Mercurial > repos > iuc > snpeff
view 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 source
<tool id="snpEff" name="SnpEff" version="@WRAPPER_VERSION@.0"> <description>Variant effect and annotation</description> <macros> <import>snpEff_macros.xml</import> </macros> <expand macro="requirements" /> <expand macro="stdio" /> <expand macro="version_command" /> <command><![CDATA[ snpEff -Xmx8g eff -i $inputFormat -o ${outputConditional.outputFormat} -upDownStreamLen $udLength #if $spliceSiteSize and str($spliceSiteSize) != '': -spliceSiteSize "$spliceSiteSize" #end if #if $spliceRegion.setSpliceRegions == 'yes': #if str($spliceRegion.spliceRegionExonSize) -spliceRegionExonSize $spliceRegion.spliceRegionExonSize #end if #if str($spliceRegion.spliceRegionIntronMin) -spliceRegionIntronMin $spliceRegion.spliceRegionIntronMin #end if #if str($spliceRegion.spliceRegionIntronMax) -spliceRegionIntronMax $spliceRegion.spliceRegionIntronMax #end if #end if #if $annotations and str($annotations) != '': #echo " " #echo ' '.join(str($annotations).split(',')) #end if #if $filterOut and str($filterOut) != '': #echo " " #echo ' '.join(str($filterOut).split(',')) #end if #if $filter.specificEffects == 'yes' and $filter.effects: #for $eff in str($filter.effects).split(','): -no $eff #end for #end if #if $transcripts -onlyTr '$transcripts' #end if #if $intervals ### fix this for multiple dataset input -interval '$intervals' #end if #if $statsFile: -stats '$statsFile' #end if #if str($offset) != 'default': ${offset} #end if #if str($chr).strip() != '': -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 $snpDb.reg_section.regulation and str($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 $snpDb.reg_section.regulation and str($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 '${snpDb.snpeff_db.metadata.genome_version}' #else -download '$snpDb.genome_version' #end if '$input' > '$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)#' #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' #end if ]]></command> <inputs> <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> <option value="bed">BED (Deprecated)</option> </param> <conditional name="outputConditional"> <param name="outputFormat" type="select" label="Output format"> <option value="vcf" selected="true">VCF (only if input is VCF)</option> <option value="gatk">GATK-compatible VCF (only if input is VCF)</option> <option value="bed">BED</option> <option value="bedAnn">BED annotations</option> </param> <when value="vcf" /> <when value="gatk"> <param name="gatk_v1" type="boolean" checked="true" label="Compatible with GATK 1.x" /> </when> <when value="bed" /> <when value="bedAnn" /> </conditional> <conditional name="snpDb"> <param name="genomeSrc" type="select" label="Genome source"> <option value="cached">Locally installed reference genome</option> <option value="history">Reference genome from your history</option> <option value="named">Named on demand</option> </param> <when value="cached"> <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" /> </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 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> </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)"> <help>@SNPEFF_DATABASE_URL@</help> <validator type="regex" message="A genome version name is required">\S+</validator> </param> </when> </conditional> <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"> <option value="1">1 base</option> <option value="2" selected="true">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> <conditional name="spliceRegion"> <param name="setSpliceRegions" type="select" label="spliceRegion Settings"> <option value="no">Use Defaults</option> <option value="yes">Set Splice Region Parameters</option> </param> <when value="no"/> <when value="yes"> <param name="spliceRegionExonSize" type="integer" value="" min="1" max="10" optional="true" label="Set size for splice site region within exons. Default: 3 bases"/> <param name="spliceRegionIntronMin" type="integer" value="" min="1" max="10" optional="true" label="Set