annotate tools/mira4_0/mira4_de_novo.xml @ 2:4eb32a3d67d1 draft

v0.0.8 - renamed folder, added note about mirabait

<tool id="mira_4_0_de_novo" name="MIRA v4.0 de novo assember" version="0.0.8">
    <description>Takes Sanger, Roche 454, Solexa/Illumina, Ion Torrent and PacBio reads</description>
    <requirements>
        <requirement type="binary">mira</requirement>
        <requirement type="binary">miraconvert</requirement>
        <requirement type="package" version="4.0.2">MIRA</requirement>
        <requirement type="binary">samtools</requirement>
        <requirement type="package" version="0.1.19">samtools</requirement>
    </requirements>
    <code file="mira4_validator.py" />
    <stdio>
        <!-- Assume anything other than zero is an error -->
        <exit_code range="1:" />
        <exit_code range=":-1" />
    </stdio>
    <version_command interpreter="python">mira4.py --version</version_command>
    <command interpreter="python">mira4.py
--manifest "$manifest"
#if str($maf_wanted)=="true":
--maf "$out_maf"
#end if
#if str($bam_wanted)=="true":
--bam "$out_bam"
#end if
--fasta "$out_fasta"
--log "$out_log"
    </command>
    <configfiles>
        <configfile name="manifest">
project = MIRA
job = denovo,${job_type},${job_quality}
parameters = -NW:cmrnl=no -DI:trt=/tmp -OUT:orc=no
## -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.
##
## -DI:trt is short for -DIRECTORY:tmp_redirected_to and should
## point to a local hard drive (not something like NFS on network).
## We replace /tmp with an environment variable via mira4.py
##
## -OUT:orc=no is short for -OUTPUT:output_result_caf=no 
## which turns off an output file we don't want anyway.

#for $rg in $read_group

##This bar goes into the manifest as a comment line
#------------------------------------------------------------------------------

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 $f.ext.startswith("fastq")
##MIRA doesn't like fastqsanger etc, just plain old fastq:
data = fastq::$f
#elif $f.ext == "mira"
##We're calling *.maf the "mira" format in Galaxy (name space collision)
data = maf::$f
#else
##MIRA is happy with fasta as name,
data = ${f.ext}::$f
#end if
#end for
#end for
        </configfile>
    </configfiles>
    <inputs>
        <param name="job_type" type="select" label="Assembly type">
            <option value="genome">Genome</option>
            <option value="est">EST (transcriptome)</option>
        </param>
        <param name="job_quality" type="select" label="Assembly quality grade">
            <option value="accurate">Accurate</option>
            <option value="draft">Draft</option>
        </param>
        <repeat name="read_group" title="Read Group" min="1">
            <param name="technology" type="select" label="Read technology">
                <option value="solexa">Solexa/Illumina</option>
                <option value="sanger">Sanger cappillary sequencing</option>
                <option value="454">Roche 454</option>
                <option value="iontor">Ion Torrent</option>
                <option value="pcbiolq">PacBio low quality (raw)</option>
                <option value="pcbiohq">PacBio high quality (corrected)</option>
                <option value="text">Synthetic reads (database entries, consensus sequences, artifical reads, etc)</option>
                <!-- TODO reference/backbone as an entry here? -->
            </param>
            <conditional name="segments">
                <param name="type" type="select" label="Are these paired reads?">
                    <option value="paired">Paired reads</option>
                    <option value="none">Single reads or not relevant (e.g. primer walking with Sanger capillary sequencing)</option>
                </param>
                <when value="paired">
                    <param name="placement" type="select" label="Pairing type (segment placing)">
                        <option value="FR">---&gt; &lt;--- (e.g. Sanger capillary or Solexa/Illumina paired-end library)</option>
                        <option value="RF">&lt;--- ---&gt; (e.g. Solexa/Illumina mate-pair library)</option>
                        <option value="SB">2---&gt; 1---&gt; (e.g. Roche 454 paired-end libraries or IonTorrent long-mate; see note)</option>
                    </param>
                    <!-- min/max validation is done via the <code> tag -->
                    <param name="min_size" type="integer" optional="true" min="0" value=""
                           label="Minimum size of 'good' DNA templates in the library preparation"
                           help="Optional, but if used you must also supply a maximum value." />
                    <param name="max_size" type="integer" optional="true" min="0" value=""
                           label="Maximum size of 'good' DNA templates in the library preparation"
                           help="Optional, but if used you must also supply a minimum value." />
                    <param name="naming" type="select" label="Pair naming convention">
                        <option value="solexa">Solexa/Illumina (using '/1' and '/2' suffixes, or later Illumina colon system)</option>
                        <option value="FR">Forward/Reverse scheme (using '.f*' and '.r*' suffixes)</option>
                        <option value="tigr">TIGR scheme (using 'TF*' and 'TR*' suffixes)</option>
                        <option value="sanger">Sanger scheme (see notes)</option>
                        <option value="stlouis">St. Louis scheme (see notes)</option>
                    </param>
                </when>
                <when value="none" /><!-- no further questions -->
            </conditional>
            <param name="filenames" type="data" format="fastq,mira" multiple="true" required="true" label="Read file(s)"
                  help="Multiple files allowed, for example paired reads can be given as two files (MIRA looks at read names to identify pairs)." />
        </repeat>
        <param name="maf_wanted" type="boolean" label="Output assembly in MIRA's own format?" checked="False" />
        <param name="bam_wanted" type="boolean" label="Convert assembly into BAM format?" checked="True" />
    </inputs>
    <outputs>
        <data name="out_fasta" format="fasta" label="MIRA de novo contigs (FASTA)" />
        <data name="out_bam" format="bam" label="MIRA de novo assembly (BAM)">
            <filter>bam_wanted is True</filter>
        </data>
        <data name="out_maf" format="mira" label="MIRA de novo assembly">
            <filter>maf_wanted is True</filter>
        </data>
        <!-- TODO?                                                                                                                          
        <data name="out_contigstats" format="tabular" label="MIRA contig stats" />                                                          
        -->
        <data name="out_log" format="txt" label="MIRA de novo log" />
    </outputs>
    <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/demo4 example
             Note we're using just one repeat group,
             but several parameters with the repeat
        -->
        <test>
            <param name="job_type" value="genome" />
            <param name="job_quality" value="accurate" />
            <param name="technology" value="sanger" />
            <param name="type" value="none" />
            <param name="filenames" value="U13small_m.fastq" ftype="fastqsanger" />
            <param name="maf_wanted" value="true"/>
            <param name="bam_wanted" value="true"/>
            <output name="out_fasta" file="U13small_m.mira4_de_novo.fasta" ftype="fasta" />
            <output name="out_bam" file="empty_file.dat" compare="contains" />
            <!-- TODO: Suggest startswith as a compare method? -->
            <output name="out_maf" file="header.mira" compare="contains" />
            <output name="out_log" file="empty_file.dat" compare="contains" />
        </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" />
            <param name="maf_wanted" value="false"/>
            <param name="bam_wanted" value="false"/>
            <output name="out_fasta" file="ecoli.mira4_de_novo.fasta" ftype="fasta" />
            <output name="out_log" file="empty_file.dat" compare="contains" />
        </test>
    </tests>
    <help>

