Mercurial > repos > jjohnson > snpeff_with_dep
view snpEff.xml @ 25:7c1c337fb21c default tip
Update tool_dependencies.xml for testtoolshed
author | Jim Johnson <jj@umn.edu> |
---|---|
date | Tue, 07 May 2013 15:05:54 -0500 |
parents | f22f28cd881e |
children |
line wrap: on
line source
<tool id="snpEff" name="SnpEff" version="3.2"> <description>Variant effect and annotation</description> <!-- You will need to change the path to wherever your installation is. You can change the amount of memory used by snpEff, just change the -Xmx parameter (e.g. use -Xmx2G for 2Gb of memory) <command>java -Xmx6G -jar /path/to/your/snpEff/snpEff.jar eff -c /path/to/your/snpEff/snpEff/snpEff.config $inputFormat $offset -upDownStreamLen $udLength $filterIn $filterHomHet -no $filterOut -stats $statsFile $genomeVersion $input > $output </command> Options: -a , -around : Show N codons and amino acids around change (only in coding regions). Default is 0 codons. -i <format> : Input format [ vcf, txt, pileup, bed ]. Default: VCF. -o <format> : Ouput format [ txt, vcf, gatk, bed, bedAnn ]. Default: VCF. -interval : Use a custom interval file (you may use this option many times) -chr <string> : Prepend 'string' to chromosome name (e.g. 'chr1' instead of '1'). Only on TXT output. -s, -stats : Name of stats file (summary). Default is 'snpEff_summary.html' -t : Use multiple threads (implies '-noStats'). Default 'off' Sequence change filter options: -del : Analyze deletions only -ins : Analyze insertions only -hom : Analyze homozygous variants only -het : Analyze heterozygous variants only -minQ X, -minQuality X : Filter out variants with quality lower than X -maxQ X, -maxQuality X : Filter out variants with quality higher than X -minC X, -minCoverage X : Filter out variants with coverage lower than X -maxC X, -maxCoverage X : Filter out variants with coverage higher than X -nmp : Only MNPs (multiple nucleotide polymorphisms) -snp : Only SNPs (single nucleotide polymorphisms) Results filter options: -fi <bedFile> : Only analyze changes that intersect with the intervals specified in this file (you may use this option many times) -no-downstream : Do not show DOWNSTREAM changes -no-intergenic : Do not show INTERGENIC changes -no-intron : Do not show INTRON changes -no-upstream : Do not show UPSTREAM changes -no-utr : Do not show 5_PRIME_UTR or 3_PRIME_UTR changes Annotations options: -cancer : Perform 'cancer' comparissons (Somatic vs Germline). Default: false -canon : Only use canonical transcripts. -geneId : Use gene ID instead of gene name (VCF output). Default: false -hgvs : Use HGVS annotations for amino acid sub-field. Default: false -lof : Add loss of function (LOF) and Nonsense mediated decay (NMD) tags. -reg <name> : Regulation track to use (this option can be used add several times). -oicr : Add OICR tag in VCF file. Default: false -onlyReg : Only use regulation tracks. -onlyTr <file.txt> : Only use the transcripts in this file. Format: One transcript ID per line. -sequenceOntolgy : Use Sequence Ontolgy terms. Default: false -ss, -spliceSiteSize <int> : Set size for splice sites (donor and acceptor) in bases. Default: 2 -ud, -upDownStreamLen <int> : Set upstream downstream interval length (in bases) Generic options: -0 : File positions are zero-based (same as '-inOffset 0 -outOffset 0') -1 : File positions are one-based (same as '-inOffset 1 -outOffset 1') -c , -config : Specify config file -h , -help : Show this help and exit -if, -inOffset : Offset input by a number of bases. E.g. '-inOffset 1' for one-based input files -of, -outOffset : Offset output by a number of bases. E.g. '-outOffset 1' for one-based output files -noLog : Do not report usage statistics to server -noStats : Do not create stats (summary) file -q , -quiet : Quiet mode (do not show any messages or errors) -v , -verbose : Verbose mode --> <requirements> <requirement type="package" version="3.2">snpEff</requirement> </requirements> <command> SNPEFF_DATA_DIR=`grep '^data_dir' \$JAVA_JAR_PATH/snpEff.config | sed 's/.*data_dir.*[=:]//'`; eval "if [ ! -e \$SNPEFF_DATA_DIR/$genomeVersion ] ; then java -Xmx6G -jar \$JAVA_JAR_PATH/snpEff.jar download -c \$JAVA_JAR_PATH/snpEff.config $genomeVersion ; fi"; java -Xmx6G -jar \$JAVA_JAR_PATH/snpEff.jar eff -c \$JAVA_JAR_PATH/snpEff.config -i $inputFormat -o $outputFormat -upDownStreamLen $udLength #if $spliceSiteSize and $spliceSiteSize.