Mercurial > repos > iuc > snpsift

comparison snpSift_filter.xml @ 1:98708b88af9f draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tool_collections/snpsift/snpsift commit 21b46ae2c90ba7e569b2b3a9eaf938f8dedb2c31
author iuc
date Tue, 07 Jun 2016 10:04:09 -0400
parents 9e8280e19338
children bf8c1526871b
comparison
equal deleted inserted replaced
0:9e8280e19338 1:98708b88af9f
1 <tool id="snpSift_filter" name="SnpSift Filter" version="4.0.0"> 1 <tool id="snpSift_filter" name="SnpSift Filter" version="@WRAPPER_VERSION@.0">
2 <options sanitize="False" />
3 <description>Filter variants using arbitrary expressions</description> 2 <description>Filter variants using arbitrary expressions</description>
4 <expand macro="requirements" />
5 <macros> 3 <macros>
6 <import>snpSift_macros.xml</import> 4 <import>snpSift_macros.xml</import>
7 </macros> 5 </macros>
8 <command> 6 <expand macro="requirements" />
9 java -Xmx6G -jar \$SNPEFF_JAR_PATH/SnpSift.jar filter -f $input -e $exprFile $inverse 7 <expand macro="stdio" />
8 <expand macro="version_command" />
9
10 <command><![CDATA[
11 java -Xmx6G -jar "\$SNPEFF_JAR_PATH/SnpSift.jar" filter -f "$input" -e "$exprFile" $inverse
10 #if $filtering.mode == 'field': 12 #if $filtering.mode == 'field':
11 #if $filtering.replace.pass: 13 #if $filtering.replace.pass:
12 --pass 14 --pass
13 #if $filtering.replace.filterId and len($filtering.replace.filterId.__str__.strip()) > 0: 15 #if $filtering.replace.filterId and len(str($filtering.replace.filterId).strip()) > 0:
14 --filterId "$filtering.replace.filterId" 16 --filterId "$filtering.replace.filterId"
15 #end if 17 #end if
16 #end if 18 #end if
17 #if $filtering.addFilter and len($filtering.addFilter.__str__.strip()) > 0: 19 #if $filtering.addFilter and len(str($filtering.addFilter).strip()) > 0:
18 --addFilter "$filtering.addFilter" 20 --addFilter "$filtering.addFilter"
19 #end if 21 #end if
20 #if $filtering.rmFilter and len($filtering.rmFilter.__str__.strip()) > 0: 22 #if $filtering.rmFilter and len(str($filtering.rmFilter).strip()) > 0:
21 --rmFilter "$filtering.rmFilter" 23 --rmFilter "$filtering.rmFilter"
22 #end if 24 #end if
23 #end if 25 #end if
24 > $output 26 > "$output"
27 ]]>
25 </command> 28 </command>
29 <configfiles>
30 <configfile name="exprFile">
31 $expr#slurp
32 </configfile>
33 </configfiles>
26 <inputs> 34 <inputs>
27 <param format="vcf" name="input" type="data" label="Variant input file in VCF format"/> 35 <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." /> 36 <param name="expr" type="text" label="Filter criteria" help="Need help? See below a few examples." >
37 <sanitizer sanitize="False"/>
38 </param>
29 <param name="inverse" type="boolean" truevalue="--inverse" falsevalue="" checked="false" label="Inverse filter" help="Show lines that do not match filter expression" /> 39 <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"> 40 <conditional name="filtering">
31 <param name="mode" type="select" label="Filter mode"> 41 <param name="mode" type="select" label="Filter mode">
32 <option value="entries" selected="true">Retain entries that pass filter, remove other entries</option> 42 <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> 43 <option value="field">Change the FILTER field, but retain all entries</option>
37 <conditional name="replace"> 47 <conditional name="replace">
38 <param name="pass" type="boolean" truevalue="yes" falsevalue="no" checked="false" label="Set matching entry FILTER to 'PASS'" 48 <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 "/> 49 help="appends an ID tag to non-matching entry FILTER "/>
40 <when value="no"/> 50 <when value="no"/>
41 <when value="yes"> 51 <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" 52 <param name="filterId" type="text" value="" optional="true" label="ID appended to non-matching (##FILTER tag in header and FILTER VCF field)."
