comparison macros_process.xml @ 5:aef37afe214f draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/stacks2 commit 4e87a14a5479800df9675c1cbcdbe1b11f63653b-dirty

4:176f2a0c6683

<?xml version="1.0"?>

<!-- macros and tokens for process_radtags and process_short_reads -->

<macros>
    <!-- fastq input for process_radtags/shortreads-->
    <xml name="process_inputs">
        <conditional name="input_type">
            <param name="options_type_selector" type="select" label="Single-end or paired-end reads files">
                <option value="single" selected="True">Single-end files</option>
                <option value="paired">Paired-end files</option>
            </param>
            <when value="single">
                <param name="fqinputs" argument="-f" format="fastqsanger,fastqsanger.gz" multiple="true" type="data" label="singles-end reads infile(s)" help="input files" />
                <param name="barcode_encoding" type="select" label="Barcode location">
                    <expand macro="barcode_encoding_single" type="Barcode" />
                </param>
            </when>
            <when value="paired">
                <param name="fqinputs" type="data_collection" collection_type="list:paired" label="paired-end reads infile(s)" format="fastqsanger,fastqsanger.gz"/>
                <param name="barcode_encoding" type="select" label="Barcode location">
                    <expand macro="barcode_encoding_pair" type="Barcode" />
                </param>
            </when>
        </conditional>
        <param name="barcode" argument="-b" type="data"  format="tabular,txt" label="Barcode file" />
    </xml>
    <token name="@FASTQ_INPUT_PREPROC@"><![CDATA[
    #for $input in $input_type.fqinputs:
        #if $input_type.options_type_selector == "single"
            #set $isfq=$input.is_of_type('fastqsanger')
            #set $name=$clean_ext($input.element_identifier)
        #else:
            #set $isfq=$input.forward.is_of_type('fastqsanger')
            ## TODO if https://github.com/galaxyproject/galaxy/pull/7031 is
            ## backported use element_identifier consistently and fix release in <tool>?
            #set $name=$clean_ext($input.name)
        #end if
    
        #if $isfq:
            #set $ext = "fastq"
            #set inputype = "fastq"
        #else
            #set $ext = "fastq.gz"
            #set inputype = "gzfastq"
        #end if
    
        #if $input_type.options_type_selector == "single"
            ln -s '$input' 'stacks_inputs/${name}.${ext}' &&
        #else:
            ## procrad needs _R[12]_ in the file name, so we add an add 0
            ln -s '$input.forward' 'stacks_inputs/${name}_R1_0.${ext}' &&
            ln -s '$input.reverse' 'stacks_inputs/${name}_R2_0.${ext}' &&
        #end if
    #end for
    ]]></token>
    <token name="@PROCESS_IOOPTIONS@"><![CDATA[
    -p stacks_inputs/
    #if $input_type.options_type_selector == "paired"
        --paired
    #end if
    -i $inputype
    -b '$barcode'
    $input_type.barcode_encoding

        <discover_datasets pattern="@PATTERN@\.fa$" ext="fasta" directory="@DIR@/" />
    </xml>

    <xml name="process_outputs">
        <collection name="demultiplexed" type="list" label="${tool.name} on ${on_string} Demultiplexed reads">
            <filter>input_type['options_type_selector'] == "single"</filter>
            <expand macro="discover_faqgz_output_macro" pattern="(?P&lt;name&gt;.+)" dir="stacks_outputs"/>
        </collection>
        <collection name="demultiplexed_paired" type="list:paired" label="${tool.name} on ${on_string} Demultiplexed reads">
            <filter>input_type['options_type_selector'] == "paired"</filter>
            <expand macro="discover_faqgz_output_macro" pattern="(?P&lt;identifier_0&gt;.+)\.(?P&lt;identifier_1&gt;[^.]+)" dir="stacks_outputs"/>
        </collection>

        <collection name="remaining" type="list:paired" label="${tool.name} on ${on_string} Remaining orphan reads">
            <filter>input_type['options_type_selector'] == "paired"</filter>
            <expand macro="discover_faqgz_output_macro" pattern="(?P&lt;identifier_0&gt;.+)\.rem\.(?P&lt;identifier_1&gt;[^.]+)" dir="stacks_outputs/remaining"/>
        </collection>

