Mercurial > repos > iuc > snpsift
changeset 13:ed810da439cc draft
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tool_collections/snpsift/snpsift commit d12a2e9dd273b4c23db48bbb747f32700887710e
| author | iuc |
|---|---|
| date | Tue, 07 Jun 2016 09:41:13 -0400 |
| parents | 6bf58286d795 |
| children | 80da7fae14b8 |
| files | snpSift_annotate.xml snpSift_caseControl.xml snpSift_extractFields.xml snpSift_filter.xml snpSift_int.xml snpSift_macros.xml snpSift_rmInfo.xml snpSift_vartype.xml snpSift_vcfCheck.xml tool_dependencies.xml |
| diffstat | 10 files changed, 340 insertions(+), 97 deletions(-) [+] |
line wrap: on
line diff
--- a/snpSift_annotate.xml Tue Oct 13 17:31:24 2015 -0400 +++ b/snpSift_annotate.xml Tue Jun 07 09:41:13 2016 -0400 @@ -1,6 +1,6 @@ -<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> @@ -8,33 +8,35 @@ </macros> <expand macro="requirements" /> <expand macro="stdio" /> - <command> - java -Xmx6G -jar \$SNPEFF_JAR_PATH/SnpSift.jar $annotate_cmd + <expand macro="version_command" /> + <command><![CDATA[ + java -Xmx6G -jar "\$SNPEFF_JAR_PATH/SnpSift.jar" $annotate_cmd #if $annotate.id : -id - #elif $annotate.info_ids.__str__.strip() != '' : + #elif str($annotate.info_ids).strip() != '' : -info "$annotate.info_ids" - #end if - -q $dbSnp $input > $output + #end if + -q "$dbSnp" "$input" > "$output" +]]> </command> <inputs> <param format="vcf" name="input" type="data" label="Variant input file in VCF format"/> - <param format="vcf" name="dbSnp" type="data" label="VCF File with ID field annotated (e.g. dnSNP.vcf)" + <param format="vcf" name="dbSnp" type="data" label="VCF File with ID field annotated (e.g. dnSNP.vcf)" help="The ID field for a variant in input will be assigned from a matching variant in this file."/> <conditional name="annotate"> <param name="id" type="boolean" truevalue="id" falsevalue="info" checked="True" label="Only annotate ID field (do not add INFO field)" help=""/> <when value="id"/> <when value="info"> <param name="info_ids" type="text" value="" optional="true" label="Limit INFO annotation to these INFO IDs" - help="list is a comma separated list of fields. When blank, all INFO fields are included"> + help="list is a comma separated list of fields. When blank, all INFO fields are included"> <validator type="regex" message="IDs separted by commas">^(([a-zA-Z][a-zA-Z0-9_-]*)(,[a-zA-Z][a-zA-Z0-9_-]*)*)?$</validator> </param> </when> </conditional> - <param name="annotate_cmd" type="boolean" truevalue="annMem" falsevalue="annotate" checked="false" label="Allow unsorted VCF files"> + <param name="annotate_cmd" type="boolean" truevalue="annMem" falsevalue="annotate" checked="false" label="Allow unsorted VCF files"> <help> This option will load the entire 'database' VCF file into memory (which may not be practical for large 'database' VCF files). - Otherwise, both the database and the input VCF files should be sorted by position (Chromosome sort order can differ between files). + Otherwise, both the database and the input VCF files should be sorted by position (Chromosome sort order can differ between files). </help> </param> </inputs> @@ -54,7 +56,7 @@ </output> </test> </tests> - <help> + <help><![CDATA[ This is typically used to annotate IDs from dbSnp. @@ -92,9 +94,8 @@ @EXTERNAL_DOCUMENTATION@ http://snpeff.sourceforge.net/SnpSift.html#annotate -@CITATION_SECTION@ - - +]]> </help> + <expand macro="citations" /> </tool>
