annotate tools/rgenetics/rgHaploView.xml @ 1:cdcb0ce84a1b

Uploaded

<tool id="rgHaploView1" name="LD plots:" version="0.3">

    <description>and comparisons with HapMap data</description>

    <command interpreter="python">
    rgHaploView.py "$ucsc_region" "$rslist" "$title" "$out_file1"
    "$lhistIn.extra_files_path" "$lhistIn.metadata.base_name"
    "$minmaf" "$maxdist" "$ldtype" "$hires" "$memsize" "$out_file1.files_path"
    "$infoTrack" "$tagr2" "$hmpanel" ${GALAXY_DATA_INDEX_DIR}/shared/jars/haploview.jar
    </command>

    <inputs>

       <param name="lhistIn" type="data" format="lped"
        label="Current history lPed format data"
        size="80" help="Linkage Ped format data from your current history" />

       <param name="ucsc_region" type="text" label="Optional subset region (blank=ALL. WARNING: doing this will fail if >1 chromosome in input data!)"
        size="80" optional="true"
        help="Region eg: chr9:119,506,000-119,518,000 Leave blank for all or to extract the rs list supplied below."/>

       <param name="rslist" type="text" area='true' size='5x20' label="rs list" optional="true"
       help="List of rs numbers to select - cut and paste or type, use space delimiters. Leave blank to extract region supplied above."  />

       <param name="title" type="text" size="80" label="Title for output files" optional="true"
        help="Descriptive title for new genotype/map files" value="LD Plots" />

    <param name="ldtype" type="select" label="Type of LD measure to estimate and plot"
        size="80" help="" >
        <option value="RSQ" selected="True">rsquared (default)</option>
        <option value="DEFAULT">D prime</option>
        <option value="DPALT">D prime alternative</option>
        <option value="GAB">Gabriel</option>
        <option value="GAM">4 Gamete test</option>
    </param>

   <param name="minmaf" type="float" label = "Minimum minor allele frequency to use" value="0.05"
    help="If &gt; 0.0, markers below this MAF will be ignored for calculations"/>

    <param name="maxdist" type="integer" label = "Maximum distance (kbp) between markers for LD estimate"
    value="200" help="If &lt; &gt; 0, only marker pairs at or below this distance will have LD calculated"/>

    <param name="hmpanel" type="select" multiple="true" label="Hapmap panels to compare"
        size="40" help="HapMap data LD plots will also be produced for each selected population panel" >
        <option value='CEU' selected="True">CEPH (European) (default)</option>
        <option value='YRI'>Yoruba (African)</option>
        <option value='CHB+JPT'>Chinese + Japanese</option>
        <option value="">(None - no comparison)</option>
    </param>
    <param name="tagr2" type="float" label = "rsquared threshold for tagging outputs" value="0.8"
    help="Tagging output will use this value as the minimum rsquared threshold"/>

    <param name="infoTrack" type="select" label="Add Hapmap information track to image"
    help="Refseq genes and snp density can be added to the plot if desired for orientation" >
    <option value="info">Add Information track (DISABLED! Awaiting bug fix from Haploview authors since reported in October 2009)</option>
    <option value="noinfo" selected="True">No Information track</option>
    </param>

    <param name="hires" type="select" label="High resolution plots"
    help="A high resolution plot file may be possible but only for small regions - not reliable &gt;100's of snps">
    <option value="hi">High resolution - only a few (hundreds of) markers</option>
    <option value="lo" selected="True">Low resolution - large number of markers</option>
    </param>

    <param name="memsize" type="select" label="System RAM to allocate"
        size="80" help="Very large files will need extra memory (java is a bit of a pig)" >
        <option value="1024">1GB</option>
        <option value="2048" selected="True">2GB (default)</option>
        <option value="4096">4GB</option>
        <option value="6144">6GB</option>
        <option value="8192">8GB</option>
    </param>

   </inputs>

   <outputs>
       <data format="html" name="out_file1" label="${title}.html" />
   </outputs>

