# HG changeset patch
# User drosofff
# Date 1403510220 14400
# Node ID aa7092c7a3c81c3b35f9a7dc1c6fdb75d27043f7
# Parent  06e465694fd12065b3d3e0847f772333ba20079e
Uploaded

diff -r 06e465694fd1 -r aa7092c7a3c8 sRbowtieParser.py
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/sRbowtieParser.py	Mon Jun 23 03:57:00 2014 -0400
@@ -0,0 +1,35 @@
+#!/usr/bin/python
+# python parser module to analyse sRbowtie alignments
+# version 0.9
+# Usage sRbowtieParser.py  <1:index source> <2:extraction directive> <3:outputL> <4:polarity> <5:6:7 filePath:FileExt:FileLabel> <.. ad  lib>
+
+import sys
+from smRtools import *
+
+IndexSource = sys.argv[1]
+ExtractionDirective = sys.argv[2]
+if ExtractionDirective == "--do_not_extract_index":
+  genomeRefFormat = "fastaSource"
+elif  ExtractionDirective == "--extract_index":
+  genomeRefFormat = "bowtieIndex"
+Output = sys.argv[3]
+Polarity = sys.argv[4] # maybe "both", "forward", "reverse"
+Triplets = [sys.argv[5:][i:i+3] for i in xrange(0, len(sys.argv[5:]), 3)]
+MasterListOfGenomes = {}
+
+for [filePath, FileExt, FileLabel] in Triplets:
+  MasterListOfGenomes[FileLabel] = HandleSmRNAwindows (filePath, FileExt, IndexSource, genomeRefFormat) 
+
+header = ["gene"]
+for [filePath, FileExt, FileLabel] in Triplets:
+  header.append(FileLabel)
+
+F = open (sys.argv[3], "w")
+print >> F, "\t".join(header)
+for item in sorted (MasterListOfGenomes[header[1]].instanceDict.keys() ):
+  line=[item]
+  for sample in header[1:]:
+    count = str (MasterListOfGenomes[sample].instanceDict[item].readcount(polarity=Polarity))
+    line.append(count)
+  print >> F,  "\t".join(line )
+F.close()