        <!-- note irrespective of -y output is always named fastq and are never zipped -->
        <collection name="discarded" type="list" label="${tool.name} on ${on_string} Discarded reads">
            <filter>capture is True and input_type['options_type_selector'] == "single"</filter>
            <expand macro="discover_faq_output_macro" pattern="(?P&lt;name&gt;.*)" dir="stacks_outputs/discarded"/>
        </collection>
        <collection name="discarded_paired" type="list:paired" label="${tool.name} on ${on_string} Discarded reads">
            <filter>capture is True and input_type['options_type_selector'] == "paired"</filter>
            <expand macro="discover_faq_output_macro" pattern="(?P&lt;identifier_0&gt;.+)\.(?P&lt;identifier_1&gt;[^.]+)" dir="stacks_outputs/discarded"/>
        </collection>
    </xml>

    <!-- FASTQ filtering options -->
    <xml name="process_filter">
        <conditional name="filter_cond" >
            <param name="filter_select" type="select" label="do quality filtering">
                <option value="yes">Yes</option>
                <option value="no" selected="true">No</option>
            </param>
            <when value="yes">
                <param name="sliding" type="float" value="0.15" min="0" max="1" argument="-w" label="Set the size of the sliding window as a fraction of the read length, between 0 and 1" />
                <param name="score" type="integer" value="10" min="0" max="40" argument="-s" label="Set the score limit. If the average score within the sliding window drops below this value, the read is discarded" />
                <param name="remove" type="boolean" checked="false" truevalue="-c" falsevalue="" argument="-c" label="Clean data, remove any read with an uncalled base" />
                <param name="discard" type="boolean" checked="false" truevalue="-q" falsevalue="" argument="-q" label="Discard reads with low quality scores"/>
                <param argument="--filter_illumina" type="boolean" checked="false" truevalue="--filter_illumina" falsevalue="" label="discard reads that have been marked by Illumina's chastity/purity filter as failing" />
            </when>
            <when value="no">
                <param argument="--len_limit" type="integer" value="" optional="true" label="minimum sequence length" help="useful if your data has already been trimmed"/>
            </when>
        </conditional>
        <param name="capture" type="boolean" checked="false" truevalue="-D" falsevalue="" argument="-D" label="Capture discarded reads to a file" />
    </xml>
    <token name="@PROCESS_FILTER@"><![CDATA[

    #if $capture:
        && mkdir stacks_outputs/discarded/
        && mv stacks_outputs/*discards stacks_outputs/discarded/

        ## fix the _R[12]_0 that was added for preparing the input
        #if $input_type.options_type_selector == 'paired':
            && find stacks_outputs/discarded/ -type f | while read file; do mv "\$file" "\$(echo \$file | sed 's/_R1_0/.1/; s/_R2_0/.2/;')"; done
        #end if
        ## also remove the gz which is added by procrad (but its uncompressed)
        && find stacks_outputs/discarded/ -type f -iname "*.gz.discards" | while read file; do mv "\$file" "\$(echo \$file | sed 's/.gz.discards$/.discards/;')"; done

        #else
            && find stacks_outputs/discarded/ -type f | while read file; do mv "\$file" "\$(echo \$file | sed 's/\.fastq.discards/.fq/;')"; done
        #end if
    #end if
    ## prepare paired read output for processing in galaxy
    #if $input_type.options_type_selector == 'paired':
        && mkdir stacks_outputs/remaining
        && find stacks_outputs -iregex ".*\.rem\.[12]\.f[aq]\(\.gz\)?" | while read file; do mv "\$file" stacks_outputs/remaining/; done
        && find stacks_outputs/ -iregex ".*.f[aq]\(\.gz\)?" | while read file; do mv "\$file" "\$(echo \$file | sed 's/\.1\./.forward./; s/\.2\./.reverse./')"; done
    #end if
    ]]></token>



    <!-- adapter trimming options -->
    <xml name="process_adapter">
            <param argument="--adapter_1" type="text" value="" optional="true" label="adaptor sequence that may occur on the first read" />
            <param argument="--adapter_2" type="text" value="" optional="true" label="adaptor sequence that may occur on the paired-read" />
            <param argument="--adapter_mm" type="integer" value="" optional="true" label="number of mismatches allowed in the adapter sequence"/>
    </xml>
    <token name="@PROCESS_ADAPTER@"><![CDATA[
    ## Adapter options
    #if str($options_advanced.adapter_1) != "":
        --adapter_1 $options_advanced.adapter_1

