comparison sortmerna.xml @ 1:b482293b2987 draft

planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/rna_tools/sortmerna commit 844d980a7de5f199487ca9591420a23df63c5246-dirty

0:a8ac09e937f3

<tool id="bg_sortmerna" name="Filter with SortMeRNA" version="1.9.0">
    <description>Fast and accurate filtering of ribosomal RNAs in metatranscriptomic data</description>
    <requirements>
        <requirement type='package' version="1.9">sortmerna</requirement>
    </requirements>
    <stdio>
        <regex match="This program builds a Burst trie on an input rRNA database"
            source="both"
            level="fatal"

    <version_command>
<![CDATA[
sortmerna --version 2>&1|grep 'SortMeRNA version'
]]>
    </version_command>
    <command interpreter="python">
<![CDATA[
    sortmerna.py
    --sortmerna "
        $strand_search
        #if str( $read_family.read_family_selector ) == 'other':
            --I $input_reads -r $read_family.ratio_parameter
        #else:
            $read_family.read_family_selector $input_reads
        #end if

        #if str( $sequencing_type.sequencing_type_selector ) == 'paired':
            $sequencing_type.paired_type
        #end if

        #if $outputs_selected:
            #if 'accept' in $outputs_selected.value:
                --accept accept_file
            #end if
            #if 'other' in $outputs_selected.value:
                --other other_file
            #end if
        #end if

        $log
        -a \${GALAXY_SLOTS:-4}
        "
        #if str( $databases_type.databases_selector ) == 'history':
            --buildtrie
            #for $db in $databases_type.input_databases
                $db.database_name
            #end for
        #else:
            ## databases path is not directly accessible, must match by hand with LOC file contents
            ${' '.join([dict([(x[0], x[2]) for x in $databases_type.input_databases.input.options.tool_data_table.data])[y]
                       for y in $databases_type.input_databases.value])}
        #end if
]]>
    </command>
    <inputs>
    <conditional name="read_family">
        <param name="read_family_selector" type="select" format="text" label="Sequencing technology of querying sequences (reads)"
            help="The Illumina platform is more common for large scale metatranscriptomic projects requiring a high throughput.">
            <option value="--I">Illumina Solexa</option>
            <option value="--454">454 Roche</option>
            <option value="other">Other</option>
        </param>
        <when value="other">
            <param name="ratio_parameter" type="float" value="1" min="0" max="1"
                label="Ratio parameter (the number of hits on the read / read length)"
                help="The ratio parameter for SortMeRNA has been set to r=0.25 for Illumina Solexa reads and to r=0.15 for 454 Roche reads.
                    For other read types, if the sequencing technology produces high quality reads with a low substitution error rate
                    (0.1 substitutions per 100 bases, such as Illumina), then the ratio parameter can be set to r=[0.23,0.27].
                    If the sequencing technology has a high indel error rate (1-2 indels per 100 bases, such as 454 or Ion Torrent),
                    then the ratio parameter can be set to r=[0.13,0.17] (-r)."/>
        </when>
    </conditional>
    <param format="fasta,fastq" name="input_reads" type="data" label="Querying sequences (reads)" help=""/>
    <conditional name="sequencing_type">
        <param name="sequencing_type_selector" type="select" label="Sequencing type">
            <option value="not_paired">Reads are not paired</option>
            <option value="paired">Reads are paired</option>
        </param>
        <when value="paired">
            <param name="paired_type" type="select" display="radio" label="If one read of a pair is accepted and the other not, output both reads"
                help="SortMeRNA does not use the pairing information for filtering RNA,
                    however if one read of a pair is accepted and the other is not,
                    the resulting output may break apart the pair into two separate files.
                    The purpose of 'Reads are paired' option is to preserve the pairing of the reads.">
                <option value="--paired-in">to accepted file (--paired-in)</option>
                <option value="--paired-out">to rejected file (--paired-out)</option>
            </param>
        </when>
    </conditional>

    <param name="strand_search" type="select" label="Which strands to search" display="radio">
        <option value="">Search both strands</option>
        <option value="-F">Search only the forward strand (-F)</option>
        <option value="-R">Search only the reverse-complementary strand (-R)</option>
    </param>

    <conditional name="databases_type">
        <param name="databases_selector" type="select" label="Databases to query"
            help="Public rRNA databases provided with SortMeRNA have been indexed.
                On the contrary, personal databases must be indexed each time SortMeRNA is launched.
                Please be patient, this may take some time depending on the size of the given database.">
            <option value="cached" selected="true">Public ribosomal databases</option>
            <option value="history">Databases from your history</option>
        </param>
        <when value="cached">
            <param name="input_databases" label="rRNA database" type="select" display="checkboxes" multiple="true">
                <options from_data_table="rRNA_databases" />
                <validator type="no_options" message="Select at least one database"/>
            </param>
        </when>
        <when value="history">
            <repeat name="input_databases" title="Database" min="1">
                <param name="database_name" type="data" format="fasta" label="rRNA database"
                    help="Your database will be indexed first, which may take up to several minutes."/>
            </repeat>
        </when>
    </conditional>

