changeset 10:c081f25e1572

Updated CompareOverlappingSmallRef.py
author m-zytnicki
date Thu, 14 Mar 2013 05:25:40 -0400
parents 1eb55963fe39
children 2da30502c2f1
files SMART/Java/Python/CompareOverlappingSmallRef.py
diffstat 1 files changed, 48 insertions(+), 15 deletions(-) [+]
line wrap: on
line diff
--- a/SMART/Java/Python/CompareOverlappingSmallRef.py	Thu Mar 14 05:23:05 2013 -0400
+++ b/SMART/Java/Python/CompareOverlappingSmallRef.py	Thu Mar 14 05:25:40 2013 -0400
@@ -72,6 +72,11 @@
 		self.antisense      = False
 		self.collinear      = False
 		self.distance       = None
+		self.minOverlap     = False
+		self.pcOverlapQuery = False
+		self.pcOverlapRef   = False
+		self.included       = False
+		self.including      = False
 		self.bins	        = {}
 		self.notOverlapping = False
 
@@ -100,6 +105,14 @@
 	def setInvert(self, boolean):
 		self.invert = boolean
 
+	def setMinPercentOverlap(self, pcOverlapQuery, pcOverlapRef):
+		self.pcOverlapQuery = pcOverlapQuery
+		self.pcOverlapRef   = pcOverlapRef
+
+	def setInclude(self, included, including):
+		self.included  = included
+		self.including = including
+
 	def includeNotOverlapping(self, boolean):
 		self.notOverlapping = boolean
 
@@ -133,6 +146,18 @@
 			return False
 		if self.antisense and queryTranscript.getDirection() == refTranscript.getDirection():
 			return False
+		if self.included and not queryTranscript.isIncluded(refTranscript):
+			return False
+		if self.including and not refTranscript.isIncluded(queryTranscript):
+			return False
+		querySize = queryTranscript.getSize()
+		if self.pcOverlapQuery and not queryTranscript.overlapWithExon(refTranscript, int(querySize * self.pcOverlapQuery / 100.0)):
+			return False
+		refSize = refTranscript.getSize()
+		if self.pcOverlapRef and not queryTranscript.overlapWithExon(refTranscript, int(refSize * self.pcOverlapRef / 100.0)):
+			return False
+		if self.minOverlap and not queryTranscript.overlapWithExon(refTranscript, self.minOverlap):
+			return False
 		return True
 
 	def _compareTranscript(self, queryTranscript):
@@ -177,9 +202,10 @@
 		self.writer.close()
 
 	def displayResults(self):
-		print "# queries:  %d" % (self.nbQueries)
-		print "# refs:     %d" % (self.nbRefs)
-		print "# written:  %d (%d overlaps)" % (self.nbWritten, self.nbOverlaps)
+		if self.verbosity > 0:
+			print "# queries:  %d" % (self.nbQueries)
+			print "# refs:     %d" % (self.nbRefs)
+			print "# written:  %d (%d overlaps)" % (self.nbWritten, self.nbOverlaps)
 
 	def run(self):
 		self.loadRef()
@@ -191,17 +217,22 @@
 	description = "Compare Overlapping Small Reference v1.0.1: Provide the queries that overlap with a reference, when the reference is small. [Category: Data Comparison]"
 
