comparison stacks_ustacks.xml @ 8:bdad4fb6f85a draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/stacks commit dc23703c260d004a28fe24a2a7c00cb4371bc32e

7:c3fc406e6722

        <import>macros.xml</import>
    </macros>
    <expand macro="requirements"/>
    <expand macro="stdio"/>
    <command><![CDATA[
        #from os.path import splitext
        #import re

        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"
            #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"
            #set inputype = "fasta"
        #end if

        ln -s "${sample}" "${data_path}"

        &&

        ustacks

            -M $M
            $R
            $H

            ## Assembly
            $assembly_options.r
            $assembly_options.d
            --max_locus_stacks $assembly_options.max_locus_stacks
            #if str($assembly_options.k_len):
                --k_len $assembly_options.k_len
            #end if

            #if $gapped.use_gapped:
                --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":
                --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":
                --model_type snp
                --alpha $snp_options.select_model.alpha
            #else
                --model_type fixed
                --bc_err_freq $bc_err_freq
            #end if

            -o stacks_outputs

             > ustacks.log 2>&1
    ]]></command>

    <inputs>
        <param name="sample" argument="-f" format="fastqsanger,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"/>
        <param name="R" argument="-R" type="boolean" checked="false" truevalue="-R" falsevalue="" label="Retain unused reads" />
        <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="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="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>
        </conditional>

        </section>
    </inputs>

    <outputs>
        <data format="txt" name="output_log" label="ustacks.log with ${tool.name} on ${on_string}" from_work_dir="ustacks.log" />

        <collection name="tabs" type="list" label="Stacks from ${on_string}">
            <discover_datasets pattern="(?P&lt;name&gt;.+\.tags)\.tsv$" ext="tabular" directory="stacks_outputs" />
            <discover_datasets pattern="(?P&lt;name&gt;.+\.snps)\.tsv$" ext="tabular" directory="stacks_outputs" />
            <discover_datasets pattern="(?P&lt;name&gt;.+\.alleles)\.tsv$" ext="tabular" directory="stacks_outputs" />

            <output name="output_log">
                <assert_contents>
                    <has_text text="done." />
                </assert_contents>
            </output>

            <output_collection name="tabs">
                <element name="PopA_01.tags">
                    <assert_contents>
                        <has_text text="generated on " />

8:bdad4fb6f85a

        <import>macros.xml</import>
    </macros>
    <expand macro="requirements"/>
    <expand macro="stdio"/>
    <command><![CDATA[

        @CLEAN_EXT@

        mkdir stacks_inputs stacks_outputs

        &&

        #if $sample.is_of_type('fastqsanger')
            #set $data_path = "stacks_inputs/" + $clean_ext($sample.element_identifier) + ".fq"
            #set inputype = "fastq"
        #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}'

        &&

        ustacks

            -M $M
            $R
            $H

            ## Assembly
            $assembly_options.keep_high_cov
            $assembly_options.d
            --max_locus_stacks $assembly_options.max_locus_stacks
            #if str($assembly_options.k_len)
                --k_len $assembly_options.k_len
            #end if

            #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"
                --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"
                --model_type snp
                --alpha $snp_options.select_model.alpha
            #else
                --model_type fixed
                --bc_err_freq $bc_err_freq
            #end if

            -o stacks_outputs

            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,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"/>
        <param name="R" argument="-R" type="boolean" checked="false" truevalue="-R" falsevalue="" label="Retain unused reads" />
        <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="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="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>
        </conditional>

        </section>
    </inputs>

    <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 ${on_string}">
            <discover_datasets pattern="(?P&lt;name&gt;.+\.tags)\.tsv$" ext="tabular" directory="stacks_outputs" />
            <discover_datasets pattern="(?P&lt;name&gt;.+\.snps)\.tsv$" ext="tabular" directory="stacks_outputs" />
            <discover_datasets pattern="(?P&lt;name&gt;.+\.alleles)\.tsv$" ext="tabular" directory="stacks_outputs" />

            <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">
                    <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">
                    <assert_contents>
                        <has_text text="generated on " />