annotate tools/clc_assembly_cell/clc_mapper.xml @ 0:0996169ac2e8 draft

Uploaded v0.0.2, previously only on the TestToolShed

<tool id="clc_mapper" name="CLC Mapper" version="0.0.2">
    <description>Maps reads giving a SAM/BAM file</description>
    <requirements>
        <requirement type="binary">clc_mapper</requirement>    
        <requirement type="binary">clc_cas_to_sam</requirement>
        <requirement type="binary">samtools</requirement>
        <requirement type="package" version="0.1.19">samtools</requirement>
    </requirements>
    <version_command>\${CLC_ASSEMBLY_CELL:-/mnt/apps/clcBio/clc-assembly-cell-4.1.0-linux_64/}clc_mapper | grep -i version</version_command>
    <command>echo Mapping reads with clc_mapper...
&amp;&amp; \${CLC_ASSEMBLY_CELL:-/mnt/apps/clcBio/clc-assembly-cell-4.1.0-linux_64/}clc_mapper
#for $ref in $references
#if str($ref.ref_type)=="circular"
-d -z "$ref.ref_file"
#else
-d "$ref.ref_file"
#end if
#end for
#for $rg in $read_group
##--------------------------------------
#if str($rg.segments.type) == "paired"
-p $rg.segments.placement $rg.segments.dist_mode $rg.segments.min_size $rg.segments.max_size -q -i "$rg.segments.filename1" "$rg.segments.filename2"
#end if
##--------------------------------------
#if str($rg.segments.type) == "interleaved"
-p $rg.segments.placement $rg.segments.dist_mode $rg.segments.min_size $rg.segments.max_size -q "$rg.segments.filename"
#end if
##--------------------------------------
#if str($rg.segments.type) == "none"
-p no -q
#for $f in $rg.segments.filenames
"$f"
#end for
#end if
##--------------------------------------
#end for
-o "temp_job.cas"
--cpus \${GALAXY_SLOTS:-4}
## TODO - filtering out the progress lines seems to mess up the multiple commands
## | grep -v "^Progress: "
##===========================================
## TODO - I've required all the input in Sanger FASTQ format (or FASTA) so can
## use the offset 33, rather then the CLCbio default of 64 which is only for
## obsolete Illumina FASTQ files. Really need this option per input file...
&amp;&amp; echo Converting CAS file to BAM with clc_cas_to_sam...
&amp;&amp; /mnt/apps/clcBio/clc-assembly-cell-4.1.0-linux_64/clc_cas_to_sam --cas "temp_job.cas" -o "temp_job.bam" --no-progress --qualityoffset 33
&amp;&amp; rm "temp_job.cas"
##===========================================
&amp;&amp; echo Sorting BAM file with samtools...
&amp;&amp; samtools sort "temp_job.bam" "temp_sorted"
&amp;&amp; mv "temp_sorted.bam" "$out_bam"
&amp;&amp; echo Indexing BAM file with samtools...
&amp;&amp; samtools index "$out_bam"</command>
    <stdio>
        <!-- Assume anything other than zero is an error -->
        <exit_code range="1:" />
        <exit_code range=":-1" />
    </stdio>
    <!-- Job splitting with merge via clc_join_mappings? -->
    <inputs>
        <!-- Support linear and circular references (-z) -->
        <repeat name="references" title="Reference Sequence" min="1">
            <param name="ref_file" type="data" format="fasta" required="true" label="Reference sequence(s) (FASTA)" />
            <param name="ref_type" type="select" label="Reference type">
                <option value="linear">Linear (e.g. most chromosomes)</option>
                <option value="circular">Circular (e.g. bacterial chromosomes, mitochondria)</option>
            </param>
        </repeat>
        <repeat name="read_group" title="Read Group" min="1">
            <conditional name="segments">
                <param name="type" type="select" label="Are these paired reads?">
                    <option value="paired">Paired reads (as two files)</option>
                    <option value="interleaved">Paired reads (as one interleaved file)</option>
                    <option value="none">Unpaired reads (single or orphan reads)</option>
                </param>
                <when value="paired">
                    <param name="placement" type="select" label="Pairing type (segment placing)">
                        <option value="fb">---&gt; &lt;--- (e.g. Sanger capillary or Solexa/Illumina paired-end library)</option>
                        <option value="bf">&lt;--- ---&gt; (e.g. Solexa/Illumina mate-pair library)</option>
                        <option value="ff">---&gt; ---&gt;</option>
                        <option value="bb">&lt;--- &lt;---</option>
                    </param>
                    <param name="dist_mode" type="select" label="How is the fragment distance measured?">
                        <option value="ss">Start to start (e.g. Sanger capillary or Solexa/Illumina libraries)</option>
                        <option value="se">Start to end</option>
                        <option value="es">End to start</option>
                        <option value="ee">End to end</option>
                    </param>
