Mercurial > repos > iuc > stacks_ustacks
changeset 8:bdad4fb6f85a draft
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/stacks commit dc23703c260d004a28fe24a2a7c00cb4371bc32e
| author | iuc |
|---|---|
| date | Thu, 27 Apr 2017 04:17:27 -0400 |
| parents | c3fc406e6722 |
| children | e5c97f09fe06 |
| files | macros.xml stacks_ustacks.xml test-data/demultiplexed/PopA_01.1.fq.gzip test-data/denovo_map/popmap_cstacks.tsv test-data/procrad/R1.fq.gzip test-data/ustacks/ustacks.out |
| diffstat | 6 files changed, 136 insertions(+), 25 deletions(-) [+] |
line wrap: on
line diff
--- a/macros.xml Fri Apr 07 11:47:24 2017 -0400 +++ b/macros.xml Thu Apr 27 04:17:27 2017 -0400 @@ -2,14 +2,14 @@ <macros> <xml name="requirements"> <requirements> - <requirement type="package" version="1.42">stacks</requirement> + <requirement type="package" version="1.46">stacks</requirement> <requirement type="package" version="1.2.10">velvet</requirement> - <container type="docker">quay.io/biocontainers/stacks:1.42--2</container> + <requirement type="package" version="1.1">stacks_summary</requirement> <yield/> </requirements> </xml> - <token name="@WRAPPER_VERSION@">1.42</token> + <token name="@WRAPPER_VERSION@">1.46</token> <xml name="stdio"> <stdio> @@ -90,6 +90,7 @@ <option value="bsaHI">bsaHI</option> <option value="hpaII">hpaII</option> <option value="ncoI">ncoI</option> + <option value="ApaLI">ApaLI</option> </xml> <xml name="cross_types"> @@ -100,6 +101,19 @@ <option value="GEN">GEN (generic, unspecific to any map type)</option> </xml> + <token name="@CLEAN_EXT@"> + <![CDATA[ + #from os.path import splitext + #import re + #def clean_ext($identifier) + #while $identifier.endswith(('.1', '.fa', '.fq', '.fasta', '.fastq', '.gz', '.gzip', '.sam', '.bam')) + #set $identifier = splitext($identifier)[0] + #end while +$identifier#slurp + #end def + ]]> + </token> + <token name="@NORM_GENOTYPES_OUTPUT_LIGHT@"> <![CDATA[ ## We need to do this as the output file names contains the value of an option (min progeny)
--- a/stacks_ustacks.xml Fri Apr 07 11:47:24 2017 -0400 +++ b/stacks_ustacks.xml Thu Apr 27 04:17:27 2017 -0400 @@ -6,26 +6,25 @@ <expand macro="requirements"/> <expand macro="stdio"/> <command><![CDATA[ - #from os.path import splitext - #import re + + @CLEAN_EXT@ mkdir stacks_inputs stacks_outputs && - #if $sample.is_of_type('fastqsanger'): - #set $data_path = splitext($sample.element_identifier)[0] - #set $data_path = re.sub(r'\.1$', '', $data_path) - #set $data_path = "stacks_inputs/" + $data_path + ".fq" + #if $sample.is_of_type('fastqsanger') + #set $data_path = "stacks_inputs/" + $clean_ext($sample.element_identifier) + ".fq" #set inputype = "fastq" - #else: - #set $data_path = splitext($sample.element_identifier)[0] - #set $data_path = re.sub(r'\.1$', '', $data_path) - #set $data_path = "stacks_inputs/" + $data_path + ".fa" + #else if $sample.is_of_type('fastqsanger.gz') + #set $data_path = "stacks_inputs/" + $clean_ext($sample.element_identifier) + ".fq.gz" + #set inputype = "gzfastq" + #else + #set $data_path = "stacks_inputs/" + $clean_ext($sample.element_identifier) + ".fa" #set inputype = "fasta" #end if - ln -s "${sample}" "${data_path}" + ln -s '${sample}' '${data_path}' && @@ -46,26 +45,26 @@ $H ## Assembly - $assembly_options.r + $assembly_options.keep_high_cov $assembly_options.d --max_locus_stacks $assembly_options.max_locus_stacks - #if str($assembly_options.k_len): + #if str($assembly_options.k_len) --k_len $assembly_options.k_len #end if - #if $gapped.use_gapped: + #if $gapped.use_gapped == "yes" --gapped --max_gaps $gapped.max_gaps --min_aln_len $gapped.min_aln_len #end if ## snp_model - #if