Mercurial > repos > iuc > delly_merge
changeset 2:148389992630 draft
"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/delly commit d18d984264f54b45e94d97b5b97ed499a32a334a"
| author | iuc |
|---|---|
| date | Fri, 22 Jan 2021 14:32:24 +0000 |
| parents | 97c7441aed0d |
| children | 1efb2b927957 |
| files | macros.xml merge.xml |
| diffstat | 2 files changed, 96 insertions(+), 74 deletions(-) [+] |
line wrap: on
line diff
--- a/macros.xml Thu Oct 29 20:51:37 2020 +0000 +++ b/macros.xml Fri Jan 22 14:32:24 2021 +0000 @@ -1,6 +1,6 @@ <?xml version="1.0"?> <macros> - <token name="@TOOL_VERSION@">0.8.5</token> + <token name="@TOOL_VERSION@">0.8.7</token> <token name="@VERSION_SUFFIX@">0</token> <xml name="requirements"> <requirements> @@ -17,14 +17,12 @@ </citations> </xml> - <!-- - command - --> + <!-- command --> <token name="@BAM@"><![CDATA[ -#for $i, $current in enumerate($samples) - ln -s '${current}' 'sample_${i}.bam' && - ln -s '${current.metadata.bam_index}' 'sample_${i}.bam.bai' && +#for $i, $current in enumerate($input) + ln -s '${current}' 'input_${i}.bam' && + ln -s '${current.metadata.bam_index}' 'input_${i}.bam.bai' && #end for ]]></token> <token name="@DUMP@"><![CDATA[ @@ -43,68 +41,79 @@ #end if ]]></token> - <!-- - input - --> + <!-- input --> + <xml name="cnoffset" token_default=""> + <param name="cnoffset" type="float" min="0.0" max="1.0" value="@DEFAULT@" label="Set minimum CN offset" help="(--cn-offset)"/> + </xml> + <xml name="coverage" token_label=""> + <param argument="--coverage" type="integer" value="10" label="@LABEL@"/> + </xml> <xml name="exclude"> <param argument="--exclude" type="data" format="tabular" optional="true" label="Select file with regions to exclude"/> </xml> <xml name="genome"> - <param argument="--genome" type="data" format="fasta" label="Select genome"/> + <param argument="--genome" type="data" format="fasta" label="Select genome file"/> </xml> <xml name="genoqual"> <param name="genoqual" type="integer" value="5" label="Set minimum mapping quality for genotyping" help="(--geno-qual)"/> </xml> + <xml name="input" token_format="" token_multiple="false" token_label=""> + <param name="input" type="data" format="@FORMAT@" multiple="@MULTIPLE@" label="@LABEL@"/> + </xml> + <xml name="maxreadsep" token_default=""> + <param argument="--maxreadsep" type="integer" value="@DEFAULT@" label="Set maximum read separation"/> + </xml> + <xml name="maxsize" token_default="" token_label=""> + <param argument="--maxsize" type="integer" value="@DEFAULT@" label="@LABEL@"/> + </xml> <xml name="minclip"> <param argument="--minclip" type="integer" value="25" label="Set minimum clipping length"/> </xml> - <xml name="maxreadsep" token_default="40"> - <param argument="--maxreadsep" type="integer" value="@DEFAULT@" label="Set maximum read separation"/> + <xml name="mincliquesize"> + <param name="mincliquesize" type="integer" value="2" label="Set minimum paired-end/single-read clique size" help="(--min-clique-size)"/> </xml> - <xml name="maxsize" token_default="1000000"> - <param argument="--maxsize" type="integer" value="@DEFAULT@" label="Set maximum SV size"/> - </xml> - <xml name="mincliquesize"> - <param name="mincliquesize" type="integer" value="2" label="Set minimum min. PE/SR clique size" help="(--min-clique-size)"/> - </xml> - <xml name="minrefsep" token_default="25"> + <xml name="minrefsep" token_default=""> <param argument="--minrefsep" type="integer" value="@DEFAULT@" label="Set minimum reference separation"/> </xml> - <xml name="minsize"> - <param argument="--minsize" type="integer" value="0" label="Set minimum SV size"/> + <xml name="minsize" token_default="" token_label=""> + <param argument="--minsize" type="integer" value="@DEFAULT@" label="@LABEL@"/> + </xml> + <xml name="pass"> + <param argument="--pass" type="boolean" truevalue="--pass" falsevalue="" label="Filter sites for PASS?"/> </xml> - <xml name="samples" token_format="bam" token_multiple="true" token_label="Select sample file(s)"> - <param name="samples" type="data" format="@FORMAT@" multiple="@MULTIPLE@" label="@LABEL@"/> + <xml name="ploidy"> + <param argument="--ploidy" type="integer" value="2" label="Set baseline ploidy"/> + </xml> + <xml name="samples"> + <param argument="--samples" type="data" format="tabular" label="Select sample file" help="Two-column sample file listing sample name and tumor or control."