**What it does**

Runs MIRA v4.0 in de novo mode, collects the output, generates a sorted BAM
file, and then throws away all the temporary files.

MIRA is an open source assembly tool capable of handling sequence data from
a range of platforms (Sanger capillary, Solexa/Illumina, Roche 454, Ion Torrent
and also PacBio).

It is particularly suited to small genomes such as bacteria.


**Notes on paired reads**

.. class:: warningmark

MIRA uses read naming conventions to identify paired read partners
(and does not care about their order in the input files). In most cases,
the Solexa/Illumina setting is fine. For Sanger capillary sequencing,
you may need to rename your reads to match one of the standard conventions
supported by MIRA. For Roche 454 or Ion Torrent the appropriate settings
depend on how the FASTQ file was produced:

* If using Roche's ``sffinfo`` or older versions of ``sff_extract``
  to convert SFF files to FASTQ, your reads will probably have the
  ``---&gt; &lt;---`` orientation and use the ``.f`` and ``.r``
  suffixes (FR naming).

* If using a recent version of ``sff_extract``, then the ``/1`` and ``/2``
  suffixes are used (Solexa/Illumina style naming) and the original
  ``2---&gt; 1---&gt;`` orientation is preserved.

The reason for this is the raw data for Roche 454 and Ion Torrent paired-end
libraries sequences a circularised fragment such that the raw data begins
with the end of the fragment, a linker, then the start of the fragment.
This means both the start and end are sequenced from the same strand, and
have the orientation ``2---&gt; 1---&gt;``. However, in order to use the data
with traditional tools expecting Sanger capillary style ``---&gt; &lt;---``
orientation it was common to reverse complement one of the pair to mimic this.


**Citation**

If you use this Galaxy tool in work leading to a scientific publication please
cite the following papers:

Peter J.A. Cock, Björn A. Grüning, Konrad Paszkiewicz and Leighton Pritchard (2013).
Galaxy tools and workflows for sequence analysis with applications
in molecular plant pathology. PeerJ 1:e167
http://dx.doi.org/10.7717/peerj.167

Bastien Chevreux, Thomas Wetter and Sándor Suhai (1999).
Genome Sequence Assembly Using Trace Signals and Additional Sequence Information.
Computer Science and Biology: Proceedings of the German Conference on Bioinformatics (GCB) 99, pp. 45-56.
http://www.bioinfo.de/isb/gcb99/talks/chevreux/main.html

This wrapper is available to install into other Galaxy Instances via the Galaxy
Tool Shed at http://toolshed.g2.bx.psu.edu/view/peterjc/mira4_assembler
    </help>
    <citations>
        <citation type="doi">10.7717/peerj.167</citation>
        <citation type="bibtex">@ARTICLE{Chevreux1999-mira3,
        author = {B. Chevreux and T. Wetter and S. Suhai},
        year = {1999},
        title = {Genome Sequence Assembly Using Trace Signals and Additional Sequence Information},
        journal = {Computer Science and Biology: Proceedings of the German Conference on Bioinformatics (GCB)}
        volume = {99},
        pages = {45-56},
        url = {http://www.bioinfo.de/isb/gcb99/talks/chevreux/main.html}
        }</citation>
    </citations>
</tool>