Mercurial > repos > jjohnson > snpeff
comparison snpSift_annotate.xml @ 7:0ad9733e22a4
Uploaded
| author | bgruening |
|---|---|
| date | Fri, 29 Nov 2013 09:27:22 -0500 |
| parents | 8952990fcab9 |
| children |
comparison
equal
deleted
inserted
replaced
| 6:eb394dd65c98 | 7:0ad9733e22a4 |
|---|---|
| 1 <tool id="snpSift_annotate" name="SnpSift Annotate" version="3.4"> | 1 <tool id="snpSift_annotate" name="SnpSift Annotate" version="3.4"> |
| 2 <description>Annotate SNPs from dbSnp</description> | 2 <description>SNPs from dbSnp</description> |
| 3 <!-- | 3 <!-- |
| 4 You will need to change the path to wherever your installation is. | 4 You can change the amount of memory used, just change the -Xmx parameter (e.g. use -Xmx2G for 2Gb of memory) |
| 5 You can change the amount of memory used, just change the -Xmx parameter (e.g. use -Xmx2G for 2Gb of memory) | 5 --> |
| 6 --> | 6 <expand macro="requirements" /> |
| 7 <requirements> | 7 <macros> |
| 8 <requirement type="package" version="3.4">snpEff</requirement> | 8 <import>snpEff_macros.xml</import> |
| 9 </requirements> | 9 </macros> |
| 10 <command> | 10 <command> |
| 11 java -Xmx6G -jar \$SNPEFF_JAR_PATH/SnpSift.jar $annotate_cmd | 11 java -Xmx6G -jar \$SNPEFF_JAR_PATH/SnpSift.jar $annotate_cmd |
| 12 #if $annotate.id : | 12 #if $annotate.id : |
| 13 -id | 13 -id |
| 14 #elif $annotate.info_ids.__str__.strip() != '' : | 14 #elif $annotate.info_ids.__str__.strip() != '' : |
| 15 -info "$annotate.info_ids" | 15 -info "$annotate.info_ids" |
| 16 #end if | 16 #end if |
| 17 -q $dbSnp $input > $output | 17 -q $dbSnp $input > $output |
| 18 </command> | 18 </command> |
| 19 <inputs> | 19 <inputs> |
| 20 <param format="vcf" name="input" type="data" label="VCF input"/> | 20 <param format="vcf" name="input" type="data" label="Variant input file in VCF format"/> |
| 21 <param format="vcf" name="dbSnp" type="data" label="VCF File with ID field annotated (e.g. dnSNP.vcf)" | 21 <param format="vcf" name="dbSnp" type="data" label="VCF File with ID field annotated (e.g. dnSNP.vcf)" |
| 22 help="The ID field for a variant in input will be assigned from a matching variant in this file."/> | 22 help="The ID field for a variant in input will be assigned from a matching variant in this file."/> |
| 23 <conditional name="annotate"> | 23 <conditional name="annotate"> |
| 24 <param name="id" type="boolean" truevalue="id" falsevalue="info" checked="True" label="Only annotate ID field (do not add INFO field)" help=""/> | 24 <param name="id" type="boolean" truevalue="id" falsevalue="info" checked="True" label="Only annotate ID field (do not add INFO field)" help=""/> |
| 25 <when value="id"/> | 25 <when value="id"/> |
| 26 <when value="info"> | 26 <when value="info"> |
| 27 <param name="info_ids" type="text" value="" size="60" optional="true" label="Limit INFO annotation to these INFO IDs" | 27 <param name="info_ids" type="text" value="" size="60" optional="true" label="Limit INFO annotation to these INFO IDs" |
| 28 help="list is a comma separated list of fields. When blank, all INFO fields are included"> | 28 help="list is a comma separated list of fields. When blank, all INFO fields are included"> |
| 29 <validator type="regex" message="IDs separted by commas">^(([a-zA-Z][a-zA-Z0-9_-]*)(,[a-zA-Z][a-zA-Z0-9_-]*)*)?$</validator> | 29 <validator type="regex" message="IDs separted by commas">^(([a-zA-Z][a-zA-Z0-9_-]*)(,[a-zA-Z][a-zA-Z0-9_-]*)*)?$</validator> |
| 30 </param> | |
| 31 </when> | |
| 32 </conditional> | |
| 33 <param name="annotate_cmd" type="boolean" truevalue="annMem" falsevalue="annotate" checked="false" label="Annotate in Memory"> | |
