annotate sam2rma.xml @ 1:ef0443c0eaba draft default tip

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/megan commit 6b0c3dbd5bdf9c272cf32f39e0004d504f953ff0

<tool id="megan_sam2rma" name="MEGAN: Generate a MEGAN rma6 file" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@">
    <description>from a DIAMOND or MALT sam file</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 sam1 = $input_type_cond.sam1
#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 sam1 = $input_type_cond.sam1
#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

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

#set sam1_identifier = 'sam1.' + $sam1.ext
ln -s '${sam1}' '${sam1_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 sam2 = $input_type_cond.sam2
    #else if str($input_type_cond.input_type) == 'paired':
        #set read2 = $input_type_cond.reads_collection['reverse']
        #set sam2 = $input_type_cond.sam2
    #end if
    #set read2_identifier = 'read2' + $read_ext
    ln -s '${read2}' '${read2_identifier}' &&
    #set sam2_identifier = 'sam2.' + $sam2.ext
    ln -s '${sam2}' '${sam2_identifier}' &&
#end if

## The output must be a directory when we have multiple
## inputs, and the outputs inherit the base name of the
## inputs.

sam2rma
#if str($input_type_cond.input_type) == 'single':
    --in '${sam1_identifier}'
    --reads '${read1_identifier}'
    --out '${output_single}'
#else if str($input_type_cond.input_type) == 'pair':
    --in '${sam1_identifier}' '${sam2_identifier}'
    --reads '${read1_identifier}' '${read2_identifier}'
    --paired
    --pairedSuffixLength $input_type_cond.pairedSuffixLength 
    --out '.'
#else if str($input_type_cond.input_type) == 'paired':
    --in '${sam1_identifier}' '${sam2_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 '.'
#end if
#if $advanced_options.metaDataFile:
    --metaDataFile '$advanced_options.metaDataFile'
#end if
#if str($advanced_options.paired_reads_cond.paired_reads) == 'yes':
    --paired
    $advanced_options.paired_reads_cond.pairedSuffixLength
#end if
$advanced_options.longReads
--maxMatchesPerRead $advanced_options.maxMatchesPerRead
$advanced_options.classify
--minScore $advanced_options.minScore
--maxExpected $advanced_options.maxExpected
--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 $advanced_options.conFile:
    --conFile '$advanced_options.conFile'
#end if
#if $advanced_options.mapDB:
    --mapDB '$advanced_options.mapDB'
#end if
#if str($advanced_options.only) != '':
    --only '$advanced_options.only'
#end if
--useCompression 'false'
--threads \${GALAXY_SLOTS:-8}
--tempStoreDir '.'
#if str($input_type_cond.input_type) in ['pair', 'paired']:
    && mv 'sam1.rma6' '$output_forward'
    && mv 'sam2.rma6' '$output_reverse'
#end if
    ]]></command>
    <inputs>
        <conditional name="input_type_cond">
            <param name="input_type" type="select" label="Choose the category of the reads files to be analyzed">
                <option value="single" selected="true">Single dataset</option>
                <option value="pair">Dataset pair</option>
                <option value="paired">List of dataset pairs</option>
            </param>
            <when value="single">
                <param name="read1" type="data" format="fasta,fasta.gz,fastqsanger.gz,fastqsanger" label="Forward read file" help="This read file should be the one used by DIAMOND or MALT to generate the SAM file below"/>
                <param name="sam1" type="data" format="sam" label="Output file of DIAMOND or MALT on input forward read file"/>
            </when>
            <when value="pair">
                <param name="read1" type="data" format="fasta,fasta.gz,fastqsanger.gz,fastqsanger" label="Forward read file" help="This read file should be the one used by DIAMOND or MALT to generate the SAM file below"/>
                <param name="sam1" type="data" format="sam" label="Output file of DIAMOND or MALT on input forward read file"/>
                <param name="read2" type="data" format="fasta,fasta.gz,fastqsanger.gz,fastqsanger" label="Reverse read file" help="This read file should be the one used by DIAMOND or MALT to generate the SAM file below"/>
                <param name="sam2" type="data" format="sam" label="Output file of DIAMOND or MALT on input reverse read file"/>
                <param argument="--pairedSuffixLength" type="integer" value="0" label="Length of name suffix used to distinguish read names" help="Use 0 if read and mate have the same name"/>
            </when>
            <when value="paired">
                <param name="reads_collection" type="data_collection" format="fasta,fasta.gz,fastqsanger,fastqsanger.gz" collection_type="paired" label="Collection of paired read files"/>
                <param name="sam1" type="data" format="sam" label="Output file of DIAMOND or MALT on input forward read file"/>
                <param name="sam2" type="data" format="sam" label="Output file of DIAMOND or MALT on input reverse read file"/>
                <param argument="--pairedSuffixLength" type="integer" value="0" label="Length of name suffix used to distinguish read names" help="Use 0 if read and mate have the same name"/>
            </when>
        </conditional>
        <section name="advanced_options" title="Advanced options" expanded="false">
            <param argument="--metaDataFile" type="data" format="tabular" multiple="true" optional="true" label="Files containing metadata to be included in the output files"/>
            <conditional name="paired_reads_cond">
                <param name="paired_reads" type="select" label="DAA file was created using paired reads?">
                    <option value="no" selected="true">no</option>
                    <option value="yes">Yes</option>
                </param>
                <when value="no"/>
                <when value="yes">
                    <param argument="--pairedSuffixLength" type="integer" value="0" label="Length of name suffix used to distinguish read names" help="Use 0 if read and mate have the same name"/>
                </when>
            </conditional>
            <expand macro="long_reads_param"/>
            <expand macro="max_matches_per_read_param"/>
            <expand macro="classify_param"/>
            <expand macro="min_score_param"/>
            <expand macro="max_expected_param"/>
            <expand macro="top_percent_param"/>
            <expand macro="min_max_params"/>
            <expand macro="lca_params"/>
            <expand macro="read_assignment_mode_param"/>
            <expand macro="con_file_param"/>
            <expand macro="mapdb_param"/>
            <expand macro="only_named_classifications_param"/>
        </section>
    </inputs>
    <outputs>
        <data name="output_single" format="rma6">
            <filter>input_type_cond['input_type'] == 'single'</filter>
        </data>
        <data name="output_forward" format="rma6" label="${tool.name} on ${on_string} (forward">
            <filter>input_type_cond['input_type'] != 'single'</filter>
        </data>
        <data name="output_reverse" format="rma6" label="${tool.name} on ${on_string} (reverse)">
            <filter>input_type_cond['input_type'] != 'single'</filter>
        </data>
    </outputs>
    <tests>
        <!-- Single dataset input -->
        <test expect_num_outputs="1">
            <param name="sam1" ftype="sam" value="input1.sam"/>
            <param name="read1" ftype="fastqsanger.gz" value="13-1941-6_S4_L001_R1_600000.fastq.gz"/>
            <output name="output_single" ftype="rma6">
                <assert_contents>
                    <has_size value="885" delta="15"/>
                </assert_contents>
            </output>
       </test>
        <!-- Dataset pair input -->
        <test expect_num_outputs="2">
            <param name="input_type" value="pair"/>
            <param name="read1" value="13-1941-6_S4_L001_R1_600000.fastq.gz" ftype="fastqsanger.gz"/>
            <param name="sam1" value="input1.sam" ftype="sam"/>
            <param name="read2" value="13-1941-6_S4_L001_R2_600000.fastq.gz" ftype="fastqsanger.gz"/>
            <param name="sam2" value="input2.sam" ftype="sam"/>
            <output name="output_forward" ftype="rma6">
                <assert_contents>
                    <has_size value="805" delta="1"/>
                </assert_contents>
            </output>
            <output name="output_reverse" ftype="rma6">
                <assert_contents>
                    <has_size value="805" delta="1"/>
                </assert_contents>
            </output>
        </test>
        <!-- List of dataset pairs input -->
        <test expect_num_outputs="2">
            <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="sam1" value="input1.sam" ftype="sam"/>
            <param name="sam2" value="input2.sam" ftype="sam"/>
            <output name="output_forward" ftype="rma6">
                <assert_contents>
                    <has_size value="805" delta="1"/>
                </assert_contents>
            </output>
            <output name="output_reverse" ftype="rma6">
                <assert_contents>
                    <has_size value="805" delta="1"/>
                </assert_contents>
            </output>
        </test>
    </tests>
    <help>
**What it does**

Generates a MEGAN RMA (RealMedia Audio) file from a SAM file that was generated by DIAMOND or MALT.  MEGAN uses an
update of the original RMA file format known as RMA6.

Inputs consist of reads in fasta or fasqsanger format (gzip compression is supported) and associated SAM files.
Each read file should have been used previously as the input to DIAMOND or MALT to produce the associated SAM file
for this tool.
    </help>
    <expand macro="citations"/>
</tool>