# HG changeset patch
# User davidvanzessen
# Date 1411473035 14400
# Node ID 71a12810eff3647aa792301738e55bb6bf86f72b
# Parent  069419cccba4c17300ffc3619b51593186e4bfdc
Uploaded

diff -r 069419cccba4 -r 71a12810eff3 gene_identification.py
--- a/gene_identification.py	Mon Sep 22 10:19:36 2014 -0400
+++ b/gene_identification.py	Tue Sep 23 07:50:35 2014 -0400
@@ -112,11 +112,23 @@
 		lastindex = 0
 		start = [0] * len(seq)
 		for i, regexp in enumerate(regularexpressions): #for every regular expression
+			relativeStartLocation = lastindex - (chunklength / 2) * i
+			if relativeStartLocation < 0 or relativeStartLocation >= len(seq):
+				break
 			regex, hasVar = regexp
 			matches = regex.finditer(seq[lastindex:])
 			for match in matches: #for every match with the current regex, only uses the first hit
 				lastindex += match.start()
-				start[lastindex - chunklength / 2 * i] += 1
+				print ID
+				print lastindex
+				print chunklength
+				print i
+				print seq[lastindex:]
+				print start
+				print len(seq)
+				print relativeStartLocation
+				print "-------------------"
+				start[relativeStartLocation] += 1
 				if hasVar: #if the regex has a variable nt in it
 					chunkstart = chunklength / 2 * i #where in the reference does this chunk start
 					chunkend = chunklength / 2 * i + chunklength #where in the reference does this chunk end