str( $snp_options.select_model.model_type) == "bounded": + #if str( $snp_options.select_model.model_type) == "bounded" --model_type bounded --bound_low $snp_options.select_model.bound_low --bound_high $snp_options.select_model.bound_high --alpha $snp_options.select_model.alpha - #else if str( $snp_options.select_model.model_type) == "snp": + #else if str( $snp_options.select_model.model_type) == "snp" --model_type snp --alpha $snp_options.select_model.alpha #else @@ -75,11 +74,20 @@ -o stacks_outputs - > ustacks.log 2>&1 + 2>&1 | tee ustacks.log + + ## If input is in gz format, stacks will output gzipped files (no option to control this) + #if $sample.is_of_type('fastqsanger.gz') + && gunzip stacks_outputs/*.gz + #end if + + && + + stacks_summary.py --stacks-prog ustacks --res-dir stacks_outputs --logfile ustacks.log --summary stacks_outputs/summary.html ]]></command> <inputs> - <param name="sample" argument="-f" format="fastqsanger,fasta" type="data" label="Input short reads from an individual" /> + <param name="sample" argument="-f" format="fastqsanger,fastqsanger.gz,fasta" type="data" label="Input short reads from an individual" /> <param name="m" argument="-m" type="integer" value="2" label="Minimum depth of coverage required to create a stack"/> <param name="M" argument="-M" type="integer" value="2" label="Maximum distance (in nucleotides) allowed between stacks"/> @@ -87,16 +95,19 @@ <param name="H" argument="-H" type="boolean" checked="false" truevalue="-H" falsevalue="" label="Disable calling haplotypes from secondary reads" /> <section name="assembly_options" title="SNP Model Options (ustacks options)" expanded="True"> - <param name="r" argument="-r" type="boolean" checked="false" truevalue="-r" falsevalue="" label="Enable the Removal algorithm, to drop highly-repetitive stacks (and nearby errors) from the algorithm" /> + <param name="keep_high_cov" argument="--keep_high_cov" type="boolean" checked="false" truevalue="--keep-high-cov" falsevalue="" label="Disable the algorithm that removes highly-repetitive stacks and nearby errors. " /> <param name="d" argument="-d" type="boolean" checked="false" truevalue="-d" falsevalue="" label="Enable the Deleveraging algorithm, used for resolving over merged tags" /> <param name="max_locus_stacks" argument="--max_locus_stacks" type="integer" value="3" label="Maximum number of stacks at a single de novo locus"/> <param name="k_len" argument="--k_len" type="integer" value="" optional="true" label="K-mer size for matching between alleles and loci (automatically calculated by default)"/> </section> <conditional name="gapped"> - <param name="use_gapped" argument="--gapped" type="boolean" checked="false" label="Perform gapped alignments between stacks" /> - <when value="false"></when> - <when value="true"> + <param name="use_gapped" argument="--gapped" type="select" label="Perform gapped alignments between stacks"> + <option value="no" selected="true">No</option> + <option value="yes">Yes</option> + </param> + <when value="no"/> + <when value="yes"> <param name="max_gaps" argument="--max_gaps" type="integer" value="2" label="Number of gaps allowed between stacks before merging"/> <param name="min_aln_len" argument="--min_aln_len" type="float" value="0.8" min="0.0" max="1.0" label="Minimum length of aligned sequence in a gapped alignment"/> </when> @@ -111,6 +122,8 @@ <outputs> <data format="txt" name="output_log" label="ustacks.log with ${tool.name} on ${on_string}" from_work_dir="ustacks.log" /> + <data format="html" name="output_summary" label="Summary from ${tool.name} on ${on_string}" from_work_dir="stacks_outputs/summary.html" /> + <collection name="tabs" type="list" label="Stacks from ${on_string}"> <discover_datasets pattern="(?P<name>.