Mercurial > repos > iuc > snpeff
diff snpEff.xml @ 7:7adfd0589f49 draft
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tool_collections/snpeff commit 5c6d595ecbf2e4e39c25662a165c9e475e01ecd1
author | iuc |
---|---|
date | Tue, 18 Apr 2017 09:33:56 -0400 |
parents | 2950d5afa3fe |
children | ce135864629c |
line wrap: on
line diff
--- a/snpEff.xml Mon Dec 19 11:56:53 2016 -0500 +++ b/snpEff.xml Tue Apr 18 09:33:56 2017 -0400 @@ -6,23 +6,20 @@ <expand macro="requirements" /> <expand macro="stdio" /> <expand macro="version_command" /> - <command> -<![CDATA[ - @CONDA_SNPEFF_JAR_PATH@ && - java -Xmx6G -jar "\$SNPEFF_JAR_PATH/snpEff.jar" eff - -c "\$SNPEFF_JAR_PATH/snpEff.config" + <command><![CDATA[ + snpEff -Xmx8g eff -i $inputFormat -o ${outputConditional.outputFormat} -upDownStreamLen $udLength #if $spliceSiteSize and str($spliceSiteSize) != '': -spliceSiteSize "$spliceSiteSize" #end if #if $spliceRegion.setSpliceRegions == 'yes': - #if $spliceRegion.spliceRegionExonSize and str($spliceRegion.spliceRegionExonSize) != '': + #if str($spliceRegion.spliceRegionExonSize) -spliceRegionExonSize $spliceRegion.spliceRegionExonSize #end if - #if $spliceRegion.spliceRegionIntronMin and str($spliceRegion.spliceRegionIntronMin) != '': + #if str($spliceRegion.spliceRegionIntronMin) -spliceRegionIntronMin $spliceRegion.spliceRegionIntronMin #end if - #if $spliceRegion.spliceRegionIntronMax and str($spliceRegion.spliceRegionIntronMax) != '': + #if str($spliceRegion.spliceRegionIntronMax) -spliceRegionIntronMax $spliceRegion.spliceRegionIntronMax #end if #end if @@ -39,63 +36,63 @@ -no $eff #end for #end if - #if str( $transcripts ) != 'None': - -onlyTr $transcripts + #if $transcripts + -onlyTr '$transcripts' #end if - #if str( $intervals ) != 'None': ### fix this for multiple dataset input - -interval $intervals + #if $intervals ### fix this for multiple dataset input + -interval '$intervals' #end if #if $statsFile: - -stats $statsFile + -stats '$statsFile' #end if #if str($offset) != 'default': ${offset} #end if #if str($chr).strip() != '': - -chr "$chr" + -chr '$chr' #end if $noLog + ## Regulation names can include parentheses: H3K4me3-MSC_(VB)_enriched_sites + ## Enclose them in in single and double quotes, as the conda snpEff bash script will remove outer quotes #if $snpDb.genomeSrc == 'cached': -dataDir ${snpDb.genomeVersion.fields.path} - #if $snpDb.extra_annotations and str($snpDb.extra_annotations) != '': - #echo " " - #echo ' '.join(str($snpDb.extra_annotations).split(',')) - #end if - #if $snpDb.regulation and str($snpDb.regulation) != '': - -reg #echo ' -reg '.join(str($snpDb.regulation).split(','))# + #if $snpDb.reg_section.regulation and str($snpDb.reg_section.regulation) != '': + #set $regs = [x for x in str($snpDb.reg_section.regulation).split(',')] + #for reg in $regs: + -reg '"${reg}"' + #end for #end if $snpDb.genomeVersion #elif $snpDb.genomeSrc == 'history': - -dataDir ${snpDb.snpeff_db.extra_files_path} - #if $snpDb.extra_annotations and str($snpDb.extra_annotations) != '': - #set xannotations = [' '] + str($snpDb.extra_annotations).split(',') - #echo " " - #echo ' -'.join($xannotations) + -dataDir '${snpDb.snpeff_db.extra_files_path}' + #if $snpDb.reg_section.regulation and str($snpDb.reg_section.regulation) != '': + #set $regs = [x for x in str($snpDb.reg_section.regulation).split(',')] + #for reg in $regs: + -reg '"${reg}"' + #end for #end if - #if $snpDb.regulation and str($snpDb.regulation) != '': - -reg #echo ' -reg '.join(str($snpDb.regulation).split(','))# - #end if - ${snpDb.snpeff_db.metadata.genome_version} + '${snpDb.snpeff_db.metadata.genome_version}' #else -download - $snpDb.genome_version + '$snpDb.genome_version' #end if - "$input" > "$snpeff_output"; + '$input' > '$snpeff_output' #if $statsFile: + && #import os #set $genes_file = str($statsFile) + '.genes.txt' #set $genes_file_name = os.path.split($genes_file)[-1] - mkdir $statsFile.files_path; - mv "$genes_file" #echo os.path.join($statsFile.files_path, $genes_file_name)#; + mkdir '$statsFile.files_path' && + mv '$genes_file' '#echo os.path.join($statsFile.files_path, $genes_file_name)#' #end if #if $outputConditional.outputFormat == 'gatk' and $outputConditional.gatk_v1 + && ## Replace real SnpEff version with 2.0.5 to prevent this GATK 1.x error: "The version of SnpEff used to generate the SnpEff input file (x.x) is not currently supported by the GATK. Supported versions are: [2.0.5]" - sed -i.bak -e 's/^\#\#SnpEffVersion="\(\S*\s\)/\#\#SnpEffVersion="2.0.5 - real is \1/' "$snpeff_output" + sed -i.bak -e 's/^\#\#SnpEffVersion="\(\S*\s\)/\#\#SnpEffVersion="2.0.5 - real is \1/' '$snpeff_output' #end if -]]> - </command> + ]]></command> <inputs> - <param format="vcf,tabular,pileup,bed" name="input" type="data" label="Sequence changes (SNPs, MNPs, InDels)"/> + <param name="input" type="data" format="vcf,tabular,pileup,bed" label="Sequence changes (SNPs, MNPs, InDels)"/> <param name="inputFormat" type="select" label="Input format"> <option value="vcf" selected="true">VCF</option> @@ -127,45 +124,34 @@ <param name="genomeVersion" type="select" label="Genome"> <!--GENOME DESCRIPTION--> <options from_data_table="snpeffv_genomedb"> - <filter type="static_value" name="snpeff_version" value="@SNPEFF_VERSION@" column="1"/> - <filter type="unique_value" column="2" /> + <filter type="static_value" name="snpeff_version" value="@SNPEFF_VERSION@" column="1"/> + <filter type="unique_value" column="2" /> </options> </param> - <param name="extra_annotations" type="select" display="checkboxes" multiple="true" label="Additional annotations"> - <help>These are available for only a few genomes</help> - <options from_data_table="snpeffv_annotations"> - <filter type="param_value" ref="genomeVersion" key="genome" column="2" /> - <filter type="unique_value" column="3" /> - </options> - </param> - <param name="regulation" type="select" display="checkboxes" multiple="true" label="Non-coding and regulatory annotation"> - <help>These are available for only a few genomes</help> - <options from_data_table="snpeffv_regulationdb"> - <filter type="param_value" ref="genomeVersion" key="genome" column="2" /> - <filter type="unique_value" column="3" /> - </options> - </param> + <section name="reg_section" expanded="false" title="Regulation options"> + <param name="regulation" type="select" display="checkboxes" multiple="true" label="Non-coding and regulatory annotation" help="These are available for only a few genomes"> + <options from_data_table="snpeffv_regulationdb"> + <filter type="param_value" ref="genomeVersion" key="genome" column="2" /> + <filter type="unique_value" column="3" /> + </options> + </param> + </section> </when> <when value="history"> - <param format="snpeffdb" name="snpeff_db" type="data" label="@SNPEFF_VERSION@ Genome Data"> + <param name="snpeff_db" type="data" format="snpeffdb" label="@SNPEFF_VERSION@ Genome Data"> <options options_filter_attribute="metadata.snpeff_version" > <filter type="add_value" value="@SNPEFF_VERSION@" /> </options> - <validator type="expression" message="This version of SnpEff will only work with @SNPEFF_VERSION@ Genome databases.">value is not None and value.metadata.snpeff_version == "@SNPEFF_VERSION@"</validator> + <validator type="expression" message="This version of SnpEff will only work with @SNPEFF_VERSION@ genome databases">value is not None and value.metadata.snpeff_version == "@SNPEFF_VERSION@"</validator> </param> - <!