Mercurial > repos > iuc > bcftools_stats
changeset 7:baa8823f8073 draft
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/bcftools commit 2684e1443f03bfe2ae20c31d23817415ec8f7e69
| author | iuc |
|---|---|
| date | Thu, 21 Feb 2019 15:56:16 -0500 |
| parents | b641062a2587 |
| children | e3c64225cbe6 |
| files | bcftools_stats.xml macros.xml test-data/summary.pdf test-data/view.bcf test-data/view.bcf.csi test-data/view.vcf_bgzip |
| diffstat | 6 files changed, 72 insertions(+), 52 deletions(-) [+] |
line wrap: on
line diff
--- a/bcftools_stats.xml Tue Dec 12 13:56:27 2017 -0500 +++ b/bcftools_stats.xml Thu Feb 21 15:56:16 2019 -0500 @@ -1,5 +1,5 @@ <?xml version='1.0' encoding='utf-8'?> -<tool name="bcftools @EXECUTABLE@" id="bcftools_@EXECUTABLE@" version="@VERSION@"> +<tool name="bcftools @EXECUTABLE@" id="bcftools_@EXECUTABLE@" version="@TOOL_VERSION@"> <description>Parses VCF or BCF and produces stats which can be plotted using plot-vcfstats</description> <macros> <token name="@EXECUTABLE@">stats</token> @@ -7,11 +7,16 @@ </macros> <expand macro="requirements"> <expand macro="samtools_requirement"/> - <requirement type="package" version="2.0.0">matplotlib</requirement> + <requirement type="package" version="3.0.2">matplotlib</requirement> + <requirement type="package" version="0.1.11">tectonic</requirement> </expand> <expand macro="version_command" /> <command detect_errors="aggressive"><![CDATA[ @PREPARE_ENV@ +#set $input_files = [$input_file] +#if $inputB_file: + #silent $input_files.append($inputB_file) +#end if @PREPARE_INPUT_FILES@ #set $section = $sec_restrict @PREPARE_TARGETS_FILE@ @@ -29,21 +34,21 @@ @EXONS_FILE@ ${section.first_allele_only} #if $section.depth.set_depth == 'yes': - --depth "${section.depth.depth_min},${section.depth.depth_max},${section.depth.depth_bin_size}" + --depth ${section.depth.depth_min},${section.depth.depth_max},${section.depth.depth_bin_size} #end if #if $section.user_tstv: - --user-tstv "${section.user_tstv}" + --user-tstv '${section.user_tstv}' #end if #if $section.afbins.afbins_select == 'af_bins_list': - --af-bins $section.afbins.af_bins_list + --af-bins '$section.afbins.af_bins_list' #elif $section.afbins.afbins_select == 'af_bins_file': - --af-bins $section.afbins.af_bins_file + --af-bins '$section.afbins.af_bins_file' #end if #if $section.af_tag: - --af-tag "${section.af_tag}" + --af-tag '${section.af_tag}' #end if #if len($input_vcfs) == 1: -${section.split_by_ID} + ${section.split_by_ID} #end if ${section.verbose} @@ -59,15 +64,19 @@ ## Primary Input/Outputs @INPUT_FILES@ -> $output_file -## requires: matplotlib and pdflatex +> '$output_file' #if $plot_title: -&& plot-vcfstats -p 'plot_tmp/' -T $plot_title -s $output_file + && plot-vcfstats + -p 'plot_tmp/' + -T '$plot_title' + -s + '$output_file' + || (printf "The content of plot_tmp/plot-vcfstats.log is:\n" >&2 && cat plot_tmp/plot-vcfstats.log >&2 && exit 1) #end if -]]> - </command> + ]]></command> <inputs> - <expand macro="macro_inputs" /> + <expand macro="macro_input" /> + <param name="inputB_file" type="data" format="vcf,vcf_bgzip,bcf" optional="true" label="Optional VCF/BCF Data to compare against" help="When this second dataset is also specified, separate stats for intersection and the complements are generated" /> <section name="sec_restrict" expanded="false" title="Restrict to"> <expand macro="macro_samples" /> <expand macro="macro_apply_filters" /> @@ -128,13 +137,14 @@ </inputs> <outputs> <data name="output_file" format="txt"/> - <data name="output_pdf" format="pdf"> + <data name="output_pdf" format="pdf" from_work_dir="plot_tmp/summary.pdf"> <filter>plot_title</filter> </data> </outputs> <tests> <test> - <param name="input_files" ftype="vcf" value="stats.b.vcf,stats.a.vcf" /> + <param name="input_file" ftype="vcf" value="stats.b.vcf" /> + <param name="inputB_file" ftype="vcf" value="stats.a.vcf" /> <output name="output_file"> <assert_contents> <has_text_matching expression="SN\t0\tnumber of samples:\t3"/> @@ -143,7 +153,8 @@ </output> </test> <test> - <param name="input_files" ftype="vcf" value="mpileup.vcf" /> + <param