    <!-- Outputs -->
    <param name="outputs_selected" type="select" display="checkboxes" multiple="true" label="Output options">
        <option value="accept" selected="True">Reads matching to at least one database</option>
        <option value="other">Reads not found in any database</option>
    </param>
    <param name="log" type="boolean" checked="False" truevalue="--log log_file" falsevalue="" label="Statistics file"
           help="Generates statistics for the rRNA content of reads, as well as rRNA subunit distribution. (--log)">
    </param>

    </inputs>
    <outputs>
        <data format_source="input_reads" name="output_accept" from_work_dir="accept_file.dat"
            label="Matching reads on ${on_string} (${input_reads.datatype.file_ext})">
            <filter>outputs_selected and 'accept' in outputs_selected</filter>
        </data>
        <data format_source="input_reads" name="output_other" from_work_dir="other_file.dat"
            label="Reads not found on ${on_string} (${input_reads.datatype.file_ext})">
            <filter>outputs_selected and 'other' in outputs_selected</filter>
        </data>
        <data format="txt" name="output_log" label="${tool.name} statistics (txt)" from_work_dir="log_file.log">
            <filter>log</filter>
        </data>
    </outputs>
    <tests>
        <test>
            <param name="read_family_selector" value="I" />
            <param name="input_reads" value="sortmerna_wrapper_in1.fastq" />
            <param name="sequencing_type_selector" value="not_paired" />
            <param name="strand_search" value="" />
            <param name="databases_selector" value="cached" />
            <param name="input_databases" value="rfam-5.8s,rfam-5s" />
            <param name="outputs_selected" value="accept,other" />
            <param name="log" value="" />
            <param name="options_type_selector" value="less" />
            <output name="output_accept" file="sortmerna_wrapper_accept1.fastq" />
            <output name="output_other" file="sortmerna_wrapper_other1.fastq" />
        </test>
    </tests>
    <help>
<![CDATA[
**What it does**

1:b482293b2987

<tool id="bg_sortmerna" name="Filter with SortMeRNA" version="2.0.0">
    <description>Fast and accurate filtering of ribosomal RNAs in metatranscriptomic data</description>
    <requirements>
        <requirement type='package' version="2.0">sortmerna</requirement>
    </requirements>
    <stdio>
        <regex match="This program builds a Burst trie on an input rRNA database"
            source="both"
            level="fatal"

    <version_command>
<![CDATA[
sortmerna --version 2>&1|grep 'SortMeRNA version'
]]>
    </version_command>
    <command>
<![CDATA[
    #set $ref = ''
    #set $sep=''
    #if str( $databases_type.databases_selector ) == 'history':
        #for $db in $databases_type.database_name
            #set $ref += $sep + str($db) + ',' + $os.path.splitext($os.path.basename(str($db)))[0]
            #set $sep = ':'
        #end for
        indexdb_rna --ref $ref
        &&
    #else:
        ## databases path is not directly accessible, must match by hand with LOC file contents
        #set $data_table = dict([(_[0], _[2]) for _ in $databases_type.input_databases.input.options.tool_data_table.data])
        #for $db in $databases_type.input_databases.value
            #set $ref += $sep + $data_table[$db] + ',' + $os.path.splitext($data_table[$db])[0]
            #set $sep = ':'
        #end for
    #end if
    sortmerna --ref $ref --reads $input_reads --aligned aligned
    #if str( $sequencing_type.sequencing_type_selector ) == 'paired'
        $sequencing_type.paired_type
    #end if
    $strand_search
    $aligned_fastx.aligned_fastx_selector
    #if $aligned_fastx.aligned_fastx_selector == '--fastx'
        #if $aligned_fastx.other
            --other other_file
        #end if
    #end if
    $aligned_sam.aligned_sam_selector
    #if $aligned_sam.aligned_sam_selector == '--sam'
        $aligned_sam.sq
    #end if
    $aligned_blast
    $log
    -a \${GALAXY_SLOTS:-1}
]]>
    </command>
    <inputs>
        <param format="fasta,fastq" name="input_reads" type="data" label="Querying sequences" help="In FASTA or FASTQ format (--reads)"/>
        <conditional name="sequencing_type">
            <param name="sequencing_type_selector" type="select" label="Sequencing type">
                <option value="not_paired">Reads are not paired</option>
                <option value="paired">Reads are paired</option>
            </param>
            <when value="paired">
                <param name="paired_type" type="select" display="radio" label="If one of the paired-end reads aligns and the other one does not">
                    <option value="">leave the reads split between aligned and rejected files</option>
                    <option value="--paired-in">output both reads to aligned file (--paired-in)</option>
                    <option value="--paired-out">output both reads to rejected file (--paired-out)</option>
                </param>
            </when>
        </conditional>

        <param name="strand_search" type="select" label="Which strands to search" display="radio">
            <option value="">Search both strands</option>
            <option value="-F">Search only the forward strand (-F)</option>
            <option value="-R">Search only the reverse-complementary strand (-R)</option>
        </param>

