comparison snpSift_annotate.xml @ 0:e8adfc4c0a6b draft

Uploaded
author iuc
date Wed, 11 Dec 2013 08:53:32 -0500
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:e8adfc4c0a6b
1 <tool id="snpSift_annotate" name="SnpSift Annotate" version="3.4">
2 <description>SNPs from dbSnp</description>
3 <!--
4 You can change the amount of memory used, just change the -Xmx parameter (e.g. use -Xmx2G for 2Gb of memory)
5 -->
6 <expand macro="requirements" />
7 <macros>
8 <import>snpEff_macros.xml</import>
9 </macros>
10 <command>
11 java -Xmx6G -jar \$SNPEFF_JAR_PATH/SnpSift.jar $annotate_cmd
12 #if $annotate.id :
13 -id
14 #elif $annotate.info_ids.__str__.strip() != '' :
15 -info "$annotate.info_ids"
16 #end if
17 -q $dbSnp $input > $output
18 </command>
19 <inputs>
20 <param format="vcf" name="input" type="data" label="Variant input file in VCF format"/>
21 <param format="vcf" name="dbSnp" type="data" label="VCF File with ID field annotated (e.g. dnSNP.vcf)"
22 help="The ID field for a variant in input will be assigned from a matching variant in this file."/>
23 <conditional name="annotate">
24 <param name="id" type="boolean" truevalue="id" falsevalue="info" checked="True" label="Only annotate ID field (do not add INFO field)" help=""/>
25 <when value="id"/>
26 <when value="info">
27 <param name="info_ids" type="text" value="" size="60" optional="true" label="Limit INFO annotation to these INFO IDs"
28 help="list is a comma separated list of fields. When blank, all INFO fields are included">
29 <validator type="regex" message="IDs separted by commas">^(([a-zA-Z][a-zA-Z0-9_-]*)(,[a-zA-Z][a-zA-Z0-9_-]*)*)?$</validator>
30 </param>
31 </when>
32 </conditional>
33 <param name="annotate_cmd" type="boolean" truevalue="annMem" falsevalue="annotate" checked="false" label="Allow unsorted VCF files">
34 <help>
35 This option will load 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>
39 </inputs>
40 <expand macro="stdio" />
41 <outputs>
42 <data format="vcf" name="output" />
43 </outputs>
44 <tests>
45 <test>
46 <param name="input" ftype="vcf" value="annotate_1.vcf"/>
47 <param name="dbSnp" ftype="vcf" value="db_test_1.vcf"/>
48 <param name="annotate_cmd" value="False"/>
49 <param name="id" value="True"/>
50 <output name="output">
51 <assert_contents>
52 <has_text text="rs76166080" />
53 </assert_contents>
54 </output>
55 </test>
56 </tests>
57 <help>
58
59 This is typically used to annotate IDs from dbSnp.
60
61 Annotatating only the ID field from dbSnp137.vcf ::
62
63 Input VCF:
64 CHROM POS ID REF ALT QUAL FILTER INFO
65 22 16157571 . T G 0.0 FAIL NS=53
66 22 16346045 . T C 0.0 FAIL NS=244
67 22 16350245 . C A 0.0 FAIL NS=192
68
69 Annotated Output VCF:
70 #CHROM POS ID REF ALT QUAL FILTER INFO
71 22 16157571 . T G 0.0 FAIL NS=53
72 22 16346045 rs56234788 T C 0.0 FAIL NS=244
73 22 16350245 rs2905295 C A 0.0 FAIL NS=192
74
75
76
77 Annotatating both the ID and INFO fields from dbSnp137.vcf ::
78
79 Input VCF:
80 #CHROM POS ID REF ALT QUAL FILTER INFO
81 22 16157571 . T G 0.0 FAIL NS=53
82 22 16346045 . T C 0.0 FAIL NS=244
83 22 16350245 . C A 0.0 FAIL NS=192
84
85 Annotated Output VCF:
86 #CHROM POS ID REF ALT QUAL FILTER INFO
87 22 16157571 . T G 0.0 FAIL NS=53
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
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
90
91
92 @EXTERNAL_DOCUMENTATION@
93
94 @CITATION_SECTION@
95
96
97 </help>
98 </tool>
99