| Previous changeset 3:1739678def32 (2014-10-23) Next changeset 5:675fa55f5c02 (2016-01-08) |
|
Commit message:
Uploaded |
|
modified:
snpSift_annotate.xml snpSift_caseControl.xml snpSift_filter.xml snpSift_int.xml snpSift_rmInfo.xml snpSift_vcfCheck.xml tool_dependencies.xml |
|
added:
snpSift_extractFields.xml snpSift_macros.xml snpSift_vartype.xml |
|
removed:
snpEff_macros.xml |
| b |
| diff -r 1739678def32 -r baf6602903e1 snpEff_macros.xml --- a/snpEff_macros.xml Thu Oct 23 06:06:25 2014 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 |
| [ |
| @@ -1,32 +0,0 @@ -<macros> - <xml name="requirements"> - <requirements> - <requirement type="package" version="4.0">snpEff</requirement> - </requirements> - </xml> - <xml name="stdio"> - <stdio> - <exit_code range=":-1" level="fatal" description="Error: Cannot open file" /> - <exit_code range="1:" level="fatal" description="Error" /> - </stdio> - </xml> - <token name="@EXTERNAL_DOCUMENTATION@"> - -For details about this tool, please go to: - http://snpeff.sourceforge.net/SnpEff_manual.html - - </token> - <token name="@CITATION_SECTION@">------ - -**Citation** - -For the underlying tool, please cite the following two publications: - -SnpEff citation: -"A program for annotating and predicting the effects of single nucleotide polymorphisms, SnpEff: SNPs in the genome of Drosophila melanogaster strain w1118; iso-2; iso-3.", Cingolani P, Platts A, Wang le L, Coon M, Nguyen T, Wang L, Land SJ, Lu X, Ruden DM. Fly (Austin). 2012 Apr-Jun;6(2):80-92. PMID: 22728672 [PubMed - in process] - -SnpSift citation: -"Using Drosophila melanogaster as a model for genotoxic chemical mutational studies with a new program, SnpSift", Cingolani, P., et. al., Frontiers in Genetics, 3, 2012. - - </token> -</macros> |
| b |
| diff -r 1739678def32 -r baf6602903e1 snpSift_annotate.xml --- a/snpSift_annotate.xml Thu Oct 23 06:06:25 2014 -0500 +++ b/snpSift_annotate.xml Wed Dec 09 14:03:26 2015 -0500 |
| [ |
| @@ -1,13 +1,15 @@ -<tool id="snpSift_annotate" name="SnpSift Annotate" version="4.0.0"> +<tool id="snpSift_annotate" name="SnpSift Annotate" version="@WRAPPER_VERSION@.0"> <description>SNPs from dbSnp</description> <!-- You can change the amount of memory used, just change the -Xmx parameter (e.g. use -Xmx2G for 2Gb of memory) --> + <macros> + <import>snpSift_macros.xml</import> + </macros> <expand macro="requirements" /> - <macros> - <import>snpEff_macros.xml</import> - </macros> - <command> + <expand macro="stdio" /> + <expand macro="version_command" /> + <command><![CDATA[ java -Xmx6G -jar \$SNPEFF_JAR_PATH/SnpSift.jar $annotate_cmd #if $annotate.id : -id @@ -15,6 +17,7 @@ -info "$annotate.info_ids" #end if -q $dbSnp $input > $output +]]> </command> <inputs> <param format="vcf" name="input" type="data" label="Variant input file in VCF format"/> @@ -37,7 +40,6 @@ </help> </param> </inputs> - <expand macro="stdio" /> <outputs> <data format="vcf" name="output" /> </outputs> @@ -54,7 +56,7 @@ </output> </test> </tests> - <help> + <help><![CDATA[ This is typically used to annotate IDs from dbSnp. @@ -95,6 +97,7 @@ @CITATION_SECTION@ +]]> </help> </tool> |
| b |
| diff -r 1739678def32 -r baf6602903e1 snpSift_caseControl.xml --- a/snpSift_caseControl.xml Thu Oct 23 06:06:25 2014 -0500 +++ b/snpSift_caseControl.xml Wed Dec 09 14:03:26 2015 -0500 |
| [ |
