Mercurial > repos > iuc > snpeff

comparison snpSift_filter.xml @ 0:e8adfc4c0a6b draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
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_filter" name="SnpSift Filter" version="3.4">
2 <options sanitize="False" />
3 <description>Filter variants using arbitrary expressions</description>
4 <expand macro="requirements" />
5 <macros>
6 <import>snpEff_macros.xml</import>
7 </macros>
8 <command>
9 java -Xmx6G -jar \$SNPEFF_JAR_PATH/SnpSift.jar filter -f $input -e $exprFile $inverse
10 #if $filtering.mode == 'field':
11 #if $filtering.replace.pass:
12 --pass
13 #if $filtering.replace.filterId and len($filtering.replace.filterId.__str__.strip()) > 0:
14 --filterId "$filtering.replace.filterId"
15 #end if
16 #end if
17 #if $filtering.addFilter and len($filtering.addFilter.__str__.strip()) > 0:
18 --addFilter "$filtering.addFilter"
19 #end if
20 #if $filtering.rmFilter and len($filtering.rmFilter.__str__.strip()) > 0:
21 --rmFilter "$filtering.rmFilter"
22 #end if
23 #end if
24 > $output
25 </command>
26 <inputs>
27 <param format="vcf" name="input" type="data" label="Variant input file in VCF format"/>
28 <param name="expr" type="text" label="Filter criteria" size="160" help="Need help? See below a few examples." />
29 <param name="inverse" type="boolean" truevalue="--inverse" falsevalue="" checked="false" label="Inverse filter" help="Show lines that do not match filter expression" />
30 <conditional name="filtering">
31 <param name="mode" type="select" label="Filter mode">
32 <option value="entries" selected="true">Retain entries that pass filter, remove other entries</option>
33 <option value="field">Change the FILTER field, but retain all entries</option>
34 </param>
35 <when value="entries"/>
36 <when value="field">
37 <conditional name="replace">
38 <param name="pass" type="boolean" truevalue="yes" falsevalue="no" checked="false" label="Set matching entry FILTER to 'PASS'"
39 help="appends an ID tag to non-matching entry FILTER "/>
40 <when value="no"/>
41 <when value="yes">
42 <param name="filterId" type="text" value="" optional="true" label="ID appended to non-matching (##FILTER tag in header and FILTER VCF field)." size="10"
43 help="Default ID is 'SnpSift'"/>
44 </when>
45 </conditional>
46 <param name="addFilter" type="text" value="" optional="true" label="Add a string to FILTER VCF field if 'expression' is true." size="10"/>
47 <param name="rmFilter" type="text" value="" optional="true" label="Remove a string from FILTER VCF field if 'expression' is true (and 'str' is in the field)." size="10"/>
48 </when>
49 </conditional>
50 </inputs>
51 <configfiles>
52 <configfile name="exprFile">
53 $expr
54 </configfile>
55 </configfiles>
56
57 <outputs>
58 <data format="vcf" name="output" />
59 </outputs>
60 <expand macro="stdio" />
61 <tests>
62 <test>
63 <param name="input" ftype="vcf" value="test01.vcf"/>
64 <param name="expr" value="QUAL >= 50"/>
65 <param name="mode" value="entries"/>
66 <output name="output">
67 <assert_contents>
68 <has_text text="28837706" />
69 <not_has_text text="NT_166464" />
70 </assert_contents>
71 </output>
72 </test>
73
74 <test>
75 <param name="input" ftype="vcf" value="test01.vcf"/>
76 <param name="expr" value="(CHROM = '19')"/>
77 <param name="mode" value="entries"/>
78 <output name="output">
79 <assert_contents>
80 <has_text text="3205820" />
81 <not_has_text text="NT_16" />
82 </assert_contents>
83 </output>
84 </test>
85
86 <test>
87 <param name="input" ftype="vcf" value="test01.vcf"/>
88 <param name="expr" value="(POS >= 20175) &amp; (POS &lt;= 35549)"/>
89 <param name="mode" value="entries"/>
90 <output name="output">
91 <assert_contents>
92 <has_text text="20175" />
93 <has_text text="35549" />
94 <has_text text="22256" />
95 <not_has_text text="18933" />
96 <not_has_text text="37567" />
97 </assert_contents>
98 </output>
99 </test>
100
101 <test>
102 <param name="input" ftype="vcf" value="test01.vcf"/>
103 <param name="expr" value="( DP >= 5 )"/>
104 <param name="mode" value="entries"/>
105 <output name="output">
106 <assert_contents>
107 <has_text text="DP=5;" />
108 <has_text text="DP=6;" />
109 <not_has_text text="DP=1;" />
110 </assert_contents>
111 </output>
112 </test>
113 </tests>
114 <help>
115
116 **SnpSift filter**
117
118 You can filter ia vcf file using arbitrary expressions, for instance "(QUAL > 30) | (exists INDEL) | ( countHet() > 2 )". The actual expressions can be quite complex, so it allows for a lot of flexibility.
119
120 Some examples:
121
122 - *I want to filter out samples with quality less than 30*:
123
124 * **( QUAL &gt; 30 )**
125
126 - *...but we also want InDels that have quality 20 or more*:
127
128 * **(( exists INDEL ) &amp; (QUAL >= 20)) | (QUAL >= 30 )**
129
130 - *...or any homozygous variant present in more than 3 samples*:
131
132 * **(countHom() > 3) | (( exists INDEL ) &amp; (QUAL >= 20)) | (QUAL >= 30 )**
133
134 - *...or any heterozygous sample with coverage 25 or more*:
135
136 * **((countHet() > 0) &amp; (DP >= 25)) | (countHom() > 3) | (( exists INDEL ) &amp; (QUAL >= 20)) | (QUAL >= 30 )**
137
138 - *I want to keep samples where the genotype for the first sample is homozygous variant and the genotype for the second sample is reference*:
139
140 * **isHom( GEN[0] ) &amp; isVariant( GEN[0] ) &amp; isRef( GEN[1] )**
141
142
143 @EXTERNAL_DOCUMENTATION@
144
145 @CITATION_SECTION@
146
147 </help>
148 </tool>