minimum number of bases for splice site region within intron. Default: 3 bases"/> <param name="spliceRegionIntronMax" type="integer" value="" min="1" max="10" optional="true" label="Set maximum number of bases for splice site region within intron. Default: 8 bases"/> </when> </conditional> <param name="annotations" type="select" display="checkboxes" multiple="true" label="Annotation options"> <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="-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" 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> <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> <conditional name="filter"> <param name="specificEffects" type="select" label="Filter out specific Effects"> <option value="no">No</option> <option value="yes">Yes</option> </param> <when value="no"/> <when value="yes"> <param name="effects" type="select" display="checkboxes" multiple="true" label="Filter output: do not report these Effects"> <option value="CDS">CDS (coding_sequence_variant) The variant hits a CDS. MODIFIER</option> <option value="CHROMOSOME_LARGE_DELETION">CHROMOSOME_LARGE_DELETION (chromosome) A large parte (over 1%) of the chromosome was deleted. HIGH</option> <option value="CODON_CHANGE">CODON_CHANGE (coding_sequence_variant) One or many codons are changed e.g.: An MNP of size multiple of 3 MODERATE</option> <option value="CODON_INSERTION">CODON_INSERTION (inframe_insertion) One or many codons are inserted e.g.: An insert multiple of three in a codon boundary MODERATE</option> <option value="CODON_CHANGE_PLUS_CODON_INSERTION">CODON_CHANGE_PLUS_CODON_INSERTION (disruptive_inframe_insertion) One codon is changed and one or many codons are inserted e.g.: An insert of size multiple of three, not at codon boundary MODERATE</option> <option value="CODON_DELETION">CODON_DELETION (inframe_deletion) One or many codons are deleted e.g.: A deletion multiple of three at codon boundary MODERATE</option> <option value="CODON_CHANGE_PLUS_CODON_DELETION">CODON_CHANGE_PLUS_CODON_DELETION (disruptive_inframe_deletion) One codon is changed and one or more codons are deleted e.g.: A deletion of size multiple of three, not at codon boundary MODERATE</option> <option value="DOWNSTREAM">DOWNSTREAM (downstream_gene_variant) Downstream of a gene (default length: 5K bases) MODIFIER</option> <option value="EXON">EXON (exon_variant) The variant hits an exon (from a non-coding transcript) or a retained intron. MODIFIER</option> <option value="EXON_DELETED">EXON_DELETED (exon_loss_variant) A deletion removes the whole exon. HIGH</option> <option value="FRAME_SHIFT">FRAME_SHIFT (frameshift_variant) Insertion or deletion causes a frame shift e.g.: An indel size is not multple of 3 HIGH</option> <option value="GENE">GENE (gene_variant) The variant hits a gene. MODIFIER</option> <option value="INTERGENIC">INTERGENIC (intergenic_region) The variant is in an intergenic region MODIFIER</option> <option value="INTERGENIC_CONSERVED">INTERGENIC_CONSERVED (conserved_intergenic_variant) The variant is in a highly conserved intergenic region MODIFIER</option> <option value="INTRAGENIC">INTRAGENIC (intragenic_variant) The variant hits a gene, but no transcripts within the gene MODIFIER</option> <option value="INTRON">INTRON (intron_variant) Variant hits and intron. Technically, hits no exon in the transcript. MODIFIER</option> <option value="INTRON_CONSERVED">INTRON_CONSERVED (conserved_intron_variant) The variant is in a highly conserved intronic region MODIFIER</option> <option value="MICRO_RNA">MICRO_RNA (miRNA) Variant affects an miRNA MODIFIER</option> <option value="NON_SYNONYMOUS_CODING">NON_SYNONYMOUS_CODING (missense_variant) Variant causes a codon that produces a different amino acid e.g.: Tgg/Cgg, W/R MODERATE</option> <option value="NON_SYNONYMOUS_START">NON_SYNONYMOUS_START (initiator_codon_variant) Variant causes start codon to be mutated into another start codon (the new codon produces a different AA). e.g.: Atg/Ctg, M/L (ATG and CTG can be