| @@ -1,13 +1,15 @@ -<tool id="snpSift_caseControl" name="SnpSift CaseControl" version="4.0.0"> +<tool id="snpSift_caseControl" name="SnpSift CaseControl" version="@WRAPPER_VERSION@.0"> <description>Count samples are in 'case' and 'control' groups.</description> <!-- You can change the amount of memory used, just change the -Xmx parameter (e.g. use -Xmx2G for 2Gb of memory) --> + <macros> + <import>snpSift_macros.xml</import> + </macros> <expand macro="requirements" /> - <macros> - <import>snpEff_macros.xml</import> - </macros> - <command> + <expand macro="stdio" /> + <expand macro="version_command" /> + <command><![CDATA[ java -Xmx1G -jar \$SNPEFF_JAR_PATH/SnpSift.jar caseControl -q #if $name.__str__.strip() != '': -name $name @@ -18,6 +20,7 @@ -tfam "$ctrl.tfam" #end if $input > $output +]]> </command> <inputs> <param format="vcf" name="input" type="data" label="Variant input file in VCF format"/> @@ -45,7 +48,6 @@ <outputs> <data format="vcf" name="output" /> </outputs> - <expand macro="stdio" /> <tests> <test> <param name="input" ftype="vcf" value="test.private.01.vcf"/> @@ -84,7 +86,7 @@ </output> </test> </tests> - <help> + <help><![CDATA[ **SnpSift CaseControl** @@ -118,5 +120,6 @@ @CITATION_SECTION@ +]]> </help> </tool> |
| b |
| diff -r 1739678def32 -r baf6602903e1 snpSift_extractFields.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/snpSift_extractFields.xml Wed Dec 09 14:03:26 2015 -0500 |
| [ |
| b'@@ -0,0 +1,221 @@\n+<tool id="snpSift_extractFields" name="SnpSift Extract Fields" version="@WRAPPER_VERSION@.0">\n+ <options sanitize="False" />\n+ <description>from a VCF file inot a tabular file</description>\n+ <macros>\n+ <import>snpSift_macros.xml</import>\n+ </macros>\n+ <expand macro="requirements" />\n+ <expand macro="stdio" />\n+ <expand macro="version_command" />\n+ <command><![CDATA[\n+ cat "$input"\n+ #if $one_effect_per_line:\n+ | \\$SNPEFF_JAR_PATH/scripts/vcfEffOnePerLine.pl\n+ #end if \n+ | java -Xmx6G -jar \\$SNPEFF_JAR_PATH/SnpSift.jar extractFields \n+ #if $separator:\n+ -s \'$separator\' \n+ #end if\n+ #if $empty_text:\n+ -e \'$empty_text\' \n+ #end if\n+ -\n+ #echo \' \'.join([\'"%s"\' % x for x in $extract.split()])\n+ > $output\n+]]>\n+ </command>\n+ <inputs>\n+ <param format="vcf" name="input" type="data" label="Variant input file in VCF format"/>\n+ <param name="extract" type="text" label="Extract" size="160" help="Need help? See below a few examples." />\n+ <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" />\n+ <param name="separator" type="text" value="" optional="true" label="multiple field separator" size="1" help="Separate multiple fields in one column with this character, e.g. a comma, rather than a column for each of the multiple values">\n+ </param>\n+ <param name="empty_text" type="text" value="" optional="true" label="empty field text" size="10" help="Represent empty fields with this value, rather than leaving them blank" >\n+ </param>\n+ </inputs>\n+ <outputs>\n+ <data format="tabular" name="output" />\n+ </outputs>\n+ <tests>\n+ <test>\n+ <param name="input" ftype="vcf" value="test_rmInfo.vcf"/>\n+ <param name="extract" value="CHROM POS REF ALT EFF[*].EFFECT"/>\n+ <output name="output">\n+ <assert_contents>\n+ <has_text text="INTRAGENIC" />\n+ <not_has_text text="DOWNSTREAM,INTRAGENIC,INTRON,UTR_3_PRIME" />\n+ </assert_contents>\n+ </output>\n+ </test>\n+\n+ <test>\n+ <param name="input" ftype="vcf" value="test_rmInfo.vcf"/>\n+ <param name="extract" value="CHROM POS REF ALT EFF[*].EFFECT"/>\n+ <param name="separator" value=","/>\n+ <output name="output">\n+ <assert_contents>\n+\t\t<has_text text="DOWNSTREAM,INTRAGENIC,INTRON,UTR_3_PRIME" />\n+ </assert_contents>\n+ </output>\n+ </test>\n+\n+ </tests>\n+ <help><![CDATA[\n+\n+**SnpSift Extract Fields**\n+\n+Extract fields from a VCF file to a TXT, tab separated format, that you can easily load in R, XLS, etc.