Mercurial > repos > iuc > seqtk
changeset 3:bc7d99f46a5d draft
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/seqtk commit 7379d9f8823d3c639c8119b116e141d0a736ca1d
| author | iuc |
|---|---|
| date | Mon, 05 Jun 2017 13:27:11 -0400 |
| parents | f73729b62b51 |
| children | ecf1c30da3a2 |
| files | macros.xml seqtk_comp.xml seqtk_cutN.xml seqtk_dropse.xml seqtk_fqchk.xml seqtk_hety.xml seqtk_listhet.xml seqtk_mergefa.xml seqtk_mergepe.xml seqtk_mutfa.xml seqtk_randbase.xml seqtk_sample.xml seqtk_seq.xml seqtk_subseq.xml seqtk_trimfq.xml tool_dependencies.xml |
| diffstat | 16 files changed, 515 insertions(+), 498 deletions(-) [+] |
line wrap: on
line diff
--- a/macros.xml Fri Jan 01 14:49:42 2016 -0500 +++ b/macros.xml Mon Jun 05 13:27:11 2017 -0400 @@ -1,37 +1,36 @@ <?xml version="1.0"?> <macros> - <xml name="requirements"> - <requirements> - <requirement type="package" version="1.0-r75-dirty">seqtk</requirement> - <yield/> - </requirements> - </xml> - <token name="@WRAPPER_VERSION@">1.0-r75-dirty</token> - <xml name="stdio"> - <stdio> - <!-- Anything other than zero is an error --> - <exit_code range="1:"/> - <exit_code range=":-1"/> - <!-- In case the return code has not been set propery check stderr too --> - <regex match="Error:"/> - <regex match="Exception:"/> - </stdio> - </xml> - <xml name="in_fq"> - <param name="in_file" type="data" format="fastq" label="Input FASTQ file"/> - </xml> - <xml name="in_faq"> - <param name="in_file" type="data" format="fasta,fastq" label="Input FASTA/Q file"/> - </xml> - <token name="@ATTRIBUTION@"><![CDATA[ + <xml name="requirements"> + <requirements> + <requirement type="package" version="1.2">seqtk</requirement> + <yield/> + </requirements> + </xml> + <token name="@WRAPPER_VERSION@">1.2</token> + <xml name="stdio"> + <stdio> + <!-- Anything other than zero is an error --> + <exit_code range="1:"/> + <exit_code range=":-1"/> + <!-- In case the return code has not been set propery check stderr too --> + <regex match="Error:"/> + <regex match="Exception:"/> + </stdio> + </xml> + <xml name="in_fq"> + <param name="in_file" type="data" format="fastq" label="Input FASTQ file"/> + </xml> + <xml name="in_faq"> + <param name="in_file" type="data" format="fasta,fastq" label="Input FASTA/Q file"/> + </xml> + <token name="@ATTRIBUTION@"><![CDATA[ **Attribution** This Galaxy tool relies on the seqtk toolkit from `lh3/seqtk <https://github.com/lh3/seqtk/>`_, developed by Heng Li at the Broad Institute - ]]> - </token> - <xml name="citation"> - <citations> - </citations> - </xml> + ]]></token> + <xml name="citation"> + <citations> + </citations> + </xml> </macros>
--- a/seqtk_comp.xml Fri Jan 01 14:49:42 2016 -0500 +++ b/seqtk_comp.xml Mon Jun 05 13:27:11 2017 -0400 @@ -1,33 +1,33 @@ <?xml version="1.0"?> <tool id="seqtk_comp" name="seqtk_comp" version="@WRAPPER_VERSION@.0"> - <description>get the nucleotide composition of FASTA/Q</description> - <macros> - <import>macros.xml</import> - </macros> - <expand macro="requirements"/> - <expand macro="stdio"/> - <command><![CDATA[seqtk comp + <description>get the nucleotide composition of FASTA/Q</description> + <macros> + <import>macros.xml</import> + </macros> + <expand macro="requirements"/> + <expand macro="stdio"/> + <command><![CDATA[ +seqtk comp #if $in_bed: --r $in_bed + -r '$in_bed' #end if - -$in_file | awk 'BEGIN{print "#chr\tlength\t#A\t#C\t#G\t#T\t#2\t#3\t#4\t#CpG\t#tv\t#ts\t#CpG-ts"}1' - -> $default]]></command> - <inputs> - <expand macro="in_faq"/> - <param name="in_bed" optional="True" type="data" format="bed" label="bed file"/> - </inputs> - <outputs> - <data format="tabular" hidden="false" name="default" label="Nucleotide composition of $in_file.name"/> - </outputs> - <tests> - <test> - <param name="in_file" value="seqtk_comp.fa" ftype="fasta"/> - <output name="default" file="seqtk_comp.out" ftype="tabular"/> - </test> - </tests> - <help><![CDATA[ +'$in_file' | awk 'BEGIN{print "#chr\tlength\t#A\t#C\t#G\t#T\t#2\t#3\t#4\t#CpG\t#tv\t#ts\t#CpG-ts"}1' +> '$default' + ]]></command> + <inputs> + <expand macro="in_faq"/> + <param name="in_bed" type="data" format="bed" optional="true" label="BED file"/> + </inputs> + <outputs> + <data name="default" format="tabular" label="Nucleotide composition of $in_file.name"/> + </outputs> + <tests> + <test> + <param name="in_file" value="seqtk_comp.fa" ftype="fasta"/> + <output name="default" file="seqtk_comp.out" ftype="tabular"/> + </test> + </tests> + <help><![CDATA[ **What it does** Reports composition of fasta/fastq sequences. For an example sequence like @@ -46,8 +46,7 @@ test0 11 4 2 2 2 0 0 1 0 0 0 0 ambig_ref 15 1 2 3 4 0 4 1 4 0 0 0 - @ATTRIBUTION@ -]]></help> - <expand macro="citation" /> + ]]></help> + <expand macro="citation" /> </tool>