-- From metadata --> - <param name="extra_annotations" type="select" display="checkboxes" multiple="true" label="Additional annotations"> - <help>These are available for only a few genomes</help> - <options> - <filter type="data_meta" ref="snpeff_db" key="annotation" /> - </options> - </param> - <param name="regulation" type="select" display="checkboxes" multiple="true" label="Non-coding and regulatory annotation"> - <help>These are available for only a few genomes</help> - <options> - <filter type="data_meta" ref="snpeff_db" key="regulation" /> - </options> - </param> + <section name="reg_section" expanded="false" title="Regulation options"> + <!-- From metadata --> + <param name="regulation" type="select" display="checkboxes" multiple="true" label="Non-coding and regulatory annotation" help="These are available for only a few genomes"> + <options> + <filter type="data_meta" ref="snpeff_db" key="regulation" /> + </options> + </param> + </section> </when> <when value="named"> <param name="genome_version" type="text" value="" label="Snpff Genome Version Name (e.g. GRCh38.76)"> @@ -186,7 +172,7 @@ <option value="20000">20000 bases</option> </param> - <param name="spliceSiteSize" type="select" optional="true" label="Set size for splice sites (donor and acceptor) in bases" help="Default: 2"> + <param name="spliceSiteSize" type="select" optional="true" label="Set size for splice sites (donor and acceptor) in bases"> <option value="1">1 base</option> <option value="2" selected="true">2 bases</option> <option value="3">3 bases</option> @@ -212,24 +198,33 @@ </conditional> <param name="annotations" type="select" display="checkboxes" multiple="true" label="Annotation options"> - <option value="-cancer">Perform 'cancer' comparisons (somatic vs. germline)</option> - <option value="-canon">Only use canonical transcripts</option> - <option value="-geneId">Use gene ID instead of gene name (VCF output)</option> - <option value="-lof">Add loss of function (LOF) and nonsense mediated decay (NMD) tags</option> - <option value="-oicr">Add OICR tag in VCF file</option> - <option value="-onlyReg">Only use regulation tracks</option> + <option value="-formatEff">Use 'EFF' field compatible with older versions (instead of 'ANN')</option> <option value="-classic">Use Classic Effect names and amino acid variant annotations (NON_SYNONYMOUS_CODING vs missense_variant and G180R vs p.Gly180Arg/c.538G>C)</option> + <option value="-sequenceOntology">Override classic and use Sequence Ontolgy terms for effects (missense_variant vs NON_SYNONYMOUS_CODING)</option> <option value="-hgvs">Override classic and use HGVS annotations for amino acid annotations (p.Gly180Arg/c.538G>C vs G180R)</option> - <option value="-sequenceOntology">Override classic and use Sequence Ontolgy terms for effects (missense_variant vs NON_SYNONYMOUS_CODING)</option> - <option value="-formatEff">Use 'EFF' field compatible with older versions (instead of 'ANN').</option> - <option value="-noHgvs">Do not add HGVS annotations.</option> - <option value="-noLof">Do not add LOF and NMD annotations.</option> - <option value="-noShiftHgvs">Do not shift variants according to HGVS notation (most 3prime end).</option> - <option value="-oicr">Add OICR tag in VCF file. Default: false</option> + <option value="-hgvsOld">Old notation style notation: E.g. 