--- a/snpSift_caseControl.xml Tue Oct 13 17:31:24 2015 -0400 +++ b/snpSift_caseControl.xml Tue Jun 07 09:41:13 2016 -0400 @@ -1,6 +1,6 @@ -<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> @@ -8,17 +8,19 @@ </macros> <expand macro="requirements" /> <expand macro="stdio" /> - <command> - java -Xmx1G -jar \$SNPEFF_JAR_PATH/SnpSift.jar caseControl -q - #if $name.__str__.strip() != '': - -name $name + <expand macro="version_command" /> + <command><![CDATA[ + java -Xmx1G -jar "\$SNPEFF_JAR_PATH/SnpSift.jar" caseControl -q + #if str($name).strip() != '': + -name "$name" #end if #if $ctrl.ctrl_src == 'caseString': - '$ctrl.caseControlStr' + '$ctrl.caseControlStr' #else -tfam "$ctrl.tfam" #end if - $input > $output + "$input" > "$output" +]]> </command> <inputs> <param format="vcf" name="input" type="data" label="Variant input file in VCF format"/> @@ -28,7 +30,7 @@ <option value="tfam">TFAM file</option> </param> <when value="caseString"> - <param name="caseControlStr" type="text" label="Case / Control column designation"> + <param name="caseControlStr" type="text" label="Case / Control column designation" size="50"> <help> Case and control are defined by a string containing plus and minus symbols {'+', '-', '0'} where '+' is case, '-' is control and '0' is neutral </help> @@ -84,17 +86,17 @@ </output> </test> </tests> - <help> + <help><![CDATA[ **SnpSift CaseControl** -Allows you to count how many samples are in 'case' group and a 'control' group. You can count 'homozygous', 'heterozygous' or 'any' variants. +Allows you to count how many samples are in 'case' group and a 'control' group. You can count 'homozygous', 'heterozygous' or 'any' variants. -Case and control are defined by a string containing plus and minus symbols {'+', '-', '0'} where '+' is case, '-' is control and '0' is neutral. +Case and control are defined by a string containing plus and minus symbols {'+', '-', '0'} where '+' is case, '-' is control and '0' is neutral. This command adds two annotations to the VCF file: - - **CaseControl**: Two comma separated numbers numbers representing the number of samples that have the variant in the case and the control group. Example: + - **CaseControl**: Two comma separated numbers numbers representing the number of samples that have the variant in the case and the control group. Example: "CaseControl=3,4" *the variant is present in 3 cases and 4 controls.* @@ -108,7 +110,7 @@ - Hom/Het case = "hom" - - Hom/Het control = "any" + - Hom/Het control = "any" - Case / Control column designation = ""++++------" @@ -116,7 +118,7 @@ @EXTERNAL_DOCUMENTATION@ http://snpeff.sourceforge.net/SnpSift.html#casecontrol -@CITATION_SECTION@ - - </help> +]]> + </help> + <expand macro="citations" /> </tool>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/snpSift_extractFields.xml Tue Jun 07 09:41:13 2016 -0400 @@ -0,0 +1,220 @@ +<tool id="snpSift_extractFields" name="SnpSift Extract Fields" version="@WRAPPER_VERSION@.0"> + <options sanitize="False" /> + <description>from a VCF file inot a tabular file</description> + <macros> + <import>snpSift_macros.xml</import> + </macros> + <expand macro="requirements" /> + <expand macro="stdio" /> + <expand macro="version_command" /> + <command><![CDATA[ + cat "$input" + #if $one_effect_per_line: + | "\$SNPEFF_JAR_PATH/scripts/vcfEffOnePerLine.pl" + #end if + | java -Xmx6G -jar "\$SNPEFF_JAR_PATH/SnpSift.jar" extractFields + #if $separator: + -s '$separator' + #end if + #if $empty_text: + -e '$empty_text' + #end if + - + #echo ' '.join(['"%s"' % x for x in $extract.split()]) + > "$output" +]]> + </command> + <inputs> + <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> + </inputs> + <outputs> + <data format="tabular" name="output" /> + </outputs> + <tests> + <test> + <param name="input" ftype="vcf" value="test_rmInfo.vcf"/> + <param name="extract" value="CHROM POS REF ALT EFF[*].EFFECT"/> + <output name="output"> + <assert_contents> + <has_text text="INTRAGENIC" /> + <not_has_text text="DOWNSTREAM,INTRAGENIC,INTRON,UTR_3_PRIME" /> + </assert_contents> + </output> + </test> + + <test> + <param name="input" ftype="vcf" value="test_rmInfo.vcf"/> + <param name="extract" value="CHROM POS REF ALT EFF[*].EFFECT"/> + <param name="separator" value=","/> + <output name="output"> + <assert_contents> + <has_text text="DOWNSTREAM,INTRAGENIC,INTRON,UTR_3_PRIME" /> + </assert_contents> + </output> + </test> + + </tests> + <help><![CDATA[ + +**SnpSift Extract Fields** + +Extract fields from a VCF file to a TXT, tab separated format, that you can easily load in R, XLS, etc. + +http://snpeff.sourceforge.net/SnpSift.html#Extract + +You can also use sub-fields and genotype fields / sub-fields such as: + + :: + + Standard VCF fields: + CHROM + POS + ID + REF + ALT + FILTER + INFO fields: + AF + AC + DP + MQ + 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.) + "ANN[*].IMPACT" { HIGH, MODERATE, LOW, MODIFIER } + "ANN[*].GENE" Gene name (e.g. 'PSD3') + "ANN[*].GENEID" Gene ID + "ANN[*].FEATURE" + "ANN[*].FEATUREID" (alias TRID: Transcript ID) + "ANN[*].BIOTYPE" Biotype, as described by the annotations (e.g. 'protein_coding') + "ANN[*].RANK" Exon or Intron rank (i.e. exon number in a transcript) + "ANN[*].HGVS_C" (alias HGVS_DNA, CODON): Variant in HGVS (DNA) notation + "ANN[*].HGVS_P" (alias HGVS, HGVS_PROT, AA): Variant in HGVS (protein) notation + "ANN[*].CDNA_POS" (alias POS_CDNA) + "ANN[*].CDNA_LEN" (alias LEN_CDNA) + "ANN[*].CDS_POS" (alias POS_CDS) + "ANN[*].CDS_LEN" (alias LEN_CDS) + "ANN[*].AA_POS" (alias POS_AA) + "ANN[*].AA_LEN" (alias LEN_AA) + "ANN[*].DISTANCE" + "ANN[*].ERRORS" (alias WARNING, INFOS) + SnpEff 'EFF' fields (this is for older SnpEff/SnpSift versions, new version use 'ANN' field): + "EFF[*].EFFECT" + "EFF[*].IMPACT" + "EFF[*].FUNCLASS" + "EFF[*].CODON" + "EFF[*].AA" + "EFF[*].AA_LEN" + "EFF[*].GENE" + "EFF[*].BIOTYPE" + "EFF[*].CODING" + "EFF[*].TRID" + "EFF[*].RANK" + SnpEff 'LOF' fields: + "LOF[*].GENE" + "LOF[*].GENEID" + "LOF[*].NUMTR" + "LOF[*].PERC" + SnpEff' NMD' fields: + "NMD[*].GENE" + "NMD[*].GENEID" + "NMD[*].NUMTR" + "NMD[*].PERC" + + +Some examples: + + - *Extracting chromosome, position, ID and allele frequency from a VCF file:* + + **CHROM POS ID AF** + + The result will look something like: + + :: + + #CHROM POS ID AF + 1 69134 0.086 + 1 69496 rs150690004 0.001 + + + - *Extracting genotype fields:* + + **CHROM POS ID THETA GEN[0].GL[1] GEN[1].GL GEN[3].GL[*] GEN[*].GT** + + This means to extract: + + - CHROM POS ID: regular fields (as in the previous example) + - THETA : This one is from INFO + - 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). + + 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 + + - *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: + + :: + + #CHROM POS REF ALT ANN[*].EFFECT + 22 17071756 T C 3_prime_UTR_variant downstream_gene_variant + 22 17072035 C T missense_variant downstream_gene_variant + 22 17072258 C A missense_variant downstream_gene_variant + + - *Extracting fields with multiple values using a comma as a multipe field separator:* + + **CHROM POS REF ALT ANN[*].EFFECT ANN[*].HGVS_P** + + 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 .,. + 22 17072035 C T missense_variant,downstream_gene_variant p.Gly469Glu,. + 22 17072258 C A missense_variant,downstream_gene_variant p.Gly395Cys,. + + + - *Extracting fields with multiple values, one effect per line:* + + **CHROM POS REF ALT ANN[*].EFFECT** + + The result will look something like: + + :: + + #CHROM POS REF ALT ANN[*].EFFECT + 22 17071756 T C 3_prime_UTR_variant + 22 17071756 T C downstream_gene_variant + 22 17072035 C T missense_variant + 22 17072035 C T downstream_gene_variant + 22 17072258 C A missense_variant + 22 17072258 C A downstream_gene_variant + + +@EXTERNAL_DOCUMENTATION@ + http://snpeff.sourceforge.net/SnpSift.html#Extract + +]]> + </help> + <expand macro="citations" /> +</tool>
