annotate blast2rma.xml @ 0:fa3c3a64c993 draft

"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/megan commit 2a49a6cdc1b4d37ab30eb85b8c658ccf9f5a0644"

<tool id="megan_blast2rma" name="MEGAN: Generate RMA files" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@">
    <description>from BLAST output</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="bio_tools"/>
    <expand macro="requirements"/>
    <command detect_errors="exit_code"><![CDATA[
#import re

#if str($input_type_cond.input_type) in ['single', 'pair']:
    #set read1 = $input_type_cond.read1
    #set blast1 = $input_type_cond.blast1
#else:
    ## Processing paired reads are tricky if we're
    ## downstream from MALT.  MALT doesn’t have a
    ## paired-read mode, so it won’t attempt to analyze
    ## reads in pairs.  To do paired read processing,
    ## set MALT to generate SAM files and then import the
    ## SAM files into MEGAN, specifying paired read mode
    ## there. If you have multiple SAM files for the same
    ## sample, then import them all at the same time to
    ## create one unified rma6 file.

    #set read1 = $input_type_cond.reads_collection['forward']
    #set blast1 = $input_type_cond.blast1
#end if

#if $read1.is_of_type('fasta', 'fasta.gz'):
    #set read_ext = '.fasta'
#else:
    #set read_ext = '.fastq'
#end if
#if $read1.ext.endswith('.gz'):
    #set read_ext = $read_ext + '.gz'
#end if

#if $blast1.is_of_type('daa'):
    #set blast_format = 'DAA'
#else if $blast1.is_of_type('txt'):
    #set blast_format = 'BlastText'
#else if $blast1.is_of_type('blastxml'):
    #set blast_format = 'BlastXML'
#else if $blast1.is_of_type('tabular'):
    #set blast_format = 'BlastTab'
#else if $blast1.is_of_type('sam'):
    #set blast_format = 'SAM'
#end if
#set blast_ext = '.' + $blast_format
#if $blast1.ext.endswith('.gz'):
    #set blast_ext = $blast_ext + '.gz'
#end if

#set read1_identifier = 'read1' + $read_ext
ln -s '${read1}' '${read1_identifier}' &&

#set blast1_identifier = 'blast1' + $blast_ext
ln -s '${blast1}' '${blast1_identifier}' &&

#if str($input_type_cond.input_type) in ['pair', 'paired']:
    #if str($input_type_cond.input_type) == 'pair':
        #set read2 = $input_type_cond.read2
        #set blast2 = $input_type_cond.blast2
    #else if str($input_type_cond.input_type) == 'paired':
        #set read2 = $input_type_cond.reads_collection['reverse']
        #set blast2 = $input_type_cond.blast2
    #end if
    #set read2_identifier = 'read2' + $read_ext
    ln -s '${read2}' '${read2_identifier}' &&
    #set blast2_identifier = 'blast2' + $blast_ext
    ln -s '${blast2}' '${blast2_identifier}' &&
#end if