name="input_file" ftype="vcf" value="mpileup.vcf" /> + <param name="plot_title" value="Plot for mpileup.vcf" /> <output name="output_file"> <assert_contents> <has_text_matching expression="SN\t0\tnumber of samples:\t3"/> @@ -151,6 +162,7 @@ <has_text_matching expression="ST\t0\tA>C\t16"/> </assert_contents> </output> + <output name="output_pdf" file="summary.pdf" compare="sim_size" delta="20000" /> </test> </tests> <help><![CDATA[ @@ -163,6 +175,8 @@ When two files are given, the program generates separate stats for intersection and the complements. By default only sites are compared, -s/-S must given to include also sample columns. +When one VCF file is specified, then stats by non-reference allele frequency, depth distribution, stats by quality and per-sample counts, singleton stats, etc. are printed. When two VCF files are given, then stats such as concordance (Genotype concordance by non-reference allele frequency, Genotype concordance by sample, Non-Reference Discordance) and correlation are also printed. Per-site discordance (PSD) is also printed in --verbose mode. + @COLLAPSE_HELP@ @REGIONS_HELP@ @TARGETS_HELP@
--- a/macros.xml Tue Dec 12 13:56:27 2017 -0500 +++ b/macros.xml Thu Feb 21 15:56:16 2019 -0500 @@ -1,5 +1,5 @@ <macros> - <token name="@VERSION@">1.4.0</token> + <token name="@TOOL_VERSION@">1.9</token> <xml name="stdio"> <stdio> <exit_code range="1:" /> @@ -10,13 +10,13 @@ </xml> <xml name="requirements"> <requirements> - <requirement type="package" version="1.4">bcftools</requirement> - <requirement type="package" version="1.4">htslib</requirement> + <requirement type="package" version="@TOOL_VERSION@">bcftools</requirement> + <requirement type="package" version="1.9">htslib</requirement> <yield /> </requirements> </xml> <xml name="samtools_requirement"> - <requirement type="package" version="1.3.1">samtools</requirement> + <requirement type="package" version="1.9">samtools</requirement> </xml> <xml name="version_command"> <version_command>bcftools 2>&1 | grep 'Version:'</version_command> @@ -39,7 +39,7 @@ ]]> </token> <xml name="macro_input"> - <param name="input_file" type="data" format="vcf,vcf_bgzip,bcf,bcf_bgzip" label="VCF/BCF Data" /> + <param name="input_file" type="data" format="vcf,vcf_bgzip,bcf" label="VCF/BCF Data" /> </xml> <token name="@PREPARE_INPUT_FILE@"> <![CDATA[ @@ -50,6 +50,11 @@ bcftools index $input_vcf && #elif $input_file.is_of_type('vcf_bgzip') ln -s '$input_file' $input_vcf && + #if $input_file.metadata.tabix_index: + ln -s '${input_file.metadata.tabix_index}' ${input_vcf}.tbi && + #else + bcftools index $input_vcf && + #end if #elif $input_file.is_of_type('bcf') #set $input_vcf = 'input.bcf' ln -s '$input_file' $input_vcf && @@ -58,8 +63,6 @@ #else bcftools index $input_vcf && #end if -#elif $input_file.is_of_type('bcf_bgzip') - ln -s '$input_file' $input_vcf && #end if ]]> </token> @@ -68,7 +71,7 @@ </token> <xml name="macro_inputs"> - <param name="input_files" type="data" format="vcf,bcf" label="Other VCF/BCF Datasets" multiple="True" /> + <param name="input_files" type="data" format="vcf,vcf_bgzip,bcf" label="Other VCF/BCF Datasets" multiple="True" /> </xml> <token name="@PREPARE_INPUT_FILES@"> <![CDATA[ @@ -80,8 +83,13 @@ #if $input_file.is_of_type('vcf') bgzip -c '$input_file' > $input_vcf && bcftools index $input_vcf && - #elif $input_file.is_of_type('vcf_bgz') - ln -s '$input_file' $input_vcf + #elif $input_file.is_of_type('vcf_bgzip') + ln -s '$input_file' $input_vcf && + #if $input_file.metadata.tabix_index: + ln -s '${input_file.metadata.tabix_index}' ${input_vcf}.tbi && + #else + bcftools index $input_vcf && + #end if #elif $input_file.is_of_type('bcf') #set $input_vcf = 'input' + str($i) + '.bcf.gz' ln -s '$input_file' $input_vcf && @@ -90,8 +98,6 @@ #else bcftools index $input_vcf && #end if - #elif $input_file.is_of_type('bcfvcf_bgz') - ln -s '$input_file' $input_vcf && #end if echo '$input_vcf' >> $vcfs_list_file && $input_vcfs.append($input_vcf) @@ -106,7 +112,7 @@ </token> <xml name="macro_fasta_ref"> - <param name="fasta_ref" argument="--fasta-ref" type="data" format="data" label="Reference