first pass cleanup of cistematic/genomes; change bamPreprocessing

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

diff --git a/cistematic/genomes/rnorvegicus.py b/cistematic/genomes/rnorvegicus.py
index b0fae70e721bc11e5046d9a15b4e34120144c16e..6f4c7bac981945074543d916bf5b6cf4d307fd39 100644 (file)
--- a/cistematic/genomes/rnorvegicus.py
+++ b/cistematic/genomes/rnorvegicus.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.                                                 #
@@ -34,36 +34,57 @@ from cistematic.core.geneinfo import geneinfoDB
 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/R_norvegicus/rnorvegicus.genedb" % cisRoot
 
 
-def loadChromosome(db, chromID, chromPath, chromOut):
-    seqArray = []
-    rnGenome = Genome("rnorvegicus", dbFile=db)
-    inFile = open(chromPath, "r")
-    line = inFile.readline()
-    for line in inFile:
-        seqArray.append(line.strip())
+def buildRatDB(db=geneDB, downloadDir="%s/download" % cisRoot):
+    genePath = "%s/seq_gene.md" % downloadDir
+    goDefPath = "%s/GO.terms_and_ids" % downloadDir
+    goPath = "%s/gene2go" % downloadDir
 
-    seq = string.join(seqArray, "")
-    seqLen = len(seq)
-    if seqLen < 1:
-        print "Problems reading sequence from file"
+    print "Creating database %s" % db
+    createDBFile(db)
 
-    print "writing to file %s" % chromOut
-    outFile = open("%s%s" % (cisRoot, chromOut), "w")
-    outFile.write(seq)
-    outFile.close()
-    rnGenome.addChromosomeEntry(chromID, chromOut, "file")
+    print "Adding gene entries"
+    loadGeneEntries(db, genePath)
+
+    print "Adding gene features"
+    loadGeneFeatures(db, genePath)
+
+    print "Adding gene annotations"
+    loadGeneAnnotations(db)
+
+    print "Adding gene ontology"
+    loadGeneOntology(db, goPath, goDefPath)
+
+    # ignoring all random chromosomes
+    chromList = ["1", "2", "3", "4", "5", "6", "7", "8", "9", "10",
+                 "11", "12", "13", "14", "15", "16", "17", "18", "19", "20",
+                 "Un", "X", "M"
+    ]
+    for chromID in chromList:
+        print "Loading chromosome %s" % chromID
+        chromPath = "%s/chr%s.fa" % (downloadDir, chromID)
+        loadChromosome(db, chromID, chromPath, "/R_norvegicus/chromo%s.bin" % chromID)
+
+    print "Creating Indices"
+    createDBindices(db)
+
+    print "Finished creating database %s" % db
+
+
+def createDBFile(db):
+    rnGenome = Genome("rnorvegicus",  dbFile=db)
+    rnGenome.createGeneDB(db)
 
 
 def loadGeneEntries(db, gFile):
-    """ FIXME - NEED TO DEAL WITH ALTERNATIVE SPLICING ENTRIES
-    """
+    #TODO: - NEED TO DEAL WITH ALTERNATIVE SPLICING ENTRIES
+
     geneEntries = []
     rnGenome = Genome("rnorvegicus", dbFile=db)
     geneFile = open(gFile, "r")
@@ -130,7 +151,7 @@ def loadGeneFeatures(db, gFile):
 
 def loadGeneAnnotations(db):
     geneAnnotations = []
-    idb = geneinfoDB()  
+    idb = geneinfoDB()
     rnGenome = Genome("rnorvegicus", dbFile=db)
     gidList = rnGenome.allGIDs()
     for locID in gidList:
@@ -176,7 +197,7 @@ def loadGeneOntology(db, goPath, goDefPath):
                 synonyms = idb.geneIDSynonyms(gID)
                 if len(synonyms) >0:
                     for entry in synonyms:
-                        gene_name += ","    
+                        gene_name += ","
                         gene_name += entry
                 else:
                     gene_name = " "
@@ -190,66 +211,26 @@ def loadGeneOntology(db, goPath, goDefPath):
     rnGenome.addGoInfoBatch(goArray)
 
 
-def createDBFile(db):
-    rnGenome = Genome("rnorvegicus",  dbFile=db)
-    rnGenome.createGeneDB(db)
-
-
-def createDBindices(db):
+def loadChromosome(db, chromID, chromPath, chromOut):
+    seqArray = []
     rnGenome = Genome("rnorvegicus", dbFile=db)
-    rnGenome.createIndices()
-
-
-def buildRatDB(db=geneDB, downloadDir="%s/download" % cisRoot):
-    genePath = "%s/seq_gene.md" % downloadDir
-    goDefPath = "%s/GO.terms_and_ids" % downloadDir
-    goPath = "%s/gene2go" % downloadDir
-    # ignoring all random chromosomes
-    chromos = {"1": "%s/chr1.fa" % downloadDir,
-               "2": "%s/chr2.fa" % downloadDir,
-               "3": "%s/chr3.fa" % downloadDir,
-               "4": "%s/chr4.fa" % downloadDir,
-               "5": "%s/chr5.fa" % downloadDir,
-               "6": "%s/chr6.fa" % downloadDir,
-               "7": "%s/chr7.fa" % downloadDir,
-               "8": "%s/chr8.fa" % downloadDir,
-               "9": "%s/chr9.fa" % downloadDir,
-               "10": "%s/chr10.fa" % downloadDir,
-               "11": "%s/chr11.fa" % downloadDir,
-               "12": "%s/chr12.fa" % downloadDir,
-               "13": "%s/chr13.fa" % downloadDir,
-               "14": "%s/chr14.fa" % downloadDir,
-               "15": "%s/chr15.fa" % downloadDir,
-               "16": "%s/chr16.fa" % downloadDir,
-               "17": "%s/chr17.fa" % downloadDir,
-               "18": "%s/chr18.fa" % downloadDir,
-               "19": "%s/chr19.fa" % downloadDir,
-               "Un": "%s/chrUn.fa" % downloadDir,
-               "X": "%s/chrX.fa" % downloadDir,
-               "20": "%s/chr20.fa" % downloadDir,
-               "M": "%s/chrM.fa" % downloadDir
-    }
-
-    print "Creating database %s" % db
-    createDBFile(db)
-
-    print "Adding gene entries"
-    loadGeneEntries(db, genePath)
-
-    print "Adding gene features"
-    loadGeneFeatures(db, genePath)
-
-    print "Adding gene annotations"
-    loadGeneAnnotations(db)
+    inFile = open(chromPath, "r")
+    line = inFile.readline()
+    for line in inFile:
+        seqArray.append(line.strip())
 
-    print "Adding gene ontology"
-    loadGeneOntology(db, goPath, goDefPath)
+    seq = string.join(seqArray, "")
+    seqLen = len(seq)
+    if seqLen < 1:
+        print "Problems reading sequence from file"
 
-    for chromID in chromos.keys():
-        print "Loading chromosome %s" % chromID
-        loadChromosome(db, chromID, chromos[chromID], "/R_norvegicus/chromo%s.bin" % chromID)
+    print "writing to file %s" % chromOut
+    outFile = open("%s%s" % (cisRoot, chromOut), "w")
+    outFile.write(seq)
+    outFile.close()
+    rnGenome.addChromosomeEntry(chromID, chromOut, "file")
 
-    print "Creating Indices"
-    createDBindices(db)
 
-    print "Finished creating database %s" % db
\ No newline at end of file
+def createDBindices(db):
+    rnGenome = Genome("rnorvegicus", dbFile=db)
+    rnGenome.createIndices()