| 34 <help> | |
| 35 Allows unsorted VCF files, but it loads the entire 'database' VCF file into memory (which may not be practical for large 'database' VCF files). | |
| 36 Otherwise, both the database and the input VCF files should be sorted by position (Chromosome sort order can differ between files). | |
| 37 </help> | |
| 38 </param> | 30 </param> |
| 39 </inputs> | 31 </when> |
| 40 <stdio> | 32 </conditional> |
| 41 <exit_code range=":-1" level="fatal" description="Error: Cannot open file" /> | 33 <param name="annotate_cmd" type="boolean" truevalue="annMem" falsevalue="annotate" checked="false" label="Allow unsorted VCF files"> |
| 42 <exit_code range="1:" level="fatal" description="Error" /> | 34 <help> |
| 43 </stdio> | 35 This option will load the entire 'database' VCF file into memory (which may not be practical for large 'database' VCF files). |
| 44 | 36 Otherwise, both the database and the input VCF files should be sorted by position (Chromosome sort order can differ between files). |
| 45 <outputs> | 37 </help> |
| 46 <data format="vcf" name="output" /> | 38 </param> |
| 47 </outputs> | 39 </inputs> |
| 48 <tests> | 40 <expand macro="stdio" /> |
| 49 <test> | 41 <outputs> |
| 50 <param name="input" ftype="vcf" value="annotate_1.vcf"/> | 42 <data format="vcf" name="output" /> |
| 51 <param name="dbSnp" ftype="vcf" value="db_test_1.vcf"/> | 43 </outputs> |
| 52 <param name="annotate_cmd" value="False"/> | 44 <tests> |
| 53 <param name="id" value="True"/> | 45 <test> |
| 54 <output name="output"> | 46 <param name="input" ftype="vcf" value="annotate_1.vcf"/> |
| 55 <assert_contents> | 47 <param name="dbSnp" ftype="vcf" value="db_test_1.vcf"/> |
| 56 <has_text text="rs76166080" /> | 48 <param name="annotate_cmd" value="False"/> |
| 57 </assert_contents> | 49 <param name="id" value="True"/> |
| 58 </output> | 50 <output name="output"> |
| 59 </test> | 51 <assert_contents> |
| 60 </tests> | 52 <has_text text="rs76166080" /> |
| 61 <help> | 53 </assert_contents> |
| 54 </output> | |
| 55 </test> | |
| 56 </tests> | |
| 57 <help> | |
| 62 | 58 |
| 63 This is typically used to annotate IDs from dbSnp. | 59 This is typically used to annotate IDs from dbSnp. |
| 64 | |
| 65 For details about this tool, please go to http://snpeff.sourceforge.net/SnpSift.html#annotate | |
| 66 | 60 |
| 67 Annotatating only the ID field from dbSnp137.vcf :: | 61 Annotatating only the ID field from dbSnp137.vcf :: |
| 68 | 62 |
| 69 Input VCF: | 63 Input VCF: |
| 70 CHROM POS ID REF ALT QUAL FILTER INFO | 64 CHROM POS ID REF ALT QUAL FILTER INFO |
| 93 22 16157571 . T G 0.0 FAIL NS=53 | 87 22 16157571 . T G 0.0 FAIL NS=53 |
| 94 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 | 88 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 |
| 95 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 | 89 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 |
| 96 | 90 |
| 97 | 91 |
| 98 SnpEff citation: | 92 @EXTERNAL_DOCUMENTATION@ |
| 99 "A program for annotating and predicting the effects of single nucleotide polymorphisms, SnpEff: SNPs in the genome of Drosophila melanogaster strain w1118; iso-2; iso-3.", Cingolani P, Platts A, Wang le L, Coon M, Nguyen T, Wang L, Land SJ, Lu X, Ruden DM. Fly (Austin). 2012 Apr-Jun;6(2):80-92. PMID: 22728672 [PubMed - in process] | |
| 100 | 93 |
| 101 SnpSift citation: | 94 @CITATION_SECTION@ |
| 102 "Using Drosophila melanogaster as a model for genotoxic chemical mutational studies with a new program, SnpSift", Cingolani, P., et. al., Frontiers in Genetics, 3, 2012. | |
| 103 | 95 |
| 104 | 96 |
| 105 </help> | 97 </help> |
| 106 </tool> | 98 </tool> |
| 107 | 99 |