START codons) LOW</option> <option value="NON_SYNONYMOUS_STOP">NON_SYNONYMOUS_STOP (stop_retained_variant) Variant causes stop codon to be mutated into another stop codon (the new codon produces a different AA). e.g.: Atg/Ctg, M/L (ATG and CTG can be START codons) LOW</option> <option value="RARE_AMINO_ACID">RARE_AMINO_ACID (rare_amino_acid_variant) The variant hits a rare amino acid thus is likely to produce protein loss of function HIGH</option> <option value="SPLICE_SITE_ACCEPTOR">SPLICE_SITE_ACCEPTOR (splice_acceptor_variant) The variant hits a splice acceptor site (defined as two bases before exon start, except for the first exon). HIGH</option> <option value="SPLICE_SITE_DONOR">SPLICE_SITE_DONOR (splice_donor_variant) The variant hits a Splice donor site (defined as two bases after coding exon end, except for the last exon). HIGH</option> <option value="SPLICE_SITE_REGION">SPLICE_SITE_REGION (splice_region_variant) A sequence variant in which a change has occurred within the region of the splice site, either within 1-3 bases of the exon or 3-8 bases of the intron. LOW</option> <option value="SPLICE_SITE_BRANCH">SPLICE_SITE_BRANCH (splice_region_variant) A varaint affective putative (Lariat) branch point, located in the intron. LOW</option> <option value="SPLICE_SITE_BRANCH_U12">SPLICE_SITE_BRANCH_U12 (splice_region_variant) A varaint affective putative (Lariat) branch point from U12 splicing machinery, located in the intron. MODERATE</option> <option value="STOP_LOST">STOP_LOST (stop_lost) Variant causes stop codon to be mutated into a non-stop codon e.g.: Tga/Cga, */R HIGH</option> <option value="START_GAINED">START_GAINED (5_prime_UTR_premature start_codon_gain_variant) A variant in 5'UTR region produces a three base sequence that can be a START codon. LOW</option> <option value="START_LOST">START_LOST (start_lost) Variant causes start codon to be mutated into a non-start codon. e.g.: aTg/aGg, M/R HIGH</option> <option value="STOP_GAINED">STOP_GAINED (stop_gained) Variant causes a STOP codon e.g.: Cag/Tag, Q/* HIGH</option> <option value="SYNONYMOUS_CODING">SYNONYMOUS_CODING (synonymous_variant) Variant causes a codon that produces the same amino acid e.g.: Ttg/Ctg, L/L LOW</option> <option value="SYNONYMOUS_START">SYNONYMOUS_START (start_retained) Variant causes start codon to be mutated into another start codon. e.g.: Ttg/Ctg, L/L (TTG and CTG can be START codons) LOW</option> <option value="SYNONYMOUS_STOP">SYNONYMOUS_STOP (stop_retained_variant) Variant causes stop codon to be mutated into another stop codon. e.g.: taA/taG, */* LOW</option> <option value="TRANSCRIPT">TRANSCRIPT (transcript_variant) The variant hits a transcript. MODIFIER</option> <option value="REGULATION">REGULATION (regulatory_region_variant) The variant hits a known regulatory feature (non-coding). MODIFIER</option> <option value="UPSTREAM">UPSTREAM (upstream_gene_variant) Upstream of a gene (default length: 5K bases) MODIFIER</option> <option value="UTR_3_PRIME">UTR_3_PRIME (3_prime_UTR_variant) Variant hits 3'UTR region MODIFIER</option> <option value="UTR_3_DELETED">UTR_3_DELETED (3_prime_UTR_truncation + exon_loss) The variant deletes an exon which is in the 3'UTR of the transcript MODERATE</option> <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" 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> </param> <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 </help> <validator type="regex" message="No whitespace allowed">^\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="Suppress reporting usage statistics to server"/> </inputs> <outputs> <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 name="statsFile" format="html" label="${tool.name} on ${on_string} - stats"> <filter>generate_stats == True</filter> </data> </outputs> <tests> <test> <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> </tests> <help><![CDATA[ This tool calculate the effect of variants (SNPs/MNPs/Insertions) and deletions. @EXTERNAL_DOCUMENTATION@ ]]> </help> <expand macro="citations" /> </tool>