comparison mapper.xml @ 4:dbbe92348c7a draft default tip

planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/mirdeep2/mirdeep2_mapper commit 04c75332ac618b43ce5c3f307f7866e97147e865

3:a8d24f4b6d95

<tool id="rbc_mirdeep2_mapper" name="MiRDeep2 Mapper" version="2.0.0">
    <description>process and map reads to a reference genome</description>
    <macros>
        <macro name="map_params">
            <conditional name="refGenomeSource">
                <param name="genomeSource" type="select" label="Will you select a reference genome from your history or use a built-in index?" help="Map to genome. (-p)">

        </macro>
    </macros>
    <requirements>
        <requirement type="package" version="2.0.0.8">mirdeep2</requirement>
    </requirements>
    <stdio>
        <!-- Anything other than zero is an error -->
        <exit_code range="1:" />
        <exit_code range=":-1" />
        <!-- In case the return code has not been set propery check stderr too -->
        <regex match="Error:" />
        <regex match="Exception:" />
    </stdio>
    <command>
<![CDATA[

        #if $operation.collapse_map == "collapse_and_map" or $operation.collapse_map == "only_map"
            #if $operation.refGenomeSource.genomeSource == "history"
                bowtie-build '$operation.refGenomeSource.ownFile' custom_bowtie_indices &&
            #end if
        #end if

        mapper.pl 
    
        '$reads'
        
        #if $reads.extension.startswith("fasta")
            -c
        #else if $reads.extension.startswith("fastq")
            -e
            -h
        #end if

        $remove_non_canon
        
        $convert_rna_dna

        #if $clip_adapter.clip == "true"
            -k $clip_adapter.adapter_seq
        #end if

        -l $discard_short_reads

        #if $operation.collapse_map == "collapse_and_map" or $operation.collapse_map == "only_collapse"
            -m -s '$output_reads_collapsed'
        #end if
        
        #if $operation.collapse_map == "collapse_and_map" or $operation.collapse_map == "only_map"
            -p 
            
            #if $operation.refGenomeSource.genomeSource == "history"
                custom_bowtie_indices
            #else
                '$operation.refGenomeSource.index.fields.path'
            #end if
            $operation.map_mismatch
            -r $operation.map_threshold
            
            -t '$output_mapping'
        #end if

        -v -n
]]>
    </command>
    <inputs>
        <param format="fastq, fasta" name="reads" type="data" optional="false" label="Deep sequencing reads" help="Reads in fastq or FASTA format"/>
        <param name="remove_non_canon" type="boolean" truevalue="-j" falsevalue="" checked="false" label="Remove reads with non-standard nucleotides" help="Remove all entries that have a sequence that contains letters other than a,c,g,t,u,n,A,C,G,T,U,N. (-j)"/>
        <param name="convert_rna_dna" type="boolean" truevalue="-i" falsevalue="" checked="false" label="Convert RNA to DNA alphabet (to map against genome)" help="(-i)"/>

        <conditional name="clip_adapter">
            <param name="clip" type="select" label="Clip 3' Adapter Sequence" help="(-k)">

                    <validator type="regex" message="Adapter can ONLY contain a,c,g,t,u,n,A,C,G,T,U,N">^[ACGTUacgtu]+$</validator>
                </param>
            </when>
            <when value="false"/>
        </conditional>
        
        <param name="discard_short_reads" value="18" type="integer" optional="false" label="Discard reads shorter than this length" help="Set to 0 to keep all reads. (-l)">
            <validator type="in_range" min="0" message="Minimum value is 0"/>
        </param>
        
        <conditional name="operation">
            <param name="collapse_map" type="select" label="Collapse reads and/or Map" help="(-m) and/or (-p)">
                <option value="collapse_and_map">Collapse reads and Map</option>
                <option value="only_map">Map</option>
                <option value="only_collapse">Collapse</option>

            </filter>
        </data>
    </outputs>
    <tests>
        <test>
            <param name="reads" value="reads.fa"/>
            <param name="remove_non_canon" value="True"/>
            <param name="clip" value="true"/>
            <param name="adapter_seq" value="TCGTATGCCGTCTTCTGCTTGT"/>
            <param name="discard_short_reads" value="18"/>
            <param name="collapse_map" value="collapse_and_map"/>

                    <has_line_matching expression="^.*22\t1\t22\ttcaccgggagaaaaactggtgt\tchrII:11534525-11540624\t22\t3382\t3403.*$"/>
                    <has_line_matching expression="^.*25\t1\t25\ttcaccgggtggaaactagcagtggc\tchrII:11534525-11540624\t25\t3060\t3084.*$"/>
                </assert_contents>
            </output>
        </test>
    </tests>
    <help>
<![CDATA[
**What it does**

The MiRDeep2 Mapper module is designed as a tool to process deep sequencing reads and/or map them to the reference genome. 
The module works in sequence space, and can process or map data that is in sequence FASTA format. 
A number of the functions of the mapper module are implemented specifically with Solexa/Illumina data in mind.

