diff evaluate_population_numbers.xml @ 14:8ae67e9fb6ff

Uploaded Miller Lab Devshed version a51c894f5bed again [possible toolshed.g2 bug]

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/evaluate_population_numbers.xml	Fri Sep 28 11:35:56 2012 -0400
@@ -0,0 +1,83 @@
+<tool id="gd_evaluate_population_numbers" name="Population Complexity" version="1.0.0">
+  <description>: Evaluate possible numbers of ancestral populations</description>
+
+  <command interpreter="bash">
+    evaluate_population_numbers.bash "${input.extra_files_path}/admix.ped" "$output" "$max_populations"
+  </command>
+
+  <inputs>
+    <param name="input" type="data" format="gd_ped" label="Dataset" />
+    <param name="max_populations" type="integer" min="1" value="5" label="Maximum number of populations" />
+  </inputs>
+
+  <outputs>
+    <data name="output" format="txt" />
+  </outputs>
+
+  <!--
+  <tests>
+    <test>
+      <param name="input" value="fake" ftype="gd_ped" >
+        <metadata name="base_name" value="admix" />
+        <composite_data value="test_out/prepare_population_structure/prepare_population_structure.html" />
+        <composite_data value="test_out/prepare_population_structure/admix.ped" />
+        <composite_data value="test_out/prepare_population_structure/admix.map" />
+        <edit_attributes type="name" value="fake" />
+      </param>
+      <param name="max_populations" value="2" />
+
+      <output name="output" file="test_out/evaluate_population_numbers/evaluate_population_numbers.txt" />
+    </test>
+  </tests>
+  -->
+
+  <help>
+
+**Dataset formats**
+
+The input dataset is in gd_ped_ format.
+The output dataset is text.  (`Dataset missing?`_)
+
+.. _gd_ped: ./static/formatHelp.html#gd_ped
+.. _Dataset missing?: ./static/formatHelp.html
+
+-----
+
+**What it does**
+
+The user selects a gd_ped dataset generated by the Prepare Input tool.
+For all possible numbers K of ancestral
+populations, from 1 up to a user-specified maximum, this tool produces values
+that indicate how well the data can be explained as genotypes from individuals
+derived from K ancestral populations.  These values are computed by a 5-fold
+cross-validation procedure, so that a good choice for K will exhibit a low
+cross-validation error (CVE) compared with other potential settings for K.
+
+-----
+
+**Acknowledgments**
+
+We use the program "Admixture", downloaded from
+
+http://www.genetics.ucla.edu/software/admixture/
+
+and described in the paper "Fast model-based estimation of ancestry in
+unrelated individuals" by David H. Alexander, John Novembre and Kenneth Lange,
+Genome Research 19 (2009), pp. 1655-1664. Admixture is called with the "--cv"
+flag to produce these values.
+
+----- 
+
+**Example**
+
+- output with max populations of 6::
+
+    CVE (K=1): 1.10120
+    CVE (K=2): 1.34683
+    CVE (K=3): 1.80611
+    CVE (K=4): 1.96339
+    CVE (K=5): 1.21522
+    CVE (K=6): 0.51501
+
+  </help>
+</tool>