference",         required_argument, NULL, 'f'},
+        {"output",            required_argument, NULL, 'o'},
         {"align-file-list",   optional_argument, NULL, 'L'},
 
         {"min-af",            optional_argument, NULL, 'm'},
@@ -84,12 +84,12 @@ BaseTypeRunner::BaseTypeRunner(int cmd_argc, char *cmd_argv[]) {
 
     char c;
     std::vector<std::string> bv;
-    while((c = getopt_long(cmd_argc, cmd_argv, "L:R:O:m:q:Q:B:t:r:G:h", BASETYPE_CMDLINE_LOPTS, nullptr)) >= 0) {
+    while((c = getopt_long(cmd_argc, cmd_argv, "L:f:o:m:q:Q:B:t:r:G:h", BASETYPE_CMDLINE_LOPTS, nullptr)) >= 0) {
         // 字符流解决命令行参数转浮点等类型的问题
         std::stringstream ss(optarg ? optarg: "");  
         switch (c) {
-            case 'R': _args->reference  = optarg;              break;  /* 临参 */
-            case 'O': _args->output_vcf = optarg;              break;  // 恒参
+            case 'f': _args->reference  = optarg;              break;  /* 临参 */
+            case 'o': _args->output_vcf = optarg;              break;  // 恒参
             case 'L':
                 bv = ngslib::get_firstcolumn_from_file(optarg); 
                 _args->input_bf.insert(_args->input_bf.end(), 
@@ -124,9 +124,9 @@ BaseTypeRunner::BaseTypeRunner(int cmd_argc, char *cmd_argv[]) {
     if (_args->input_bf.empty())
         throw std::invalid_argument("[ERROR] Missing required BAM/CRAM files.");
     if (_args->reference.empty())
-        throw std::invalid_argument("[ERROR] Missing argument '-R/--reference'");
+        throw std::invalid_argument("[ERROR] Missing argument '-f/--reference'");
     if (_args->output_vcf.empty())
-        throw std::invalid_argument("[ERROR] Missing argument '--output-vcf'");
+        throw std::invalid_argument("[ERROR] Missing argument '-o/--output-vcf'");
 
     if (_args->min_af < 0)
         throw std::invalid_argument("[ERROR] '-m/--min-af' argument must be > 0");
@@ -147,7 +147,7 @@ BaseTypeRunner::BaseTypeRunner(int cmd_argc, char *cmd_argv[]) {
     // Output the commandline options
     std::cout << 
         "[INFO] BaseVar arguments:\n"
-        "basevar caller -R "+ _args->reference + " \\ \n"
+        "basevar caller -f "+ _args->reference + " \\ \n"
         "   -Q " << _args->min_baseq          << " \\ \n"
         "   -q " << _args->min_mapq           << " \\ \n"
         "   -m " << _args->min_af             << " \\ \n"

tests/data/work.log.sh

@@ -1,11 +1,11 @@
-../../bin/basevar caller --mapq=10 --min-af=0.05 --batch-count=1 --thread=1 --regions=CHROMOSOME_I:900-1200 --pop-group=sample_group.info --output-vcf vz.vcf --output-cvg t.cvg -R ce.fa.gz -I range.bam -I range.cram -I range.bam --filename-has-samplename
+../../bin/basevar caller --min-mapq=10 --min-af=0.05 --batch-count=1 --thread=1 --regions=CHROMOSOME_I:900-1200 --pop-group=sample_group.info --output vz.vcf -f ce.fa.gz --filename-has-samplename range.bam range.cram range.bam
 
 #chr11:5246595-5248428,chr13:32890633-32972781,chr16:222869-227506,chr17:41197764-41276135
 # long options
-../../bin/basevar caller --min-BQ=0 --min-mapq=10 --min-af=0.05 --batch-count=20 --thread=4 --regions=chr11:5246595-5248428,chr17:41197764-41276135 --pop-group=sample_group.info --output-vcf tt.vcf.gz -R ~/Projects/BaseVar/tests/data/hg19.NC_012920.fasta.gz -L bam90.list bam100/00alzqq6jw.bam bam100/09t3r9n2rg.bam bam100/0fkpl1p55b.bam bam100/13dg1gvsfk.bam bam100/17phildszl.bam bam100/1dbpgqt0dq.bam bam100/1kyws27hoc.bam bam100/1ych8rmufr.bam bam100/4e56w6ezsx.bam bam100/51rwla2fps.bam > log2
+../../bin/basevar caller --min-BQ=0 --min-mapq=10 --min-af=0.05 --batch-count=20 --thread=4 --regions=chr11:5246595-5248428,chr17:41197764-41276135 --pop-group=sample_group.info --output tt.vcf.gz -f ~/Projects/BaseVar/tests/data/hg19.NC_012920.fasta.gz -L bam90.list bam100/00alzqq6jw.bam bam100/09t3r9n2rg.bam bam100/0fkpl1p55b.bam bam100/13dg1gvsfk.bam bam100/17phildszl.bam bam100/1dbpgqt0dq.bam bam100/1kyws27hoc.bam bam100/1ych8rmufr.bam bam100/4e56w6ezsx.bam bam100/51rwla2fps.bam > log2
 
 # short options
-ulimit -n 100000 && ../../bin/basevar caller -Q 0 -q 10 -m 0.05 -B 20 -t 4 -r chr11:5246595-5248428,chr17:41197764-41276135 -G sample_group.info --output-vcf tt.vcf -R ~/Projects/BaseVar/tests/data/hg19.NC_012920.fasta.gz -L bam90.list bam100/00alzqq6jw.bam bam100/09t3r9n2rg.bam bam100/0fkpl1p55b.bam bam100/13dg1gvsfk.bam bam100/17phildszl.bam bam100/1dbpgqt0dq.bam bam100/1kyws27hoc.bam bam100/1ych8rmufr.bam bam100/4e56w6ezsx.bam bam100/51rwla2fps.bam
+ulimit -n 100000 && ../../bin/basevar caller -Q 0 -q 10 -m 0.05 -B 20 -t 4 -r chr11:5246595-5248428,chr17:41197764-41276135 -G sample_group.info -o tt.vcf -f ~/Projects/BaseVar/tests/data/hg19.NC_012920.fasta.gz -L bam90.list bam100/00alzqq6jw.bam bam100/09t3r9n2rg.bam bam100/0fkpl1p55b.bam bam100/13dg1gvsfk.bam bam100/17phildszl.bam bam100/1dbpgqt0dq.bam bam100/1kyws27hoc.bam bam100/1ych8rmufr.bam bam100/4e56w6ezsx.bam bam100/51rwla2fps.bam
 
 # subsam
 ../../bin/basevar subsam -i tt.vcf~ -o t.vcf 5ffp4ybnks 9jikb1nr7d