43 help="Default ID is 'SnpSift'"/> 53 help="Default ID is 'SnpSift'"/>
44 </when> 54 </when>
45 </conditional> 55 </conditional>
46 <param name="addFilter" type="text" value="" optional="true" label="Add a string to FILTER VCF field if 'expression' is true." size="10"/> 56 <param name="addFilter" type="text" value="" optional="true" label="Add a string to FILTER VCF field if 'expression' is true." />
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"/> 57 <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)." />
48 </when> 58 </when>
49 </conditional> 59 </conditional>
50 </inputs> 60 </inputs>
51 <configfiles>
52 <configfile name="exprFile">
53 $expr#slurp
54 </configfile>
55 </configfiles>
56 61
57 <outputs> 62 <outputs>
58 <data format="vcf" name="output" /> 63 <data format="vcf" name="output" />
59 </outputs> 64 </outputs>
60 <expand macro="stdio" />
61 <tests> 65 <tests>
62 <test> 66 <test>
63 <param name="input" ftype="vcf" value="test01.vcf"/> 67 <param name="input" ftype="vcf" value="test01.vcf"/>
64 <param name="expr" value="QUAL >= 50"/> 68 <param name="expr" value="QUAL >= 50"/>
65 <param name="mode" value="entries"/> 69 <param name="mode" value="entries"/>
83 </output> 87 </output>
84 </test> 88 </test>
85 89
86 <test> 90 <test>
87 <param name="input" ftype="vcf" value="test01.vcf"/> 91 <param name="input" ftype="vcf" value="test01.vcf"/>
88 <param name="expr" value="(POS >= 20175) &amp; (POS &lt;= 35549)"/> 92 <param name="expr" value="(POS &gt;= 20175) &amp; (POS &lt;= 35549)"/>
89 <param name="mode" value="entries"/> 93 <param name="mode" value="entries"/>
90 <output name="output"> 94 <output name="output">
91 <assert_contents> 95 <assert_contents>
92 <has_text text="20175" /> 96 <has_text text="20175" />
93 <has_text text="35549" /> 97 <has_text text="35549" />
98 </output> 102 </output>
99 </test> 103 </test>
100 104
101 <test> 105 <test>
102 <param name="input" ftype="vcf" value="test01.vcf"/> 106 <param name="input" ftype="vcf" value="test01.vcf"/>
103 <param name="expr" value="( DP >= 5 )"/> 107 <param name="expr" value="( DP &gt;= 5 )"/>
104 <param name="mode" value="entries"/> 108 <param name="mode" value="entries"/>
105 <output name="output"> 109 <output name="output">
106 <assert_contents> 110 <assert_contents>
107 <has_text text="DP=5;" /> 111 <has_text text="DP=5;" />
108 <has_text text="DP=6;" /> 112 <has_text text="DP=6;" />
109 <not_has_text text="DP=1;" /> 113 <not_has_text text="DP=1;" />
110 </assert_contents> 114 </assert_contents>
111 </output> 115 </output>
112 </test> 116 </test>
113 </tests> 117 </tests>
114 <help> 118 <help><![CDATA[
115 119
116 **SnpSift filter** 120 **SnpSift filter**
117 121
118 You can filter a 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. 122 You can filter a 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.