sequence in FASTA format" optional="True" /> + <param name="fasta_ref" argument="--fasta-ref" type="data" format="data" optional="true" label="Reference sequence in FASTA format" /> </xml> <token name="@PREPARE_FASTA_REF@"> <![CDATA[ @@ -148,7 +154,7 @@ <xml name="macro_AF_file"> - <param name="AF_file" argument="--AF-file" type="data" format="tabular" label="Allele frequencies file" optional="True" help="Tab-delimited file containing the columns CHR,POS,REF,ALT,AF" /> + <param name="AF_file" argument="--AF-file" type="data" format="tabular" optional="true" label="Allele frequencies file" help="Tab-delimited file containing the columns CHR,POS,REF,ALT,AF" /> </xml> <!-- This may need to bgzip and tabix the file --> <token name="@PREPARE_AF_FILE@"> @@ -165,7 +171,7 @@ </token> <xml name="macro_estimate_AF"> - <param name="estimate_AF" argument="--estimate-AF" type="data" format="data" label="Estimate allele frequency" optional="True" help="calculate AC,AN counts on the fly, using either all samples ("-") or samples listed in <file>" /> + <param name="estimate_AF" argument="--estimate-AF" type="data" format="data" optional="true" label="Estimate allele frequency" help="Calculate AC,AN counts on the fly, using either all samples ("-") or samples listed in <file>" /> </xml> <token name="@ESTIMATE_AF@"> #if 'estimate_AF' in $section and $section.estimate_AF: @@ -174,7 +180,7 @@ </token> <xml name="macro_exons_file"> - <param name="exons_file" type="data" format="tabular" label="exons file" optional="True" help="tab-delimited file with exons for indel frameshifts (chr,from,to; 1-based, inclusive, bgzip compressed)" /> + <param name="exons_file" type="data" format="tabular" optional="true" label="Exons file" help="Tab-delimited file with exons for indel frameshifts (chr,from,to; 1-based, inclusive, bgzip compressed)" /> </xml> <token name="@PREPARE_EXONS_FILE@"> <![CDATA[ @@ -193,7 +199,7 @@ </token> <xml name="macro_ploidy_file"> - <param name="ploidy_file" type="data" format="tabular" label="Ploidy file" optional="True" help="tab-delimited list of CHROM,FROM,TO,SEX,PLOIDY" /> + <param name="ploidy_file" type="data" format="tabular" optional="true" label="Ploidy file" help="Tab-delimited list of CHROM,FROM,TO,SEX,PLOIDY" /> </xml> <token name="@PLOIDY_FILE@"> #if 'ploidy_file' in $section and $section.ploidy_file: @@ -208,7 +214,7 @@ <option value="id">id - only records with identical ID column are compatible. </option> </xml> <xml name="macro_collapse"> - <param name="collapse" type="select" label="Collapse" optional="True" help="Controls how to treat records with duplicate positions and defines compatible records across multiple input files"> + <param name="collapse" type="select" optional="true" label="Collapse" help="Controls how to treat records with duplicate positions and defines compatible records across multiple input files"> <option value="snps">snps - allow different alleles, as long as they all are SNPs</option> <option value="indels">indels - allow different alleles, as long as they all are indels</option> <option value="both">both - indels and snps </option> @@ -224,8 +230,8 @@ </token> <xml name="macro_apply_filters"> - <param name="apply_filters" type="text" value="" label="Apply Filters" optional="true" - help="(-f --apply-filters) Skip sites where FILTER column does not contain any of the strings listed (e.g. "PASS,.")"> + <param argument="--apply_filters" type="text" value="" optional="true" label="Apply filters" + help="Skip sites where FILTER column does not contain any of the strings listed (e.g. "PASS,.")"> <validator type="regex" message="FILTER terms separated by commas">^([^ \t\n\r\f\v,]+(,[^ \t\n\r\f\v,]+)*)?$</validator> </param> </xml> @@ -271,13 +277,13 @@ </param> <when value="__none__"/> <when value="regions"> - <param name="regions" type="text" value="" label="restrict to comma-separated list of regions" optional="true" + <param name="regions" type="text" value="" optional="true" label="Restrict to comma-separated list of regions" help="Each region is specifed as: chr or chr:pos or chr:from-to"> <validator type="regex" message="">^(\w+(:\d+(-\d+)?)