**Input**

Default input is a file in FASTA format, seq.txt or qseq.txt format. More input can be given depending on the options used. 

**Output**

The output depends on the options used. Either a FASTA file with processed reads or an arf file with with mapped reads, or both, are output. 

Arf format:
Is a proprietary file format generated and processed by miRDeep2. It contains information of reads mapped to a reference genome. Each line in such a file contains 13 columns:

1. read identifier

4:dbbe92348c7a

<tool id="rbc_mirdeep2_mapper" name="MiRDeep2 Mapper" version="2.0.0.8.1">
    <description>process and map reads to a reference genome</description>
    <macros>
        <macro name="map_params">
            <conditional name="refGenomeSource">
                <param name="genomeSource" type="select" label="Will you select a reference genome from your history or use a built-in index?" help="Map to genome. (-p)">

        </macro>
    </macros>
    <requirements>
        <requirement type="package" version="2.0.0.8">mirdeep2</requirement>
    </requirements>
    <command detect_errors="aggressive">
<![CDATA[
        #if $operation.collapse_map == "collapse_and_map" or $operation.collapse_map == "only_map"
            #if $operation.refGenomeSource.genomeSource == "history"
                bowtie-build '$operation.refGenomeSource.ownFile' custom_bowtie_indices &&
            #end if
        #end if

        mapper.pl

        #if $input.type == "single":
            '$input.reads'

            #if $input.reads.extension.startswith("fasta")
                -c
            #else if $input.reads.extension.startswith("fastq")
                -e
                -h
            #end if
        #else:
            '$samples' -d

            #if $input.reads_list[0].reads.extension.startswith("fasta")
                -c
            #else if $input.reads_list[0].reads.extension.startswith("fastq")
                -e
                -h
            #end if
        #end if

        $remove_non_canon

        $convert_rna_dna

        #if $clip_adapter.clip == "true"
            -k $clip_adapter.adapter_seq
        #end if

        -l $discard_short_reads

        #if $operation.collapse_map == "collapse_and_map" or $operation.collapse_map == "only_collapse"
            -m -s '$output_reads_collapsed'
        #end if

        #if $operation.collapse_map == "collapse_and_map" or $operation.collapse_map == "only_map"
            -p

            #if $operation.refGenomeSource.genomeSource == "history"
                custom_bowtie_indices
            #else
                '$operation.refGenomeSource.index.fields.path'
            #end if
            $operation.map_mismatch
            -r $operation.map_threshold

            -t '$output_mapping'
        #end if

        -v -n
]]>
    </command>
    <configfiles>
        <configfile name="samples"><![CDATA[#if $input.type == "multiple":
#for $r in $input.reads_list:
$r.reads    $r.sample_name
#end for
#end if]]></configfile>
    </configfiles>
    <inputs>
        <conditional name="input">
            <param name="type" type="select" label="Pool multiple read sets">
                <option value="single" selected="true">No</option>
                <option value="multiple">Yes</option>
            </param>
            <when value="single">
                <param format="fastq,fasta" name="reads" type="data" label="Deep sequencing reads" help="Reads in fastq or FASTA format"/>
            </when>
            <when value="multiple">
                <repeat name="reads_list" title="Reads">
                    <param name="sample_name" value="" type="text" label="Sample name" help="Must be a 3 letters/digits code">
                        <validator type="expression" message="The sample name must be a 3 letters/digits code">len(value) == 3 and value.isalnum()</validator>
                    </param>
                    <param format="fastq,fasta" name="reads" type="data" optional="false" label="Deep sequencing reads" help="Reads in fastq or FASTA format"/>
                </repeat>
            </when>
        </conditional>
        <param name="remove_non_canon" type="boolean" truevalue="-j" falsevalue="" checked="false" label="Remove reads with non-standard nucleotides" help="Remove all entries that have a sequence that contains letters other than a,c,g,t,u,n,A,C,G,T,U,N. (-j)"/>
        <param name="convert_rna_dna" type="boolean" truevalue="-i" falsevalue="" checked="false" label="Convert RNA to DNA alphabet (to map against genome)" help="(-i)"/>