+\.tags)\.tsv$" ext="tabular" directory="stacks_outputs" /> <discover_datasets pattern="(?P<name>.+\.snps)\.tsv$" ext="tabular" directory="stacks_outputs" /> @@ -128,6 +141,48 @@ <has_text text="done." /> </assert_contents> </output> + <output name="output_summary"> + <assert_contents> + <has_text text="Stacks Statistics" /> + </assert_contents> + </output> + + <output_collection name="tabs"> + <element name="PopA_01.tags"> + <assert_contents> + <has_text text="generated on " /> + </assert_contents> + </element> + <element name="PopA_01.snps"> + <assert_contents> + <has_text text="generated on " /> + </assert_contents> + </element> + <element name="PopA_01.alleles"> + <assert_contents> + <has_text text="generated on " /> + </assert_contents> + </element> + <element name="PopA_01.models"> + <assert_contents> + <has_text text="generated on " /> + </assert_contents> + </element> + </output_collection> + </test> + <test> + <param name="sample" value="demultiplexed/PopA_01.1.fq.gzip" ftype="fastqsanger.gz" /> + + <output name="output_log"> + <assert_contents> + <has_text text="done." /> + </assert_contents> + </output> + <output name="output_summary"> + <assert_contents> + <has_text text="Stacks Statistics" /> + </assert_contents> + </output> <output_collection name="tabs"> <element name="PopA_01.tags">
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/denovo_map/popmap_cstacks.tsv Thu Apr 27 04:17:27 2017 -0400 @@ -0,0 +1,1 @@ +PopA_01 myPopA
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/ustacks/ustacks.out Thu Apr 27 04:17:27 2017 -0400 @@ -0,0 +1,41 @@ +ustacks parameters selected: + Sample ID: 1 + Min depth of coverage to create a stack: 2 + Max distance allowed between stacks: 2 + Max distance allowed to align secondary reads: 4 + Max number of stacks allowed per de novo locus: 3 + Deleveraging algorithm: disabled + Removal algorithm: enabled + Model type: SNP + Alpha significance level for model: 0.05 + Gapped alignments: disabled +Parsing stacks_inputs/PopA_01.fq +Loading RAD-Tags...done +Loaded 66 RAD-Tags. + Inserted 7 elements into the RAD-Tags hash map. + 0 reads contained uncalled nucleotides that were modified. +4 initial stacks were populated; 3 stacks were set aside as secondary reads. +Initial coverage mean: 15.75; Std Dev: 7.46241; Max: 27 +Deleveraging trigger: 23; Removal trigger: 31 +Calculating distance for removing repetitive stacks. + Distance allowed between stacks: 1; searching with a k-mer length of 47 (48 k-mers per read); 1 k-mer hits required. +Removing repetitive stacks. + Removed 0 stacks. + 4 stacks remain for merging. +Post-Repeat Removal, coverage depth Mean: 15.75; Std Dev: 7.46241; Max: 27 +Calculating distance between stacks... + Distance allowed between stacks: 2; searching with a k-mer length of 31 (64 k-mers per read); 2 k-mer hits required. +Merging stacks, maximum allowed distance: 2 nucleotide(s) + 4 stacks merged into 3 loci; deleveraged 0 loci; blacklisted 0 loci. +After merging, coverage depth Mean: 21; Std Dev: 4.24264; Max: 27 +Merging remainder radtags + 3 remainder sequences left to merge. + Distance allowed between stacks: 4; searching with a k-mer length of 17 (78 k-mers per read); 10 k-mer hits required. + Matched 3 remainder reads; unable to match 0 remainder reads. +After remainders merged, coverage depth Mean: 22; Std Dev: 4.32049; Max: 28 +Calling final consensus sequences, invoking SNP-calling model... +Number of utilized reads: 66 +Writing loci, SNPs, and alleles to 'stacks_outputs/'... + Refetching sequencing IDs from stacks_inputs/PopA_01.fq... read 66 sequence IDs. +done. +ustacks is done.