kggseq_variant_selection: kggseq_variant

comparison kggseq_variant_selection.xml @ 1:e9758eee6697 draft

Update to KggSeq v0.7_20150118

author	crs4
date	Tue, 28 Apr 2015 04:42:14 -0400
parents	d388273fb83f
children	e1a21c2f4997

comparison

equal deleted inserted replaced

-:d388273fb83f
+:e9758eee6697
-<tool id="kggseq_variant_selection" name="Variant selection with KGGSeq" version="1.1">
+<tool id="kggseq_variant_selection" name="Variant selection with KGGSeq" version="1.2">
 <description></description>
 <requirements>
-<requirement type="package" version="0.4_20140910">kggseq</requirement>
+<requirement type="package" version="0.7_20150118">kggseq</requirement>
 </requirements>
 <command>
 java -jar \$KGGSEQ_JAR_PATH/kggseq.jar
 ## Environmental settings
 --buildver hg19
 --vcf-file $inputFile
 --ped-file $pedFile
 --db-gene $db_gene
 $composite_subject_id
-## Variant filters
+## Variant and genotype filters
 $pass_variant_only
-#if str($variant_filters.variant_filters_select) == "yes"
+#if str($variant_genotype_filters.variant_genotype_filters_select) == "yes"
---seq-qual $variant_filters.seq_qual
+--seq-qual $variant_genotype_filters.seq_qual
---seq-mq $variant_filters.seq_mq
+--seq-mq $variant_genotype_filters.seq_mq
---seq-sb $variant_filters.seq_sb
+--seq-sb $variant_genotype_filters.seq_sb
---seq-fs $variant_filters.seq_fs
+--seq-fs $variant_genotype_filters.seq_fs
---min-heta $variant_filters.min_heta
+--min-heta $variant_genotype_filters.min_heta
---min-homa $variant_filters.min_homa
+--min-homa $variant_genotype_filters.min_homa
---min-hetu $variant_filters.min_hetu
+--min-hetu $variant_genotype_filters.min_hetu
---min-homu $variant_filters.min_homu
+--min-homu $variant_genotype_filters.min_homu
---min-obsa $variant_filters.min_obsa
+--min-obsa $variant_genotype_filters.min_obsa
---min-obsu $variant_filters.min_obsu
+--min-obsu $variant_genotype_filters.min_obsu
---min-obs $variant_filters.min_obs
+--min-obs $variant_genotype_filters.min_obs
-#if str($variant_filters.hwe_control)
+#if str($variant_genotype_filters.hwe_control)
---hwe-control $variant_filters.hwe_control
+--hwe-control $variant_genotype_filters.hwe_control
 #end if
-#if str($variant_filters.hwe_case)
+#if str($variant_genotype_filters.hwe_case)
---hwe-case $variant_filters.hwe_case
+--hwe-case $variant_genotype_filters.hwe_case
 #end if
-#if str($variant_filters.hwe_all)
+#if str($variant_genotype_filters.hwe_all)
---hwe-all $variant_filters.hwe_all
+--hwe-all $variant_genotype_filters.hwe_all
 #end if
+--gty-qual $variant_genotype_filters.gty_qual
+--gty-dp $variant_genotype_filters.gty_dp
+--gty-sec-pl $variant_genotype_filters.gty_sec_pl
+--gty-af-ref $variant_genotype_filters.gty_af_ref
+--gty-af-het $variant_genotype_filters.gty_af_het
+--gty-af-alt $variant_genotype_filters.gty_af_alt
 #else
---seq-qual 0
+--no-qc
---seq-mq 0
-#end if
-## Genotype filters
-#if str($genotype_filters.genotype_filters_select) == "yes"
---gty-qual $genotype_filters.gty_qual
---gty-dp $genotype_filters.gty_dp
---gty-sec-pl $genotype_filters.gty_sec_pl
---gty-af-ref $genotype_filters.gty_af_ref
---gty-af-het $genotype_filters.gty_af_het
---gty-af-alt $genotype_filters.gty_af_alt
-#else
---gty-qual 0
---gty-dp 0
---gty-sec-pl 0
---gty-af-ref 1
---gty-af-het 0
---gty-af-alt 0
 #end if
 ## Genetic inheritance
 #if str($genetic_filters.genetic_filters_select) == "yes"
 #if str($genetic_filters.genetic_model.genetic_model_select) == "yes"
 #else
 $genetic_filters.genetic_model.suggested_genetic_params
 #end if
 #end if
+## Homozygosity - IBS - IBD filters
+#if str($hom_ibs_ibd_filters.hom_ibs_ibd_filters_select) == "yes"
+#if str($hom_ibs_ibd_filters.homozygosity_case_filter)
+--homozygosity-case-filter $hom_ibs_ibd_filters.homozygosity_case_filter
+#end if
+#if str($hom_ibs_ibd_filters.ibs_case_filter)