        <conditional name="clip_adapter">
            <param name="clip" type="select" label="Clip 3' Adapter Sequence" help="(-k)">

                    <validator type="regex" message="Adapter can ONLY contain a,c,g,t,u,n,A,C,G,T,U,N">^[ACGTUacgtu]+$</validator>
                </param>
            </when>
            <when value="false"/>
        </conditional>

        <param name="discard_short_reads" value="18" type="integer" optional="false" label="Discard reads shorter than this length" help="Set to 0 to keep all reads. (-l)">
            <validator type="in_range" min="0" message="Minimum value is 0"/>
        </param>

        <conditional name="operation">
            <param name="collapse_map" type="select" label="Collapse reads and/or Map" help="(-m) and/or (-p)">
                <option value="collapse_and_map">Collapse reads and Map</option>
                <option value="only_map">Map</option>
                <option value="only_collapse">Collapse</option>

            </filter>
        </data>
    </outputs>
    <tests>
        <test>
            <conditional name="input">
                <param name="type" value="single"/>
                <param name="reads" value="reads.fa"/>
            </conditional>
            <param name="remove_non_canon" value="True"/>
            <param name="clip" value="true"/>
            <param name="adapter_seq" value="TCGTATGCCGTCTTCTGCTTGT"/>
            <param name="discard_short_reads" value="18"/>
            <param name="collapse_map" value="collapse_and_map"/>

                    <has_line_matching expression="^.*22\t1\t22\ttcaccgggagaaaaactggtgt\tchrII:11534525-11540624\t22\t3382\t3403.*$"/>
                    <has_line_matching expression="^.*25\t1\t25\ttcaccgggtggaaactagcagtggc\tchrII:11534525-11540624\t25\t3060\t3084.*$"/>
                </assert_contents>
            </output>
        </test>
        <test>
            <conditional name="input">
                <param name="type" value="multiple"/>
                <repeat name="reads_list">
                    <param name="sample_name" value="sa1"/>
                    <param name="reads" value="reads_sample1.fa"/>
                </repeat>
                <repeat name="reads_list">
                    <param name="sample_name" value="sa2"/>
                    <param name="reads" value="reads_sample2.fa"/>
                </repeat>
            </conditional>
            <param name="remove_non_canon" value="True"/>
            <param name="clip" value="true"/>
            <param name="adapter_seq" value="TCGTATGCCGTCTTCTGCTTGT"/>
            <param name="discard_short_reads" value="18"/>
            <param name="collapse_map" value="collapse_and_map"/>
            <param name="genomeSource" value="history"/>
            <param name="ownFile" value="cel_cluster.fa"/>
            <output name="output_reads_collapsed">
                <assert_contents>
                    <has_text text=">sa1_220_x1"/>
                    <has_text text="TCACCGGGTGTACATCAGC"/>
                    <has_text text=">sa2_0_x250"/>
                    <has_text text="AATGACACTGGTTATCTTTTCCATCG"/>
                </assert_contents>
            </output>
            <output name="output_mapping">
                <assert_contents>
                    <has_line_matching expression="^.*22\t1\t22\ttcaccgggtggaaactagcagt\tchrII:11534525-11540624\t22\t3060\t3081.*$"/>
                    <has_line_matching expression="^.*21\t1\t21\ttcaccgggtggaaactagcag\tchrII:11534525-11540624\t21\t3060\t3080.*$"/>
                    <has_line_matching expression="^.*22\t1\t22\ttcaccgggtgtacatcagctaa\tchrII:11534525-11540624\t22\t3631\t3652.*$"/>
                </assert_contents>
            </output>
        </test>
    </tests>
    <help>
<![CDATA[
**What it does**

The MiRDeep2 Mapper module is designed as a tool to process deep sequencing reads and/or map them to the reference genome.
The module works in sequence space, and can process or map data that is in sequence FASTA format.
A number of the functions of the mapper module are implemented specifically with Solexa/Illumina data in mind.

**Input**

Default input is a file in FASTA format, seq.txt or qseq.txt format. More input can be given depending on the options used.

**Output**

The output depends on the options used. Either a FASTA file with processed reads or an arf file with with mapped reads, or both, are output.

Arf format:
Is a proprietary file format generated and processed by miRDeep2. It contains information of reads mapped to a reference genome. Each line in such a file contains 13 columns:

1. read identifier