                    <!-- TODO - min/max validation done via the <code> tag? -->
                    <param name="min_size" type="integer" optional="false" min="0" value=""
                           label="Minimum size of 'good' DNA templates in the library preparation" />
                    <param name="max_size" type="integer" optional="false" min="0" value=""
                           label="Maximum size of 'good' DNA templates in the library preparation" />
                    <param name="filename1" type="data" format="fastqsanger,fasta" required="true" label="Read file one"
                           help="FASTA or Sanger FASTQ accepted." />
                    <param name="filename2" type="data" format="fastqsanger,fasta" required="true" label="Read file two"
                           help="FASTA or Sanger FASTQ accepted." />
                </when>
                <when value="interleaved">
                    <param name="placement" type="select" label="Pairing type (segment placing)">
                        <option value="fb">---&gt; &lt;--- (e.g. Sanger capillary or Solexa/Illumina paired-end library)</option>
                        <option value="bf">&lt;--- ---&gt; (e.g. Solexa/Illumina mate-pair library)</option>
                        <option value="ff">---&gt; ---&gt;</option>
                        <option value="bb">&lt;-- &lt;--</option>
                    </param>
                    <param name="dist_mode" type="select" label="How is the fragment distance measured?">
                        <option value="ss">Start to start (e.g. Sanger capillary or Solexa/Illumina libraries)</option>
                        <option value="se">Start to end</option>
                        <option value="es">End to start</option>
                        <option value="ee">End to end</option>
                    </param>
                    <!-- TODO - min/max validation done via the <code> tag? -->
                    <param name="min_size" type="integer" optional="false" min="0" value=""
                           label="Minimum size of 'good' DNA templates in the library preparation" />
                    <param name="max_size" type="integer" optional="false" min="0" value=""
                           label="Maximum size of 'good' DNA templates in the library preparation" />
                    <param name="filename" type="data" format="fastqsanger,fasta" required="true" label="Interleaved read file"
                           help="FASTA or Sanger FASTQ accepted."/>
                </when>
                <when value="none">
                    <param name="filenames" type="data" format="fastqsanger,fasta" multiple="true" required="true" label="Read file(s)"
                           help="Multiple files allowed, for example several files of orphan reads. FASTA or Sanger FASTQ accepted." />
                </when>
            </conditional>
        </repeat>
        <!-- Length fraction (-l), default 0.5 -->
        <!-- Similarity (-s), default 0.8 -->
        <!-- Option for unmapped reads via clc_unmapped_reads ? -->
    </inputs>
    <outputs>
        <data name="out_bam" format="bam" label="CLCbio mapping (BAM)" />
    </outputs>
    <tests>
        <!-- CLC's SAM header @PG and @RG lines include filenames so will change -->
        <test>
            <param name="ref_file" value="NC_010642.fna" ftype="fasta" />
            <param name="ref_type" value="circular" />
            <param name="read_group_0|segments|type" value="interleaved" />
            <param name="read_group_0|segments|placement" value="fb" />
            <param name="read_group_0|segments|dist_mode" value="ss" />
            <param name="read_group_0|segments|min_size" value="1" />
            <param name="read_group_0|segments|max_size" value="1000" />
            <param name="read_group_0|segments|dist_mode" value="ss" />
            <param name="read_group_0|segments|filename" value="SRR639755_mito_pairs.fastq.gz" ftype="fastqsanger" />
            <output name="out_fasta" file="SRR639755_mito_pairs_vs_NC_010642_clc.bam" ftype="bam" lines_diff="4"/>
        </test>
    </tests>
    <help>

**What it does**

Runs the CLCbio tool ``clc_mapper`` which produces a proprietary binary
CAS format file, which is immediately processed using ``clc_cas_to_sam``
to generate a self-contained standard BAM file, which is then sorted
and indexed using ``samtools``.


**Citation**

If you use this Galaxy tool in work leading to a scientific publication please
cite this wrapper as:

Peter J.A. Cock (2013), Galaxy wrapper for the CLC Assembly Cell suite from CLCbio
http://toolshed.g2.bx.psu.edu/view/peterjc/clc_assembly_cell

This wrapper is available to install into other Galaxy Instances via the Galaxy
Tool Shed at http://toolshed.g2.bx.psu.edu/view/peterjc/clc_assembly_cell
    </help>
</tool>