?(,\w+(:\d+(-\d+)?)?)*)?$</validator> </param> </when> <when value="regions_file"> - <param name="regions_file" type="data" format="vcf,bed,tabular" label="Regions File" optional="True" help="restrict to regions listed in a file" /> + <param name="regions_file" type="data" format="vcf,bed,tabular" optional="true" label="Regions file" help="Restrict to regions listed in a file" /> </when> </conditional> </xml> @@ -346,7 +352,7 @@ </param> <when value="__none__"/> <when value="targets"> - <param name="targets" type="text" value="" label="Restrict to comma-separated list of targets" optional="true" + <param name="targets" type="text" value="" optional="true" label="Restrict to comma-separated list of targets" help="Each target is specifed as: chr or chr:pos or chr:from-to"> <validator type="regex" message="">^(\w+(:\d+(-\d+)?)?(,\w+(:\d+(-\d+)?)?)*)?$</validator> </param> @@ -373,16 +379,16 @@ </token> <xml name="macro_samples"> - <param name="samples" type="text" value="" label="Samples" optional="true" - help="(-s) comma separated list of samples to annotate (or exclude)"> + <param argument="--samples" type="text" value="" optional="true" label="Samples" + help="Comma separated list of samples to annotate (or exclude)"> <validator type="regex" message="">^(\w+(,\w+)*)?$</validator> </param> <param name="invert_samples" type="boolean" truevalue="^" falsevalue="" checked="false" label="Invert Samples" - help="inverts the query/filtering applied by Samples (adds "^" prefix to exclude)" /> - <param name="samples_file" type="data" format="tabular" label="Samples File" optional="True" - help="(-S) file of samples to include" /> - <param name="invert_samples_file" type="boolean" truevalue="^" falsevalue="" checked="false" label="Invert Samples File" - help="inverts the query/filtering applied by Samples File" /> + help="Inverts the query/filtering applied by Samples (adds "^" prefix to exclude)" /> + <param argument="--samples_file" type="data" format="tabular" optional="true" label="Samples file" + help="File of samples to include" /> + <param name="invert_samples_file" type="boolean" truevalue="^" falsevalue="" checked="false" label="Invert Samples file" + help="inverts the query/filtering applied by Samples file" /> </xml> <token name="@SAMPLES@"> #set $samples_defined = False @@ -397,7 +403,7 @@ </token> <xml name="macro_sample"> - <param name="sample" type="text" label="Sample" optional="True" help="apply variants of the given sample" /> + <param name="sample" type="text" optional="true" label="Sample" help="Apply variants of the given sample" /> </xml> <token name="@SAMPLE@"> #if $section.sample: @@ -407,7 +413,7 @@ <xml name="macro_include"> - <param name="include" type="text" label="Include" optional="True" help="(-i) select sites for which the expression is true"> + <param argument="--include" type="text" optional="true" label="Include" help="Select sites for which the expression is true"> <validator type="regex" message="Single quote not allowed">^[^']*$</validator> <sanitizer sanitize="False"/> </param> @@ -419,7 +425,7 @@ </token> <xml name="macro_exclude"> - <param name="exclude" type="text" label="Exclude" optional="True" help="(-e) exclude sites for which the expression is true"> + <param argument="--exclude" type="text" optional="true" label="Exclude" help="Exclude sites for which the expression is true"> <validator type="regex" message="Single quote not allowed">^[^']*$</validator> <sanitizer sanitize="False"/> </param> @@ -431,8 +437,8 @@ </token> <xml name="macro_columns"> - <param name="columns" type="text" value="" label="Columns" optional="true" - help="list of columns in the annotation file, e.g. CHROM,POS,REF,ALT,-,INFO/TAG. See man page for details"> + <param name="columns" type="text" value="" optional="true" label="Columns" + help="List of columns in the annotation file, e.g. CHROM,POS,REF,ALT,-,INFO/TAG. See man page for details"> <validator type="regex" message="COLUMN names separated by commas">^([^,]+(,[^,]+)*)?$</validator> </param> </xml>