        <conditional name="rescue_cond">
            <param name="rescue" type="select" argument="-r" label="Rescue mutated barcodes and RAD-Tags?">
                <option value="-r">yes</option>
                <option value="" selected="true">no</option>
            </param>
	    <when value="-r">
                <param argument="--barcode_dist_1" type="integer" value="" optional="true" label="number of allowed mismatches when rescuing first read barcodes" help="(default 1)"/>
    	        <param argument="--barcode_dist_2" type="integer" value="" optional="true" label="number of allowed mismatches when rescuing paired read barcodes" help="(default value for single end barcodes)"/>
            </when>
            <when value=""/>
        </conditional>
    </xml>
    <token name="@RESCUE_BARCODE@"><![CDATA[

            --barcode_dist_2 $options_advanced.rescue_cond.barcode_dist_2
        #end if
    #end if
    ]]></token>

    <!-- advanced options that are shared --> 
    <xml name="common_advanced">
        <param name="truncate" type="integer" value="" optional="True" argument="-t" label="Truncate final read length to this value" />
        <param argument="--retain_header" type="boolean" checked="false" truevalue="--retain_header" falsevalue="" label="Retain unmodified FASTQ headers in the output" />
    </xml>
    <token name="@COMMON_ADVANCED@"><![CDATA[

5:aef37afe214f

<?xml version="1.0"?>

<!-- macros and tokens for process_radtags and process_short_reads -->

<macros>

    <token name="@PROCESS_IOOPTIONS@"><![CDATA[
    -p stacks_inputs/
    #if $input_type.input_type_select == "paired"
        --paired
    #end if
    -i $inputype
    -b '$barcode'
    $input_type.barcode_encoding

        <discover_datasets pattern="@PATTERN@\.fa$" ext="fasta" directory="@DIR@/" />
    </xml>

    <xml name="process_outputs">
        <collection name="demultiplexed" type="list" label="${tool.name} on ${on_string} Demultiplexed reads">
            <filter>input_type['input_type_select'] == "single"</filter>
            <expand macro="discover_faqgz_output_macro" pattern="(?P&lt;name&gt;.+)" dir="stacks_outputs"/>
        </collection>
        <collection name="demultiplexed_paired" type="list:paired" label="${tool.name} on ${on_string} Demultiplexed reads">
            <filter>input_type['input_type_select'] == "paired"</filter>
            <expand macro="discover_faqgz_output_macro" pattern="(?P&lt;identifier_0&gt;.+)\.(?P&lt;identifier_1&gt;[^.]+)" dir="stacks_outputs"/>
        </collection>

        <collection name="remaining" type="list:paired" label="${tool.name} on ${on_string} Remaining orphan reads">
            <filter>input_type['input_type_select'] == "paired"</filter>
            <expand macro="discover_faqgz_output_macro" pattern="(?P&lt;identifier_0&gt;.+)\.rem\.(?P&lt;identifier_1&gt;[^.]+)" dir="stacks_outputs/remaining"/>
        </collection>

        <!-- note irrespective of -y output is always named fastq and are never zipped -->
        <collection name="discarded" type="list" label="${tool.name} on ${on_string} Discarded reads">
            <filter>capture is True and input_type['input_type_select'] == "single"</filter>
            <expand macro="discover_faq_output_macro" pattern="(?P&lt;name&gt;.*)" dir="stacks_outputs/discarded"/>
        </collection>
        <collection name="discarded_paired" type="list:paired" label="${tool.name} on ${on_string} Discarded reads">
            <filter>capture is True and input_type['input_type_select'] == "paired"</filter>
            <expand macro="discover_faq_output_macro" pattern="(?P&lt;identifier_0&gt;.+)\.(?P&lt;identifier_1&gt;[^.]+)" dir="stacks_outputs/discarded"/>
        </collection>
    </xml>