+--ibs-case-filter $hom_ibs_ibd_filters.ibs_case_filter
+#end if
+#if str($hom_ibs_ibd_filters.ibd_annot) != 'None'
+--ibd-annot $hom_ibs_ibd_filters.ibd_annot
+#end if
+#end if
 ## Gene feature filters
 #if str($gene_feature_filters.gene_feature_filters_select) == "yes" and $gene_feature_filters.gene_features
 --gene-feature-in $gene_feature_filters.gene_features
 --splicing $gene_feature_filters.splicing
 --neargene $gene_feature_filters.neargene
 $impact_filters.mendel_causing
 #end if
 ## Add annotations
 #if str($add_annotations.add_annotations_select) == "yes"
+#if str($add_annotations.o_flanking_seq)
+--o-flanking-seq $add_annotations.o_flanking_seq
+#end if
 $add_annotations.genome_annotation
 $add_annotations.omim_annotation
 $add_annotations.cosmic_annotation
 #if $add_annotations.pubmed_mining_gene
 $add_annotations.pubmed_type "$add_annotations.pubmed_mining_gene"
 &gt; $logFile
 </command>
 <inputs>
 <param name="inputFile" type="data" format="vcf" label="VCF Variant file (--vcf-file)" help="Coordinates must refer to hg19" />
 <param name="pedFile" type="data" format="tabular" label="Pedigree (--ped-file)" />
+<param name="composite_subject_id" type="boolean" truevalue="--composite-subject-id" falsevalue="" checked="false" label="Composite subject ID (--composite-subject-id)" />
 <param name="db_gene" type="select" display="checkboxes" multiple="true" label="Database(s) to annotate and filter variants (--db-gene)">
 <option value="refgene" selected="true">refgene: The RefGene database compiled by UCSC from hg19 refGene. Note: RefSeq has NO mitochondria gene definition</option>
-<option value="gencode">gencode: The GENCODE gene sets. Note: GECODE contains similar number of coding genes but more transcripts than RefGene. It HAS the mitochondria gene definition</option>
+<option value="gencode">gencode: The GENCODE gene sets. Note: GENCODE contains similar number of coding genes but more transcripts than RefGene. It HAS the mitochondria gene definition</option>
 <option value="knowngene">knowngene: The UCSC knonwGene datasase compiled by UCSC from hg19 knownGene</option>
+<option value="ensembl">ensembl: The Ensembl gene datasase compiled by UCSC from hg19 ensGene</option>
 <validator type="no_options" message="Select at least one database" />
 </param>
-<param name="composite_subject_id" type="boolean" truevalue="--composite-subject-id" falsevalue="" checked="false" label="Composite subject ID (--composite-subject-id)" />
 <param name="pass_variant_only" type="boolean" truevalue="--vcf-filter-in PASS" falsevalue="" checked="true" label="Don't include filtered loci (--vcf-filter-in PASS)" help="Keep only variants with FILTER equal to PASS" />
-<!-- Variant quality control -->
+<!-- Variant and genotype quality control -->
-<conditional name="variant_filters">
+<conditional name="variant_genotype_filters">
-<param name="variant_filters_select" type="select" label="Specify variant quality filters?">
+<param name="variant_genotype_filters_select" type="select" label="Specify variant and genotype quality filters?">
 <option value="yes">Yes</option>
 <option value="no" selected="true">No</option>
 </param>
 <when value="yes">
 <param name="seq_qual" type="integer" value="50" label="Minimum overall Phred-scaled sequencing quality score for the variant (--seq-qual)" />
 <param name="seq_mq" type="integer" value="20" label="Minimum overall Phred-scaled mapping quality score for the variant (--seq-mq)" />
 <param name="seq_sb" type="float" value="-10" label="Maximal overall strand bias score for the variant (--seq-sb)" />
 <param name="seq_fs" type="integer" value="60" label="Maximal overall strand bias Phred-scaled p-value (using Fisher's exact test) for the variant (--seq-fs)" />
-<param name="min_heta" type="integer" value="1" label="Minimal observed number of heterozygote genotypes in cases (the affected) (--min-heta)" />
+<param name="min_heta" type="integer" value="0" label="Minimal observed number of heterozygote genotypes in cases (the affected) (--min-heta)" />
-<param name="min_homa" type="integer" value="1" label="Minimal observed number of alternate homozygote genotypes in cases (the affected) (--min-homa)" />
+<param name="min_homa" type="integer" value="0" label="Minimal observed number of alternate homozygote genotypes in cases (the affected) (--min-homa)" />
-<param name="min_hetu" type="integer" value="1" label="Minimal observed number of heterozygote genotypes in controls (the unaffected) (--min-hetu)" />
+<param name="min_hetu" type="integer" value="0" label="Minimal observed number of heterozygote genotypes in controls (the unaffected) (--min-hetu)" />
-<param name="min_homu" type="integer" value="1" label="Minimal observed number of alternate homozygote genotypes in controls (the unaffected) (--min-homu)" />
+<param name="min_homu" type="integer" value="0" label="Minimal observed number of alternate homozygote genotypes in controls (the unaffected) (--min-homu)" />
-<param name="min_obsa" type="integer" value="1" label="Minimal observed number of non-missing genotypes in cases (the affected) (--min-obsa)" />
+<param name="min_obsa" type="integer" value="0" label="Minimal observed number of non-missing genotypes in cases (the affected) (--min-obsa)" />
-<param name="min_obsu" type="integer" value="1" label="Minimal observed number of non-missing genotypes in controls (the unaffected) (--min-obsu)" />
+<param name="min_obsu" type="integer" value="0" label="Minimal observed number of non-missing genotypes in controls (the unaffected) (--min-obsu)" />
-<param name="min_obs" type="integer" value="2" label="Minimal observed number of non-missing genotypes in all samples (--min-obs)" />
+<param name="min_obs" type="integer" value="1" label="Minimal observed number of non-missing genotypes in all samples (--min-obs)" />
 <param name="hwe_control" type="float" value="" optional="true" label="Exclude variants in controls with the Hardy-Weinberg test p-value &lt;= this value (--hwe-control)" />
 <param name="hwe_case" type="float" value="" optional="true" label="Exclude variants in cases with the Hardy-Weinberg test p-value &lt;= this value (--hwe-case)" />
 <param name="hwe_all" type="float" value="" optional="true" label="Exclude variants in all subjects with the Hardy-Weinberg test p-value &lt;= this value (--hwe-all)" />
-</when>
-<when value="no" />
-</conditional>
-<!-- Genotype quality control -->
-<conditional name="genotype_filters">
-<param name="genotype_filters_select" type="select" label="Specify genotype quality filters?">
-<option value="yes">Yes</option>
-<option value="no" selected="true">No</option>
-</param>
-<when value="yes">
 <param name="gty_qual" type="integer" value="10" label="Minimum Phred-scaled genotyping quality (--gty-qual)" />
 <param name="gty_dp" type="integer" value="4" label="Minimal read depth per genotype (--gty-dp)" />
 <param name="gty_sec_pl" type="integer" value="20" label="Minimal value for second smallest normalized Phred-scaled genotype quality (--gty-sec-pl)" />
 <param name="gty_af_ref" type="float" value="0.05" label="Maximal fraction of reads carrying alternative allele at a reference allele homozygous genotype (--gty-af-ref)" />
 <param name="gty_af_het" type="float" value="0.25" label="Minimal fraction of reads carrying alternative allele at a heterozygous genotype (--gty-af-het)" />
 </conditional>
 </when>
 <when value="no" />
 </conditional>
+<!-- Homozygosity filtering -->
+<conditional name="hom_ibs_ibd_filters">
+<param name="hom_ibs_ibd_filters_select" type="select" label="Specify homozygosity filters?">
+<option value="yes">Yes</option>
+<option value="no" selected="true">No</option>
+</param>
+<when value="yes">
