annotate wrapper.xml @ 0:231e4c669675 draft

Initial commit - v0.10.3 git commit deeded0

<tool id="viga" name="viga" version="0.10.3">
    <description>de novo VIral Genome Annotator</description>
    <requirements>
        <container type="docker">vimalkvn/viga</container>
    </requirements>
    <stdio>
        <exit_code range="1:" />
    </stdio>
    <command><![CDATA[
python $__tool_directory__/VIGA.py
--input $input
--rfamdb $rfamdb.fields.path
--modifiers $modifiers
--threads \${GALAXY_SLOTS:-5}
--typedata $typedata_select
--gcode $gcode_select
--out "default"
--minrepeat $minrepeat
--maxrepeat $maxrepeat
--minspacer $minspacer
--maxspacer $maxspacer

#if $readlength
    --readlength $readlength
#end if
#if $windowsize
    --windowsize $windowsize
#end if
#if $slidingsize
    --slidingsize $slidingsize
#end if
#if $locus
    --locus $locus
#end if
#if $gffprint
    --gff
#end if
#if str($blastevalue)
    --blastevalue $blastevalue
#end if
#if str($mincontigsize)
    --mincontigsize $mincontigsize
#end if
#if str($idthr)
    --idthr $idthr
#end if
#if str($coverthr)
    --coverthr $coverthr
#end if
#if str($diffid)
    --diffid $diffid
#end if
#if $blastexh
    --blastexh
#end if
#if str($homologysearch.use_diamond) == "yes":
   --noblast
   --diamonddb $homologysearch.diamonddb.fields.path
#else
   --blastdb $homologysearch.blastdb.fields.path
#end if
#if str($hmmsearch.use_phmmer) == "yes":
  --hmmdb $hmmsearch.hmmdb.fields.path
  --hmmerevalue $hmmsearch.hmmerevalue
#else
  --nohmmer
#end if
]]></command>
    <inputs>
        <param name="input" type="data" format="fasta" label="(Viral) contigs to annotate" help="Input file as a FASTA file. It can contain multiple sequences (e.g. metagenomic contigs)" />
        <param name="rfamdb" type="select" label="RFAM database used for ribosomal RNA prediction">
            <options from_data_table="viga_rfamdb">
                <filter type="sort_by" column="2"/>
                <validator type="no_options" message="No indexes are available for the selected input dataset"/>
            </options>
        </param>
        <param name="modifiers" type="data" format="txt" label="Metadata of the contigs" help="Modifiers per every FASTA header according to SeqIn (https://www.ncbi.nlm.nih.gov/Sequin/modifiers.html)" />
	<param name="typedata_select" type="select" label="GenBank division (--typedata)">
	    <option value="CON" selected="true">Contig</option>
	    <option value="PHG">Phages</option>
	    <option value="VRL">Eukaryotic/Archaea virus</option>
	    <option value="BCT">Prokaryotic chromosome</option>
	</param>
	<param name="gcode_select" type="select" label="Number of GenBank translation table (--gcode)">
	  <option value="1">Standard genetic code [Eukaryotic]</option>
	  <option value="2">Vertebrate mitochondrial code</option>
	  <option value="3">Yeast mitochondrial code</option>
	  <option value="4">Mycoplasma/Spiroplasma and Protozoan/mold/coelenterate mitochondrial code</option>
	  <option value="5">Invertebrate mitochondrial code</option>
	  <option value="6">Ciliate, dasycladacean and hexamita nuclear code</option>
	  <option value="9">Echinoderm/flatworm mitochondrial code</option>
	  <option value="10">Euplotid nuclear code</option>
	  <option value="11" selected="true">Bacteria/Archaea/Phages/Plant plastid</option>
	  <option value="12">Alternative yeast nuclear code</option>
	  <option value="13">Ascidian mitochondrial code</option>
	  <option value="14">Alternative flatworm mitochondrial code</option>
	  <option value="16">Chlorophycean mitochondrial code</option>
	  <option value="21">Trematode mitochondrial code</option>
	  <option value="22">Scedenesmus obliquus mitochondrial code</option>
	  <option value="23">Thraustochytrium mitochondrial code</option>
	  <option value="24">Pterobranquia mitochondrial code</option>
	  <option value="25">Gracilibacteria and Candidate division SR1</option>
	  <option value="26">Pachysolen tannophilus nuclear code</option>
	  <option value="27">Karyorelict nuclear code</option>
	  <option value="28">Condylostoma nuclear code</option>
	  <option value="29">Mesodinium nuclear code</option>
	  <option value="30">Peritrich nuclear code</option>
	  <option value="31">Blastocrithidia nuclear code</option>
	</param>
        <param name="readlength" type="integer" value="101" min="1" optional="true" label="Read length (--readlength)" help="Read length for the circularity prediction"/>
        <param name="windowsize" type="integer" value="100" min="2" optional="true" label="Window size (--windowsize)" help="Window size used to determine the origin of replication in circular contigs according to the cumulative GC skew"/>
        <param name="slidingsize" type="integer" value="10" min="1" optional="true" label="sliding window size (--slidingsize)" help="Sliding window size for the origin of replication prediction"/>
        <param name="locus" type="text" value="LOC" optional="true" label="Locus tag prefix (--locustag)" help="Name of the sequences. If the input is a multifasta file, please put a general name"/>
        <param name="gffprint" type="boolean" checked="false" optional="true" label="Print the output also as GFF3 file" help="Printing the output as GFF3 file (Default: FALSE)" />
        <param name="blastevalue" type="float" value="1e-5" min="0" optional="true" label="Blast e-value threshold" />

	<conditional name="hmmsearch">
	  <param name="use_phmmer" type="select" label="Use PHMMER to predict protein function using HMM">
	    <option value="yes" selected="True">Yes (slow, more accurate)</option>
	    <option value="no">No (fast, less accurate)</option>
	  </param>
	  <when value="yes">
	    <param name="hmmdb" type="select" label="PHMMER database to use for protein function prediction">
	      <options from_data_table="viga_hmmdb">
		<filter type="sort_by" column="2"/>
		<validator type="no_options" message="No indexes are available for the selected input dataset"/>
	      </options>
	    </param>
	    <param name="hmmerevalue" type="float" value="0.001" label="PHMMER e-value threshold"/>
		</when>
	</conditional>
	<conditional name="homologysearch">
 	  <param name="use_diamond" type="select" label="Use DIAMOND instead of BLAST to predict protein function">
	    <option value="yes" selected="True">Yes (fast, less accurate)</option>
	    <option value="no">No (slow, more accurate)</option>
	  </param>
	  <when value="yes">
	    <param name="diamonddb" type="select" label="DIAMOND database" help="DIAMOND Protein Database that will be used for the protein function prediction">
	      <options from_data_table="viga_diamonddb">
		<filter type="sort_by" column="2"/>
		<validator type="no_options" message="No indexes are available for the selected input dataset"/>
	      </options>
	    </param>
 	  </when>
	  <when value="no">
            <param name="blastdb" type="select" label="BLAST Database" help="BLAST Protein Database that will be used for the protein function prediction">
              <options from_data_table="viga_blastdb">
                <filter type="sort_by" column="2"/>
                <validator type="no_options" message="No indexes are available for the selected input dataset"/>
              </options>
            </param>
	  </when>
	</conditional>
	<param name="mincontigsize" type="integer" value="200" min="1" optional="true" label="Minimum contig length to be considered in the output" />
        <param name="idthr" type="float" value="50.0" min="0.01" max="100.00" optional="true" label="ID threshold" />
        <param name="coverthr" type="float" value="50.0" min="0.01" max="100.00" optional="true" label="Coverage threshold" />
        <param name="diffid" type="float" value="5.00" min="0.01" max="100.00" optional="true" label="Max allowed difference between the ID percentages of BLAST and HHSEARCH" />

        <param name="minrepeat" type="integer" value="16" min="1" optional="true" label="Minimum repeat length for CRISPR detection (--minrepeat)"/>
        <param name="maxrepeat" type="integer" value="64" min="1" optional="true" label="Maximum repeat length for CRISPR detection (--maxrepeat)"/>
        <param name="minspacer" type="integer" value="8" min="1" optional="true" label="Minimum spacer length for CRISPR detection (--minspacer)"/>
        <param name="maxspacer" type="integer" value="64" min="1" optional="true" label="Maximum spacer length for CRISPR detection (--maxspacer)"/>	
	