--- a/seqtk_cutN.xml Fri Jan 01 14:49:42 2016 -0500 +++ b/seqtk_cutN.xml Mon Jun 05 13:27:11 2017 -0400 @@ -1,33 +1,36 @@ <?xml version="1.0"?> <tool id="seqtk_cutN" name="seqtk_cutN" version="@WRAPPER_VERSION@.0"> - <description>cut sequence at long N</description> - <macros> - <import>macros.xml</import> - </macros> - <expand macro="requirements"/> - <expand macro="stdio"/> - <command><![CDATA[seqtk cutN -n $n + <description>cut sequence at long N</description> + <macros> + <import>macros.xml</import> + </macros> + <expand macro="requirements"/> + <expand macro="stdio"/> + <command><![CDATA[ +seqtk cutN +-n $n -p $p $g -$in_file -> $default]]></command> - <inputs> - <expand macro="in_faq"/> - <param label="min size of N tract" help="(-n)" name="n" type="integer" value="1000"/> - <param label="penalty for a non-N" help="(-p)" name="p" type="integer" value="10"/> - <param checked="false" label="print gaps only, no sequence" help="(-g)" name="g" type="boolean" falsevalue="" truevalue="-g"/> - </inputs> - <outputs> - <data format_source="in_file" hidden="false" name="default" label="$in_file.name split on N runs longer than $n"/> - </outputs> - <tests> - <test> - <param name="in_file" value="seqtk_cutn.fa"/> - <param name="n" value="1"/> - <output name="default" file="seqtk_cutn.out" ftype="fasta"/> - </test> - </tests> - <help><![CDATA[ +'$in_file' +> '$default' + ]]></command> + <inputs> + <expand macro="in_faq"/> + <param argument="-n" type="integer" value="1000" label="Minimum size of N tract" /> + <param argument="-p" type="integer" value="10" label="Penalty for a non-N" /> + <param argument="-g" type="boolean" truevalue="-g" falsevalue="" checked="false" label="Print gaps only, no sequence" /> + </inputs> + <outputs> + <data name="default" format_source="in_file" label="$in_file.name split on N runs longer than $n"/> + </outputs> + <tests> + <test> + <param name="in_file" value="seqtk_cutn.fa"/> + <param name="n" value="1"/> + <output name="default" file="seqtk_cutn.out" ftype="fasta"/> + </test> + </tests> + <help><![CDATA[ **What it does** Splits long sequences with runs of Ns @@ -46,8 +49,7 @@ >test:29-33 ACATG - @ATTRIBUTION@ -]]></help> - <expand macro="citation" /> + ]]></help> + <expand macro="citation" /> </tool>
--- a/seqtk_dropse.xml Fri Jan 01 14:49:42 2016 -0500 +++ b/seqtk_dropse.xml Mon Jun 05 13:27:11 2017 -0400 @@ -1,27 +1,29 @@ <?xml version="1.0"?> <tool id="seqtk_dropse" name="seqtk_dropse" version="@WRAPPER_VERSION@.0"> - <description>drop unpaired from interleaved Paired End FASTA/Q</description> - <macros> - <import>macros.xml</import> - </macros> - <expand macro="requirements"/> - <expand macro="stdio"/> - <command><![CDATA[seqtk dropse - $in_file -> $default]]></command> - <inputs> - <expand macro="in_faq"/> - </inputs> - <outputs> - <data format_source="in_file" hidden="false" name="default" label="Only paired-end reads from $in_file.name"/> - </outputs> - <tests> - <test> - <param name="in_file" value="seqtk_dropse.fq"/> - <output name="default" file="seqtk_dropse.out" ftype="fastq"/> - </test> - </tests> - <help><![CDATA[ + <description>drop unpaired from interleaved Paired End FASTA/Q</description> + <macros> + <import>macros.xml</import> + </macros> + <expand macro="requirements"/> + <expand macro="stdio"/> + <command><![CDATA[ +seqtk dropse +'$in_file' +> '$default' + ]]></command> + <inputs> + <expand macro="in_faq"/> + </inputs> + <outputs> + <data name="default" format_source="in_file" label="Only paired-end reads from $in_file.name"/> + </outputs> + <tests> + <test> + <param name="in_file" value="seqtk_dropse.fq"/> + <output name="default" file="seqtk_dropse.out" ftype="fastq"/> + </test> + </tests> + <help><![CDATA[ **What it does** Remove unpaired reads in an interleaved paired-end FASTA/Q file. Given a fastq file with unpaired reads: @@ -70,8 +72,7 @@ + ?=?*?A?<?@ - @ATTRIBUTION@ -]]></help> - <expand macro="citation" /> + ]]></help> + <expand macro="citation" /> </tool>
--- a/seqtk_fqchk.xml Fri Jan 01 14:49:42 2016 -0500 +++ b/seqtk_fqchk.xml Mon Jun 05 13:27:11 2017 -0400 @@ -1,29 +1,31 @@ <?xml version="1.0"?> <tool id="seqtk_fqchk" name="seqtk_fqchk" version="@WRAPPER_VERSION@.0"> - <description>fastq QC (base/quality summary)</description> - <macros> - <import>macros.xml</import> - </macros> - <expand macro="requirements"/> - <expand macro="stdio"/> - <command><![CDATA[seqtk fqchk + <description>fastq QC (base/quality summary)</description> + <macros> + <import>macros.xml</import> + </macros> + <expand macro="requirements"/> + <expand macro="stdio"/> + <command><![CDATA[ +seqtk fqchk -q $q -$in_file | awk '{if(NR<4){print "#"$0}else{print $0}}' -> $default]]></command> - <inputs> - <expand macro="in_fq"/> - <param name="q" type="integer" value="20" label="quality values" help="use 0 to get the distribution of all quality values (-q)"/> - </inputs> - <outputs> - <data format="tabular" hidden="false" name="default" label="Quality information for $in_file.name"/> - </outputs> - <tests> - <test> - <param name="in_file" value="seqtk_fqchk.fq"/> - <output name="default" file="seqtk_fqchk.out" ftype="tabular"/> - </test> - </tests> - <help><![CDATA[ +'$in_file' | awk '{if(NR<4){print "#"$0}else{print $0}}' +> '$default' + ]]></command> + <inputs> + <expand macro="in_fq"/> + <param argument="-q" type="integer" value="20" label="Quality values" help="Use 0 to get the distribution of all quality values"/> + </inputs> + <outputs> + <data name="default" format="tabular" label="Quality information for $in_file.name"/> + </outputs> + <tests> + <test> + <param name="in_file" value="seqtk_fqchk.fq"/> + <output name="default" file="seqtk_fqchk.out" ftype="tabular"/> + </test> + </tests> + <help><![CDATA[ **What it does** Returns quality score information base-by-base. @@ -54,6 +56,6 @@ 10 1 0.0 0.0 0.0 100.0 0.0 9.0 9.0 100.0 0.0 @ATTRIBUTION@ -]]></help> - <expand macro="citation" /> + ]]></help> + <expand macro="citation" /> </tool>