 	parser = OptionParser(description = description)
-	parser.add_option("-i", "--input1",	        dest="inputFileName1", action="store",			          type="string", help="query input file [compulsory] [format: file in transcript format given by -f]")
-	parser.add_option("-f", "--format1",        dest="format1",		  action="store",			          type="string", help="format of previous file [compulsory] [format: transcript file format]")
-	parser.add_option("-j", "--input2",	        dest="inputFileName2", action="store",			          type="string", help="reference input file [compulsory] [format: file in transcript format given by -g]")
-	parser.add_option("-g", "--format2",        dest="format2",		  action="store",			          type="string", help="format of previous file [compulsory] [format: transcript file format]")
-	parser.add_option("-o", "--output",	        dest="outputFileName", action="store",			          type="string", help="output file [format: output file in GFF3 format]")
-	parser.add_option("-O", "--notOverlapping", dest="notOverlapping", action="store_true", default=False,				help="also output not overlapping data [format: bool] [default: false]")
-	parser.add_option("-d", "--distance",		dest="distance",	   action="store",	    default=0,	  type="int",	 help="accept some distance between query and reference [format: int]")
-	parser.add_option("-c", "--collinear",		dest="collinear",	   action="store_true", default=False,			 	 help="provide collinear features [format: bool] [default: false]")
-	parser.add_option("-a", "--antisense",		dest="antisense",	   action="store_true", default=False,			 	 help="provide antisense features [format: bool] [default: false]")
-	parser.add_option("-x", "--exclude",		dest="exclude",		   action="store_true", default=False,			 	 help="invert the match [format: bool] [default: false]")
-	parser.add_option("-v", "--verbosity",      dest="verbosity",	  action="store",       default=1,    type="int",	help="trace level [format: int]")
+	parser.add_option("-i", "--input1",	        dest="inputFileName1", action="store",			           type="string", help="query input file [compulsory] [format: file in transcript format given by -f]")
+	parser.add_option("-f", "--format1",        dest="format1",		  action="store",			           type="string", help="format of previous file [compulsory] [format: transcript file format]")
+	parser.add_option("-j", "--input2",	        dest="inputFileName2", action="store",			           type="string", help="reference input file [compulsory] [format: file in transcript format given by -g]")
+	parser.add_option("-g", "--format2",        dest="format2",		  action="store",			           type="string", help="format of previous file [compulsory] [format: transcript file format]")
+	parser.add_option("-o", "--output",	        dest="outputFileName", action="store",			           type="string", help="output file [format: output file in GFF3 format]")
+	parser.add_option("-O", "--notOverlapping", dest="notOverlapping", action="store_true", default=False,				  help="also output not overlapping data [format: bool] [default: false]")
+	parser.add_option("-d", "--distance",		dest="distance",	   action="store",	    default=0,	   type="int",	  help="accept some distance between query and reference [format: int]")
+	parser.add_option("-c", "--collinear",		dest="collinear",	   action="store_true", default=False,			 	  help="provide collinear features [format: bool] [default: false]")
+	parser.add_option("-a", "--antisense",		dest="antisense",	   action="store_true", default=False,			 	  help="provide antisense features [format: bool] [default: false]")
+	parser.add_option("-m", "--minOverlap",	    dest="minOverlap",     action="store",      default=False, type="int",	  help="min. #nt overlap [format: bool] [default: false]")
+	parser.add_option("-p", "--pcOverlapQuery",	dest="pcOverlapQuery", action="store",      default=False, type="int",	  help="min. % overlap of the query [format: bool] [default: false]")
+	parser.add_option("-P", "--pcOverlapRef",	dest="pcOverlapRef",   action="store",      default=False, type="int",    help="min. % overlap of the reference [format: bool] [default: false]")
+	parser.add_option("-k", "--included",		dest="included",	   action="store_true", default=False,			 	  help="provide query elements which are nested in reference elements [format: bool] [default: false]")
+	parser.add_option("-K", "--including",		dest="including",	   action="store_true", default=False,			 	  help="provide query elements in which reference elements are nested [format: bool] [default: false]")
+	parser.add_option("-x", "--exclude",		dest="exclude",		   action="store_true", default=False,			 	  help="invert the match [format: bool] [default: false]")
+	parser.add_option("-v", "--verbosity",      dest="verbosity",	   action="store",      default=1,     type="int",	  help="trace level [format: int]")
 	(options, args) = parser.parse_args()
 
 	cosr = CompareOverlappingSmallRef(options.verbosity)
@@ -211,7 +242,9 @@
 	cosr.includeNotOverlapping(options.notOverlapping)
 	cosr.setDistance(options.distance)
 	cosr.setAntisense(options.antisense)
+	cosr.setInclude(options.included, options.including)
 	cosr.setInvert(options.exclude)
-	cosr.setInvert(options.exclude)
+	cosr.setMinOverlap(options.minOverlap)
+	cosr.setMinPercentOverlap(options.pcOverlapQuery, options.pcOverlapRef)
 	cosr.run()