+<param name="homozygosity_case_filter" type="integer" value="" optional="true" label="Filter by Runs of Homozygosity (ROH) (--homozygosity-case-filter)" help="Minimal length (in kb) of consecutive homozygous genotype for each interesting variant" />
+<param name="ibs_case_filter" type="integer" value="" optional="true" label="Filter by Identical by State (IBS) (--ibs-case-filter)" help="Minimal length (in kb) of the region in which there is at least one allele identical among all cases" />
+<param name="ibd_annot" type="data" format="txt,tabular,bed" optional="true" label="Add Identical by Descent (IBD) annotation (--ibd-annot)" help="File with IBD or significant linkage regions. Variants within these regions will be highlighted. Note: title line CHR START END is needed" />
+</when>
+<when value="no" />
+</conditional>
 <!-- Gene feature filtering -->
 <conditional name="gene_feature_filters">
 <param name="gene_feature_filters_select" type="select" label="Specify gene feature filters?">
 <option value="yes">Yes</option>
 <option value="no" selected="true">No</option>
 <option value="10">Intronic</option>
 <option value="11">Upstream of transcription start site</option>
 <option value="12">Downstream of transcription end site</option>
 <option value="13">ncRNA</option>
 <option value="14">Intergenic</option>
-<option value="15">Unknown</option>
+<option value="15">Monomorphic</option>
+<option value="16">Unknown</option>
 </param>
 <param name="splicing" type="integer" value="2" label="Window size in base-pair around the splicing junction to flag the variant as splicing (--splicing)" />
-<param name="neargene" type="integer" value="1000" label="Size of region upstream and downstream (--neargene)" />
+<param name="neargene" type="integer" value="1000" label="Size in base-pair of region upstream and downstream (--neargene)" />
 </when>
 <when value="no" />
 </conditional>
 <!-- Allele frequency filtering -->
 <conditional name="allele_freq_filters">
-<param name="allele_freq_filters_select" type="select" label="Specify common variants filters?">
+<param name="allele_freq_filters_select" type="select" label="Specify filters by allele frequency?">
 <option value="yes">Yes</option>
 <option value="no" selected="true">No</option>
 </param>
 <when value="yes">
 <param name="allele_freq_db" type="select" display="checkboxes" multiple="true" label="Select databases for allelic frequency filtering (--db-filter)">
-<option value="hg19_1kg201305" selected="true">hg19_1kg201305: 1000 Genomes Project 2013 May release</option>
+<option value="1kg201305" selected="true">1KG 201305: 1000 Genomes Project 2013 May release</option>
-<option value="hg19_1kg201204">hg19_1kg201204: 1000 Genomes Project 2012 April release</option>
+<option value="1kg201204">1KG 201204: 1000 Genomes Project 2012 April release</option>
-<option value="hg19_ESP6500AA" selected="true">hg19_ESP6500AA: African American dataset from NHLBI GO Exome Sequencing Project (ESP6500)</option>
+<option value="1kgafr201204">1KG 201204 AFR: 1000 Genomes Project 2012 April release - African</option>
-<option value="hg19_ESP6500EA" selected="true">hg19_ESP6500EA: European American dataset from NHLBI GO Exome Sequencing Project (ESP6500)</option>
+<option value="1kgeur201204">1KG 201204 EUR: 1000 Genomes Project 2012 April release - European</option>
-<option value="hg19_dbsnp141" selected="true">hg19_dbsnp141: dbSNP version 141</option>
+<option value="1kgamr201204">1KG 201204 AMR: 1000 Genomes Project 2012 April release - Mixed American</option>
-<option value="hg19_dbsnp138">hg19_dbsnp138: dbSNP version 138</option>
+<option value="1kgasn201204">1KG 201204 ASN: 1000 Genomes Project 2012 April release - Asian</option>
-<option value="hg19_dbsnp137">hg19_dbsnp137: dbSNP version 137</option>