119 123
121 125
122 - *I want just the variants from the second million bases of chr1*: 126 - *I want just the variants from the second million bases of chr1*:
123 127
124 :: 128 ::
125 129
126 ( CHROM = 'chr1' ) &amp; ( POS &gt; 1000000 ) &amp; ( POS &lt; 2000000 ) 130 ( CHROM = 'chr1' ) & ( POS > 1000000 ) & ( POS < 2000000 )
127 131
128 - *Filter value is either 'PASS' or it is missing*: 132 - *Filter value is either 'PASS' or it is missing*:
129 133
130 :: 134 ::
131 135
132 (FILTER = 'PASS') | ( na FILTER ) 136 (FILTER = 'PASS') | ( na FILTER )
133 137
134 - *I want to filter lines with an EFF of 'frameshift_variant' ( for vcf files using Sequence Ontology terms )*: 138 - *I want to filter lines with an ANN annotation EFFECT of 'frameshift_variant' ( for vcf files using Sequence Ontology terms )*:
135 139
136 :: 140 ::
137 141
138 ( EFF[*].EFFECT = 'frameshift_variant' ) 142 ( ANN[*].EFFECT has 'frameshift_variant' )
143
144 **Important** According to the specification, there can be more than one EFFECT separated by & (e.g. 'missense_variant&splice_region_variant', thus using has operator is better than using equality operator (=). For instance 'missense_variant&splice_region_variant' = 'missense_variant' is false, whereas 'missense_variant&splice_region_variant' has 'missense_variant' is true.
139 145
140 - *I want to filter lines with an EFF of 'FRAME_SHIFT' ( for vcf files using Classic Effect names )*: 146 - *I want to filter lines with an EFF of 'FRAME_SHIFT' ( for vcf files using Classic Effect names )*:
141 147
142 :: 148 ::
143 149
145 151
146 - *I want to filter out samples with quality less than 30*: 152 - *I want to filter out samples with quality less than 30*:
147 153
148 :: 154 ::
149 155
150 ( QUAL &gt; 30 ) 156 ( QUAL > 30 )
151 157
152 - *...but we also want InDels that have quality 20 or more*: 158 - *...but we also want InDels that have quality 20 or more*:
153 159
154 :: 160 ::
155 161
156 (( exists INDEL ) &amp; (QUAL >= 20)) | (QUAL >= 30 ) 162 (( exists INDEL ) & (QUAL >= 20)) | (QUAL >= 30 )
157 163
158 - *...or any homozygous variant present in more than 3 samples*: 164 - *...or any homozygous variant present in more than 3 samples*:
159 165
160 :: 166 ::
161 167
162 (countHom() > 3) | (( exists INDEL ) &amp; (QUAL >= 20)) | (QUAL >= 30 ) 168 (countHom() > 3) | (( exists INDEL ) & (QUAL >= 20)) | (QUAL >= 30 )
163 169
164 - *...or any heterozygous sample with coverage 25 or more*: 170 - *...or any heterozygous sample with coverage 25 or more*:
165 171
166 :: 172 ::
167 173
168 ((countHet() > 0) &amp; (DP >= 25)) | (countHom() > 3) | (( exists INDEL ) &amp; (QUAL >= 20)) | (QUAL >= 30 ) 174 ((countHet() > 0) & (DP >= 25)) | (countHom() > 3) | (( exists INDEL ) & (QUAL >= 20)) | (QUAL >= 30 )
169 175
170 - *I want to keep samples where the genotype for the first sample is homozygous variant and the genotype for the second sample is reference*: 176 - *I want to keep samples where the genotype for the first sample is homozygous variant and the genotype for the second sample is reference*:
171 177
172 :: 178 ::
173 179
174 (isHom( GEN[0] ) &amp; isVariant( GEN[0] ) &amp; isRef( GEN[1] )) 180 (isHom( GEN[0] ) & isVariant( GEN[0] ) & isRef( GEN[1] ))
175 181
176 182
177 **For information regarding HGVS and Sequence Ontology terms versus classic names**: 183 **For information regarding HGVS and Sequence Ontology terms versus classic names**:
178 184
179 - http://snpeff.sourceforge.net/SnpEff_manual.html#cmdline for the options: -classic, -hgvs, and -sequenceOntology 185 - http://snpeff.sourceforge.net/SnpEff_manual.html#cmdline for the options: -classic, -hgvs, and -sequenceOntology
181 187
182 188
183 @EXTERNAL_DOCUMENTATION@ 189 @EXTERNAL_DOCUMENTATION@
184 http://snpeff.sourceforge.net/SnpSift.html#filter 190 http://snpeff.sourceforge.net/SnpSift.html#filter
185 191
186 @CITATION_SECTION@ 192 ]]>
187
188 </help> 193 </help>
194 <expand macro="citations" />
189 </tool> 195 </tool>