Mercurial > repos > jjohnson > snpsift
annotate snpSift_filter.xml @ 6:824f78c0d0df
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tool_collections/snpsift/snpsift commit 915e0f28e6bc2701ca8f333d7b30cf399cd6e9da-dirty
| author | jjohnson |
|---|---|
| date | Mon, 25 Jan 2016 17:40:56 -0500 |
| parents | baf6602903e1 |
| children | c29f29a6f26c |
| rev | line source |
|---|---|
| 4 | 1 <tool id="snpSift_filter" name="SnpSift Filter" version="@WRAPPER_VERSION@.0"> |
| 0 | 2 <options sanitize="False" /> |
| 3 <description>Filter variants using arbitrary expressions</description> | |
| 4 | 4 <macros> |
| 5 <import>snpSift_macros.xml</import> | |
| 6 </macros> | |
| 0 | 7 <expand macro="requirements" /> |
| 4 | 8 <expand macro="stdio" /> |
| 9 <expand macro="version_command" /> | |
| 10 <command><![CDATA[ | |
| 0 | 11 java -Xmx6G -jar \$SNPEFF_JAR_PATH/SnpSift.jar filter -f $input -e $exprFile $inverse |
| 12 #if $filtering.mode == 'field': | |
| 13 #if $filtering.replace.pass: | |
| 14 --pass | |
| 15 #if $filtering.replace.filterId and len($filtering.replace.filterId.__str__.strip()) > 0: | |
| 16 --filterId "$filtering.replace.filterId" | |
| 17 #end if | |
| 18 #end if | |
| 19 #if $filtering.addFilter and len($filtering.addFilter.__str__.strip()) > 0: | |
| 20 --addFilter "$filtering.addFilter" | |
| 21 #end if | |
| 22 #if $filtering.rmFilter and len($filtering.rmFilter.__str__.strip()) > 0: | |
| 23 --rmFilter "$filtering.rmFilter" | |
| 24 #end if | |
| 25 #end if | |
| 26 > $output | |
| 4 | 27 ]]> |
| 0 | 28 </command> |
| 29 <inputs> | |
| 30 <param format="vcf" name="input" type="data" label="Variant input file in VCF format"/> | |
|
6
824f78c0d0df
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tool_collections/snpsift/snpsift commit 915e0f28e6bc2701ca8f333d7b30cf399cd6e9da-dirty
jjohnson
parents:
4
diff
changeset
|
31 <param name="expr" type="text" label="Filter criteria" help="Need help? See below a few examples." /> |
| 0 | 32 <param name="inverse" type="boolean" truevalue="--inverse" falsevalue="" checked="false" label="Inverse filter" help="Show lines that do not match filter expression" /> |
| 33 <conditional name="filtering"> | |
| 34 <param name="mode" type="select" label="Filter mode"> | |
| 35 <option value="entries" selected="true">Retain entries that pass filter, remove other entries</option> | |
| 36 <option value="field">Change the FILTER field, but retain all entries</option> | |
| 37 </param> | |
| 38 <when value="entries"/> | |
| 39 <when value="field"> | |
| 40 <conditional name="replace"> | |
| 41 <param name="pass" type="boolean" truevalue="yes" falsevalue="no" checked="false" label="Set matching entry FILTER to 'PASS'" | |
| 42 help="appends an ID tag to non-matching entry FILTER "/> | |
| 43 <when value="no"/> | |
| 44 <when value="yes"> | |
|
6
824f78c0d0df
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tool_collections/snpsift/snpsift commit 915e0f28e6bc2701ca8f333d7b30cf399cd6e9da-dirty
jjohnson
parents:
4
diff
changeset
|
45 <param name="filterId" type="text" value="" optional="true" label="ID appended to non-matching (##FILTER tag in header and FILTER VCF field)." |
| 0 | 46 help="Default ID is 'SnpSift'"/> |
| 47 </when> | |
| 48 </conditional> | |
|
6
824f78c0d0df
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tool_collections/snpsift/snpsift commit 915e0f28e6bc2701ca8f333d7b30cf399cd6e9da-dirty
jjohnson
parents:
4
diff
changeset
|
49 <param name="addFilter" type="text" value="" optional="true" label="Add a string to FILTER VCF field if 'expression' is true." /> |
|
824f78c0d0df
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tool_collections/snpsift/snpsift commit 915e0f28e6bc2701ca8f333d7b30cf399cd6e9da-dirty
jjohnson
parents:
4
diff
changeset
|
50 <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)." /> |
| 0 | 51 </when> |
| 52 </conditional> | |
| 53 </inputs> | |
| 54 <configfiles> | |
| 55 <configfile name="exprFile"> | |
| 1 | 56 $expr#slurp |
| 0 | 57 </configfile> |
| 58 </configfiles> | |
| 59 | |
| 60 <outputs> | |
| 61 <data format="vcf" name="output" /> | |
| 62 </outputs> | |
| 63 <tests> | |
| 64 <test> | |
| 65 <param name="input" ftype="vcf" value="test01.vcf"/> | |
| 66 <param name="expr" value="QUAL >= 50"/> | |
| 67 <param name="mode" value="entries"/> | |
| 68 <output name="output"> | |
| 69 <assert_contents> | |