__str__ != '': -spliceSiteSize $spliceSiteSize #end if #if $filterIn and $filterIn.__str__ != 'no_filter': -$filterIn #end if #if $filterHomHet and $filterHomHet.__str__ != 'no_filter': -$filterHomHet #end if #if $annotations and $annotations.__str__ != '': -#slurp #echo ' -'.join($annotations.__str__.split(',')) #end if #if $filterOut and $filterOut.__str__ != '': -#slurp #echo ' -'.join($filterOut.__str__.split(',')) #end if #if str( $transcripts ) != 'None': -onlyTr $transcripts #end if #if str( $intervals ) != 'None': ### fix this for multiple dataset input -interval $intervals #end if #if $statsFile: -stats $statsFile #end if #if $offset.__str__ != '': -${offset} #end if #if $chr.__str__.strip() != '': -chr "$chr" #end if $noLog $genomeVersion $input > $snpeff_output </command> <inputs> <param format="vcf,tabular,pileup,bed" name="input" type="data" label="Sequence changes (SNPs, MNPs, InDels)"/> <param name="inputFormat" type="select" label="Input format"> <option value="vcf" selected="true">VCF</option> <option value="txt">Tabular (Deprecated)</option> <option value="pileup">Pileup (Deprecated)</option> <option value="bed">BED (Deprecated)</option> </param> <param name="outputFormat" type="select" label="Output format"> <option value="vcf" selected="true">VCF (only if input is VCF)</option> <option value="txt">Tabular</option> <option value="bed">BED</option> <option value="bedAnn">BED Annotations</option> </param> <param name="genomeVersion" type="select" label="Genome"> <!--GENOME DESCRIPTION--> <options from_file="snpeffect_genomedb.loc"> <column name="name" index="1"/> <column name="value" index="0"/> </options> </param> <param name="udLength" type="select" label="Upstream / Downstream length"> <option value="0">No upstream / downstream intervals (0 bases)</option> <option value="200">200 bases</option> <option value="500">500 bases</option> <option value="1000">1000 bases</option> <option value="2000">2000 bases</option> <option value="5000" selected="true">5000 bases</option> <option value="10000">10000 bases</option> <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. Default: 2"> <option value="1">1 base</option> <option value="2">2 bases</option> <option value="3">3 bases</option> <option value="4">4 bases</option> <option value="5">5 bases</option> <option value="6">6 bases</option> <option value="7">7 bases</option> <option value="8">8 bases</option> <option value="9">9 bases</option> </param> <param name="filterHomHet" type="select" display="radio" label="Filter homozygous / heterozygous changes"> <option value="no_filter" selected="true">No filter (analyze everything)</option> <option value="hom">Analyze homozygous sequence changes only </option> <option value="het">Analyze heterozygous sequence changes only </option> </param> <!-- The tool testing code can not handle select,radio,checkbox values that start with '-', so the '-' is added in the command generation --> <param name="filterIn" type="select" display="radio" label="Filter sequence changes"> <option value="no_filter" selected="true">No filter (analyze everything)</option> <option value="del">Analyze deletions only </option> <option value="ins">Analyze insertions only </option> <option value="mnp">Only MNPs (multiple nucleotide polymorphisms) </option> <option value="snp">Only SNPs (single nucleotide polymorphisms) </option> </param> <param name="annotations" type="select" display="checkboxes" multiple="true" optional="true" label="Annotation options"> <option value="cancer">Perform 'cancer' comparissons (Somatic vs Germline). Default: false</option> <option value="canon">Only use canonical transcripts.</option> <option value="geneId">Use gene ID instead of gene name (VCF output). Default: false</option> <option value="hgvs">Use HGVS annotations for amino acid sub-field. Default: false</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. Default: false</option> <option value="onlyReg">Only use regulation tracks.</option> <option value="sequenceOntolgy">Use Sequence Ontolgy terms. Default: false</option> </param> <param name="regulation" type="select" display="checkboxes" multiple="true" optional="true" label="Non-coding and regulatory Annotation"> <help>These are available for only a few genomes</help> <!