blast2rma 
#if str($input_type_cond.input_type) == 'single':
    --in '${blast1_identifier}'
    --reads '${read1_identifier}'
    --out '${rma6_output}'
#else if str($input_type_cond.input_type) == 'pair':
    --in '${blast1_identifier}' '${blast2_identifier}'
    --reads '${read1_identifier}' '${read2_identifier}'
    --paired
    --pairedSuffixLength $input_type_cond.pairedSuffixLength 
    --out '${rma6_output}'
#else if str($input_type_cond.input_type) == 'paired':
    --in '${blast1_identifier}' '${blast2_identifier}'
    --reads '${read1_identifier}' '${read2_identifier}'
    --paired
    --pairedSuffixLength $input_type_cond.pairedSuffixLength 
    ## Strangely, megan requires an output
    ## directory when processing paired reads
    ## even though it produces a single file.
    ## We'll accommodate thie by prepending ./
    ## to a temporary output file and then move
    ## it later.
    --out './tmp.rma6'
#end if
--format '${blast_format}'
--blastMode '${blastMode}'
--threads \${GALAXY_SLOTS:-8}
--useCompression false
$advanced_options.longReads
--maxMatchesPerRead '$advanced_options.maxMatchesPerRead'
$advanced_options.classify
--minScore $advanced_options.minScore
--maxExpected $advanced_options.maxExpected
--minPercentIdentity $advanced_options.minPercentIdentity
--topPercent $advanced_options.topPercent
--minSupportPercent $advanced_options.minSupportPercent
--minSupport $advanced_options.minSupport
--minPercentReadCover $advanced_options.minPercentReadCover
--minPercentReferenceCover $advanced_options.minPercentReferenceCover
--minReadLength $advanced_options.minReadLength
--lcaAlgorithm '$advanced_options.lcaAlgorithm'
--lcaCoveragePercent $advanced_options.lcaCoveragePercent
--readAssignmentMode '$advanced_options.readAssignmentMode'
#if str($advanced_options.con_file_cond.conFile) == 'yes':
    --conFile '$advanced_options.con_file_cond.conFile'
#end if
#if str($input_type_cond.input_type) == 'paired':
    && mv './tmp.rma6' '$rma6_output'
#end if
]]></command>
    <inputs>
        <expand macro="input_type_cond"/>
        <param argument="--blastMode" type="select" label="Blast mode">
            <expand macro="blast_mode_options"/>
        </param>
        <section name="advanced_options" title="Advanced options" expanded="false">
            <param argument="--longReads" type="boolean" truevalue="--longReads" falsevalue="" checked="false" label="Parse and analyse input reads as long reads?"/>
            <param argument="--maxMatchesPerRead" type="integer" value="100" label="Maximum matches per read"/>
            <param argument="--classify" type="boolean" truevalue="--classify" falsevalue="" checked="true" label="Run classification algorithm?"/>
            <expand macro="common_blast_params"/>
            <param argument="--minSupportPercent" type="float" value="0.05" min="0.0" max="100.0" label="Minimum support as percent of assigned reads" help="0 value ignores"/>
            <param argument="--minSupport" type="integer" value="0" label="Minimum support" help="0 value ignores"/>
            <param argument="--minPercentReadCover" type="float" value="0.0" min="0.0" max="100.0" label="Minimum percent of read length to be covered by alignments"/>
            <param argument="--minPercentReferenceCover" type="float" value="0.0" min="0.0" max="100.0" label="Minimum percent of reference length to be covered by alignments"/>
            <param argument="--minReadLength" type="integer" value="0" label="Minimum read length"/>
            <param argument="--lcaAlgorithm" type="select" label="Select the LCA algorithm to use for taxonomic assignment">
                <option value="naive" selected="true">naive</option>
                <option value="weighted">weighted</option>
                <option value="longReads">longReads</option>
            </param>
            <param argument="--lcaCoveragePercent" type="float" value="100.0" min="0.0" max="100.0" label="Percent for the LCA to cover"/>
            <param argument="--readAssignmentMode" type="select" label="Select the read assignment mode">
                <option value="alignedBases" selected="true">alignedBases</option>
                <option value="readCount">readCount</option>
            </param>
            <conditional name="con_file_cond">
                <param argument="--conFile" type="select" label="Process a file of contaminant taxa" help="One id or name per line">
                    <option value="no" selected="true">No</option>
                    <option value="yes">Yes</option>
                </param>
                <when value="no"/>
                <when value="yes">
                    <param argument="conFile" type="data" format="txt" label="File of contaminant taxa"/>
                </when>
            </conditional>
        </section>
    </inputs>
    <outputs>
        <data name="rma6_output" format="rma6"/>
    </outputs>
    <tests>
        <!-- Single dataset input -->
        <test expect_num_outputs="1">
            <param name="read1" value="13-1941-6_S4_L001_R1_600000.fastq.gz" ftype="fastqsanger.gz"/>
            <param name="blast1" value="blast_R1.txt" ftype="txt"/>
            <param name="blastMode" value="BlastN"/>
            <output name="rma6_output" ftype="rma6">
                <assert_contents>
                    <has_size value="19596"/>
                </assert_contents>
            </output>
        </test>
        <!-- Single dataset input, contaminants file -->
        <test expect_num_outputs="1">
            <param name="read1" value="13-1941-6_S4_L001_R1_600000.fastq.gz" ftype="fastqsanger.gz"/>
            <param name="blast1" value="blast_R1.txt" ftype="txt"/>
            <param name="blastMode" value="BlastN"/>
            <param name="conFile" value="yes"/>
            <param name="conFile" value="contaminants.txt" ftype="txt"/>
            <output name="rma6_output" ftype="rma6">
                <assert_contents>
                    <has_size value="19596"/>
                </assert_contents>
            </output>
        </test>
        <!-- Dataset pair input -->
        <test expect_num_outputs="1">
            <param name="input_type" value="pair"/>
            <param name="read1" value="13-1941-6_S4_L001_R1_600000.fastq.gz" ftype="fastqsanger.gz"/>
            <param name="read2" value="13-1941-6_S4_L001_R2_600000.fastq.gz" ftype="fastqsanger.gz"/>
            <param name="blast1" value="blast_R1.txt" ftype="txt"/>
            <param name="blast2" value="blast_R2.txt" ftype="txt"/>
            <param name="blastMode" value="BlastN"/>
            <output name="rma6_output" ftype="rma6">
                <assert_contents>
                    <has_size value="39887"/>
                </assert_contents>
            </output>
        </test>
        <!-- List of dataset pairs input -->
        <test expect_num_outputs="1">
            <param name="input_type" value="paired"/>
            <param name="reads_collection">
                <collection type="paired">
                    <element name="forward" value="13-1941-6_S4_L001_R1_600000.fastq.gz"/>
                    <element name="reverse" value="13-1941-6_S4_L001_R2_600000.fastq.gz"/>
                </collection>
            </param>
            <param name="blast1" value="blast_R1.txt" ftype="txt"/>
            <param name="blast2" value="blast_R2.txt" ftype="txt"/>
            <param name="blastMode" value="BlastN"/>
            <output name="rma6_output" ftype="rma6">
                <assert_contents>
                    <has_size value="39806"/>
                </assert_contents>
            </output>
        </test>
    </tests>
    <help>
**What it does**

Computes MEGAN RMA files from BLAST (or similar) files.  Inputs consist of reads in fasta or fasqsanger format (gzip compressin
is supported) and associated Blast files.  Each read file should have been used previously as the Blast input to produce the
associated Blast file for this tool.

This wrapper supports the following formats for the input Blast file.  The SAM, Tabular and Text formats can be produced by
The Galaxy MALT Analyzer tool.  When these formats are used, this tool will apply the SAM, BlastText and BlastTab format options
required by MEGAN.

 * **Direct Access Archive (DAA)** - a proprietary file format developed by PowerISO Computing for disk image files
 * **BlastXML** - XML output from Blast
 * **Sequence Alignment/Map (SAM)** - a tab-delimited text format consisting of a header section, which is optional, and an alignment section
 * **Tabular** - information presented in the form of a table with rows and columns
 * **Text** - plain text format

This tool outputs a RealMedia Audio (RMA) file.  MEGAN uses an update of the original RMA file format known as RMA6.  This update
requires less disk space for files.
    </help>
    <citations>
        <citation type="doi">https://doi.org/10.1101/050559</citation>
    </citations>
</tool>