diff tools/regVariation/featureCounter.xml @ 0:9071e359b9a3

Uploaded
author xuebing
date Fri, 09 Mar 2012 19:37:19 -0500
parents
children
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tools/regVariation/featureCounter.xml	Fri Mar 09 19:37:19 2012 -0500
@@ -0,0 +1,75 @@
+<tool id="featureCoverage1" name="Feature coverage" version="2.0.0">
+  <description></description>
+  <command interpreter="python">featureCounter.py $input1 $input2 $output -1 ${input1.metadata.chromCol},${input1.metadata.startCol},${input1.metadata.endCol},${input1.metadata.strandCol} -2 ${input2.metadata.chromCol},${input2.metadata.startCol},${input2.metadata.endCol},${input2.metadata.strandCol}</command>
+  <inputs>
+    <param format="interval" name="input1" type="data" help="First dataset">
+      <label>What portion of</label>
+    </param>
+    <param format="interval" name="input2" type="data" help="Second dataset">
+      <label>is covered by</label>
+    </param>
+   </inputs>
+  <outputs>
+    <data format="interval" name="output" metadata_source="input1" />
+  </outputs>
+  
+  <tests>
+    <test>
+      <param name="input1" value="1.bed" />
+      <param name="input2" value="2.bed" />
+      <output name="output" file="6_feature_coverage.bed" />
+    </test>
+    <test>
+      <param name="input1" value="chrY1.bed" />
+      <param name="input2" value="chrY2.bed" />
+      <output name="output" file="chrY_Coverage.bed" />
+    </test>
+  </tests>
+  <help>
+
+.. class:: infomark
+
+**What it does**
+
+This tool finds the coverage of intervals in the first dataset on intervals in the second dataset. The coverage and count are appended as 4 new columns in the resulting dataset.
+
+-----
+
+**Example**
+
+- If **First dataset** consists of the following windows::
+
+    chrX 1     10001 seg 0 -
+    chrX 10001 20001 seg 0 -
+    chrX 20001 30001 seg 0 -
+    chrX 30001 40001 seg 0 -
+      
+- and **Second dataset** consists of the following exons::
+
+    chrX 5000  6000  seg2 0 -
+    chrX 5500  7000  seg2 0 -
+    chrX 9000  22000 seg2 0 -
+    chrX 24000 34000 seg2 0 -
+    chrX 36000 38000 seg2 0 -
+      
+- the **Result** is the coverage of exons of the second dataset in each of the windows contained in first dataset::
+
+    chrX 1     10001 seg 0 - 3001  0.3001 2 1
+    chrX 10001 20001 seg 0 - 10000 1.0    1 0
+    chrX 20001 30001 seg 0 - 8000  0.8    0 2
+    chrX 30001 40001 seg 0 - 5999  0.5999 1 1
+	  
+- To clarify, the following line of output ( added columns are indexed by a, b and c )::
+
+                         a    b      c d
+    chrX 1 10001 seg 0 - 3001 0.3001 2 1
+                                  
+  implies that 2 exons (c) fall fully in this window (chrX:1-10001), 1 exon (d) partially overlaps this window, and these 3 exons cover 30.01% (c) of the window size, spanning 3001 nucleotides (a).
+
+  * a: number of nucleotides in this window covered by the features in (c) and (d) - features overlapping with each other will be merged to calculate (a)
+  * b: fraction of window size covered by features in (c) and (d) - features overlapping with each other will be merged to calculate (b)
+  * c: number of features in the 2nd dataset that fall **completely** within this window
+  * d: number of features in the 2nd dataset that **partially** overlap this window
+  	 
+</help>
+</tool>