--GENOME REG_NAME --> <options from_file="snpeffect_regulationdb.loc"> <column name="name" index="1"/> <column name="value" index="0"/> <filter type="param_value" ref="genomeVersion" key="name" column="1" /> </options> </param> <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. Format: One transcript ID per line."/> <param name="filterOut" type="select" display="checkboxes" multiple="true" optional="true" label="Filter output"> <option value="no-downstream">Do not show DOWNSTREAM changes </option> <option value="no-intergenic">Do not show INTERGENIC changes </option> <option value="no-intron">Do not show INTRON changes </option> <option value="no-upstream">Do not show UPSTREAM changes </option> <option value="no-utr">Do not show 5_PRIME_UTR or 3_PRIME_UTR changes </option> </param> <param name="offset" type="select" display="radio" optional="true" label="Chromosomal position"> <option value="" 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> </param> <param name="chr" type="text" optionl="true" 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."> <validator type="regex" message="No whitespace allows">^\S*$</validator> </param> <param name="generate_stats" type="boolean" truevalue="" falsevalue="-noStats" checked="true" label="Produce Summary Stats"/> <param name="noLog" type="boolean" truevalue="-noLog" falsevalue="" checked="true" label="Do not report usage statistics to server"/> </inputs> <outputs> <data format="vcf" name="snpeff_output" > <change_format> <when input="outputFormat" value="vcf" format="vcf" /> <when input="outputFormat" value="txt" format="tabular" /> <when input="outputFormat" value="bed" format="bed" /> <when input="outputFormat" value="bedAnn" format="bed" /> </change_format> </data> <data format="html" name="statsFile"> <filter>generate_stats == True</filter> </data> </outputs> <stdio> <exit_code range="1:" level="fatal" description="Error" /> <exit_code range="-1" level="fatal" description="Error: Cannot open file" /> </stdio> <tests> <test> <param name="input" ftype="vcf" value="vcf_homhet.vcf"/> <param name="inputFormat" value="vcf"/> <param name="outputFormat" value="vcf"/> <param name="genomeVersion" value="testCase"/> <param name="udLength" value="0"/> <param name="filterHomHet" value="no_filter"/> <param name="filterIn" value="no_filter"/> <param name="generate_stats" value="False"/> <!-- <param name="filterOut" value="no-upstream"/> --> <output name="snpeff_output"> <assert_contents> <!-- Check that an effect was added --> <has_text text="EFF=" /> </assert_contents> </output> <!-- Check for a HTML header indicating that this was successful --> <!-- <output name="statsFile"> <assert_contents> <has_text text="SnpEff: Variant analysis" /> </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="genomeVersion" value="testCase"/> <param name="udLength" value="0"/> <param name="filterHomHet" value="het"/> <param name="filterIn" value="no_filter"/> <!-- <param name="filterOut" value=""/> --> <param name="generate_stats" value="False"/> <output name="snpeff_output"> <assert_contents> <!-- Check that NO effects were added since -het is set --> <not_has_text text="EFF=NON_SYNONYMOUS_CODING" /> </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="genomeVersion" value="testCase"/> <param name="udLength" value="0"/> <param name="filterHomHet" value="no_filter"/> <param name="filterIn" value="del"/> <!-- <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.*EFF=INTERGENIC" /> <!-- Check that insertion on last line was NOT evaluated --> <has_text_matching expression="Y\t59032947\t.*SF=5\tGT" /> </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="genomeVersion" value="testCase"/> <param name="udLength" value="0"/> <param name="filterHomHet" value="no_filter"/> <param name="filterIn" value="no_filter"/> <param name="filterOut" value="no-upstream"/> <param name="generate_stats" value="False"/> <output name="snpeff_output"> <assert_contents> <!-- Check that NO UPSTREAM effect was added --> <not_has_text text="UPSTREAM" /> </assert_contents> </output> </test> </tests> <help> This tool calculate the effect of variants (SNPs/MNPs/Insertions) and deletions. For details about this tool, please go to http://snpEff.sourceforge.net </help> </tool>