+<option value="ESP6500AA" selected="true">ESP6500AA: African American dataset from NHLBI GO Exome Sequencing Project (ESP6500)</option>
+<option value="ESP6500EA" selected="true">ESP6500EA: European American dataset from NHLBI GO Exome Sequencing Project (ESP6500)</option>
+<option value="dbsnp141" selected="true">dnSNP 141</option>
+<option value="dbsnp138">dbSNP 138</option>
+<option value="dbsnp138nf">dbSNP 138nf: dbSNP version 138 without the flagged SNPs by UCSC. Flagged SNPs include SNPs clinically associated by dbSNP, mapped to a single location in the reference genome assembly, and not known to have a minor allele frequency of at least 1%</option>
+<option value="dbsnp137">dbSNP 137</option>
+<option value="dbsnp135">dbSNP 135</option>
+<option value="exac">Exome Aggregation Consortium (ExAC): Variants from 61,486 unrelated individuals sequenced as part of various disease-specific and population genetic studies</option>
 </param>
 <param name="rare_allele_freq" type="float" value="0.01" label="Minor allele frequency (MAF) for selecting rare variants (--rare-allele-freq)" help="Set to &gt;1 to only annotate MAF, without filtering" />
 </when>
 <when value="no" />
 </conditional>
 <param name="impact_filters_select" type="select" label="Specify functional impact filters?">
 <option value="yes">Yes</option>
 <option value="no" selected="true">No</option>
 </param>
 <when value="yes">
-<param name="filter_nondisease_variant" type="boolean" truevalue="--filter-nondisease-variant" falsevalue="" checked="true" label="Filter out variants predicted to be non-disease causal (--filter-nondisease-variant)" />
+<param name="filter_nondisease_variant" type="boolean" truevalue="--filter-nondisease-variant" falsevalue="" checked="false" label="Filter out variants predicted to be non-disease causal (--filter-nondisease-variant)" />
 <param name="mendel_causing" type="boolean" truevalue="--mendel-causing-predict all" falsevalue="" checked="true" label="Predict Mendelian disease-causing variants by logistic regression model (--mendel-causing-predict)" />
 </when>
 <when value="no" />
 </conditional>
 <param name="add_annotations_select" type="select" label="Add annotations?">
 <option value="yes">Yes</option>
 <option value="no" selected="true">No</option>
 </param>
 <when value="yes">
+<param name="o_flanking_seq" type="integer" value="" label="Size in bp of flanking sequence to extract (--o-flanking-seq)" />
 <param name="genome_annotation" type="boolean" truevalue="--genome-annot" falsevalue="" checked="true" label="Add genomic functional annotations (presudogenes, TFBS, enhancer, UniProt) (--genome-annot)" />
 <param name="omim_annotation" type="boolean" truevalue="--omim-annot" falsevalue="" checked="true" label="Add OMIM annotation (--omim-annot)" />
 <param name="cosmic_annotation" type="boolean" truevalue="--cosmic-annot" falsevalue="" checked="true" label="Add COSMIC annotation (--cosmic-annot)" />
-<param name="pubmed_type" type="select" label="Text mining in PubMed: find co-mentions of the search terms specified below with:">
+<param name="pubmed_type" type="select" label="Text mining in PubMed: find co-mentions of the search terms specified below with">
 <option value="--pubmed-mining">The cytogenetic position of each variant (--pubmed-mining)</option>
 <option value="--pubmed-mining-gene">The gene in which each variant is located (--pubmed-mining-gene)</option>
 </param>
 <param name="pubmed_mining_gene" type="text" label="Text mining in PubMed: search term(s) of interest (e.g. disease name)" help="A comma-separated list of search terms, each composed by plus-separated words, e.g. spinocerebellar+ataxia,other+search+term. If empty, no search will be performed" />
 <!-- Shared protein-protein interactions and pathways -->

Mercurial > repos > crs4 > kggseq_variant_selection

comparison kggseq_variant_selection.xml @ 1:e9758eee6697 draft