diff dpmix.xml @ 14:8ae67e9fb6ff

Uploaded Miller Lab Devshed version a51c894f5bed again [possible toolshed.g2 bug]
author miller-lab
date Fri, 28 Sep 2012 11:35:56 -0400
parents
children d6b961721037
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/dpmix.xml	Fri Sep 28 11:35:56 2012 -0400
@@ -0,0 +1,93 @@
+<tool id="gd_dpmix" name="Admixture" version="1.0.0">
+  <description>: Map genomic intervals resembling specified ancestral populations</description>
+
+  <command interpreter="python">
+    dpmix.py "$input" "$data_source" "$switch_penalty" "$ap1_input" "$ap2_input" "$p_input" "$output" "$output2" "$output2.files_path" "$input.dataset.metadata.dbkey" "$input.dataset.metadata.ref" "$GALAXY_DATA_INDEX_DIR" "gd.heterochromatic.loc"
+    #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="gd_snp" label="Dataset">
+      <validator type="unspecified_build" message="This dataset does not have a reference species and cannot be used with this tool" />
+    </param>
+    <param name="ap1_input" type="data" format="gd_indivs" label="Ancestral population 1 individuals" />
+    <param name="ap2_input" type="data" format="gd_indivs" label="Ancestral population 2 individuals" />
+    <param name="p_input" type="data" format="gd_indivs" label="Potentially admixed individuals" />
+
+    <param name="data_source" type="select" format="integer" label="Data source">
+      <option value="0" selected="true">sequence coverage</option>
+      <option value="1">estimated genotype</option>
+    </param>
+
+    <param name="switch_penalty" type="integer" min="0" value="10" label="Switch penalty" />
+  </inputs>
+
+  <outputs>
+    <data name="output" format="tabular" />
+    <data name="output2" format="html" />
+  </outputs>
+
+  <tests>
+    <test>
+      <param name="input" value="test_in/sample.gd_snp" ftype="gd_snp" />
+      <param name="ap1_input" value="test_in/a.gd_indivs" ftype="gd_indivs" />
+      <param name="ap2_input" value="test_in/b.gd_indivs" ftype="gd_indivs" />
+      <param name="p_input" value="test_in/c.gd_indivs" ftype="gd_indivs" />
+      <param name="data_source" value="0" />
+      <param name="switch_penalty" value="10" />
+
+      <output name="output" file="test_out/dpmix/dpmix.tabular" />
+
+      <output name="output2" file="test_out/dpmix/dpmix.html" ftype="html" compare="diff" lines_diff="2">
+        <extra_files type="file" name="dpmix.pdf" value="test_out/dpmix/dpmix.pdf" compare="sim_size" delta = "10000" />
+        <extra_files type="file" name="misc.txt" value="test_out/dpmix/misc.txt" />
+      </output>
+    </test>
+  </tests>
+
+  <help>
+
+**Dataset formats**
+
+The input datasets are in gd_snp_ and gd_indivs_ formats.  It is important for
+the Individuals datasets to have unique names and for there to be no overlap
+between the two populations.  Rename these datasets if
+needed to make them unique.  
+There are two output datasets, one tabular_ and one composite. (`Dataset missing?`_)
+
+.. _gd_snp: ./static/formatHelp.html#gd_snp
+.. _gd_indivs: ./static/formatHelp.html#gd_indivs
+.. _tabular: ./static/formatHelp.html#tab
+.. _Dataset missing?: ./static/formatHelp.html
+
+-----
+
+**What it does**
+
+The user specifies two "ancestral" populations (i.e., sources for
+chromosomes) and a set of potentially admixed individuals, and chooses
+between the sequence coverage or the estimated genotypes to measure
+the similarity of genomic intervals in admixed individuals to the two
+classes of ancestral chromosomes.  The user also picks a "switch penalty",
+typically between 10 and 100.  For each potentially admixed individual,
+the program divides the genome into three "genotypes": (0) homozygous
+for the first ancestral population (i.e., both chromosomes from that
+population), (1) heterozygous, or (2) homozygous for the second ancestral
+population.  Parts of a chromosome that are labeled as "heterochromatic"
+are given the non-genotype, 3.  Smaller values of the switch penalty
+(corresponding to more ancient admixture events) generally lead to the
+reconstruction of more frequent changes between genotypes.
+
+There are two output datasets generated.  A tabular dataset with chromosome,
+start, stop, and pairs of columns containing the "genotypes" from above
+and label from the admixed individual.  The second dataset is a composite
+dataset with general information from the run and a link to a pdf which
+graphically shows the ancestral population along each of the chromosomes.
+The second link is to a text file with summary information of the 
+"genotypes" over the whole genome.
+
+  </help>
+</tool>