# HG changeset patch
# User test0004
# Date 1346360604 14400
# Node ID 410a2d3c7b6ccfeb1e5d38fb3403d80065873718

Uploaded

diff -r 000000000000 -r 410a2d3c7b6c gencode_partition.xml
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/gencode_partition.xml	Thu Aug 30 17:03:24 2012 -0400
@@ -0,0 +1,45 @@
+<tool id="gencode_partition1" name="Gencode Partition">
+  <description>an interval file</description>
+  <command interpreter="python">split_by_partitions.py ${GALAXY_DATA_INDEX_DIR} $input1 $out_file1 ${input1.metadata.chromCol} ${input1.metadata.startCol} ${input1.metadata.endCol} ${input1.metadata.strandCol}</command>
+  <inputs>
+    <param name="input1" type="data" format="interval" label="File to Partition"/>
+  </inputs>
+  <outputs>
+    <data name="out_file1" format="bed"/>
+  </outputs>
+  <tests>
+    <test>
+      <param name="input1" value="encode_1.bed"/>
+      <output name="out_file1" file="gencode_partition_out.bed"/>
+    </test>
+  </tests>
+  <help>
+For detailed information about partitioning, click here_.
+
+.. _here: http://genome.imim.es/gencode/wiki/index.php/Collecting_Feature_Sets_from_All_Analysis_Groups
+
+Datasets are partitioned according to the protocol below:
+
+A partition scheme has been defined that is similar to what has previously been done with TARs/TRANSFRAGs such that any feature can be classified as falling into one of the following 6 categories:
+  1. **Coding** -- coding exons defined from the GENCODE experimentally verified coding set (coding in any transcript)
+  2. **5UTR** -- 5' UTR exons defined from the GENCODE experimentally verified coding set (5' UTR in some transcript but never coding in any other)
+  3. **3UTR** -- 3' UTR exons defined from the GENCODE experimentally verified coding set (3' UTR in some transcript but never coding in any other)
+  4. **Intronic Proximal** -- intronic and no more than 5kb away from an exon.
+  5. **Intergenic Proximal** -- between genes and no more than 5kb away from an exon.
+  6. **Intronic Distal** -- intronic and greater than 5kb away from an exon.
+  7. **Intergenic Distal** -- between genes and greater than 5kb away from an exon.
+
+-----
+
+.. class:: infomark
+
+**Note:** Features overlapping more than one partition will take the identity of the lower-numbered partition. 
+
+------
+
+**Citation**
+
+If you use this tool, please cite `Blankenberg D, Taylor J, Schenck I, He J, Zhang Y, Ghent M, Veeraraghavan N, Albert I, Miller W, Makova KD, Hardison RC, Nekrutenko A. A framework for collaborative analysis of ENCODE data: making large-scale analyses biologist-friendly. Genome Res. 2007 Jun;17(6):960-4. &lt;http://www.ncbi.nlm.nih.gov/pubmed/17568012&gt;`_
+
+  </help>
+</tool>
\ No newline at end of file