\n+\n+http://snpeff.sourceforge.net/SnpSift.html#Extract\n+\n+You can also use sub-fields and genotype fields / sub-fields such as:\n+\n+ ::\n+\n+ Standard VCF fields:\n+ CHROM\n+ POS\n+ ID\n+ REF\n+ ALT\n+ FILTER \n+ INFO fields:\n+ AF\n+ AC\n+ DP\n+ MQ\n+ etc. (any info field available) \n+ SnpEff \'ANN\' fields:\n+ "ANN[*].ALLELE" (alias GENOTYPE)\n+ "ANN[*].EFFECT" (alias ANNOTATION): Effect in Sequence ontology terms (e.g. \'missense_variant\', \'synonymous_variant\', \'stop_gained\', etc.)\n+ "ANN[*].IMPACT:" { HIGH, MODERATE, LOW, MODIFIER }\n+ "ANN[*].GENE:" Gene name (e.g. \'PSD3\')\n+ "ANN[*].GENEID:" Gene ID\n+ "ANN[*].FEATURE\n+ " ANN[*].FEATUREID (alias TRID: Transcript ID)\n+ "ANN[*].BIOTYPE:" Biotype, as described by the annotations (e.g. \'protein_coding\')\n+ "ANN[*].RANK:" Exon or Intron rank (i.e. exon number in a transcript)\n+ "ANN[*].HG'..b'EN_AA)\n+ "ANN[*].DISTANCE"\n+ "ANN[*].ERRORS" (alias WARNING, INFOS) \n+ SnpEff \'EFF\' fields (this is for older SnpEff/SnpSift versions, new version use \'ANN\' field):\n+ "EFF[*].EFFECT"\n+ "EFF[*].IMPACT"\n+ "EFF[*].FUNCLASS"\n+ "EFF[*].CODON"\n+ "EFF[*].AA"\n+ "EFF[*].AA_LEN"\n+ "EFF[*].GENE"\n+ "EFF[*].BIOTYPE"\n+ "EFF[*].CODING"\n+ "EFF[*].TRID"\n+ "EFF[*].RANK" \n+ SnpEff \'LOF\' fields:\n+ "LOF[*].GENE"\n+ "LOF[*].GENEID"\n+ "LOF[*].NUMTR"\n+ "LOF[*].PERC" \n+ SnpEff\' NMD\' fields:\n+ "NMD[*].GENE"\n+ "NMD[*].GENEID"\n+ "NMD[*].NUMTR"\n+ "NMD[*].PERC" \n+\n+\n+Some examples:\n+\n+ - *Extracting chromosome, position, ID and allele frequency from a VCF file:*\n+\n+ **CHROM POS ID AF**\n+\n+ The result will look something like: \n+\n+ ::\n+\n+ #CHROM POS ID AF\n+ 1 69134 0.086\n+ 1 69496 rs150690004 0.001\n+\n+\n+ - *Extracting genotype fields:*\n+\n+ **CHROM POS ID THETA GEN[0].GL[1] GEN[1].GL GEN[3].GL[*] GEN[*].GT**\n+\n+ This means to extract:\n+\n+ - CHROM POS ID: regular fields (as in the previous example)\n+ - THETA : This one is from INFO\n+ - GEN[0].GL[1] : Second likelihood from first genotype\n+ - GEN[1].GL : The whole GL fiels (all entries without separating them)\n+ - GEN[3].GL[*] : All likelihoods form genotype 3 (this time they will be tab separated, as opposed to the previous one).\n+ - GEN[*].GT : Genotype subfields (GT) from ALL samples (tab separated). \n+\n+ The result will look something like: \n+\n+ ::\n+\n+ #CHROM POS ID THETA GEN[0].GL[1] GEN[1].GL GEN[3].GL[*] GEN[*].GT\n+ 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 \n+ 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 \n+ 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 \n+\n+ - *Extracting fields with multiple values:*\n+ (notice that there are multiple effect columns per line because there are mutiple effects per variant)\n+\n+ **CHROM POS REF ALT ANN[*].EFFECT**\n+\n+ The result will look something like: \n+\n+ :: \n+\n+ #CHROM\tPOS\tREF\tALT\tANN[*].EFFECT\n+ 22\t17071756\tT\tC\t3_prime_UTR_variant\tdownstream_gene_variant\n+ 22\t17072035\tC\tT\tmissense_variant\tdownstream_gene_variant\n+ 22\t17072258\tC\tA\tmissense_variant\tdownstream_gene_variant\n+\n+ - *Extracting fields with multiple values using a comma as a multipe field separator:*\n+\n+ **CHROM POS REF ALT ANN[*].EFFECT ANN[*].HGVS_P**\n+\n+ The result will look something like: \n+\n+ :: \n+\n+ #CHROM\tPOS\tREF\tALT\tANN[*].EFFECT\tANN[*].HGVS_P\n+ 22\t17071756\tT\tC\t3_prime_UTR_variant,downstream_gene_variant\t.,.