    <!-- FASTQ filtering options -->
    <xml name="process_filter">
        <conditional name="filter_cond" >
            <param name="filter_select" type="select" label="Do quality filtering">
                <option value="yes">Yes</option>
                <option value="no" selected="true">No</option>
            </param>
            <when value="yes">
                <param name="sliding" type="float" value="0.15" min="0" max="1" argument="-w" label="Set the size of the sliding window as a fraction of the read length, between 0 and 1" />
                <param name="score" type="integer" value="10" min="0" max="40" argument="-s" label="Set the score limit. If the average score within the sliding window drops below this value, the read is discarded" />
                <param name="remove" type="boolean" checked="false" truevalue="-c" falsevalue="" argument="-c" label="Clean data, remove any read with an uncalled base" />
                <param name="discard" type="boolean" checked="false" truevalue="-q" falsevalue="" argument="-q" label="Discard reads with low quality scores"/>
                <param argument="--filter_illumina" type="boolean" checked="false" truevalue="--filter_illumina" falsevalue="" label="Discard reads that have been marked by Illumina's chastity/purity filter as failing" />
            </when>
            <when value="no">
                <param argument="--len_limit" type="integer" value="" optional="true" label="Minimum sequence length" help="useful if your data has already been trimmed"/>
            </when>
        </conditional>
        <param name="capture" type="boolean" checked="false" truevalue="-D" falsevalue="" argument="-D" label="Capture discarded reads to a file" />
    </xml>
    <token name="@PROCESS_FILTER@"><![CDATA[

    #if $capture:
        && mkdir stacks_outputs/discarded/
        && mv stacks_outputs/*discards stacks_outputs/discarded/

        ## fix the _R[12]_0 that was added for preparing the input
        #if $input_type.input_type_select == 'paired':
            && find stacks_outputs/discarded/ -type f | while read file; do mv "\$file" "\$(echo \$file | sed 's/_R1_0/.1/; s/_R2_0/.2/;')"; done
        #end if
        ## also remove the gz which is added by procrad (but its uncompressed)
        && find stacks_outputs/discarded/ -type f -iname "*.gz.discards" | while read file; do mv "\$file" "\$(echo \$file | sed 's/.gz.discards$/.discards/;')"; done

        #else
            && find stacks_outputs/discarded/ -type f | while read file; do mv "\$file" "\$(echo \$file | sed 's/\.fastq.discards/.fq/;')"; done
        #end if
    #end if
    ## prepare paired read output for processing in galaxy
    #if $input_type.input_type_select == 'paired':
        && mkdir stacks_outputs/remaining
        && find stacks_outputs -iregex ".*\.rem\.[12]\.f[aq]\(\.gz\)?" | while read file; do mv "\$file" stacks_outputs/remaining/; done
        && find stacks_outputs/ -iregex ".*.f[aq]\(\.gz\)?" | while read file; do mv "\$file" "\$(echo \$file | sed 's/\.1\./.forward./; s/\.2\./.reverse./')"; done
    #end if
    ]]></token>

    <!-- adapter trimming options -->
    <xml name="process_adapter">
            <param argument="--adapter_1" type="text" value="" optional="true" label="Adaptor sequence that may occur on the first read" />
            <param argument="--adapter_2" type="text" value="" optional="true" label="Adaptor sequence that may occur on the paired-read" />
            <param argument="--adapter_mm" type="integer" value="" optional="true" label="Number of mismatches allowed in the adapter sequence"/>
    </xml>
    <token name="@PROCESS_ADAPTER@"><![CDATA[
    ## Adapter options
    #if str($options_advanced.adapter_1) != "":
        --adapter_1 $options_advanced.adapter_1

        <conditional name="rescue_cond">
            <param name="rescue" type="select" argument="-r" label="Rescue mutated barcodes and RAD-Tags?">
                <option value="-r">yes</option>
                <option value="" selected="true">no</option>
            </param>
            <when value="-r">
                <param argument="--barcode_dist_1" type="integer" value="" optional="true" label="Number of allowed mismatches when rescuing first read barcodes" help="(default 1)"/>
                <param argument="--barcode_dist_2" type="integer" value="" optional="true" label="Number of allowed mismatches when rescuing paired read barcodes" help="(default value for single end barcodes)"/>
            </when>
            <when value=""/>
        </conditional>
    </xml>
    <token name="@RESCUE_BARCODE@"><![CDATA[

            --barcode_dist_2 $options_advanced.rescue_cond.barcode_dist_2
        #end if
    #end if
    ]]></token>

    <!-- advanced options that are shared -->
    <xml name="common_advanced">
        <param name="truncate" type="integer" value="" optional="True" argument="-t" label="Truncate final read length to this value" />
        <param argument="--retain_header" type="boolean" checked="false" truevalue="--retain_header" falsevalue="" label="Retain unmodified FASTQ headers in the output" />
    </xml>
    <token name="@COMMON_ADVANCED@"><![CDATA[