--- a/seqtk_hety.xml Fri Jan 01 14:49:42 2016 -0500 +++ b/seqtk_hety.xml Mon Jun 05 13:27:11 2017 -0400 @@ -1,33 +1,36 @@ <?xml version="1.0"?> <tool id="seqtk_hety" name="seqtk_hety" version="@WRAPPER_VERSION@.0"> - <description>regional heterozygosity</description> - <macros> - <import>macros.xml</import> - </macros> - <expand macro="requirements"/> - <expand macro="stdio"/> - <command><![CDATA[seqtk hety -w $w + <description>regional heterozygosity</description> + <macros> + <import>macros.xml</import> + </macros> + <expand macro="requirements"/> + <expand macro="stdio"/> + <command><![CDATA[ +seqtk hety +-w $w -t $t $m -$in_file | awk 'BEGIN{print "#chr\tstart\tend\tA\tB\tnum_het"}1' -> $default]]></command> - <inputs> - <expand macro="in_faq"/> - <param label="window size" help="(-w)" name="w" type="integer" value="50000"/> - <param label="# start positions in a window" help="(-t)" name="t" type="integer" value="5"/> - <param checked="false" label="treat lowercases as masked" help="(-m)" name="m" type="boolean" falsevalue="" truevalue="-m"/> - </inputs> - <outputs> - <data format="tabular" hidden="false" name="default" label="Heterozygous regions in $in_file.name"/> - </outputs> - <tests> - <test> - <param name="in_file" value="seqtk_hety.fa"/> - <param name="w" value="8"/> - <output name="default" file="seqtk_hety.out" ftype="tabular"/> - </test> - </tests> - <help><![CDATA[ +'$in_file' | awk 'BEGIN{print "#chr\tstart\tend\tA\tB\tnum_het"}1' +> '$default' + ]]></command> + <inputs> + <expand macro="in_faq"/> + <param argument="-w" type="integer" value="50000" label="Window size" /> + <param argument="-t" type="integer" value="5" label="# start positions in a window" /> + <param argument="-m" type="boolean" truevalue="-m" falsevalue="" checked="false" label="Treat lowercases as masked" /> + </inputs> + <outputs> + <data name="default" format="tabular" label="Heterozygous regions in $in_file.name"/> + </outputs> + <tests> + <test> + <param name="in_file" value="seqtk_hety.fa"/> + <param name="w" value="8"/> + <output name="default" file="seqtk_hety.out" ftype="tabular"/> + </test> + </tests> + <help><![CDATA[ **What it does** Reports on heterozygosity over a region @@ -69,6 +72,6 @@ If you know what A and B are measures of, please `submit an issue <https://github.com/galaxyproject/tools-iuc/issues>`__ and it will be corrected @ATTRIBUTION@ -]]></help> - <expand macro="citation" /> + ]]></help> + <expand macro="citation" /> </tool>
--- a/seqtk_listhet.xml Fri Jan 01 14:49:42 2016 -0500 +++ b/seqtk_listhet.xml Mon Jun 05 13:27:11 2017 -0400 @@ -1,25 +1,29 @@ <?xml version="1.0"?> <tool id="seqtk_listhet" name="seqtk_listhet" version="@WRAPPER_VERSION@.0"> - <description>extract the position of each het</description> - <macros> - <import>macros.xml</import> - </macros> - <expand macro="requirements"/> - <expand macro="stdio"/> - <command><![CDATA[seqtk listhet $in_file | awk 'BEGIN{print "#chr\tposition\tbase"}1' > $default]]></command> - <inputs> - <expand macro="in_faq"/> - </inputs> - <outputs> - <data format="tabular" hidden="false" name="default" label="Positions of heterozygous bases in $in_file.name"/> - </outputs> - <tests> - <test> - <param name="in_file" value="seqtk_listhet.fa"/> - <output name="default" file="seqtk_listhet.out" ftype="tabular"/> - </test> - </tests> - <help><![CDATA[ + <description>extract the position of each het</description> + <macros> + <import>macros.xml</import> + </macros> + <expand macro="requirements"/> + <expand macro="stdio"/> + <command><![CDATA[ +seqtk listhet +'$in_file' | awk 'BEGIN{print "#chr\tposition\tbase"}1' +> '$default' +]]></command> + <inputs> + <expand macro="in_faq"/> + </inputs> + <outputs> + <data name="default" format="tabular" label="Positions of heterozygous bases in $in_file.name"/> + </outputs> + <tests> + <test> + <param name="in_file" value="seqtk_listhet.fa"/> + <output name="default" file="seqtk_listhet.out" ftype="tabular"/> + </test> + </tests> + <help><![CDATA[ **What it does** Lists regions of heterozygosity. @@ -43,6 +47,6 @@ @ATTRIBUTION@ -]]></help> - <expand macro="citation" /> + ]]></help> + <expand macro="citation" /> </tool>
