diff snp_analysis_conversion/master2gd_snp.xml @ 0:3871157bc013

Initial upload to toolshed.g2 via UI.
author cathy
date Tue, 28 May 2013 17:01:14 -0400
parents
children
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/snp_analysis_conversion/master2gd_snp.xml	Tue May 28 17:01:14 2013 -0400
@@ -0,0 +1,85 @@
+<tool id="master2gd_snp" name="MasterVar to gd_snp" version="1.1.0" hidden="false">
+  <description>: Convert from MasterVar to gd_snp format</description>
+  <command interpreter="perl">
+    #if $snptab.tab2 == "yes" 
+      #if $snptab.colsOnly.value == "addColsOnly" #master2gd_snp.pl $input1 -tab=$snptab.input2 -name=$indName -build=${input1.metadata.dbkey} -addColsOnly > $out_file1 
+      #else #master2gd_snp.pl $input1 -tab=$snptab.input2 -name=$indName -build=${input1.metadata.dbkey} > $out_file1
+      #end if
+    #else #master2gd_snp.pl $input1 -name=$indName -build=${input1.metadata.dbkey} > $out_file1
+    #end if
+  </command>
+  <inputs>
+    <param format="tabular" name="input1" type="data" label="Complete Genomics MasterVar dataset" />
+    <conditional name="snptab">
+      <param name="tab2" type="select" label="Append to gd_snp dataset in history">
+        <option value="yes">yes</option>
+        <option value="no" selected="true">no</option>
+      </param>
+      <when value="yes">
+      <param format="gd_snp" name="input2" type="data" label="gd_snp dataset" />
+      <param name="colsOnly" type="select" label="Skip new SNPs">
+        <option value="" selected="true">no</option>
+        <option value="addColsOnly">yes</option>
+      </param>
+      </when>
+      <when value="no"> <!-- do nothing -->
+      </when>
+    </conditional>
+    <param name="indName" type="text" size="20" label="Label for new individual/group" value="na" />
+  </inputs>
+  <outputs>
+  <data format="gd_snp" name="out_file1" />
+  </outputs>
+  <tests>
+    <test>
+      <param name='input1' value='masterVarTest.txt' ftype='tab' />
+      <param name='tab2' value='no' />
+      <param name='indName' value='na' />
+      <output name="output" file="master2snp_output.txt" />
+    </test>
+  </tests>
+
+  <help>
+
+**Dataset formats**
+
+The input dataset is in the MasterVar_ format provided by the Complete Genomics
+analysis process (Galaxy considers this to be tabular_, but it must have the
+columns specified for MasterVar).
+The output dataset is in gd_snp_ format.  (`Dataset missing?`_)
+
+.. _MasterVar: ./static/formatHelp.html#mastervar
+.. _tabular: ./static/formatHelp.html#tab
+.. _gd_snp: ./static/formatHelp.html#gd_snp
+.. _Dataset missing?: ./static/formatHelp.html
+
+-----
+
+**What it does**
+
+This converts a Complete Genomics MasterVar file to gd_snp format,
+so it can be used with the Genome Diversity tools.  It can either
+start a new dataset or append to an old one.  When appending, if any new SNPs
+appear only in the MasterVar file they can either be skipped or backfilled with
+"-1" (unknown) for previous individuals/groups in the gd_snp dataset.
+Positions homozygous for the reference allele are skipped.
+
+-----
+
+**Example**
+
+- input MasterVar file::
+
+   934     2       chr1    41980   41981   hom     snp     A       G       G       76      97                      dbsnp.86:rs806721       425     1       1       1       2       -170                            ERVL-E-int:ERVL:47.4    2       1.17    N
+   935     2       chr1    41981   42198   hom     ref     =       =       =                                                                                       -170                                            1.17    N
+   1102    2       chr1    53205   53206   het-ref snp     G       C       G       93      127                     dbsnp.100:rs2854676     477     7       30      0       37      -127                                    2       1.17    N
+   etc.
+
+- output::
+
+   chr1    41980   A       G       -1      0       1       0       76
+   chr1    53205   G       C       -1      30      7       1       93
+   etc.
+
+</help>
+</tool>