'c.G123T' instead of 'c.123G>T' and 'X' instead of '*'</option> + <option value="-hgvs1LetterAa">Use one letter Amino acid codes in HGVS notation. E.g. p.R47G instead of p.Arg47Gly</option> + <option value="-hgvsTrId">Use transcript ID in HGVS notation. E.g. ENST00000252100:c.914C>G instead of c.914C>G</option> + <option value="-noShiftHgvs">Do not shift variants according to HGVS notation (most 3prime end)</option> + <option value="-noHgvs">Do not add HGVS annotations</option> + <option value="-canon">Only use canonical transcripts</option> + <option value="-onlyProtein">Only use protein coding transcripts</option> + <option value="-geneId">Use gene ID instead of gene name (VCF output)</option> + <option value="-noExpandIUB">Disable IUB code expansion in input variants</option> + <option value="-oicr">Add OICR tag in VCF file</option> + <option value="-lof">Add loss of function (LOF) and nonsense mediated decay (NMD) tags</option> + <option value="-noLof">Do not add LOF and NMD annotations</option> + <option value="-noMotif">Disable motif annotations</option> + <option value="-noNextProt">Disable NextProt annotations</option> + <option value="-noInteraction">Disable interaction annotations</option> + <option value="-cancer">Perform 'cancer' comparisons (somatic vs. germline)</option> + <!-- onlyReg option results in ifrequent exceptions with version 4.3k + <option value="-onlyReg">Only use regulation tracks</option> + --> </param> <!-- -cancerSamples <file> : Two column TXT file defining 'oringinal \t derived' samples. --> - <param name="intervals" format="bed" type="data" optional="true" label="Use custom interval file for annotation"/> - <param name="transcripts" format="tabular" type="data" optional="true" label="Only use the transcripts in this file." help="Format is one transcript ID per line."/> + <param name="intervals" type="data" format="bed" optional="true" label="Use custom interval file for annotation"/> + <param name="transcripts" type="data" format="tabular" optional="true" label="Only use the transcripts in this file" help="Format is one transcript ID per line"/> <param name="filterOut" type="select" display="checkboxes" multiple="true" label="Filter output"> <option value="-no-downstream">Do not show DOWNSTREAM changes</option> <option value="-no-intergenic">Do not show INTERGENIC changes</option> @@ -287,12 +282,11 @@ <option value="UTR_5_PRIME">UTR_5_PRIME (5_prime_UTR_variant) Variant hits 5'UTR region MODIFIER</option> <option value="UTR_5_DELETED">UTR_5_DELETED (5_prime_UTR_truncation + exon_loss_variant) The variant deletes an exon which is in the 5'UTR of the transcript MODERATE</option> <option value="NEXT_PROT">NEXT_PROT (sequence_feature + exon_loss_variant) A 'NextProt' based annotation. Details are provided in the 'feature type' sub-field (ANN), or in the effect details (EFF). MODERATE </option> - </param> </when> </conditional> - <param name="offset" type="select" display="radio" optional="true" label="Chromosomal position"> + <param name="offset" type="select" display="radio" label="Chromosomal position"> <option value="default" selected="true">Use default (based on input type)</option> <option value="-0">Force zero-based positions (both input and output)</option> <option value="-1">Force one-based positions (both input and output)</option> @@ -300,7 +294,7 @@ <param name="chr" type="text" label="Text to prepend to chromosome name"> <help> By default SnpEff simplifies all chromosome names. For instance 'chr1' is just '1'. - You can prepend any string you want to the chromosome name. + You can prepend any string you want to the chromosome name </help> <validator type="regex" message="No whitespace allowed">^\S*$</validator> </param> @@ -308,93 +302,38 @@ <param name="noLog" type="boolean" truevalue="-noLog" falsevalue="" checked="true" label="Suppress reporting usage statistics to server"/> </inputs> <outputs> - <data format="vcf" name="snpeff_output" > + <data name="snpeff_output" format="vcf"> <change_format> <when input="outputConditional.outputFormat" value="bed" format="bed" /> <when input="outputConditional.outputFormat" value="bedAnn" format="bed" /> </change_format> </data> - <data format="html" name="statsFile" label="${tool.name} on ${on_string} - stats"> + <data name="statsFile" format="html" label="${tool.name} on ${on_string} - stats"> <filter>generate_stats == True</filter> </data> </outputs> <tests> - <!-- Check that an effect was added in out VCF --> - <!-- Check for a HTML header indicating that this was successful --> - <!-- - <output name="statsFile"> - <assert_contents> - <has_text text="SnpEff: Variant analysis" /> - </assert_contents> - </output> - --> - <!-- Setting filterOut throws exception in twilltestcase.py <test> - <param name="input" ftype="vcf" value="vcf_homhet.vcf"/> - <param name="inputFormat" value="vcf"/> - <param name="outputFormat" value="vcf"/> - <param name="genomeSrc" value="named"/> - <param name="genome_version" value="testCase"/> - <param name="udLength" value="0"/> - <param name="generate_stats" value="False"/> - <param name="filterOut" value="+-no-upstream"/> - <output name="snpeff_output"> - <assert_contents> - <has_text text="EFF=" /> - </assert_contents> - </output> + <param name="input" ftype="vcf" value="input.vcf"/> + <param name="inputFormat" value="vcf"/> + <param name="outputFormat" value="vcf"/> + <param name="genomeSrc" value="named"/> + <param name="genome_version" value="ebola_zaire"/> + <param name="udLength" value="0"/> + <param name="generate_stats" value="False"/> + <output name="snpeff_output"> + <assert_contents> + <has_text_matching expression="KJ660346\t572\t.*missense_variant" /> + <has_text_matching expression="KJ660346\t1024\t.*synonymous_variant" /> + </assert_contents> + </output> </test> - --> - - <test> - <param name="input" ftype="vcf" value="vcf_homhet.vcf"/> - <param name="inputFormat" value="vcf"/> - <param name="outputFormat" value="vcf"/> - <param name="genomeSrc" value="named"/> - <param name="genome_version" value="testCase"/> - <param name="udLength" value="0"/> - <!-- - <param name="filterOut" value=""/> - --> - <param name="generate_stats" value="False"/> - <output name="snpeff_output"> - <assert_contents> - <!-- Check that deleletions were evaluated --> - <has_text_matching expression="Y\t59030478\t.*intergenic_region" /> - <!-- Check that insertion on last line was NOT evaluated --> - <has_text_matching expression="Y\t59032947\t.*\tGT" /> - </assert_contents> - </output> - </test> - - <!-- Check that NO UPSTREAM effect was added --> - <!-- Setting filterOut throws exception in twilltestcase.py - <test> - <param name="input" ftype="vcf" value="vcf_homhet.vcf"/> - <param name="inputFormat" value="vcf"/> - <param name="outputFormat" value="vcf"/> - <param name="genomeSrc" value="named"/> - <param name="genome_version" value="testCase"/> - <param name="udLength" value="0"/> - <param name="filterOut" value="+-no-upstream"/> - <param name="generate_stats" value="False"/> - <output name="snpeff_output"> - <assert_contents> - <not_has_text text="UPSTREAM" /> - </assert_contents> - </output> - </test> - --> - </tests> <help><![CDATA[ - This tool calculate the effect of variants (SNPs/MNPs/Insertions) and deletions. @EXTERNAL_DOCUMENTATION@ - ]]> </help> <expand macro="citations" /> </tool> -