diff modify_snp_table.xml @ 0:2c498d40ecde

Uploaded

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/modify_snp_table.xml	Mon Apr 09 12:03:06 2012 -0400
@@ -0,0 +1,67 @@
+<tool id="gd_modify_snp_table" name="Modify" version="1.0.0">
+  <description>a SNP table</description>
+
+  <command interpreter="python">
+    modify_snp_table.py "$input" "$p1_input" "$output"
+    #if $limit_coverage.choice == "0"
+        "-1" "-1" "-1" "-1"
+    #else
+        "${limit_coverage.lo_coverage}" "${limit_coverage.hi_coverage}" "${limit_coverage.low_ind_cov}" "${limit_coverage.lo_quality}"
+    #end if
+    #for $individual, $individual_col in zip($input.dataset.metadata.individual_names, $input.dataset.metadata.individual_columns)
+        #set $arg = '%s:%s' % ($individual_col, $individual)
+        "$arg"
+    #end for
+  </command>
+
+  <inputs>
+    <param name="input" type="data" format="wsf" label="SNP table" />
+    <param name="p1_input" type="data" format="ind" label="Population individuals" />
+    <conditional name="limit_coverage">
+      <param name="choice" type="select" format="integer" label="Option">
+        <option value="0" selected="true">add columns to the SNP table</option>
+        <option value="1">discard some SNPs</option>
+      </param>
+      <when value="0" />
+      <when value="1">
+        <param name="lo_coverage" type="integer" min="0" value="0" label="Lower bound on total coverage" />
+        <param name="hi_coverage" type="integer" min="0" value="1000" label="Upper bound on total coverage" />
+        <param name="low_ind_cov" type="integer" min="0" value="0" label="Lower bound on individual coverage" />
+        <param name="lo_quality" type="integer" min="0" value="0" label="Lower bound on individual quality values" />
+      </when>
+    </conditional>
+  </inputs>
+
+  <outputs>
+    <data name="output" format="wsf" metadata_source="input" />
+  </outputs>
+
+  <tests>
+    <test>
+      <param name="input" value="test_in/sample.wsf" ftype="wsf" />
+      <param name="p1_input" value="test_in/a.ind" ftype="ind" />
+      <param name="choice" value="1" />
+      <param name="lo_coverage" value="0" />
+      <param name="hi_coverage" value="1000" />
+      <param name="low_ind_cov" value="3" />
+      <param name="lo_quality" value="30" />
+      <output name="output" file="test_out/modify_snp_table/modify.wsf" />
+    </test>
+  </tests>
+
+  <help>
+**What it does**
+
+The user specifies that some of the individuals in the selected SNP table are
+form a "population" that has been previously defined using the Galaxy tool to
+select individuals from a SNP table.  One option is for the program to append
+four columns to the table, giving the total counts for the two alleles, the
+"genotype" for the population and the maximum quality value, taken over all
+individuals in the population.  If all defined genotypes in the population
+are 2 (agree with the reference), the population's genotype is 2; similarly
+for 0; otherwise the genotype is 1 (unless all individuals have undefined
+genotype, in which case it is -1.  The other option is to remove rows from
+the table for which the total coverage for the population is either too low
+or too high, and/or if the individual coverage or quality value is too low.
+  </help>
+</tool>