--- a/seqtk_mergefa.xml Fri Jan 01 14:49:42 2016 -0500 +++ b/seqtk_mergefa.xml Mon Jun 05 13:27:11 2017 -0400 @@ -1,47 +1,48 @@ <?xml version="1.0"?> <tool id="seqtk_mergefa" name="seqtk_mergefa" version="@WRAPPER_VERSION@.0"> - <description>merge two FASTA/Q files</description> - <macros> - <import>macros.xml</import> - </macros> - <expand macro="requirements"/> - <expand macro="stdio"/> - <command><![CDATA[seqtk mergefa -q $q + <description>merge two FASTA/Q files</description> + <macros> + <import>macros.xml</import> + </macros> + <expand macro="requirements"/> + <expand macro="stdio"/> + <command><![CDATA[ +seqtk mergefa +-q $q $i $m $r $h - -$in_fa1 -$in_fa2 - -> $default]]></command> - <inputs> - <param name="in_fa1" type="data" format="fasta,fastq" label="Input FASTA/Q file #1"/> - <param name="in_fa2" type="data" format="fasta,fastq" label="Input FASTA/Q file #2"/> - <param label="quality threshold" help="(-q)" name="q" type="integer" value="0"/> - <param checked="false" label="take intersection" help="(-i)" name="i" type="boolean" falsevalue="" truevalue="-i"/> - <param checked="false" label="convert to lowercase when one of the input base is N" help="(-m)" name="m" type="boolean" falsevalue="" truevalue="-m"/> - <param checked="false" label="pick a random allele from het" help="(-r)" name="r" type="boolean" falsevalue="" truevalue="-r"/> - <param checked="false" label="suppress hets in the input" help="(-h)" name="h" type="boolean" falsevalue="" truevalue="-h"/> - </inputs> - <outputs> - <data format_source="in_fa1" hidden="false" name="default" label="Merger of $in_fa1.name and $in_fa2.name"/> - </outputs> - <tests> - <test> - <param name="in_fa1" value="seqtk_mergefa1.fa"/> - <param name="in_fa2" value="seqtk_mergefa2.fa"/> - <output name="default" file="seqtk_mergefa.out" ftype="fasta"/> - </test> - <test> - <param name="in_fa1" value="seqtk_mergefa1.fa"/> - <param name="in_fa2" value="seqtk_mergefa2.fa"/> - <param name="m" value="True" /> - <output name="default" file="seqtk_mergefa2.out" ftype="fasta"/> - </test> - </tests> - <help><![CDATA[ +'$in_fa1' +'$in_fa2' +> '$default' + ]]></command> + <inputs> + <param name="in_fa1" type="data" format="fasta,fastq" label="Input FASTA/Q file #1"/> + <param name="in_fa2" type="data" format="fasta,fastq" label="Input FASTA/Q file #2"/> + <param argument="-q" type="integer" value="0" label="Quality threshold"/> + <param argument="-i" type="boolean" truevalue="-i" falsevalue="" checked="false" label="Take intersection" /> + <param argument="-m" type="boolean" truevalue="-m" falsevalue="" checked="false" label="Convert to lowercase when one of the input base is N" /> + <param argument="-r" type="boolean" truevalue="-r" falsevalue="" checked="false" label="Pick a random allele from het" /> + <param argument="-h" type="boolean" truevalue="-h" falsevalue="" checked="false" label="Suppress hets in the input" /> + </inputs> + <outputs> + <data name="default" format_source="in_fa1" label="Merger of $in_fa1.name and $in_fa2.name"/> + </outputs> + <tests> + <test> + <param name="in_fa1" value="seqtk_mergefa1.fa"/> + <param name="in_fa2" value="seqtk_mergefa2.fa"/> + <output name="default" file="seqtk_mergefa.out" ftype="fasta"/> + </test> + <test> + <param name="in_fa1" value="seqtk_mergefa1.fa"/> + <param name="in_fa2" value="seqtk_mergefa2.fa"/> + <param name="m" value="True" /> + <output name="default" file="seqtk_mergefa2.out" ftype="fasta"/> + </test> + </tests> + <help><![CDATA[ **What it does** Merges two fasta files, using ambiguity codes @@ -64,6 +65,6 @@ ACTGACTGxxa @ATTRIBUTION@ -]]></help> - <expand macro="citation" /> + ]]></help> + <expand macro="citation" /> </tool>
--- a/seqtk_mergepe.xml Fri Jan 01 14:49:42 2016 -0500 +++ b/seqtk_mergepe.xml Mon Jun 05 13:27:11 2017 -0400 @@ -1,30 +1,32 @@ <?xml version="1.0"?> <tool id="seqtk_mergepe" name="seqtk_mergepe" version="@WRAPPER_VERSION@.0"> - <description>interleave two unpaired FASTA/Q files for a paired-end file</description> - <macros> - <import>macros.xml</import> - </macros> - <expand macro="requirements"/> - <expand macro="stdio"/> - <command><![CDATA[seqtk mergepe - $in_fq1 - $in_fq2 -> $default]]></command> - <inputs> - <param name="in_fq1" type="data" format="fasta,fastq" label="Input FASTA/Q file #1"/> - <param name="in_fq2" type="data" format="fasta,fastq" label="Input FASTA/Q file #2"/> - </inputs> - <outputs> - <data format_source="in_fq1" hidden="false" name="default" label="$in_fq1.name and $in_fq2.name as interleaved paired-end"/> - </outputs> - <tests> - <test> - <param name="in_fq1" value="paired_dat1.fq"/> - <param name="in_fq2" value="paired_dat2.fq"/> - <output name="default" file="paired_dat.fq" ftype="fastq"/> - </test> - </tests> - <help><![CDATA[ + <description>interleave two unpaired FASTA/Q files for a paired-end file</description> + <macros> + <import>macros.xml</import> + </macros> + <expand macro="requirements"/> + <expand macro="stdio"/> + <command><![CDATA[ +seqtk mergepe +'$in_fq1' +'$in_fq2' +> '$default' + ]]></command> + <inputs> + <param name="in_fq1" type="data" format="fasta,fastq" label="Input FASTA/Q file #1"/> + <param name="in_fq2" type="data" format="fasta,fastq" label="Input FASTA/Q file #2"/> + </inputs> + <outputs> + <data name="default" format_source="in_fq1" label="$in_fq1.name and $in_fq2.name as interleaved paired-end"/> + </outputs> + <tests> + <test> + <param name="in_fq1" value="paired_dat1.fq"/> + <param name="in_fq2" value="paired_dat2.fq"/> + <output name="default" file="paired_dat.fq" ftype="fastq"/> + </test> + </tests> + <help><![CDATA[ **What it does** Merge two files which constitute a paired-end file into a single, interleaved, paired-end FASTA/Q file @@ -89,6 +91,6 @@ @r-4/2 @ATTRIBUTION@ -]]></help> - <expand macro="citation" /> + ]]></help> + <expand macro="citation" /> </tool>
