comparison tools/mira4/mira4_de_novo.xml @ 13:7fcabeeca5df draft

Uploaded v0.0.2 preview 5, fixes for MIRA 4.0 (final), more verbose error if $MIRA4 path wrong

12:a6a56440567c

    </outputs>
    <configfiles>
        <configfile name="manifest">
project = MIRA
job = denovo,${job_type},${job_quality}
parameters = -GE:not=1 -NW:cmrnl -DI:trt=/tmp
## -GE:not is short for -GENERAL:number_of_threads and using one (1)
## can be useful for repeatability of assemblies and bug hunting.
##
## -NW:cmrnl is short for -NAG_AND_WARN:check_maxreadnamelength
## and without this MIRA aborts with read names over 40 characters
## due to limitations of some downstream tools.
##

readgroup
technology = ${rg.technology}
##Record the segment placement (if any)
#if str($rg.segments.type) == "paired"
segmentplacement = ${rg.segments.placement}
segmentnaming = ${rg.segments.naming}
#if str($rg.segments.min_size) != "" or str($rg.segments.max_size) != ""
##If our min/max validation failed I trust MIRA to give an error message...
templatesize = $rg.segments.min_size $rg.segments.max_size
#end if
#end if
#if str($rg.segments.type) == "none"
segmentplacement = ?
#end if
##MIRA will accept multiple filenames on one data line, or multiple data lines
#for $f in $rg.filenames
##Must now map Galaxy datatypes to MIRA file types...
#if $f.ext.startswith("fastq")
##MIRA doesn't like fastqsanger etc, just plain old fastq:

    </configfiles>
    <tests>
        <!-- Tiger mitochondria, selected paired end Illumina reads from SRR639755
             Note we're using just one repeat group, and only the filenames parameter
             within it, so this should work with current test framework limitations:
        <test>
            <param name="job_type" value="genome" />
            <param name="job_quality" value="accurate" />
            <param name="filenames" value="SRR639755_mito_pairs.fastq.gz" ftype="fastqsanger" />
            <output name="out_fasta" file="SRR639755_mito_pairs.mira4_de_novo.fasta" ftype="fasta" />

        </test>
        -->
	<!-- Simple assembly based on MIRA's minidemo/solexa1 example
             Note we're using just one repeat group,
             but two parameters within the repeat (filename, no pairing)
        <test>
            <param name="job_type" value="genome" />
            <param name="job_quality" value="accurate" />
            <param name="type" value="none" />
            <param name="filenames" value="ecoli.fastq" ftype="fastqsanger" />
            <output name="out_fasta" file="ecoli.mira4_de_novo.fasta" ftype="fasta" />
        </test>
        -->
    </tests>
    <help>

**What it does**

13:7fcabeeca5df

    </outputs>
    <configfiles>
        <configfile name="manifest">
project = MIRA
job = denovo,${job_type},${job_quality}
parameters = -NW:cmrnl=no -DI:trt=/tmp
## -GE:not is short for -GENERAL:number_of_threads and using one (1)
## can be useful for repeatability of assemblies and bug hunting.
## This is overriden by the command line -t switch which is easier
## to set from within Galaxy.
##
## -NW:cmrnl is short for -NAG_AND_WARN:check_maxreadnamelength
## and without this MIRA aborts with read names over 40 characters
## due to limitations of some downstream tools.
##

readgroup
technology = ${rg.technology}
##Record the segment placement (if any)
#if str($rg.segments.type) == "paired"
segment_placement = ${rg.segments.placement}
segment_naming = ${rg.segments.naming}
#if str($rg.segments.min_size) != "" or str($rg.segments.max_size) != ""
##If our min/max validation failed I trust MIRA to give an error message...
template_size = $rg.segments.min_size $rg.segments.max_size
#end if
#end if
##if str($rg.segments.type) == "none"
##MIRA4 manual says use segment_placement = unknown or ? for unpaired data
##but this stopped working in MIRA 4.0 RC5 and 4.0 (final). See:
##http://www.freelists.org/post/mira_talk/Unpaired-reads-and-segment-placement--or-unknown
##segment_placement = ?
##end if
##MIRA will accept multiple filenames on one data line, or multiple data lines
#for $f in $rg.filenames
##Must now map Galaxy datatypes to MIRA file types...
#if $f.ext.startswith("fastq")
##MIRA doesn't like fastqsanger etc, just plain old fastq:

    </configfiles>
    <tests>
        <!-- Tiger mitochondria, selected paired end Illumina reads from SRR639755
             Note we're using just one repeat group, and only the filenames parameter
             within it, so this should work with current test framework limitations:
             TODO: Revise example and/or -NW:cac=warn and -NW:acv=80 settings
             MIRA 4.0 complains as coverage is about x93 which is over 80 limit.
             Also MIRA 4.0 gives three contigs as output.
        <test>
            <param name="job_type" value="genome" />
            <param name="job_quality" value="accurate" />
            <param name="filenames" value="SRR639755_mito_pairs.fastq.gz" ftype="fastqsanger" />
            <output name="out_fasta" file="SRR639755_mito_pairs.mira4_de_novo.fasta" ftype="fasta" />

        </test>
        -->
	<!-- Simple assembly based on MIRA's minidemo/solexa1 example
             Note we're using just one repeat group,
             but two parameters within the repeat (filename, no pairing)
	     -->
        <test>
            <param name="job_type" value="genome" />
            <param name="job_quality" value="accurate" />
            <param name="type" value="none" />
            <param name="filenames" value="ecoli.fastq" ftype="fastqsanger" />
            <output name="out_fasta" file="ecoli.mira4_de_novo.fasta" ftype="fasta" />
            <output name="out_bam" file="empty_file.dat" compare="contains" />
            <output name="out_maf" file="empty_file.dat" compare="contains" />
            <output name="out_log" file="empty_file.dat" compare="contains" />
        </test>
    </tests>
    <help>

**What it does**