        <conditional name="databases_type">
            <param name="databases_selector" type="select" label="Databases to query"
                help="Public rRNA databases provided with SortMeRNA have been indexed.
                    On the contrary, personal databases must be indexed each time SortMeRNA is launched.
                    Please be patient, this may take some time depending on the size of the given database.">
                <option value="cached" selected="true">Public ribosomal databases</option>
                <option value="history">Databases from your history</option>
            </param>
            <when value="cached">
                <param name="input_databases" label="rRNA databases" type="select" display="checkboxes" multiple="true">
                    <options from_data_table="rRNA_databases" />
                    <validator type="no_options" message="Select at least one database"/>
                </param>
            </when>
            <when value="history">
                <param name="database_name" type="data" format="fasta" multiple="true" label="rRNA databases"
                    help="Your databases will be indexed first, which may take up to several minutes."/>
            </when>
        </conditional>

        <!-- Outputs -->
        <conditional name="aligned_fastx">
            <param name="aligned_fastx_selector" type="select" label="Include aligned reads in FASTA/FASTQ format">
                <option value="--fastx">Yes (--fastx)</option>
                <option value="">No</option>
            </param>
            <when value="--fastx">
                <param name="other" type="boolean" label="Include rejected reads file" help="(--other)" />
            </when>
            <when value="" />
        </conditional>
        <conditional name="aligned_sam">
            <param name="aligned_sam_selector" type="select" label="Include alignments in SAM format">
                <option value="--sam">Yes (--sam)</option>
                <option value="">No</option>
            </param>
            <when value="--sam">
                <param name="sq" type="boolean" truevalue="--SQ" falsevalue="" label="Add SQ tags to the SAM file" help="(--SQ)" />
            </when>
            <when value="" />
        </conditional>
        <param name="aligned_blast" type="select" label="Include alignments in BLAST-like format">
            <option value="--blast 0">pairwise (--blast 0)</option>
            <option value="--blast 1">tabular BLAST -m 8 format (--blast 1)</option>
            <option value="--blast 2">tabular + column for CIGAR (--blast 2)</option>
            <option value="--blast 3">tabular + columns for CIGAR and query coverage (--blast 3)</option>
            <option value="" selected="true">No</option>
        </param>
        <param name="log" type="boolean" checked="False" truevalue="--log" falsevalue="" label="Generate statistics file"
               help="Generates statistics for the rRNA content of reads, as well as rRNA subunit distribution. (--log)">
        </param>
    </inputs>
    <outputs>
        <data format_source="input_reads" name="output_fastx" from_work_dir="aligned.dat"
            label="Aligned reads on ${on_string} (${input_reads.datatype.file_ext})">
            <filter>aligned_fastx['aligned_fastx_selector']</filter>
        </data>
        <data format_source="input_reads" name="output_other" from_work_dir="other_file.dat"
            label="Rejected reads on ${on_string} (${input_reads.datatype.file_ext})">
            <filter>aligned_fastx['aligned_fastx_selector'] and aligned_fastx['other']</filter>
        </data>
        <data format="sam" name="output_sam" from_work_dir="aligned.sam"
            label="Alignments on ${on_string} (SAM)">
            <filter>aligned_sam['aligned_sam_selector']</filter>
        </data>
        <data format="tabular" name="output_blast" from_work_dir="aligned.blast"
            label="Alignments on ${on_string} (BLAST)">
            <filter>aligned_blast</filter>
            <change_format>
                <when input="aligned_blast" value="--blast 0" format="txt" />
            </change_format>
        </data>
        <data format="txt" name="output_log" label="${tool.name} statistics (txt)" from_work_dir="aligned.log">
            <filter>log</filter>
        </data>
    </outputs>
    <tests>
        <test>
            <param name="input_reads" value="read_small.fastq" />
            <param name="sequencing_type_selector" value="not_paired" />
            <param name="strand_search" value="" />
            <param name="databases_selector" value="history" />
            <param name="database_name" value="ref_small.fasta" />
            <param name="other" value="True" />
            <param name="log" value="" />
            <output name="output_fastx" file="sortmerna_wrapper_accept1.fastq" />
            <output name="output_other" file="sortmerna_wrapper_other1.fastq" />
            <output name="output_sam" file="sortmerna_wrapper_sam1.sam" lines_diff="2" />
        </test>
        <test>
            <param name="input_reads" value="read_small.fasta" />
            <param name="sequencing_type_selector" value="not_paired" />
            <param name="strand_search" value="" />
            <param name="databases_selector" value="history" />
            <param name="database_name" value="ref_small.fasta" />
            <param name="other" value="True" />
            <param name="log" value="" />
            <output name="output_fastx" file="sortmerna_wrapper_accept2.fasta" />
            <output name="output_other" file="sortmerna_wrapper_other2.fasta" />
            <output name="output_sam" file="sortmerna_wrapper_sam2.sam" lines_diff="2" />
        </test>
    </tests>
    <help>
<![CDATA[
**What it does**