\n+ 22\t17072035\tC\tT\tmissense_variant,downstream_gene_variant\tp.Gly469Glu,.\n+ 22\t17072258\tC\tA\tmissense_variant,downstream_gene_variant\tp.Gly395Cys,.\n+\n+\n+ - *Extracting fields with multiple values, one effect per line:*\n+\n+ **CHROM POS REF ALT ANN[*].EFFECT**\n+\n+ The result will look something like: \n+\n+ :: \n+\n+ #CHROM\tPOS\tREF\tALT\tANN[*].EFFECT\n+ 22\t17071756\tT\tC\t3_prime_UTR_variant\n+ 22\t17071756\tT\tC\tdownstream_gene_variant\n+ 22\t17072035\tC\tT\tmissense_variant\n+ 22\t17072035\tC\tT\tdownstream_gene_variant\n+ 22\t17072258\tC\tA\tmissense_variant\n+ 22\t17072258\tC\tA\tdownstream_gene_variant\n+\n+\n+@EXTERNAL_DOCUMENTATION@\n+\thttp://snpeff.sourceforge.net/SnpSift.html#Extract\n+\n+@CITATION_SECTION@\n+\n+]]>\n+ </help>\n+</tool>\n' |
| b |
| diff -r 1739678def32 -r baf6602903e1 snpSift_filter.xml --- a/snpSift_filter.xml Thu Oct 23 06:06:25 2014 -0500 +++ b/snpSift_filter.xml Wed Dec 09 14:03:26 2015 -0500 |
| [ |
| @@ -1,11 +1,13 @@ -<tool id="snpSift_filter" name="SnpSift Filter" version="4.0.0"> +<tool id="snpSift_filter" name="SnpSift Filter" version="@WRAPPER_VERSION@.0"> <options sanitize="False" /> <description>Filter variants using arbitrary expressions</description> + <macros> + <import>snpSift_macros.xml</import> + </macros> <expand macro="requirements" /> - <macros> - <import>snpEff_macros.xml</import> - </macros> - <command> + <expand macro="stdio" /> + <expand macro="version_command" /> + <command><![CDATA[ java -Xmx6G -jar \$SNPEFF_JAR_PATH/SnpSift.jar filter -f $input -e $exprFile $inverse #if $filtering.mode == 'field': #if $filtering.replace.pass: @@ -22,6 +24,7 @@ #end if #end if > $output +]]> </command> <inputs> <param format="vcf" name="input" type="data" label="Variant input file in VCF format"/> @@ -57,7 +60,6 @@ <outputs> <data format="vcf" name="output" /> </outputs> - <expand macro="stdio" /> <tests> <test> <param name="input" ftype="vcf" value="test01.vcf"/> @@ -85,7 +87,7 @@ <test> <param name="input" ftype="vcf" value="test01.vcf"/> - <param name="expr" value="(POS >= 20175) & (POS <= 35549)"/> + <param name="expr" value="(POS >= 20175) & (POS <= 35549)"/> <param name="mode" value="entries"/> <output name="output"> <assert_contents> @@ -111,11 +113,11 @@ </output> </test> </tests> - <help> + <help><![CDATA[ **SnpSift filter** -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. +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. Some examples: @@ -123,7 +125,7 @@ :: - ( CHROM = 'chr1' ) & ( POS > 1000000 ) & ( POS < 2000000 ) + ( CHROM = 'chr1' ) & ( POS > 1000000 ) & ( POS < 2000000 ) - *Filter value is either 'PASS' or it is missing*: @@ -131,11 +133,13 @@ (FILTER = 'PASS') | ( na FILTER ) - - *I want to filter lines with an EFF of 'frameshift_variant' ( for vcf files using Sequence Ontology terms )*: + - *I want to filter lines with an ANN annotation EFFECT of 'frameshift_variant' ( for vcf files using Sequence Ontology terms )*: :: - ( EFF[*].EFFECT = 'frameshift_variant' ) + ( ANN[*].EFFECT has 