| 70 <has_text text="28837706" /> | |
| 71 <not_has_text text="NT_166464" /> | |
| 72 </assert_contents> | |
| 73 </output> | |
| 74 </test> | |
| 75 | |
| 76 <test> | |
| 77 <param name="input" ftype="vcf" value="test01.vcf"/> | |
| 78 <param name="expr" value="(CHROM = '19')"/> | |
| 79 <param name="mode" value="entries"/> | |
| 80 <output name="output"> | |
| 81 <assert_contents> | |
| 82 <has_text text="3205820" /> | |
| 83 <not_has_text text="NT_16" /> | |
| 84 </assert_contents> | |
| 85 </output> | |
| 86 </test> | |
| 87 | |
| 88 <test> | |
| 89 <param name="input" ftype="vcf" value="test01.vcf"/> | |
|
6
824f78c0d0df
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tool_collections/snpsift/snpsift commit 915e0f28e6bc2701ca8f333d7b30cf399cd6e9da-dirty
jjohnson
parents:
4
diff
changeset
|
90 <param name="expr" value="(POS >= 20175) & (POS < 35549)"/> |
| 0 | 91 <param name="mode" value="entries"/> |
| 92 <output name="output"> | |
| 93 <assert_contents> | |
| 94 <has_text text="20175" /> | |
| 95 <has_text text="35549" /> | |
| 96 <has_text text="22256" /> | |
| 97 <not_has_text text="18933" /> | |
| 98 <not_has_text text="37567" /> | |
| 99 </assert_contents> | |
| 100 </output> | |
| 101 </test> | |
| 102 | |
| 103 <test> | |
| 104 <param name="input" ftype="vcf" value="test01.vcf"/> | |
| 105 <param name="expr" value="( DP >= 5 )"/> | |
| 106 <param name="mode" value="entries"/> | |
| 107 <output name="output"> | |
| 108 <assert_contents> | |
| 109 <has_text text="DP=5;" /> | |
| 110 <has_text text="DP=6;" /> | |
| 111 <not_has_text text="DP=1;" /> | |
| 112 </assert_contents> | |
| 113 </output> | |
| 114 </test> | |
| 115 </tests> | |
| 4 | 116 <help><![CDATA[ |
| 0 | 117 |
| 118 **SnpSift filter** | |
| 119 | |
| 4 | 120 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. |
| 0 | 121 |
| 122 Some examples: | |
| 123 | |
| 1 | 124 - *I want just the variants from the second million bases of chr1*: |
| 125 | |
| 126 :: | |
| 127 | |
| 4 | 128 ( CHROM = 'chr1' ) & ( POS > 1000000 ) & ( POS < 2000000 ) |
| 1 | 129 |
| 130 - *Filter value is either 'PASS' or it is missing*: | |
| 131 | |
| 132 :: | |
| 133 | |
| 134 (FILTER = 'PASS') | ( na FILTER ) | |
| 135 | |
| 4 | 136 - *I want to filter lines with an ANN annotation EFFECT of 'frameshift_variant' ( for vcf files using Sequence Ontology terms )*: |
| 1 | 137 |
| 138 :: | |
| 139 | |
| 4 | 140 ( ANN[*].EFFECT has 'frameshift_variant' ) |
| 141 | |
| 142 **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. | |
| 1 | 143 |
| 144 - *I want to filter lines with an EFF of 'FRAME_SHIFT' ( for vcf files using Classic Effect names )*: | |
| 145 | |
| 146 :: | |
| 147 | |
| 148 ( EFF[*].EFFECT = 'FRAME_SHIFT' ) | |
| 149 | |
| 0 | 150 - *I want to filter out samples with quality less than 30*: |
| 151 | |
| 152 :: | |
| 153 | |
| 4 | 154 ( QUAL > 30 ) |
| 1 | 155 |
| 0 | 156 - *...but we also want InDels that have quality 20 or more*: |
| 157 | |
| 158 :: | |
| 159 | |
| 4 | 160 (( exists INDEL ) & (QUAL >= 20)) | (QUAL >= 30 ) |
| 0 | 161 |
| 162 - *...or any homozygous variant present in more than 3 samples*: | |
| 163 | |
| 164 :: | |
| 165 | |
| 4 | 166 (countHom() > 3) | (( exists INDEL ) & (QUAL >= 20)) | (QUAL >= 30 ) |
| 0 | 167 |
| 168 - *...or any heterozygous sample with coverage 25 or more*: | |
| 169 | |
| 170 :: | |
| 171 | |
| 4 | 172 ((countHet() > 0) & (DP >= 25)) | (countHom() > 3) | (( exists INDEL ) & (QUAL >= 20)) | (QUAL >= 30 ) |
| 0 | 173 |
| 174 - *I want to keep samples where the genotype for the first sample is homozygous variant and the genotype for the second sample is reference*: | |
| 175 | |
| 176 :: | |
| 177 | |
| 4 | 178 (isHom( GEN[0] ) & isVariant( GEN[0] ) & isRef( GEN[1] )) |
| 0 | 179 |
| 180 | |
| 1 | 181 **For information regarding HGVS and Sequence Ontology terms versus classic names**: |
| 0 | 182 |
| 1 | 183 - http://snpeff.sourceforge.net/SnpEff_manual.html#cmdline for the options: -classic, -hgvs, and -sequenceOntology |
| 184 - http://snpeff.sourceforge.net/SnpEff_manual.html#input for the table containing the classic name and sequence onology term for each effect | |
| 185 | |
| 0 | 186 |
| 187 @EXTERNAL_DOCUMENTATION@ | |
| 188 http://snpeff.sourceforge.net/SnpSift.html#filter | |
| 189 | |
| 190 @CITATION_SECTION@ | |
| 191 | |
| 4 | 192 ]]> |
| 0 | 193 </help> |
| 194 </tool> |