--- a/seqtk_mutfa.xml Fri Jan 01 14:49:42 2016 -0500 +++ b/seqtk_mutfa.xml Mon Jun 05 13:27:11 2017 -0400 @@ -1,29 +1,32 @@ <?xml version="1.0"?> <tool id="seqtk_mutfa" name="seqtk_mutfa" version="@WRAPPER_VERSION@.0"> - <description>point mutate FASTA at specified positions</description> - <macros> - <import>macros.xml</import> - </macros> - <expand macro="requirements"/> - <expand macro="stdio"/> - <command><![CDATA[seqtk mutfa - $in_file $in_snp -> $default]]></command> - <inputs> - <expand macro="in_faq"/> - <param name="in_snp" type="data" format="tabular" label="Input SNP file"/> - </inputs> - <outputs> - <data format_source="in_file" hidden="false" name="default" label="Mutated $in_file.name"/> - </outputs> - <tests> - <test> - <param name="in_file" value="seqtk_mutfa.fa"/> - <param name="in_snp" value="seqtk_mutfa.snp"/> - <output name="default" file="seqtk_mutfa.out" ftype="fasta"/> - </test> - </tests> - <help><![CDATA[ + <description>point mutate FASTA at specified positions</description> + <macros> + <import>macros.xml</import> + </macros> + <expand macro="requirements"/> + <expand macro="stdio"/> + <command><![CDATA[ +seqtk mutfa +'$in_file' +'$in_snp' +> '$default' + ]]></command> + <inputs> + <expand macro="in_faq"/> + <param name="in_snp" type="data" format="tabular" label="Input SNP file"/> + </inputs> + <outputs> + <data name="default" format_source="in_file" label="Mutated $in_file.name"/> + </outputs> + <tests> + <test> + <param name="in_file" value="seqtk_mutfa.fa"/> + <param name="in_snp" value="seqtk_mutfa.snp"/> + <output name="default" file="seqtk_mutfa.out" ftype="fasta"/> + </test> + </tests> + <help><![CDATA[ **What it does** the SNP inputs consist of 4 columns: chromosome, 1-based-pos, any, base-changed-to. @@ -47,6 +50,6 @@ GCTAACTGAA @ATTRIBUTION@ -]]></help> - <expand macro="citation" /> + ]]></help> + <expand macro="citation" /> </tool>
--- a/seqtk_randbase.xml Fri Jan 01 14:49:42 2016 -0500 +++ b/seqtk_randbase.xml Mon Jun 05 13:27:11 2017 -0400 @@ -1,27 +1,29 @@ <?xml version="1.0"?> <tool id="seqtk_randbase" name="seqtk_randbase" version="@WRAPPER_VERSION@.0"> - <description>choose a random base from hets</description> - <macros> - <import>macros.xml</import> - </macros> - <expand macro="requirements"/> - <expand macro="stdio"/> - <command><![CDATA[seqtk randbase - $in_file -> $default]]></command> - <inputs> - <expand macro="in_faq"/> - </inputs> - <outputs> - <data format_source="in_file" hidden="false" name="default" label="Unambiguous $in_file.name"/> - </outputs> - <tests> - <test> - <param name="in_file" value="seqtk_randbase.fa"/> - <output name="default" file="seqtk_randbase.out" ftype="fasta"/> - </test> - </tests> - <help><![CDATA[ + <description>choose a random base from hets</description> + <macros> + <import>macros.xml</import> + </macros> + <expand macro="requirements"/> + <expand macro="stdio"/> + <command><![CDATA[ +seqtk randbase +'$in_file' +> '$default' + ]]></command> + <inputs> + <expand macro="in_faq"/> + </inputs> + <outputs> + <data name="default" format_source="in_file" label="Unambiguous $in_file.name"/> + </outputs> + <tests> + <test> + <param name="in_file" value="seqtk_randbase.fa"/> + <output name="default" file="seqtk_randbase.out" ftype="fasta"/> + </test> + </tests> + <help><![CDATA[ **What it does** Randomly resolves ambiguous bases @@ -41,6 +43,6 @@ ACGTCGTGTT @ATTRIBUTION@ -]]></help> - <expand macro="citation" /> + ]]></help> + <expand macro="citation" /> </tool>
--- a/seqtk_sample.xml Fri Jan 01 14:49:42 2016 -0500 +++ b/seqtk_sample.xml Mon Jun 05 13:27:11 2017 -0400 @@ -1,39 +1,42 @@ <?xml version="1.0"?> <tool id="seqtk_sample" name="seqtk_sample" version="@WRAPPER_VERSION@.0"> <description>random subsample of fasta or fastq sequences</description> - <macros> - <import>macros.xml</import> - </macros> - <expand macro="requirements"/> - <expand macro="stdio"/> - <command><![CDATA[seqtk sample -s $s - $in_file - $subsample_size -> $default]]></command> - <inputs> - <expand macro="in_faq" /> - <param label="RNG seed" help="(-s)" name="s" type="integer" value="4"/> - <param label="Subsample (decimal fraction or number)" name="subsample_size" type="float" value="100"/> - </inputs> - <outputs> - <data format_source="in_file" hidden="false" name="default" label="Subsample of reads from $in_file.name"/> - </outputs> - <tests> - <test> - <param name="in_file" value="seqtk_sample.fa"/> - <param name="subsample_size" value="4"/> - <param name="s" value="4"/> - <output name="default" file="seqtk_sample.out" ftype="fasta"/> - </test> - </tests> - <help><![CDATA[ + <macros> + <import>macros.xml</import> + </macros> + <expand macro="requirements"/> + <expand macro="stdio"/> + <command><![CDATA[ +seqtk sample +-s $s +'$in_file' +$subsample_size +> '$default' + ]]></command> + <inputs> + <expand