'frameshift_variant' ) + + **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. - *I want to filter lines with an EFF of 'FRAME_SHIFT' ( for vcf files using Classic Effect names )*: @@ -147,31 +151,31 @@ :: - ( QUAL > 30 ) + ( QUAL > 30 ) - *...but we also want InDels that have quality 20 or more*: :: - (( exists INDEL ) & (QUAL >= 20)) | (QUAL >= 30 ) + (( exists INDEL ) & (QUAL >= 20)) | (QUAL >= 30 ) - *...or any homozygous variant present in more than 3 samples*: :: - (countHom() > 3) | (( exists INDEL ) & (QUAL >= 20)) | (QUAL >= 30 ) + (countHom() > 3) | (( exists INDEL ) & (QUAL >= 20)) | (QUAL >= 30 ) - *...or any heterozygous sample with coverage 25 or more*: :: - ((countHet() > 0) & (DP >= 25)) | (countHom() > 3) | (( exists INDEL ) & (QUAL >= 20)) | (QUAL >= 30 ) + ((countHet() > 0) & (DP >= 25)) | (countHom() > 3) | (( exists INDEL ) & (QUAL >= 20)) | (QUAL >= 30 ) - *I want to keep samples where the genotype for the first sample is homozygous variant and the genotype for the second sample is reference*: :: - (isHom( GEN[0] ) & isVariant( GEN[0] ) & isRef( GEN[1] )) + (isHom( GEN[0] ) & isVariant( GEN[0] ) & isRef( GEN[1] )) **For information regarding HGVS and Sequence Ontology terms versus classic names**: @@ -185,5 +189,6 @@ @CITATION_SECTION@ +]]> </help> </tool> |
| b |
| diff -r 1739678def32 -r baf6602903e1 snpSift_int.xml --- a/snpSift_int.xml Thu Oct 23 06:06:25 2014 -0500 +++ b/snpSift_int.xml Wed Dec 09 14:03:26 2015 -0500 |
| [ |
| @@ -1,14 +1,17 @@ -<tool id="snpSift_int" name="SnpSift Intervals" version="4.0.0"> +<tool id="snpSift_int" name="SnpSift Intervals" version="@WRAPPER_VERSION@.0"> <description>Filter variants using intervals</description> <!-- You can change the amount of memory used, just change the -Xmx parameter (e.g. use -Xmx2G for 2Gb of memory) --> + <macros> + <import>snpSift_macros.xml</import> + </macros> <expand macro="requirements" /> - <macros> - <import>snpEff_macros.xml</import> - </macros> - <command> + <expand macro="stdio" /> + <expand macro="version_command" /> + <command><![CDATA[ java -Xmx2G -jar \$SNPEFF_JAR_PATH/SnpSift.jar intervals -i $input $exclude $bedFile > $output +]]> </command> <inputs> <param format="vcf" name="input" type="data" label="Variant input file in VCF format"/> @@ -19,7 +22,6 @@ <outputs> <data format="vcf" name="output" /> </outputs> - <expand macro="stdio" /> <tests> <test> <param name="input" ftype="vcf" value="annotate_5.vcf"/> @@ -44,14 +46,15 @@ </output> </test> </tests> - <help> + <help><![CDATA[ You can filter using intervals (BED file). @EXTERNAL_DOCUMENTATION@ - http://snpeff.sourceforge.net/SnpSift.html#intervals + http://snpeff.sourceforge.net/SnpSift.html#intervals @CITATION_SECTION@ +]]> </help> </tool> |
| b |
| diff -r 1739678def32 -r baf6602903e1 snpSift_macros.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/snpSift_macros.xml Wed Dec 09 14:03:26 2015 -0500 |
| b |
| @@ -0,0 +1,39 @@ +<macros> + <xml name="requirements"> + <requirements> + <requirement type="package" version="4.1">snpEff</requirement> + </requirements> + </xml> + <xml name="stdio"> + <stdio> + <exit_code range=":-1" level="fatal" description="Error: Cannot open file" /> + <exit_code range="1:" level="fatal" description="Error" /> + </stdio> + </xml> + <xml name="version_command"> + <version_command>java -jar $SNPEFF_JAR_PATH/SnpEff.jar -version</version_command> + </xml> + <token name="@WRAPPER_VERSION@">4.1</token> + <token