diff dividePgSnpAlleles.xml.bak @ 0:137ec95c8ca6

Uploaded tool tarball.

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/dividePgSnpAlleles.xml.bak	Tue Aug 20 09:39:35 2013 -0400
@@ -0,0 +1,76 @@
+<tool id="dividePgSnp" name="Separate pgSnp alleles" hidden="false">
+  <description>into columns</description>
+  <command interpreter="perl">
+    #if $refcol.ref == "yes" #dividePgSnpAlleles.pl -ref=$refcol.ref_column $input1 > $out_file1
+    #else #dividePgSnpAlleles.pl $input1 > $out_file1
+    #end if
+  </command>
+  <inputs>
+    <param format="interval" name="input1" type="data" label="pgSnp dataset" />
+    <conditional name="refcol">
+      <param name="ref" type="select" label="Dataset has a column with the reference allele:">
+        <option value="yes">yes</option>
+        <option value="no" selected="true">no</option>
+      </param>
+      <when value="yes">
+      <param name="ref_column" type="data_column" data_ref="input1" label="Column with reference allele" />
+      </when>
+      <when value="no"> <!-- do nothing -->
+      </when>
+    </conditional>
+  </inputs>
+  <outputs>
+  <data format="interval" name="out_file1" />
+  </outputs>
+  <tests>
+    <test>
+      <param name='input1' value='dividePgSnp_input.pgSnp' ftype='interval' />
+      <param name='ref' value='no' />
+      <output name="output" file="dividePgSnp_output.txt" />
+    </test>
+  </tests>
+
+  <help>
+**Dataset formats**
+
+The input dataset is of Galaxy datatype interval_ with the columns specified
+for pgSnp_.
+Any additional columns beyond the pgSnp defined columns will be appended to
+the output.
+The output dataset is in interval_ format.  (`Dataset missing?`_)
+
+.. _interval: ./static/formatHelp.html#interval
+.. _Dataset missing?: ./static/formatHelp.html
+.. _pgSnp: ./static/formatHelp.html#pgSnp
+
+**What it does**
+
+This separates the alleles from a pgSnp dataset into separate columns,
+as well as the frequencies and scores that go with the alleles.  It will skip
+any positions with more than 2 alleles.  If only a single allele is given then "N"
+will be used for the second, with a frequency and score of zero.  Or, if a 
+column with reference alleles is provided, 
+the value in that column will be used in place of the "N" for single alleles.
+
+-----
+
+**Examples**
+
+- input pgSnp file::
+
+   chr1    256     257     A/C     2       3,4     10,20
+   chr1    56100   56101   A       1       5       30
+   chr1    77052   77053   A/G     2       6,7     40,50
+   chr1    110904  110905  A       1       8       60
+   etc.
+
+- output::
+
+   chr1    256     257     A       3       10       C       4       20
+   chr1    56100   56101   A       5       30       N       0       0
+   chr1    77052   77053   A       6       40       G       7       50
+   chr1    110904  110905  A       8       60       N       0       0
+   etc.
+
+</help>
+</tool>