<!-- python $TOOLPATH/$TOOL.py "" "rs2283802Xrs2267000Xrs16997606Xrs4820537Xrs3788347Xrs756632Xrs4820539Xrs2283804Xrs2267006Xrs4822363X" \
"$NPRE" $OUTPATH/${NPRE}.html "test" "" "$INPATH" "tinywga" 0.0 200000 "RSQ" "lo" "2048" "$OUTPATH" "hg18" "noinfo" "0.8" \
"['CEU','YRI','CHB+JPT']" $BINPATH/haploview.jar -->
<tests>
 <test>
  <param name='lhistIn' value='tinywga' ftype='lped' >
   <metadata name='base_name' value='tinywga' />
   <composite_data value='tinywga.ped' />
   <composite_data value='tinywga.map' />
   <edit_attributes type='name' value='tinywga' /> 
  </param>
 <param name='ucsc_region' value='' />
 <param name='title' value='rgHaploViewtest1' />
 <param name='rslist' value="rs2283802 rs2267000 rs16997606 rs4820537 rs3788347 rs756632Xrs4820539 rs2283804 rs2267006 rs4822363" />
 <param name='ldtype' value='RSQ' />
 <param name='minmaf' value='0.0' />
 <param name='maxdist' value='200000' />
 <param name='tagr2' value='0.8' />
 <param name='hmpanel' value="YRI" />
 <param name='infoTrack' value='noinfo' />
 <param name='hires' value='lo' />
 <param name='memsize' value='2048' />
 <output name='out_file1' file='rgtestouts/rgHaploView/rgHaploViewtest1.html' ftype='html' lines_diff="60">
    <extra_files type="file" name='alljoin.pdf' value="rgtestouts/rgHaploView/alljoin.pdf" compare="sim_size" delta="50000"/>
    <extra_files type="file" name='allnup.pdf' value="rgtestouts/rgHaploView/allnup.pdf" compare="sim_size" delta="50000" />
    <extra_files type="file" name='Log_rgHaploViewtest1.txt' value="rgtestouts/rgHaploView/Log_rgHaploViewtest1.txt" compare="diff" lines_diff="50"/>
    <extra_files type="file" name='rgHaploViewtest1.ped.TESTS' value="rgtestouts/rgHaploView/rgHaploViewtest1.ped.TESTS" compare="diff" 
            lines_diff="20"/>
    <extra_files type="file" name='rgHaploViewtest1.ped.TAGS' value="rgtestouts/rgHaploView/rgHaploViewtest1.ped.TAGS" compare="diff"
            lines_diff="20" />
 </output>
 </test>
</tests>

<help>

.. class:: infomark

**Note**

The input file must be in linkage ped format. A suitable file can be chosen from the system library,
or from the files already imported into your current history. Use either one of the selection boxes to
make your choice.

-----

**Syntax**

- **Library Linkage Ped** is a linkage format pedigree file chosen from the system file Library
- **History Linkage Ped** is a linkage format pedigree file chosen from your current Galaxy History
- **Region** is the genomic region cut and paste from a UCSC browser location window
- **Genome Build** is the version of the genome your markers are from - use hg18 for CAMP illumina data

-----

**Summary**

This tool is a special purpose tool to estimate and plot linkage disequilibrium estimated
from genotype data in linkage pedigree format (separate map file). All markers in the input file
are used as the default. To limit the calculations to a subset of the input data, supply
a specified genomic region in UCSC browser location format or a list of specific marker IDs.

Note that you can choose either a file of the correct type (linkage pedigree - lped) from
your current history **or** from the system library

This tool currently calls Haploview for estimation and plots. For full attribution, source code and documentation, see
http://www.broad.mit.edu/mpg/haploview/index.php

Copyright, Ross Lazarus, April 2008 for the Rgenetics project
Released under the LGPL. See http://www.gnu.org/licenses/lgpl.html for license terms.

</help>
</tool>