/> </xml> <xml name="svtype"> <param argument="--svtype" type="select" label="Select type(s) of structural variants to detect"> <option value="ALL" selected="true">All types (ALL)</option> <option value="DEL">Deletion (DEL)</option> + <option value="DUP">Duplication (DUP)</option> <option value="INS">Insertion (INS)</option> - <option value="DUP">Duplication (DUP)</option> <option value="INV">Inversion (INV)</option> <option value="BND">Translocation (BND)</option> </param> </xml> <xml name="vcffile"> - <param argument="--vcffile" type="data" format="vcf,bcf" optional="true" label="Select genotyping file"/> + <param argument="--vcffile" type="data" format="bcf,vcf" optional="true" label="Select genotyping file"/> </xml> - <!-- - output - --> + <!-- output --> + <xml name="bcf"> + <data name="out_bcf" format="bcf" from_work_dir="result.bcf" label="${tool.name} on ${on_string}: Result (BCF)"> + <filter>'bcf' in oo['out']</filter> + </data> + </xml> <xml name="vcf"> <data name="out_vcf" format="vcf" from_work_dir="result.vcf" label="${tool.name} on ${on_string}: Result (VCF)"> <filter>'vcf' in oo['out']</filter> </data> </xml> - <xml name="bcf"> - <data name="out_bcf" format="bcf" from_work_dir="result.bcf" label="${tool.name} on ${on_string}: Result (BCF)"> - <filter>'bcf' in oo['out']</filter> - </data> - </xml> <xml name="dump"> <data name="out_dump" format="tabular" from_work_dir="dump.tsv" label="${tool.name} on ${on_string}: SV-reads"> <filter>'dump' in oo['out']</filter> @@ -116,12 +125,25 @@ </data> </xml> - <!-- - Help - --> + <!-- help --> <token name="@WID@"><![CDATA[ Delly is an integrated structural variant (SV) prediction method that can discover, genotype and visualize deletions, tandem duplications, inversions and translocations at single-nucleotide resolution in short-read massively parallel sequencing data. It uses paired-ends, split-reads and read-depth to sensitively and accurately delineate genomic rearrangements throughout the genome. + +Short-read SV calling + +- *call* to discover and genotype structural variants +- *merge* structural variants across VCF/BCF files and within a single VCF/BCF file +- *filter* somatic or germline structural variants + +Long-read SV calling + +- *lr* for long-read SV discovery + +Copy-number variant calling + +- *cnv* to discover and genotype copy-number variants +- *classify* somatic or germline copy-number variants ]]></token> <token name="@REFERENCES@"><![CDATA[ More information are available on `GitHub <https://github.com/dellytools/delly>`_.
--- a/merge.xml Thu Oct 29 20:51:37 2020 +0000 +++ b/merge.xml Fri Jan 22 14:32:24 2021 +0000 @@ -1,20 +1,20 @@ <?xml version="1.0"?> <tool id="delly_merge" name="Delly merge" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="18.01"> - <description>structural variants across/within VCF/BCF file(s)</description> + <description>structural variants across/within BCF/VCF file(s)</description> <macros> <import>macros.xml</import> </macros> <expand macro="requirements"/> <expand macro="version_command"/> <command detect_errors="exit_code"><![CDATA[ -## initialize -#for $i, $current in enumerate($samples) +## initialize +#for $i, $current in enumerate($input) #if $current.is_of_type('vcf') - bcftools view -Ob '$current' > 'sample_${i}.bcf.gz' && - bcftools index 'sample_${i}.bcf.gz' && + bcftools view -Ob '$current' > 'input_${i}.bcf.gz' && + bcftools index 'input_${i}.bcf.gz' && #else - ln -s '${current}' 'sample_${i}.bcf.gz' && - ln -s '${current.metadata.bcf_index}' 'sample_${i}.bcf.gz.csi' && + ln -s '${current}' 'input_${i}.bcf.gz' && + ln -s '${current.metadata.bcf_index}' 'input_${i}.bcf.gz.csi' && #end if #end for @@ -27,14 +27,15 @@ --coverage $generic.coverage --minsize $generic.minsize --maxsize $generic.maxsize +$generic.cnvmode $generic.precise $generic.pass ## overlap options --bp-offset $overlap.bpoffset --rec-overlap $overlap.recoverlap -## samples -#for $i, $current in enumerate($samples) - 'sample_${i}.bcf.gz' +## input +#for $i, $current in enumerate($input) + 'input_${i}.bcf.gz' #end for ## postprocessing @@ -42,37 +43,38 @@ @VCF@ ]]></command> <inputs> - <expand macro="samples" format="bcf,vcf"/> + <expand macro="input" format="bcf,vcf" multiple="true" label="Select input files"/> <section name="generic" title="Generic options" expanded="true"> <param argument="--chunks" type="integer" value="500" label="Set maximum chunk size to merge groups of BCF files"/> <param argument="--vaf" type="float" value="0.15" min="0.0" max="1.0" label="Set minimum fractional ALT support"/> - <param argument="--coverage" type="integer" value="10" label="Set minimum coverage"/> - <expand macro="minsize"/> - <expand macro="maxsize"/> + <expand macro="coverage" label="Set minimum coverage"/> + <expand macro="minsize" default="0" label="Set minimum SV size"/> + <expand macro="maxsize" default="1000000" label="Set maximum SV size"/> + <param argument="--cnvmode" type="boolean" truevalue="--cnvmode" falsevalue="" label="Merge Delly CNV files?"/> <param argument="--precise" type="boolean" truevalue="--precise" falsevalue="" label="Filter sites for PRECISE?"/> - <param argument="--pass" type="boolean" truevalue="--pass" falsevalue="" label="Filter sites for PASS?"/> + <expand macro="pass"/> </section> <section name="overlap" title="Overlap options" expanded="true"> <param name="bpoffset" type="integer" value="1000" label="Set maximum breakpoint offset" help="(--bp-offset)"/> <param name="recoverlap" type="float" value="0.8" label="Set minimum reciprocal overlap" help="(--rec-overlap)"/> </section> - <section name="oo" title="Output options"> + <section name="oo" title="Output options" expanded="true"> <param name="out" type="select" multiple="true" optional="false" label="Select output file(s)"> <option value="bcf" selected="true">BCF</option> + <option value="log">Log</option> <option value="vcf">VCF</option> - <option value="log">Log</option> </param> </section> </inputs> <outputs> - <expand macro="vcf"/> <expand macro="bcf"/> <expand macro="log"/> + <expand macro="vcf"/> </outputs> <tests> - <!-- #1 default, bcf --> + <!-- #1 bcf, default --> <test expect_num_outputs="2"> - <param name="samples" value="call_1.bcf.gz,call_2.bcf.gz"/> + <param name="input" value="call_1.bcf.gz,call_2.bcf.gz"/> <section name="oo"> <param name="out" value="vcf,bcf"/> </section> @@ -89,15 +91,16 @@ </assert_contents> </output> </test> - <!-- #2 bcf--> + <!-- #2 bcf --> <test expect_num_outputs="3"> - <param name="samples" value="call_1.bcf.gz,call_2.bcf.gz"/> + <param name="input" value="call_1.bcf.gz,call_2.bcf.gz"/> <section name="generic"> <param name="chunks" value="500"/> <param name="vaf" value="0.16"/> <param name="coverage" value="10"/> <param name="minsize" value="0"/> <param name="maxsize" value="1000000"/> + <param name="cnvmode" value="true"/> <param name="precise" value="true"/> <param name="pass" value="true"/> </section> @@ -110,15 +113,7 @@ </section> <output name="out_bcf"> <assert_contents> - <has_size value="1851" delta="10"/> - </assert_contents> - </output> - <output name="out_vcf"> - <assert_contents> - <has_n_lines n="128"/> - <has_line line="##fileformat=VCFv4.2"/> - <has_line line="#CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO"/> - <has_text_matching expression="chr5	75911568.+"/> + <has_size value="1021" delta="10"/> </assert_contents> </output> <output name="out_log"> @@ -126,10 +121,17 @@ <has_text_matching expression=".+Done\."/> </assert_contents> </output> + <output name="out_vcf"> + <assert_contents> + <has_n_lines n="108"/> + <has_line line="##fileformat=VCFv4.2"/> + <has_line line="#CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO"/> + </assert_contents> + </output> </test> - <!-- #3 default, vcf --> + <!-- #3 vcf, default --> <test expect_num_outputs="2"> - <param name="samples" value="call_1.vcf.gz,call_2.vcf.gz"/> + <param name="input" value="call_1.vcf.gz,call_2.vcf.gz"/> <section name="oo"> <param name="out" value="vcf,bcf"/> </section> @@ -154,15 +156,13 @@ @WID@ -Delly *merge* merges SV sites into a unified site list. - **Input** -BCF or VCF files. +Delly *merge* requires BCF or VCF files. **Output** -A single BCF file. +A single file in BCF/VCF format. Additionally a log file is provided. .. class:: infomark