macro="in_faq" /> + <param argument="-s" type="integer" value="4" label="RNG seed" help="The seed used for the random number generator. Manually specifying a number here is useful for reproducing the same subsampling over time" /> + <param name="subsample_size" type="float" value="100" label="Subsample (decimal fraction or number)" /> + </inputs> + <outputs> + <data name="default" format_source="in_file" label="Subsample of reads from $in_file.name"/> + </outputs> + <tests> + <test> + <param name="in_file" value="seqtk_sample.fa"/> + <param name="subsample_size" value="4"/> + <param name="s" value="4"/> + <output name="default" file="seqtk_sample.out" ftype="fasta"/> + </test> + </tests> + <help><![CDATA[ **What it does** -Takes a random subsample of fasta or fastq sequences. The RNG is seedable to allow for reproducible results, and defaults to `4 <http://xkcd.com/221/>`__. +Takes a random subsample of FASTA or FASTQ sequences. The RNG is seedable to allow for reproducible results, and defaults to `4 <http://xkcd.com/221/>`__. The subsample size can be a decimal fraction <=1, where 1 implies 100% of the reads should be used. If a number >1 is provided, that many reads will be taken from the dataset. @ATTRIBUTION@ -]]></help> - <expand macro="citation" /> + ]]></help> + <expand macro="citation" /> </tool>
--- a/seqtk_seq.xml Fri Jan 01 14:49:42 2016 -0500 +++ b/seqtk_seq.xml Mon Jun 05 13:27:11 2017 -0400 @@ -1,22 +1,23 @@ <?xml version="1.0"?> -<tool id="seqtk_seq" name="seqtk_seq" version="@WRAPPER_VERSION@.0"> - <description>common transformation of FASTA/Q</description> - <macros> - <import>macros.xml</import> - </macros> - <expand macro="requirements"/> - <expand macro="stdio"/> - <command><![CDATA[seqtk seq -q $q +<tool id="seqtk_seq" name="seqtk_seq" version="@WRAPPER_VERSION@.2"> + <description>common transformation of FASTA/Q</description> + <macros> + <import>macros.xml</import> + </macros> + <expand macro="requirements"/> + <expand macro="stdio"/> + <command><![CDATA[ +seqtk seq -q $q -X $X -#if $n and $n != "None" and $n is not None and $n != "": --n "$n" +#if $n: + -n '$n' #end if -l $l -Q $Q -s $s -f $f -#if $M and $M != "None" and $M is not None and $M != "": --M "$M" +#if $M: + -M '$M' #end if -L $L $c @@ -26,53 +27,52 @@ $N $x1 $x2 -#if $in_file.ext == "fastqillumina" - -V +#if $in_file.is_of_type('fastqillumina') + -V #end if - -$in_file -> $default]]></command> - <inputs> - <expand macro="in_faq"/> - <param label="mask bases with quality lower than INT" help="(-q)" name="q" type="integer" value="0"/> - <param label="mask bases with quality higher than INT" help="(-X)" name="X" type="integer" value="255"/> - <param area="false" default="0" label="masked bases converted to CHAR; 0 for lowercase" help="(-n)" name="n" type="text"/> - <param label="number of residues per line; 0 for 2^32-1" help="(-l)" name="l" type="integer" value="0"/> - <param label="quality shift: ASCII-INT gives base quality" help="(-Q)" name="Q" type="integer" value="33"/> - <param label="random seed" help="effective with -f (-s)" name="s" type="integer" value="11"/> - <param label="sample fraction of sequences" help="(-f)" name="f" type="float" value="1"/> - <param area="false" default="null" label="mask regions in BED or name list FILE" help="(-M)" name="M" type="text"/> - <param label="drop sequences with length shorter than INT" help="(-L)" name="L" type="integer" value="0"/> - <param checked="false" label="mask complement region" help="effective with -M (-c)" name="c" type="boolean" falsevalue="" truevalue="-c"/> - <param checked="false" label="reverse complement" help="(-r)" name="r" type="boolean" falsevalue="" truevalue="-r"/> - <param checked="false" label="force FASTA output (discard quality)" help="(-A)" name="A" type="boolean" falsevalue="" truevalue="-A"/> - <param checked="false" label="drop comments at the header lines" help="(-C)" name="C" type="boolean" falsevalue="" truevalue="-C"/> - <param checked="false" label="drop sequences containing ambiguous bases" help="(-N)" name="N" type="boolean" falsevalue="" truevalue="-N"/> - <param checked="false" label="output the 2n-1 reads only" help="(-1)" name="x1" type="boolean" falsevalue="" truevalue="-1"/> - <param checked="false" label="output the 2n reads only" help="(-2)" name="x2" type="boolean" falsevalue="" truevalue="-2"/> - </inputs> - <outputs> - <data format_source="in_file" hidden="false" name="default"/> - </outputs> - <tests> - <test> - <!