--- a/snpSift_filter.xml Tue Oct 13 17:31:24 2015 -0400 +++ b/snpSift_filter.xml Tue Jun 07 09:41:13 2016 -0400 @@ -1,56 +1,60 @@ -<tool id="snpSift_filter" name="SnpSift Filter" version="4.0.0"> - <options sanitize="False" /> +<tool id="snpSift_filter" name="SnpSift Filter" version="@WRAPPER_VERSION@.0"> <description>Filter variants using arbitrary expressions</description> <macros> <import>snpSift_macros.xml</import> </macros> <expand macro="requirements" /> <expand macro="stdio" /> - <command> - java -Xmx6G -jar \$SNPEFF_JAR_PATH/SnpSift.jar filter -f $input -e $exprFile $inverse + <expand macro="version_command" /> + + <command><![CDATA[ + java -Xmx6G -jar "\$SNPEFF_JAR_PATH/SnpSift.jar" filter -f "$input" -e "$exprFile" $inverse #if $filtering.mode == 'field': #if $filtering.replace.pass: --pass - #if $filtering.replace.filterId and len($filtering.replace.filterId.__str__.strip()) > 0: + #if $filtering.replace.filterId and len(str($filtering.replace.filterId).strip()) > 0: --filterId "$filtering.replace.filterId" #end if #end if - #if $filtering.addFilter and len($filtering.addFilter.__str__.strip()) > 0: + #if $filtering.addFilter and len(str($filtering.addFilter).strip()) > 0: --addFilter "$filtering.addFilter" #end if - #if $filtering.rmFilter and len($filtering.rmFilter.__str__.strip()) > 0: + #if $filtering.rmFilter and len(str($filtering.rmFilter).strip()) > 0: --rmFilter "$filtering.rmFilter" #end if #end if - > $output + > "$output" +]]> </command> <configfiles> <configfile name="exprFile"> $expr#slurp - </configfile> + </configfile> </configfiles> <inputs> <param format="vcf" name="input" type="data" label="Variant input file in VCF format"/> - <param name="expr" type="text" label="Filter criteria" help="Need help? See below a few examples." /> + <param name="expr" type="text" label="Filter criteria" help="Need help? See below a few examples." > + <sanitizer sanitize="False"/> + </param> <param name="inverse" type="boolean" truevalue="--inverse" falsevalue="" checked="false" label="Inverse filter" help="Show lines that do not match filter expression" /> <conditional name="filtering"> <param name="mode" type="select" label="Filter mode"> <option value="entries" selected="true">Retain entries that pass filter, remove other entries</option> <option value="field">Change the FILTER field, but retain all entries</option> - </param> + </param> <when value="entries"/> <when value="field"> <conditional name="replace"> - <param name="pass" type="boolean" truevalue="yes" falsevalue="no" checked="false" label="Set matching entry FILTER to 'PASS'" + <param name="pass" type="boolean" truevalue="yes" falsevalue="no" checked="false" label="Set matching entry FILTER to 'PASS'" help="appends an ID tag to non-matching entry FILTER "/> <when value="no"/> <when value="yes"> - <param name="filterId" type="text" value="" optional="true" label="ID appended to non-matching (##FILTER tag in header and FILTER VCF field)." + <param name="filterId" type="text" value="" optional="true" label="ID appended to non-matching (##FILTER tag in header and FILTER VCF field)." help="Default ID is 'SnpSift'"/> </when> </conditional> - <param name="addFilter" type="text" value="" optional="true" label="Add a string to FILTER VCF field if 'expression' is true."