        <param name="blastexh" type="boolean" checked="false" optional="true" label="Use exhaustive BLAST (--blastexh)" help="Use of exhaustive BLAST to predict the proteins by homology according to Fozo et al. (2010) Nucleic Acids Res (Default=FALSE)" />
    </inputs>
    <outputs>
        <data name="default_csv" format="csv" label="${tool.name} on ${on_string}: csv" from_work_dir="default.csv" />
        <data name="default_gff" format="gff" label="${tool.name} on ${on_string}: gff" from_work_dir="default.gff">
            <filter>gffprint</filter>
        </data>
        <data name="default_gbk" format="txt" label="${tool.name} on ${on_string}: gbk" from_work_dir="default.gbk" />
        <data name="default_fasta" format="fasta" label="${tool.name} on ${on_string}: fasta" from_work_dir="default.fasta" />
        <data name="default_tbl" format="txt" label="${tool.name} on ${on_string}: tbl" from_work_dir="default.tbl" />
    </outputs>
    <tests>
        <test>
            <param name="input" ftype="fasta" value="rubella.fasta" />
            <param name="outputs" value="csv,gbk,fasta,tbl" />
            <output name="default_csv" file="default.csv" />
            <output name="default_gbk" file="default.gbk" />
            <output name="default_fasta" file="default.fasta" />
            <output name="default_tbl" file="default.tbl" />
        </test>
        <test>
            <param name="input" ftype="fasta" value="mu.fasta" />
            <param name="outputs" value="csv,gbk,fasta,tbl" />
            <output name="default_csv" file="default.csv" />
            <output name="default_gbk" file="default.gbk" />
            <output name="default_fasta" file="default.fasta" />
            <output name="default_tbl" file="default.tbl" />
        </test>
    </tests>
    <help><![CDATA[
**About VIGA**

VIGA_ is a script written in Python 2.7 that annotates viral
genomes automatically (using a de novo algorithm) and predict the
function of their proteins using BLAST and HMMER.

----

**About this Galaxy wrapper**

**Requirements**

`Docker <https://www.docker.com>`_ should first be installed and working on the
server where this Galaxy instance is setup. The user running Galaxy should be
part of the **docker** user group.

#. Download or clone the VIGA_ Github repository (as a submodule)
   in to the ``tools`` directory.

**Configuration**

**Update database paths in .loc files**

Edit the following files in the **tool-data** directory and add paths to
corresponding databases:

* viga_blastdb.loc
* viga_diamonddb.loc
* viga_rfamdb.loc
* viga_hmmdb.loc

**Create or update the Galaxy job configuration file**

If the file **config/job_conf.xml** does not exist, create it by copying the
template **config/job_conf.xml.sample_basic** in the Galaxy directory. Then
add a Docker destination for viga. Change ``/data/databases`` under
``docker_volumes`` to the location where your databases are stored. Here is
an example::

	<?xml version="1.0"?>
	<!-- A sample job config that explicitly configures job running the way it is configured by default (if there is no explicit config). -->
	<job_conf>
	    <plugins>
		<plugin id="local" type="runner" load="galaxy.jobs.runners.local:LocalJobRunner" workers="4"/>
	    </plugins>
	    <handlers>
		<handler id="main"/>
	    </handlers>
	    <destinations default="local">
		<destination id="local" runner="local"/>
		<destination id="docker" runner="local">
			<param id="docker_enabled">true</param>
			<param id="docker_sudo">false</param>
			<param id="docker_auto_rm">true</param>
			<param id="docker_volumes">$defaults,/data/databases:ro</param>
		</destination>
	    </destinations>
	    <tools>
	      <tool id="viga" destination="docker"/>
	    </tools>
	</job_conf>


**Restart Galaxy**. The tool will now be ready to use.
   
----

**Output files**

VIGA creates the following output files:

* tbl - Table file with all protein information.
* gbk - GenBank format file with annotations.
* fasta - FASTA format file for GenBank submission
* csv - Table file for GenBank submission.
* gff - GFF3 format file (if option is selected)

----

**License and citation**

VIGA_ and this Galaxy wrapper - `GPLv3 <https://www.gnu.org/copyleft/gpl.html>`_.


Galaxy

- Goecks, J, Nekrutenko, A, Taylor, J and The Galaxy Team. "Galaxy: a
  comprehensive approach for supporting accessible, reproducible, and
  transparent computational research in the life sciences." 
  Genome Biol. 2010 Aug 25;11(8):R86.

- Blankenberg D, Von Kuster G, Coraor N, Ananda G, Lazarus R, Mangan M,
  Nekrutenko A, Taylor J. "Galaxy: a web-based genome analysis tool for
  experimentalists". Current Protocols in Molecular Biology. 
  2010 Jan; Chapter 19:Unit 19.10.1-21.

- Giardine B, Riemer C, Hardison RC, Burhans R, Elnitski L, Shah P, Zhang Y,
  Blankenberg D, Albert I, Taylor J, Miller W, Kent WJ, Nekrutenko A. "Galaxy:
  a platform for interactive large-scale genome analysis." 
  Genome Research. 2005 Oct; 15(10):1451-5.

You can use this tool only if you agree to the license terms of: `VIGA`_.

.. _VIGA: https://github.com/EGTortuero/viga

]]></help>
<!--    <citations>
        <citation type="doi">NOT YET</citation>
    </citations>
-->
</tool>