-- This is a sorry excuse for a test for a tool which does way more - than it should, but upstream decided to put a TON of functionality - into a single tool rather than using the single responsibility - principle. --> - <param name="in_file" value="seqtk_seq.fa"/> - <param name="r" value="True"/> - <param name="n" value=""/> - <param name="M" value=""/> - <output name="default" file="seqtk_seq_revcom.fa" ftype="fasta"/> - </test> - </tests> - <help><![CDATA[ +'$in_file' +> '$default' + ]]></command> + <inputs> + <expand macro="in_faq"/> + <param argument="-q" type="integer" value="0" label="Mask bases with quality lower than INT" /> + <param argument="-X" type="integer" value="255" label="Mask bases with quality higher than INT" /> + <param argument="-n" type="text" value="0" label="Masked bases converted to CHAR; 0 for lowercase" /> + <param argument="-l" type="integer" value="0" label="Number of residues per line; 0 for 2^32-1" /> + <param argument="-Q" type="integer" value="33" label="Quality shift: ASCII-INT gives base quality" /> + <param argument="-s" type="integer" value="11" label="Random seed" help="Effective with -f" /> + <param argument="-f" type="float" value="1" label="Sample fraction of sequences" /> + <param argument="-M" type="data" format="bed,txt" optional="true" label="Mask regions in BED or name list file" /> + <param argument="-L" type="integer" value="0" label="Drop sequences with length shorter than INT" /> + <param argument="-c" type="boolean" truevalue="-c" falsevalue="" checked="false" label="Mask complement region" help="Effective with -M" /> + <param argument="-r" type="boolean" truevalue="-r" falsevalue="" checked="false" label="Reverse complement" /> + <param argument="-A" type="boolean" truevalue="-A" falsevalue="" checked="false" label="Force FASTA output (discard quality)" /> + <param argument="-C" type="boolean" truevalue="-C" falsevalue="" checked="false" label="Drop comments at the header lines" /> + <param argument="-N" type="boolean" truevalue="-N" falsevalue="" checked="false" label="Drop sequences containing ambiguous bases" /> + <param name="x1" argument="-1" type="boolean" truevalue="-1" falsevalue="" checked="false" label="Output the 2n-1 reads only" /> + <param name="x2" argument="-2" type="boolean" truevalue="-2" falsevalue="" checked="false" label="Output the 2n reads only" /> + </inputs> + <outputs> + <data name="default" format_source="in_file" /> + </outputs> + <tests> + <!-- This is a sorry excuse for a test for a tool which does way more + than it should, but upstream decided to put a TON of functionality + into a single tool rather than using the single responsibility + principle. --> + <test> + <param name="in_file" value="seqtk_seq.fa"/> + <param name="r" value="True"/> + <param name="n" value=""/> + <output name="default" file="seqtk_seq_revcom.fa" ftype="fasta"/> + </test> + </tests> + <help><![CDATA[ **What it does** Various utilities for transforming FASTA/Q data @ATTRIBUTION@ -]]></help> - <expand macro="citation" /> + ]]></help> + <expand macro="citation" /> </tool>
--- a/seqtk_subseq.xml Fri Jan 01 14:49:42 2016 -0500 +++ b/seqtk_subseq.xml Mon Jun 05 13:27:11 2017 -0400 @@ -1,60 +1,60 @@ <?xml version="1.0"?> <tool id="seqtk_subseq" name="seqtk_subseq" version="@WRAPPER_VERSION@.0"> - <description>extract subsequences from FASTA/Q files</description> - <macros> - <import>macros.xml</import> - </macros> - <expand macro="requirements"/> - <expand macro="stdio"/> - <command><![CDATA[seqtk subseq $t + <description>extract subsequences from FASTA/Q files</description> + <macros> + <import>macros.xml</import> + </macros> + <expand macro="requirements"/> + <expand macro="stdio"/> + <command><![CDATA[ +seqtk subseq +$t -l $l -$in_file - +'$in_file' #if $source.type == 'bed': - $in_bed + '$in_bed' #else - $name_list + '$name_list' #end if - #if $t == '-t': - | awk 'BEGIN{print "chr\tunknown\tseq"}1' + | awk 'BEGIN{print "chr\tunknown\tseq"}1' #end if - -> $default]]></command> - <inputs> - <param name="in_file" type="data" format="fasta,fastq" label="Input fasta/q file"/> - <conditional name="source"> - <param name="type" type="select" label="Select source of sequence choices"> - <option value="bed">BED</option> - <option value="name">FASTA/Q ID list</option> - </param> - <when value="bed"> - <param name="in_bed" type="data" format="bed" label="Input BED file"/> - </when> - <when value="name"> - <param name="name_list" type="data" format="txt" label="Input fasta file"/> - </when> - </conditional> - <param label="TAB delimited output" help="(-t)" name="t" type="boolean" falsevalue="" truevalue="-t"/> - <param label="sequence line length" help="(-l)" name="l" type="integer" value="0"/> - </inputs> - <outputs> - <data format_source="in_file" hidden="false" name="default" label="Selected sequences from $in_file.name"> - <change_format> - <when input="t" value="-t" format="tabular"/> - </change_format> - </data> - </outputs> - <tests> - <test> - <param name="in_file" value="seqtk_subseq.fa"/> - <param name="type" value="name"/> - <param name="t" value="False" /> - <param name="name_list" value="seqtk_subseq_list.txt"/> - <output name="default" file="seqtk_subseq.out" ftype="fasta"/> - </test> - </tests> - <help><![CDATA[ +> '$default' + ]]></command> + <inputs> + <expand macro="in_faq"/> + <conditional name="source"> + <param name="type" type="select" label="Select source of sequence choices"> + <option value="bed">BED</option> + <option value="name">FASTA/Q ID list</option> + </param> + <when value="bed"> + <param name="in_bed" type="data" format="bed" label="Input BED file"/> + </when> + <when value="name"> + <param name="name_list" type="data" format="txt" label="Input ID