Merge pull request #30 from yhoogstrate/removal_unused_trans_seq_vars

Removal unused trans seq vars

Changelog

@@ -1,3 +1,8 @@
+2016-03-16  Youri Hoogstrate
+
+	* Version 2.12.2: Removal of unused 'sequence' and 'transition
+	  sequence' variables within the Fusion object, to reduce memory.
+
 2016-03-15  Youri Hoogstrate
 
 	* Version 2.12.1: Another reuction of memory footprint - from

fuma/CompareFusionsBySpanningGenes.py

@@ -146,8 +146,6 @@ def match_fusions(self,fusion_1,fusion_2,allow_empty = True):
 						fusion_1.get_right_chromosome(), \
 						fusion_1.get_left_break_position(), \
 						fusion_1.get_right_break_position(), \
-						fusion_1.sequence, \
-						fusion_1.get_transition_sequence(), \
 						fusion_1.left_strand, \
 						fusion_1.right_strand, \
 						fusion_1.dataset_name+"_vs._"+fusion_2.dataset_name, \

fuma/Fusion.py

@@ -36,9 +36,6 @@ def __init__(self, \
 	   arg_left_pos, \
 	   arg_right_pos, \
 
-	   arg_sequence, \
-	   arg_transition_sequence, \
-
 	   arg_left_strand, \
 	   arg_right_strand, \
 
@@ -58,6 +55,7 @@ def __init__(self, \
 
 		self.matches = set([self])## initial (non merged) objects used for matching
 
+		#@todo use pointer to original dataset?
 		self.dataset_name = arg_dataset_name
 
 		self.acceptor_donor_direction = None
@@ -67,8 +65,6 @@ def __init__(self, \
 			self.cleanup_chr_name(arg_right_chr), \
 			arg_left_pos, \
 			arg_right_pos, \
-			arg_sequence, \
-			arg_transition_sequence, \
 			self.find_strand_type(arg_left_strand), \
 			self.find_strand_type(arg_right_strand), \
 			arg_uid, \
@@ -108,9 +104,6 @@ def set(self, \
 			arg_left_pos, \
 			arg_right_pos, \
 
-			arg_sequence, \
-			arg_transition_sequence, \
-
 			arg_left_strand, \
 			arg_right_strand, \
 
@@ -124,9 +117,6 @@ def set(self, \
 		self.left_break_position = int(str(arg_left_pos).replace(",",""))
 		self.right_break_position = int(str(arg_right_pos).replace(",",""))
 
-		self.sequence = arg_sequence
-		self.transition_sequence = arg_transition_sequence
-
 		self.left_strand = arg_left_strand
 		self.right_strand = arg_right_strand
 
@@ -170,11 +160,11 @@ def cleanup_chr_name(self,chr_name):
 		chr_name = chr_name.strip()
 		return chr_name[3:] if chr_name[0:3] == "chr" else chr_name
 
-	def get_left_position(self,indexed_chromosome=False):
-		return [self.get_left_chromosome(indexed_chromosome),self.get_left_break_position()]
+	def get_left_position(self,chromosome_with_prefix=False):
+		return [self.get_left_chromosome(chromosome_with_prefix),self.get_left_break_position()]
 
-	def get_right_position(self,indexed_chromosome=False):
-		return [self.get_right_chromosome(indexed_chromosome),self.get_right_break_position()]
+	def get_right_position(self,chromosome_with_prefix=False):
+		return [self.get_right_chromosome(chromosome_with_prefix),self.get_right_break_position()]
 
 	def get_left_chromosome(self,with_prefix=False):
 		if(with_prefix):
@@ -194,9 +184,6 @@ def get_left_break_position(self):
 	def get_right_break_position(self):
 		return self.right_break_position
 
-	def get_transition_sequence(self):
-		return self.transition_sequence
-
 	def get_distance(self):
 		if(self.is_interchromosomal()):
 			return -1
@@ -226,8 +213,6 @@ def swap_positions(self):
 			self.left_chr_str, \
 			self.get_right_break_position(), \
 			self.get_left_break_position(), \
-			self.sequence, \
-			self.get_transition_sequence(), \
 			self.right_strand, \
 			self.left_strand, \
 			self.uid, \

fuma/FusionDetectionExperiment.py

@@ -142,10 +142,8 @@ def export_to_CG_Junctions_file(self,filename):
 				fh.write("\t")
 				fh.write("20	Y	")
 
-				if(fusion.get_transition_sequence()):
-					fh.write(fusion.get_transition_sequence()+"	"+str(len(fusion.get_transition_sequence())))
-				else:
-					fh.write("\t")
+				# Sequences are not being stored as it consumes too much memory
+				fh.write("\t")
 
 				fh.write("			")