diff select_individuals.xml @ 12:4b6590dd7250

Uploaded
author miller-lab
date Wed, 12 Sep 2012 17:10:26 -0400
parents
children
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/select_individuals.xml	Wed Sep 12 17:10:26 2012 -0400
@@ -0,0 +1,72 @@
+<tool id="gd_select_individuals" name="Select individuals" version="1.0.0">
+  <description>from a gd_snp dataset</description>
+
+  <command interpreter="bash">
+    echo.bash "$input" "$output"
+    #for $individual in str($individuals).split(',')
+        #set $individual_idx = $input.dataset.metadata.individual_names.index($individual)
+        #set $individual_col = str( $input.dataset.metadata.individual_columns[$individual_idx] )
+        #set $arg = '\t'.join([$individual_col, $individual, ''])
+        "$arg"
+    #end for
+  </command>
+
+  <inputs>
+    <param name="input" type="data" format="gd_snp" label="gd_snp dataset"/>
+    <param name="individuals" type="select" display="checkboxes" multiple="true" label="Individuals to include">
+      <options>
+        <filter type="data_meta" ref="input" key="individual_names" />
+      </options>
+      <validator type="no_options" message="You must select at least one individual"/>
+    </param>
+  </inputs>
+
+  <outputs>
+    <data name="output" format="gd_indivs" label="Individuals from ${input.hid}" />
+  </outputs>
+
+  <tests>
+    <test>
+      <param name="input" value="test_in/sample.gd_snp" ftype="gd_snp" />
+      <param name="individuals" value="PB1,PB2" />
+      <output name="output" file="test_in/a.gd_indivs" />
+    </test>
+  </tests>
+
+  <help>
+**Dataset formats**
+
+The input dataset is in the gd_snp_ format.
+The output dataset is in gd_indivs_ format.  (`Dataset missing?`_)
+
+.. _Dataset missing?: ./static/formatHelp.html
+.. _gd_snp: ./static/formatHelp.html#gd_snp
+.. _gd_indivs: ./static/formatHelp.html#gd_indivs
+
+**What it does**
+
+This selects a set of individuals or groups from a gd_snp dataset.   This set
+can then be used by other tools to work on just part of the gd_snp dataset.
+
+**Examples**
+
+- input::
+
+   Contig161_chr1_4641264_4641879	115	C	T	73.5	chr1	4641382	        C	6	0	2	45	8	0	2	51	15	0	2	72	5	0	2	42	6	0	2	45	10	0	2	57	Y	54	0.323	0
+   Contig48_chr1_10150253_10151311	11	A	G	94.3	chr1	10150264	A	1	0	2	30	1	0	2	30	1	0	2	30	3	0	2	36	1	0	2	30	1	0	2	30	Y	22	+99.	0
+   Contig20_chr1_21313469_21313570	66	C	T	54.0	chr1	21313534	C	4	0	2	39	4	0	2	39	5	0	2	42	4	0	2	39	4	0	2	39	5	0	2	42	N	1	+99.	0
+   etc.
+
+- input metadata::
+
+   #{"column_names":["scaf","pos","A","B","qual","ref","rpos","rnuc","1A","1B","1G","1Q","2A","2B","2G","2Q","3A","3B","3G","3Q","4A","4B","4G","4Q","5A","5B","5G","5Q","6A","6B","6G","6Q","pair","dist",
+   #"prim","rflp"],"dbkey":"canFam2","individuals":[["PB1",9],["PB2",13],["PB3",17],["PB4",21],["PB6",25],["PB8",29]],"pos":2,"rPos":7,"ref":6,"scaffold":1,"species":"bear"}
+
+- output when individuals PB1, PB2, and PB3 are selected::
+
+   9	PB1
+   13	PB2
+   17	PB3
+
+  </help>
+</tool>