name="@EXTERNAL_DOCUMENTATION@"> + +For details about this tool, please go to: + http://snpeff.sourceforge.net/SnpEff_manual.html + + </token> + <token name="@CITATION_SECTION@">------ + +**Citation** + +For the underlying tool, please cite the following two publications: + +SnpSift citation: +"Using Drosophila melanogaster as a model for genotoxic chemical mutational studies with a new program, SnpSift", Cingolani, P., et. al., Frontiers in Genetics, 3:35, 2012. + + </token> + <xml name="citations"> + <citations> + <citation type="doi">10.3389/fgene.2012.00035</citation> + <yield /> + </citations> + </xml> +</macros> |
| b |
| diff -r 1739678def32 -r baf6602903e1 snpSift_rmInfo.xml --- a/snpSift_rmInfo.xml Thu Oct 23 06:06:25 2014 -0500 +++ b/snpSift_rmInfo.xml Wed Dec 09 14:03:26 2015 -0500 |
| [ |
| @@ -1,11 +1,14 @@ -<tool id="snpSift_rmInfo" name="SnpSift rmInfo" version="4.0.0"> +<tool id="snpSift_rmInfo" name="SnpSift rmInfo" version="@WRAPPER_VERSION@.0"> <description>remove INFO field annotations</description> - <expand macro="requirements" /> <macros> - <import>snpEff_macros.xml</import> + <import>snpSift_macros.xml</import> </macros> - <command> + <expand macro="requirements" /> + <expand macro="stdio" /> + <expand macro="version_command" /> + <command><![CDATA[ java -Xmx2G -jar \$SNPEFF_JAR_PATH/SnpSift.jar rmInfo $input ' '.join($info_fields.split(',')) > $output +]]> </command> <inputs> <param format="vcf" name="input" type="data" label="Variant input file in VCF format"/> @@ -17,7 +20,6 @@ <outputs> <data format="vcf" name="output" /> </outputs> - <expand macro="stdio" /> <tests> <test> <param name="input" ftype="vcf" value="test-data/test_rmInfo.vcf"/> @@ -25,8 +27,8 @@ <output name="output"> <assert_contents> <has_text text="DP=29" /> - <not_has_text text="EFF=EXON" /> - </assert_contents> + <not_has_text text="EFF=EXON" /> + </assert_contents> </output> </test> <test> @@ -34,23 +36,24 @@ <param name="info_fields" value="EFF"/> <output name="output"> <assert_contents> - <not_has_text text="DP=29;EFF=EXON" /> - </assert_contents> + <not_has_text text="DP=29;EFF=EXON" /> + </assert_contents> </output> </test> </tests> - <help> + <help><![CDATA[ This command removes INFO fields from a VCF file (i.e. removes annotations) Removing INFO fields is usually done because you want to re-annotate the VCF file, thus removing old INFO fields in order to add new ones later. -SnpEff & SnpSift only add annotations and do not change current ones. So, in order to re-annotate a file, you should first remove the old annotations and then re-annotate. +SnpEff & SnpSift only add annotations and do not change current ones. So, in order to re-annotate a file, you should first remove the old annotations and then re-annotate. The reason for this behavior is simply because replacing annotation values is considered a bad practice. Imagine that you have a VCF entry in your re-annotated file having the value "AA=1": How do you know if this is from the old annotations or from the new ones? This confusion often leads to problems in downstream steps of your pipelines, so it's better to avoid the problem by first removing all the previous annotations and then adding the new ones. @EXTERNAL_DOCUMENTATION@ - http://snpeff.sourceforge.net/SnpSift.html#rmInfo + http://snpeff.sourceforge.net/SnpSift.html#rmInfo @CITATION_SECTION@ +]]> </help> </tool> |
| b |
