Mercurial > repos > jjohnson > snpsift
diff snpSift_annotate.xml @ 0:1ae5526db990
Uploaded
author | jjohnson |
---|---|
date | Thu, 26 Jun 2014 09:22:13 -0400 |
parents | |
children | 796388c291d3 |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/snpSift_annotate.xml Thu Jun 26 09:22:13 2014 -0400 @@ -0,0 +1,100 @@ +<tool id="snpSift_annotate" name="SnpSift Annotate" version="3.6"> + <description>SNPs from dbSnp</description> + <!-- + You can change the amount of memory used, just change the -Xmx parameter (e.g. use -Xmx2G for 2Gb of memory) + --> + <expand macro="requirements" /> + <macros> + <import>snpEff_macros.xml</import> + </macros> + <command> + java -Xmx6G -jar \$SNPEFF_JAR_PATH/SnpSift.jar $annotate_cmd + #if $annotate.id : + -id + #elif $annotate.info_ids.__str__.strip() != '' : + -info "$annotate.info_ids" + #end if + -q $dbSnp $input > $output + </command> + <inputs> + <param format="vcf" name="input" type="data" label="Variant input file in VCF format"/> + <param format="vcf" name="dbSnp" type="data" label="VCF File with ID field annotated (e.g. dnSNP.vcf)" + help="The ID field for a variant in input will be assigned from a matching variant in this file."/> + <conditional name="annotate"> + <param name="id" type="boolean" truevalue="id" falsevalue="info" checked="True" label="Only annotate ID field (do not add INFO field)" help=""/> + <when value="id"/> + <when value="info"> + <param name="info_ids" type="text" value="" size="60" optional="true" label="Limit INFO annotation to these INFO IDs" + help="list is a comma separated list of fields. When blank, all INFO fields are included"> + <validator type="regex" message="IDs separted by commas">^(([a-zA-Z][a-zA-Z0-9_-]*)(,[a-zA-Z][a-zA-Z0-9_-]*)*)?$</validator> + </param> + </when> + </conditional> + <param name="annotate_cmd" type="boolean" truevalue="annMem" falsevalue="annotate" checked="false" label="Allow unsorted VCF files"> + <help> + This option will load the entire 'database' VCF file into memory (which may not be practical for large 'database' VCF files). + Otherwise, both the database and the input VCF files should be sorted by position (Chromosome sort order can differ between files). + </help> + </param> + </inputs> + <expand macro="stdio" /> + <outputs> + <data format="vcf" name="output" /> + </outputs> + <tests> + <test> + <param name="input" ftype="vcf" value="annotate_1.vcf"/> + <param name="dbSnp" ftype="vcf" value="db_test_1.vcf"/> + <param name="annotate_cmd" value="False"/> + <param name="id" value="True"/> + <output name="output"> + <assert_contents> + <has_text text="rs76166080" /> + </assert_contents> + </output> + </test> + </tests> + <help> + +This is typically used to annotate IDs from dbSnp. + +Annotatating only the ID field from dbSnp137.vcf :: + + Input VCF: + CHROM POS ID REF ALT QUAL FILTER INFO + 22 16157571 . T G 0.0 FAIL NS=53 + 22 16346045 . T C 0.0 FAIL NS=244 + 22 16350245 . C A 0.0 FAIL NS=192 + + Annotated Output VCF: + #CHROM POS ID REF ALT QUAL FILTER INFO + 22 16157571 . T G 0.0 FAIL NS=53 + 22 16346045 rs56234788 T C 0.0 FAIL NS=244 + 22 16350245 rs2905295 C A 0.0 FAIL NS=192 + + + +Annotatating both the ID and INFO fields from dbSnp137.vcf :: + + Input VCF: + #CHROM POS ID REF ALT QUAL FILTER INFO + 22 16157571 . T G 0.0 FAIL NS=53 + 22 16346045 . T C 0.0 FAIL NS=244 + 22 16350245 . C A 0.0 FAIL NS=192 + + Annotated Output VCF: + #CHROM POS ID REF ALT QUAL FILTER INFO + 22 16157571 . T G 0.0 FAIL NS=53 + 22 16346045 rs56234788 T C 0.0 FAIL NS=244;RSPOS=16346045;GMAF=0.162248628884826;dbSNPBuildID=129;SSR=0;SAO=0;VP=050100000000000100000100;WGT=0;VC=SNV;SLO;GNO + 22 16350245 rs2905295 C A 0.0 FAIL NS=192;RSPOS=16350245;GMAF=0.230804387568556;dbSNPBuildID=101;SSR=1;SAO=0;VP=050000000000000100000140;WGT=0;VC=SNV;GNO + + +@EXTERNAL_DOCUMENTATION@ + http://snpeff.sourceforge.net/SnpSift.html#annotate + +@CITATION_SECTION@ + + + </help> +</tool> +