list"/> + </when> + </conditional> + <param argument="-t" type="boolean" truevalue="-t" falsevalue="" label="TAB delimited output" /> + <param argument="-l" type="integer" value="0" label="Sequence line length" /> + </inputs> + <outputs> + <data name="default" format_source="in_file" label="Selected sequences from $in_file.name"> + <change_format> + <when input="t" value="-t" format="tabular"/> + </change_format> + </data> + </outputs> + <tests> + <test> + <param name="in_file" value="seqtk_subseq.fa"/> + <param name="type" value="name"/> + <param name="t" value="False" /> + <param name="name_list" value="seqtk_subseq_list.txt"/> + <output name="default" file="seqtk_subseq.out" ftype="fasta"/> + </test> + </tests> + <help><![CDATA[ **What it does** Given a list of newline separated IDs from a fasta file, this will extract those named fasta sequences from the input file. @@ -79,6 +79,6 @@ ACGTMRWSYK @ATTRIBUTION@ -]]></help> - <expand macro="citation" /> + ]]></help> + <expand macro="citation" /> </tool>
--- a/seqtk_trimfq.xml Fri Jan 01 14:49:42 2016 -0500 +++ b/seqtk_trimfq.xml Mon Jun 05 13:27:11 2017 -0400 @@ -1,63 +1,65 @@ <?xml version="1.0"?> <tool id="seqtk_trimfq" name="seqtk_trimfq" version="@WRAPPER_VERSION@.0"> - <description>trim FASTQ using the Phred algorithm</description> - <macros> - <import>macros.xml</import> - </macros> - <expand macro="requirements"/> - <expand macro="stdio"/> - <command><![CDATA[seqtk trimfq + <description>trim FASTQ using the Phred algorithm</description> + <macros> + <import>macros.xml</import> + </macros> + <expand macro="requirements"/> + <expand macro="stdio"/> + <command><![CDATA[ +seqtk trimfq #if $mode.mode_select == "quality": --q $mode.q --l $mode.l + -q $mode.q + -l $mode.l #else: --b $mode.b --e $mode.e + -b $mode.b + -e $mode.e #end if -$in_file -> $default]]></command> - <inputs> - <expand macro="in_faq"/> - <conditional name="mode"> - <param name="mode_select" type="select" label="Mode for trimming FASTQ File"> - <option value="quality">Quality</option> - <option value="position">Length/Position</option> - </param> - <when value="quality"> - <param label="error rate threshold" help="(-q)" name="q" type="float" value="0.05"/> - <param label="maximally trim down to INT bp" help="(-l)" name="l" type="integer" value="30"/> - </when> - <when value="position"> - <param label="trim INT bp from left" help="(-b)" name="b" type="integer" value="0"/> - <param label="trim INT bp from right" help="(-e)" name="e" type="integer" value="0"/> - </when> - </conditional> - </inputs> - <outputs> - <data format_source="in_file" hidden="false" name="default" label="$in_file.name trimmed"/> - </outputs> - <tests> - <test> - <param name="in_file" value="seqtk_trimfq.fq"/> - <param name="mode_select" value="quality"/> - <param name="q" value="0.05"/> - <param name="l" value="30"/> - <output name="default" file="seqtk_trimfq_default.fq" ftype="fastq"/> - </test> - <test> - <param name="in_file" value="seqtk_trimfq.fq"/> - <param name="mode_select" value="position"/> - <param name="b" value="5"/> - <param name="e" value="5"/> - <output name="default" file="seqtk_trimfq_be.fq" ftype="fastq"/> - </test> - </tests> - <help><![CDATA[ +'$in_file' +> '$default' + ]]></command> + <inputs> + <expand macro="in_faq"/> + <conditional name="mode"> + <param name="mode_select" type="select" label="Mode for trimming FASTQ File"> + <option value="quality">Quality</option> + <option value="position">Length/Position</option> + </param> + <when value="quality"> + <param argument="-q" type="float" value="0.05" label="Error rate threshold" /> + <param argument="-l" type="integer" value="30" label="Maximally trim down to INT bp" /> + </when> + <when value="position"> + <param argument="-b" type="integer" value="0" label="Trim INT bp from left" /> + <param argument="-e" type="integer" value="0" label="Trim INT bp from right" /> + </when> + </conditional> + </inputs> + <outputs> + <data name="default" format_source="in_file" label="$in_file.name trimmed"/> + </outputs> + <tests> + <test> + <param name="in_file" value="seqtk_trimfq.fq"/> + <param name="mode_select" value="quality"/> + <param name="q" value="0.05"/> + <param name="l" value="30"/> + <output name="default" file="seqtk_trimfq_default.fq" ftype="fastq"/> + </test> + <test> + <param name="in_file" value="seqtk_trimfq.fq"/> + <param name="mode_select" value="position"/> + <param name="b" value="5"/> + <param name="e" value="5"/> + <output name="default" file="seqtk_trimfq_be.fq" ftype="fastq"/> + </test> + </tests> + <help><![CDATA[ **What it does** Trim a fastq file based on Phred scores, or by length @ATTRIBUTION@ -]]></help> - <expand macro="citation" /> + ]]></help> + <expand macro="citation" /> </tool>
--- a/tool_dependencies.xml Fri Jan 01 14:49:42 2016 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,6 +0,0 @@ -<?xml version="1.0"?> -<tool_dependency> - <package name="seqtk" version="1.0-r75-dirty"> - <repository changeset_revision="8b7d6f6cb89b" name="package_seqtk_1_0_r75" owner="iuc" toolshed="https://toolshed.g2.bx.psu.edu" /> - </package> -</tool_dependency>