| diff -r 1739678def32 -r baf6602903e1 snpSift_vartype.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/snpSift_vartype.xml Wed Dec 09 14:03:26 2015 -0500 |
| [ |
| @@ -0,0 +1,43 @@ +<tool id="snpsift_vartype" name="SnpSift Variant Type" version="@WRAPPER_VERSION@.0"> + <description>Annotate with variant type</description> + <macros> + <import>snpSift_macros.xml</import> + </macros> + <expand macro="requirements" /> + <expand macro="stdio" /> + <expand macro="version_command" /> + <command><![CDATA[ + java -jar \$SNPEFF_JAR_PATH/SnpSift.jar varType $input 2> $log > $output +]]> + </command> + <inputs> + <param format="vcf" name="input" type="data" label="Variant file (VCF)"/> + </inputs> + <outputs> + <data format="vcf" name="output" label="${tool.name} on ${on_string}: VCF" /> + <data format="txt" name="log" label="${tool.name} on ${on_string}: log" /> + </outputs> + <tests> + </tests> + <help><![CDATA[ +**What it does** + +This tool uses `SnpSift Variant type`_ to add the variant type (SNP/MNP/INS/DEL/MIXED) in the INFO field. It also adds "HOM/HET", but this last one works if there is only one sample (otherwise it doesn't make any sense). + +.. _SnpSift Variant type: http://snpeff.sourceforge.net/SnpSift.html#VariantType + +------ + +**License** + +This Galaxy tool is Copyright © 2013-2014 `CRS4 Srl.`_ and is released under the `MIT license`_. + +.. _CRS4 Srl.: http://www.crs4.it/ +.. _MIT license: http://opensource.org/licenses/MIT + +@CITATION_SECTION@ + +]]> + </help> + <expand macro="citations" /> +</tool> |
| b |
| diff -r 1739678def32 -r baf6602903e1 snpSift_vcfCheck.xml --- a/snpSift_vcfCheck.xml Thu Oct 23 06:06:25 2014 -0500 +++ b/snpSift_vcfCheck.xml Wed Dec 09 14:03:26 2015 -0500 |
| [ |
| @@ -1,11 +1,14 @@ -<tool id="snpSift_vcfCheck" name="SnpSift vcfCheck" version="4.0.0"> +<tool id="snpSift_vcfCheck" name="SnpSift vcfCheck" version="@WRAPPER_VERSION@.0"> <description>basic checks for Vcf specification compliance</description> - <expand macro="requirements" /> <macros> - <import>snpEff_macros.xml</import> + <import>snpSift_macros.xml</import> </macros> - <command> + <expand macro="requirements" /> + <expand macro="stdio" /> + <expand macro="version_command" /> + <command><![CDATA[ java -Xmx2G -jar \$SNPEFF_JAR_PATH/SnpSift.jar vcfCheck $input > $output +]]> </command> <inputs> <param format="vcf" name="input" type="data" label="Variant input file in VCF format to check"/> @@ -13,7 +16,6 @@ <outputs> <data format="vcf" name="output" /> </outputs> - <expand macro="stdio" /> <tests> <test> <param name="input" ftype="vcf" value="test-data/test_bad.vcf"/> @@ -24,7 +26,7 @@ </output> </test> </tests> - <help> + <help><![CDATA[ Perform some basic check ups on VCF files to spot common problems. @@ -35,5 +37,6 @@ @CITATION_SECTION@ +]]> </help> </tool> |
| b |
| diff -r 1739678def32 -r baf6602903e1 tool_dependencies.xml --- a/tool_dependencies.xml Thu Oct 23 06:06:25 2014 -0500 +++ b/tool_dependencies.xml Wed Dec 09 14:03:26 2015 -0500 |
| b |
| @@ -1,7 +1,6 @@ <?xml version="1.0"?> <tool_dependency> - <package name="snpEff" version="4.0"> - <repository name="package_snpeff_4_0" owner="jjohnson" changeset_revision="4ac635fc1781" toolshed="http://testtoolshed.g2.bx.psu.edu/" /> + <package name="snpEff" version="4.1"> + <repository changeset_revision="02a5e07a4121" name="package_snpeff_4_1" owner="iuc" toolshed="https://testtoolshed.g2.bx.psu.edu" /> </package> </tool_dependency> - |