view tools/rgenetics/rgfakePed.xml @ 1:cdcb0ce84a1b

author xuebing
date Fri, 09 Mar 2012 19:45:15 -0500
parents 9071e359b9a3
line wrap: on
line source

<tool id="rgfakePed1" name="Null genotypes" version="0.02">
  <description>for testing</description>
  <command interpreter="python"> --title '$title'
  -o '$out_file1' -p '$out_file1.files_path' -c '$ncases' -n '$ntotal'
  -s '$nsnp'  -w '$lowmaf' -v '$missingValue' -l '$outFormat'
  -d '$mafdist' -m '$missingRate' -M '$mendelRate' </command>

    <param name="title"
         type="text" value="Fake_test_geno_data"
         help="Name for outputs from this job"
         label="Descriptive short name"/>
    <param name="ntotal"
         type="integer" value = "200"
         help="N total: total number of subjects"
         label="Create this total N subjects"/>
    <param name="ncases" type="integer"
         help = "N cases: Independent subjects with status set to 2. Set 0 for family data (NSubj/3 trios)"
         label="Total N Cases (0=generate family data - trios)"/>
    <param name="nsnp"
         type="integer" value="1000"
         help="nsnp: total number of markers"
         label="Total N SNP"/>
    <param name="lowmaf" type="float"
         help = "Lower limit for MAF distribution"
         label="Lower MAF limit (default=1%)"/>
    <param name="mafdist"
         help="Choose a MAF distribution"
         label="SNP Minor Allele Frequency distribution">
           <option value="U" selected="true">Uniform</option>
           <option value="T">Triangular (more low frequency SNPs)</option>
    <param name="outFormat"
         help="Choose an output format"
         label="Output format file type - linkage ped or fbat ped">
           <option value="L" selected="true">Linkage format - separate .map file</option>
           <option value="F">fbat style - marker names in a header row</option>
    <param name="missingRate" type="float"
         help = "Fraction of genotypes to be randomly set missing"
         label="Missing genotype call fraction"/>
    <param name="mendelRate"
         type="float" value = "0.05"
         help="(family data) Fraction of apparently non-Mendelian transmission patterns"
         label="Mendel error transmission rate"/>

    <param name="missingValue" type="text" size="1"
         help = "Missing allele value"
         label="Missing value for an allele for the output ped file"/>


    <data format="lped" name="out_file1" label="${title}.lped"/>
    <param name='title' value='rgfakePedtest1' />
    <param name="ntotal" value="40" />
    <param name="ncases" value="20" />
    <param name="nsnp" value="10" />
    <param name="lowmaf" value="0" />
    <param name="mafdist" value="T" />
    <param name="outFormat" value="L" />
    <param name="missingRate" value="0" />
    <param name="mendelRate" value="0" />
    <param name="missingValue" value="0" />
    <output name='out_file1' file='rgtestouts/rgfakePed/rgfakePedtest1.lped' ftype='lped' compare="diff" lines_diff='5'>
    <extra_files type="file" name='RgeneticsData.ped' value="rgtestouts/rgfakePed/rgfakePedtest1.ped" compare="diff" lines_diff='80'/>
    <extra_files type="file" name='' value="rgtestouts/rgfakePed/" compare="diff" />
.. class:: infomark

This tool allows you to generate an arbitrary (sort of)
synthetic genotype file (no attempt at LD - the markers are independent)
with optional missingness, Mendel errors, minor allele frequency settings, family structure
These might be used for testing under
the null hypothesis of no association and are certainly useful for
scale testing.

Note that although it runs reasonably fast given it's a script, generating a large data set takes
a while. An hour or so should get you a reasonable (3GB) sized simulated null data set..

A better simulator can easily be swapped in with this tool interface.


.. class:: warningmark

This tool is very experimental

.. class:: infomark

**Attribution and Licensing**

Designed and written for the Rgenetics Galaxy tools
copyright Ross Lazarus 2007 (
Licensed under the terms of the _LGPL
 .. _LGPL: