# HG changeset patch
# User gregory-minevich
# Date 1332805033 14400
# Node ID 6bd8660f3a8f5fee6c0a48fa5592bedb00b7816b
# Parent  bc7cc93ef659af8908427ca943b4072e678330a7
Uploaded

diff -r bc7cc93ef659 -r 6bd8660f3a8f ._checkSnpEffCandidates.py
Binary file ._checkSnpEffCandidates.py has changed
diff -r bc7cc93ef659 -r 6bd8660f3a8f ._checkSnpEffCandidates.xml
Binary file ._checkSnpEffCandidates.xml has changed
diff -r bc7cc93ef659 -r 6bd8660f3a8f checkSnpEffCandidates.py
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/checkSnpEffCandidates.py	Mon Mar 26 19:37:13 2012 -0400
@@ -0,0 +1,70 @@
+#!/usr/bin/python
+
+import sys
+import optparse
+import csv
+import re
+
+def main():
+	parser = optparse.OptionParser()
+	parser.add_option('-s', '--snpeff_file', dest = 'snpeff_file', action = 'store', type = 'string', default = None, help = "Path to the snpEff file")
+	parser.add_option('-c', '--candidate_list', dest = 'candidate_list', action = 'store', type = 'string', default = None, help = "Two column tabular list of candidate Gene ID, Type")
+	parser.add_option('-o', '--output', dest = 'output', action = 'store', type = 'string', default = None, help = "Output file name")	
+	(options, args) = parser.parse_args()
+	
+	snpeff_file = options.snpeff_file
+	candidate_list = options.candidate_list
+
+	candidates = parse_candidate_list(candidate_list = candidate_list)
+	mark_snpeff_file(snpeff_file = snpeff_file, output = options.output, candidates = candidates)
+
+def skip_and_write_headers(writer = None, reader = None, i_file = None):
+	# count headers
+	comment = 0
+	while reader.next()[0].startswith('#'):
+		comment = comment + 1
+	
+	# skip and write headers
+	i_file.seek(0)
+	for i in range(0, comment):
+		row = reader.next()
+		writer.writerow(row)
+
+def parse_candidate_list(candidate_list = ""):
+	i_file = open(candidate_list, 'rU')
+	reader  = csv.reader(i_file, delimiter = '\t',)
+
+	candidates = {}
+	for row in reader:
+		gene_id = row[0]
+		gene_type = row[1]
+		candidates[gene_id] = gene_type
+
+	i_file.close()
+	
+	return candidates
+
+def mark_snpeff_file(snpeff_file = "", output = "", candidates = None):
+	i_file = open(snpeff_file, 'rU')
+	reader = csv.reader(i_file, delimiter = '\t')
+
+	o_file = open(output, 'wb')
+	writer = csv.writer(o_file, delimiter = '\t')
+
+	skip_and_write_headers(writer = writer, reader = reader, i_file = i_file)
+
+	for row in reader:
+		gene_id = row[9]
+		if gene_id in candidates:
+			gene_type = candidates[gene_id]
+			row.append(gene_type)
+		else:
+			row.append('')
+
+		writer.writerow(row)
+
+	o_file.close()
+	i_file.close()
+
+if __name__ == "__main__":
+    main()
diff -r bc7cc93ef659 -r 6bd8660f3a8f checkSnpEffCandidates.xml
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/checkSnpEffCandidates.xml	Mon Mar 26 19:37:13 2012 -0400
@@ -0,0 +1,51 @@
+<tool id="check_snpeff_candidates" name="CloudMap: Check snpEff Candidates">
+    <description>Marks up a snpEff output file with matches to a gene candidate list.</description>
+    <command interpreter="python">checkSnpEffCandidates.py -s $snpeff_file -c $candidate_list -o $output</command>
+    <inputs>
+        <param name="snpeff_file" type="data" format="tabular" label="SnpEff File" help="tabular output file from snpEff"/>
+        <param name="candidate_list" type="data" format="tabular" label="Candidate List" help="2 column list consisting of candidate genes and a description"/>
+    </inputs>
+    <outputs>
+        <data format="tabular" name="output" />
+    </outputs>
+    <requirements>
+        <requirement type="python-module">sys</requirement>
+        <requirement type="python-module">optparse</requirement>
+        <requirement type="python-module">csv</requirement>
+    </requirements>
+    <tests>
+	<param name="snpeff_file" value="" />
+	<param name="candidate_list" value="" />
+    </tests>
+    <help>
+
+**What it does:** 
+
+Indicates on a SnpEff output file which genes are found in a candidate list by comparing Gene IDs.  
+
+For a description of the snpEff variant annotation and effect prediction tool:
+
+http://snpeff.sourceforge.net
+
+------
+
+**Input:** 
+
+The candidate list should be in a tabular format with two columns: Gene ID and Gene Description (e.g. C55B7.12 and transcription_factor). The file should contain no headers.
+
+Useful candidate lists (e.g. transcription factors, genes expressed in neurons, transgene silencers, chromatin factors) are available on the Hobert Lab website:
+
+http://biochemistry.hs.columbia.edu/labs/hobert/literature.html
+
+
+------
+
+**Citation:**
+
+This tool is part of the CloudMap package from the Hobert Lab. If you use this tool, please cite `Gregory Minevich, Danny Park, Richard J. Poole and Oliver Hobert.  CloudMap: A Cloud-based Pipeline for Analysis of Mutant Genome Sequences. (2012 In Preparation)`__
+
+    .. __: http://biochemistry.hs.columbia.edu/labs/hobert/literature.html
+
+Correspondence to gm2123@columbia.edu (G.M.) or or38@columbia.edu (O.H.)
+    </help>
+</tool>