Release version for Erange 4.0a

[erange.git] / makerdsfromblat.py

diff --git a/makerdsfromblat.py b/makerdsfromblat.py
index 37576ca867fb2283f9a5d497c0bbca7d06191f7e..17520401c52b5d153404aa4312a800017e9af3bb 100755 (executable)
--- a/makerdsfromblat.py
+++ b/makerdsfromblat.py
@@ -20,6 +20,9 @@ import ReadDataset
 verstring = "makerdsfromblat: version 3.10"
 print verstring
 
+NUM_HEADER_LINES = 5
+
+
 def main(argv=None):
     if not argv:
         argv = sys.argv
@@ -98,24 +101,15 @@ def makerdsfromblat(label, filename, outdbname, dataType="DNA", init=True,
                     verbose=False, cachePages=100000, geneDataFileName="",
                     propertyList=[]):
 
-    delimiter = "|"
-    minIntron = 10
-    maxBorder = 0
-    index = 0
-    insertSize = 100000
-
+    writeLog(outdbname + ".log", verstring, string.join(sys.argv[1:]))
     if forceRNA:
         print "forcing datatype to RNA"
         dataType = "RNA"
 
-    if dataType == "RNA":
-        genedatafile = open(geneDataFileName)
-
-    writeLog(outdbname + ".log", verstring, string.join(sys.argv[1:]))
-
     geneDict = {}
     mapDict = {}
     if dataType == "RNA" and not forceRNA:
+        genedatafile = open(geneDataFileName)
         for line in genedatafile:
             fields = line.strip().split("\t")
             blockCount = int(fields[7])
@@ -164,9 +158,10 @@ def makerdsfromblat(label, filename, outdbname, dataType="DNA", init=True,
 
     # make some assumptions based on first read
     infile = open(filename, "r")
-    for arg in range(6):
+    for arg in range(NUM_HEADER_LINES):
         line = infile.readline()
 
+    line = infile.readline()
     fields = line.split()
     readsize = int(fields[10])
     pairedTest = fields[9][-2:]
@@ -186,8 +181,9 @@ def makerdsfromblat(label, filename, outdbname, dataType="DNA", init=True,
         rds.insertMetadata([("blat_mapped", "True")])
 
     minReadScore = readsize - readsize/25 - 1
-    trim = -4
+    maxBorder = 0
     if dataType == "RNA":
+        trim = -4
         maxBorder = readsize + trim
 
     infile = open(filename, "r")
@@ -199,9 +195,12 @@ def makerdsfromblat(label, filename, outdbname, dataType="DNA", init=True,
     index = uIndex = mIndex = sIndex = lIndex = 0
     bestScore = 0
     # skip headers
-    for arg in range(5):
+    for arg in range(NUM_HEADER_LINES):
         line = infile.readline()
 
+    insertSize = 100000
+    delimiter = "|"
+    minIntron = 10
     for line in infile:
         lIndex += 1
         fields = line.strip().split()