/> - <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)."/> + <param name="addFilter" type="text" value="" optional="true" label="Add a string to FILTER VCF field if 'expression' is true." /> + <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)." /> </when> </conditional> </inputs> @@ -85,7 +89,7 @@ <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> @@ -100,7 +104,7 @@ <test> <param name="input" ftype="vcf" value="test01.vcf"/> - <param name="expr" value="( DP >= 5 )"/> + <param name="expr" value="( DP >= 5 )"/> <param name="mode" value="entries"/> <output name="output"> <assert_contents> @@ -111,7 +115,7 @@ </output> </test> </tests> - <help> + <help><![CDATA[ **SnpSift filter** @@ -123,55 +127,57 @@ :: - ( CHROM = 'chr1' ) & ( POS > 1000000 ) & ( POS < 2000000 ) + ( CHROM = 'chr1' ) & ( POS > 1000000 ) & ( POS < 2000000 ) - *Filter value is either 'PASS' or it is missing*: :: - (FILTER = 'PASS') | ( na FILTER ) + (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 )*: :: + + ( ANN[*].EFFECT has 'frameshift_variant' ) - ( EFF[*].EFFECT = '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 )*: :: - + ( EFF[*].EFFECT = 'FRAME_SHIFT' ) - *I want to filter out samples with quality less than 30*: :: - ( 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**: @@ -183,7 +189,7 @@ @EXTERNAL_DOCUMENTATION@ http://snpeff.sourceforge.net/SnpSift.html#filter -@CITATION_SECTION@ - +]]> </help> + <expand macro="citations" /> </tool>
--- a/snpSift_int.xml Tue Oct 13 17:31:24 2015 -0400 +++ b/snpSift_int.xml Tue Jun 07 09:41:13 2016 -0400 @@ -1,6 +1,6 @@ -<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> @@ -8,13 +8,15 @@ </macros> <expand macro="requirements" /> <expand macro="stdio" /> - <command> - java -Xmx2G -jar \$SNPEFF_JAR_PATH/SnpSift.jar intervals -i $input $exclude $bedFile > $output + <expand macro="version_command" /> + <command><![CDATA[ + java -Xmx2G -jar "\$SNPEFF_JAR_PATH/SnpSift.jar" intervals -i "$input" $exclude "$bedFile" > "$output" +]]> </command> <inputs> <param format="vcf" name="input" type="data" label="Variant input file in VCF format"/> <param format="bed" name="bedFile" type="data" label="Intervals (BED file)"/> - <param name="exclude" type="boolean" truevalue="-x" falsevalue="" checked="false" label="Exclude Intervals" + <param name="exclude" type="boolean" truevalue="-x" falsevalue="" checked="false" label="Exclude Intervals" help="Filter out (exclude) VCF entries that match any interval in the BED files"/> </inputs> <outputs> @@ -44,14 +46,14 @@ </output> </test> </tests> - <help> + <help><![CDATA[ You can filter using intervals (BED file). @EXTERNAL_DOCUMENTATION@ http://snpeff.sourceforge.net/SnpSift.html#intervals -@CITATION_SECTION@ - +]]> </help> + <expand macro="citations" /> </tool>
--- a/snpSift_macros.xml Tue Oct 13 17:31:24 2015 -0400 +++ b/snpSift_macros.xml Tue Jun 07 09:41:13 2016 -0400 @@ -1,7 +1,7 @@ <macros> <xml name="requirements"> <requirements> - <requirement type="package" version="4.0">snpEff</requirement> + <requirement type="package" version="4.1">snpEff</requirement> </requirements> </xml> <xml name="stdio"> @@ -10,6 +10,10 @@ <exit_code range="1:" level="fatal" description="Error" /> </stdio> </xml> + <xml name="version_command"> + <version_command>java -jar "$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:
