first pass cleanup of cistematic/genomes; change bamPreprocessing

[erange.git] / cistematic / genomes / cbrenneri.py

diff --git a/cistematic/genomes/cbrenneri.py b/cistematic/genomes/cbrenneri.py
index a227faacf6a5c73b6b48512c2e917875fb8d6d9c..7a338a9779a0f97983130f6a5846c03456bb3d34 100644 (file)
--- a/cistematic/genomes/cbrenneri.py
+++ b/cistematic/genomes/cbrenneri.py
@@ -1,7 +1,7 @@
 ###########################################################################
 #                                                                         #
 # C O P Y R I G H T   N O T I C E                                         #
-#  Copyright (c) 2003-10 by:                                              #
+#  Copyright (c) 2003-13 by:                                              #
 #    * California Institute of Technology                                 #
 #                                                                         #
 #    All Rights Reserved.                                                 #
@@ -33,48 +33,39 @@ from cistematic.genomes import Genome
 from os import environ
 
 if environ.get("CISTEMATIC_ROOT"):
-    cisRoot = environ.get("CISTEMATIC_ROOT") 
+    cisRoot = environ.get("CISTEMATIC_ROOT")
 else:
     cisRoot = "/proj/genome"
 
 geneDB = "%s/C_brenneri/cbrenneri.genedb" % cisRoot
 
 
-def loadChromosome(db, chromPath, chromOutPath):
-    seqArray = []
-    seqLen = 0
-    cbGenome = Genome("cbrenneri", dbFile=db)
-    inFile = open(chromPath, "r")
-    header = inFile.readline()
-    while header != "":
-        seqArray = []
-        seqLen = 0
-        chromHeader = header.strip()[1:].split()
-        chromID = chromHeader[0]
-        currentLine = inFile.readline()
+def buildCbrenneriDB(db=geneDB):
+    gffPath = "%s/download/PB2801_2007feb09.gff" % cisRoot # using EMS special version
+    chromoPath = "%s/download/PB2801_supercontigs.fa" % cisRoot
+    chromoOutPath = "/C_brenneri/"
 
-        while currentLine != "" and currentLine[0] != ">":
-            lineSeq = currentLine.strip()
-            seqLen += len(lineSeq)
-            seqArray.append(lineSeq)
-            currentLine = inFile.readline()
+    print "Creating database %s" % db
+    createDBFile(db)
 
-        seq = string.join(seqArray, "")
-        if seqLen < 100000:
-            print "Added contig %s to database" % chromID
-            cbGenome.addSequence(("cbrenneri", chromID), seq, "chromosome", str(seqLen))
-            cbGenome.addChromosomeEntry(chromID, chromID, "db")
-        else:
-            outFileName = "%s%s.bin" % (chromOutPath, chromID)
-            outFile = open( "%s%s" % (cisRoot, outFileName), "w")
-            outFile.write(seq)
-            outFile.close()
-            print "Added contig file %s to database" % outFileName
-            cbGenome.addChromosomeEntry(chromID, outFileName, "file")
+    print "Adding gene entries"
+    loadGeneEntries(db, gffPath)
 
-        header = currentLine
+    print "Adding feature entries"
+    loadFeatureEntries(db, gffPath)
 
-    inFile.close()
+    print "Loading genomic sequence"
+    loadChromosome(db, chromoPath, chromoOutPath)
+
+    print "Creating Indices"
+    createDBindices(db)
+
+    print "Finished creating database %s" % db
+
+
+def createDBFile(db):
+    cbGenome = Genome("cbrenneri", version="PB2801_001",  dbFile=db)
+    cbGenome.createGeneDB(db)
 
 
 def loadGeneEntries(db, gffFile):
@@ -164,34 +155,43 @@ def loadFeatureEntries(db, gffFile):
     cbGenome.addFeatureEntryBatch(featureEntries)
 
 
-def createDBFile(db):
-    cbGenome = Genome("cbrenneri", version="PB2801_001",  dbFile=db)
-    cbGenome.createGeneDB(db)
-
-
-def createDBindices(db):
-    cbGenome = Genome("cbrenneri", version="PB2801_001", dbFile=db)
-    cbGenome.createIndices()
-
-
-def buildCbrenneriDB(db=geneDB):
-    gffPath = "%s/download/PB2801_2007feb09.gff" % cisRoot # using EMS special version
-    chromoPath = "%s/download/PB2801_supercontigs.fa" % cisRoot
-    chromoOutPath = "/C_brenneri/"
+def loadChromosome(db, chromPath, chromOutPath):
+    seqArray = []
+    seqLen = 0
+    cbGenome = Genome("cbrenneri", dbFile=db)
+    inFile = open(chromPath, "r")
+    header = inFile.readline()
+    while header != "":
+        seqArray = []
+        seqLen = 0
+        chromHeader = header.strip()[1:].split()
+        chromID = chromHeader[0]
+        currentLine = inFile.readline()
 
-    print "Creating database %s" % db
-    createDBFile(db)
+        while currentLine != "" and currentLine[0] != ">":
+            lineSeq = currentLine.strip()
+            seqLen += len(lineSeq)
+            seqArray.append(lineSeq)
+            currentLine = inFile.readline()
 
-    print "Adding gene entries"
-    loadGeneEntries(db, gffPath)
+        seq = string.join(seqArray, "")
+        if seqLen < 100000:
+            print "Added contig %s to database" % chromID
+            cbGenome.addSequence(("cbrenneri", chromID), seq, "chromosome", str(seqLen))
+            cbGenome.addChromosomeEntry(chromID, chromID, "db")
+        else:
+            outFileName = "%s%s.bin" % (chromOutPath, chromID)
+            outFile = open( "%s%s" % (cisRoot, outFileName), "w")
+            outFile.write(seq)
+            outFile.close()
+            print "Added contig file %s to database" % outFileName
+            cbGenome.addChromosomeEntry(chromID, outFileName, "file")
 
-    print "Adding feature entries"
-    loadFeatureEntries(db, gffPath)
+        header = currentLine
 
-    print "Loading genomic sequence" 
-    loadChromosome(db, chromoPath, chromoOutPath)
+    inFile.close()
 
-    print "Creating Indices"
-    createDBindices(db)
 
-    print "Finished creating database %s" % db
\ No newline at end of file
+def createDBindices(db):
+    cbGenome = Genome("cbrenneri", version="PB2801_001", dbFile=db)
+    cbGenome.createIndices()