Mercurial > repos > iuc > snpsift
diff snpSift_extractFields.xml @ 2:bf8c1526871b draft
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tool_collections/snpsift/snpsift commit d12355cea76843e3ed6f09d96c3e9fe22afe4a4f
| author | iuc |
|---|---|
| date | Mon, 05 Dec 2016 12:11:18 -0500 |
| parents | 98708b88af9f |
| children | 20c7d583fec1 |
line wrap: on
line diff
--- a/snpSift_extractFields.xml Tue Jun 07 10:04:09 2016 -0400 +++ b/snpSift_extractFields.xml Mon Dec 05 12:11:18 2016 -0500 @@ -1,6 +1,6 @@ -<tool id="snpSift_extractFields" name="SnpSift Extract Fields" version="@WRAPPER_VERSION@.0"> +<tool id="snpSift_extractFields" name="SnpSift Extract Fields" version="@WRAPPER_VERSION@.1"> <options sanitize="False" /> - <description>from a VCF file inot a tabular file</description> + <description>from a VCF file into a tabular file</description> <macros> <import>snpSift_macros.xml</import> </macros> @@ -8,16 +8,17 @@ <expand macro="stdio" /> <expand macro="version_command" /> <command><![CDATA[ + @CONDA_SNPSIFT_JAR_PATH@ && cat "$input" #if $one_effect_per_line: - | "\$SNPEFF_JAR_PATH/scripts/vcfEffOnePerLine.pl" - #end if - | java -Xmx6G -jar "\$SNPEFF_JAR_PATH/SnpSift.jar" extractFields + | "\$SNPSIFT_JAR_PATH/scripts/vcfEffOnePerLine.pl" + #end if + | java -Xmx6G -jar "\$SNPSIFT_JAR_PATH/SnpSift.jar" extractFields #if $separator: - -s '$separator' + -s '$separator' #end if #if $empty_text: - -e '$empty_text' + -e '$empty_text' #end if - #echo ' '.join(['"%s"' % x for x in $extract.split()]) @@ -28,10 +29,8 @@ <param format="vcf" name="input" type="data" label="Variant input file in VCF format"/> <param name="extract" type="text" label="Extract" help="Need help? See below a few examples." /> <param name="one_effect_per_line" type="boolean" truevalue="yes" falsevalue="no" checked="false" label="One effect per line" help="When variants have more than one effect, lists one effect per line, while all other parameters in the line are repeated across mutiple lines" /> - <param name="separator" type="text" value="" optional="true" label="multiple field separator" help="Separate multiple fields in one column with this character, e.g. a comma, rather than a column for each of the multiple values"> - </param> - <param name="empty_text" type="text" value="" optional="true" label="empty field text" help="Represent empty fields with this value, rather than leaving them blank" > - </param> + <param name="separator" type="text" value="" label="multiple field separator" help="Separate multiple fields in one column with this character, e.g. a comma, rather than a column for each of the multiple values" /> + <param name="empty_text" type="text" value="" label="empty field text" help="Represent empty fields with this value, rather than leaving them blank" /> </inputs> <outputs> <data format="tabular" name="output" /> @@ -78,13 +77,13 @@ ID REF ALT - FILTER + FILTER INFO fields: AF AC DP MQ - etc. (any info field available) + etc. (any info field available) SnpEff 'ANN' fields: "ANN[*].ALLELE" (alias GENOTYPE) "ANN[*].EFFECT" (alias ANNOTATION): Effect in Sequence ontology terms (e.g. 'missense_variant', 'synonymous_variant', 'stop_gained', etc.) @@ -104,7 +103,7 @@ "ANN[*].AA_POS" (alias POS_AA) "ANN[*].AA_LEN" (alias LEN_AA) "ANN[*].DISTANCE" - "ANN[*].ERRORS" (alias WARNING, INFOS) + "ANN[*].ERRORS" (alias WARNING, INFOS) SnpEff 'EFF' fields (this is for older SnpEff/SnpSift versions, new version use 'ANN' field): "EFF[*].EFFECT" "EFF[*].IMPACT" @@ -116,17 +115,17 @@ "EFF[*].BIOTYPE" "EFF[*].CODING" "EFF[*].TRID" - "EFF[*].RANK" + "EFF[*].RANK" SnpEff 'LOF' fields: "LOF[*].GENE" "LOF[*].GENEID" "LOF[*].NUMTR" - "LOF[*].PERC" + "LOF[*].PERC" SnpEff' NMD' fields: "NMD[*].GENE" "NMD[*].GENEID" "NMD[*].NUMTR" - "NMD[*].PERC" + "NMD[*].PERC" Some examples: @@ -135,7 +134,7 @@ **CHROM POS ID AF** - The result will look something like: + The result will look something like: :: @@ -155,25 +154,25 @@ - GEN[0].GL[1] : Second likelihood from first genotype - GEN[1].GL : The whole GL fiels (all entries without separating them) - GEN[3].GL[*] : All likelihoods form genotype 3 (this time they will be tab separated, as opposed to the previous one). - - GEN[*].GT : Genotype subfields (GT) from ALL samples (tab separated). + - GEN[*].GT : Genotype subfields (GT) from ALL samples (tab separated). - The result will look something like: + The result will look something like: :: #CHROM POS ID THETA GEN[0].GL[1] GEN[1].GL GEN[3].GL[*] GEN[*].GT - 1 10583 rs58108140 0.0046 -0.47 -0.24,-0.44,-1.16 -0.48 -0.48 -0.48 0|0 0|0 0|0 0|1 0|0 0|1 0|0 0|0 0|1 - 1 10611 rs189107123 0.0077 -0.48 -0.24,-0.44,-1.16 -0.48 -0.48 -0.48 0|0 0|1 0|0 0|0 0|0 0|0 0|0 0|0 0|0 - 1 13302 rs180734498 0.0048 -0.58 -2.45,-0.00,-5.00 -0.48 -0.48 -0.48 0|0 0|1 0|0 0|0 0|0 1|0 0|0 0|1 0|0 + 1 10583 rs58108140 0.0046 -0.47 -0.24,-0.44,-1.16 -0.48 -0.48 -0.48 0|0 0|0 0|0 0|1 0|0 0|1 0|0 0|0 0|1 + 1 10611 rs189107123 0.0077 -0.48 -0.24,-0.44,-1.16 -0.48 -0.48 -0.48 0|0 0|1 0|0 0|0 0|0 0|0 0|0 0|0 0|0 + 1 13302 rs180734498 0.0048 -0.58 -2.45,-0.00,-5.00 -0.48 -0.48 -0.48 0|0 0|1 0|0 0|0 0|0 1|0 0|0 0|1 0|0 - *Extracting fields with multiple values:* (notice that there are multiple effect columns per line because there are mutiple effects per variant) **CHROM POS REF ALT ANN[*].EFFECT** - The result will look something like: + The result will look something like: - :: + :: #CHROM POS REF ALT ANN[*].EFFECT 22 17071756 T C 3_prime_UTR_variant downstream_gene_variant @@ -184,9 +183,9 @@ **CHROM POS REF ALT ANN[*].EFFECT ANN[*].HGVS_P** - The result will look something like: + The result will look something like: - :: + :: #CHROM POS REF ALT ANN[*].EFFECT ANN[*].HGVS_P 22 17071756 T C 3_prime_UTR_variant,downstream_gene_variant .,. @@ -198,9 +197,9 @@ **CHROM POS REF ALT ANN[*].EFFECT** - The result will look something like: + The result will look something like: - :: + :: #CHROM POS REF ALT ANN[*].EFFECT 22 17071756 T C 3_prime_UTR_variant