--- a/snpSift_rmInfo.xml Tue Oct 13 17:31:24 2015 -0400 +++ b/snpSift_rmInfo.xml Tue Jun 07 09:41:13 2016 -0400 @@ -1,12 +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> <macros> <import>snpSift_macros.xml</import> </macros> <expand macro="requirements" /> <expand macro="stdio" /> - <command> - java -Xmx2G -jar \$SNPEFF_JAR_PATH/SnpSift.jar rmInfo $input ' '.join($info_fields.split(',')) > $output + <expand macro="version_command" /> + <command><![CDATA[ + java -Xmx2G -jar "\$SNPEFF_JAR_PATH/SnpSift.jar" rmInfo "$input" ' '.join($info_fields.split(',')) > "$output" +]]> </command> <inputs> <param format="vcf" name="input" type="data" label="Variant input file in VCF format"/> @@ -39,18 +41,18 @@ </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. +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. -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. +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 -@CITATION_SECTION@ - +]]> </help> + <expand macro="citations" /> </tool>
--- a/snpSift_vartype.xml Tue Oct 13 17:31:24 2015 -0400 +++ b/snpSift_vartype.xml Tue Jun 07 09:41:13 2016 -0400 @@ -1,12 +1,14 @@ -<tool id="snpsift_vartype" name="SnpSift Variant Type" version="4.0.0"> +<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" /> - <command> - java -jar \$SNPEFF_JAR_PATH/SnpSift.jar varType $input 2> $log > $output + <expand macro="version_command" /> + <command><![CDATA[ + java -jar "\$SNPEFF_JAR_PATH/SnpSift.jar" varType "$input" 2> "$log" > "$output" +]]> </command> <inputs> <param format="vcf" name="input" type="data" label="Variant file (VCF)"/> @@ -17,7 +19,7 @@ </outputs> <tests> </tests> - <help> + <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). @@ -34,6 +36,8 @@ .. _MIT license: http://opensource.org/licenses/MIT @CITATION_SECTION@ + +]]> </help> <expand macro="citations" /> </tool>
--- a/snpSift_vcfCheck.xml Tue Oct 13 17:31:24 2015 -0400 +++ b/snpSift_vcfCheck.xml Tue Jun 07 09:41:13 2016 -0400 @@ -1,12 +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> <macros> <import>snpSift_macros.xml</import> </macros> <expand macro="requirements" /> <expand macro="stdio" /> - <command> - java -Xmx2G -jar \$SNPEFF_JAR_PATH/SnpSift.jar vcfCheck $input > $output + <expand macro="version_command" /> + <command><![CDATA[ + java -Xmx2G -jar "\$SNPEFF_JAR_PATH/SnpSift.jar" vcfCheck "$input" > "$output" +]]> </command> <inputs> <param format="vcf" name="input" type="data" label="Variant input file in VCF format to check"/> @@ -24,16 +26,16 @@ </output> </test> </tests> - <help> + <help><![CDATA[ Perform some basic check ups on VCF files to spot common problems. -SnpSift vcfCheck checks for some common problems where VCF files are not following the specification. Given that many common VCF problems cause analysis tools and pipelines to behave unexpectedly, this command is intended as a simple debugging tool. +SnpSift vcfCheck checks for some common problems where VCF files are not following the specification. Given that many common VCF problems cause analysis tools and pipelines to behave unexpectedly, this command is intended as a simple debugging tool. @EXTERNAL_DOCUMENTATION@ http://snpeff.sourceforge.net/SnpSift.html#vcfCheck -@CITATION_SECTION@ - +]]> </help> + <expand macro="citations" /> </tool>
--- a/tool_dependencies.xml Tue Oct 13 17:31:24 2015 -0400 +++ b/tool_dependencies.xml Tue Jun 07 09:41:13 2016 -0400 @@ -1,6 +1,6 @@ <?xml version="1.0"?> <tool_dependency> - <package name="snpEff" version="4.0"> - <repository changeset_revision="15d3951f1517" name="package_snpeff_4_0" owner="iuc" toolshed="https://testtoolshed.g2.bx.psu.edu" /> + <package name="snpEff" version="4.1"> + <repository changeset_revision="733a2dcb9853" name="package_snpeff_4_1" owner="iuc" toolshed="https://testtoolshed.g2.bx.psu.edu" /> </package> </tool_dependency>