###########################################################################
# #
# 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. #
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/M_musculus/mmusculus.genedb" % cisRoot
-def loadChromosome(db, chromID, chromPath, chromOut):
- seqArray = []
- mmGenome = Genome("mmusculus", dbFile=db)
- inFile = open(chromPath, "r")
- line = inFile.readline()
- for line in inFile:
- seqArray.append(line.strip())
+def buildMmusculusDB(db=geneDB, downloadDir="%s/download" % cisRoot):
+ genePath = "%s/seq_gene.md" % downloadDir # ftp://ftp.ncbi.nih.gov/genomes/M_musculus/mapview/seq_gene.md
+ goDefPath = "%s/GO.terms_and_ids" % downloadDir # ftp://ftp.geneontology.org/pub/go/doc/GO.terms_and_ids
+ goPath = "%s/gene2go" % downloadDir # ftp://ftp.ncbi.nih.gov/gene/DATA/gene2go.gz
+ # chromosomes are from ftp://hgdownload.cse.ucsc.edu/goldenPath/mm9/chromosomes
+ # but ignoring all random chromosomes
+ chromList = ["1", "2", "3", "4", "5", "6", "7", "8", "9", "10",
+ "11", "12", "13", "14", "15", "16", "17", "18", "19",
+ "X", "Y", "M"
+ ]
- 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()
- mmGenome.addChromosomeEntry(chromID, chromOut, "file")
+ print "Adding gene entries"
+ loadGeneEntries(db, genePath, chromList)
+
+ print "Adding gene features"
+ loadGeneFeatures(db, genePath, chromList)
+
+ print "Adding gene annotations"
+ loadGeneAnnotations(db)
+
+ print "Adding gene ontology"
+ loadGeneOntology(db, goPath, goDefPath)
+
+ for chromID in chromList:
+ print "Loading chromosome %s" % chromID
+ chromPath = "%s/chr%s.fa" % (downloadDir, chromID)
+ loadChromosome(db, chromID, chromPath, "/M_musculus/chromo%s.bin" % chromID)
+
+ print "Creating Indices"
+ createDBindices(db)
+
+ print "Finished creating database %s" % db
+
+
+def createDBFile(db):
+ mmGenome = Genome("mmusculus", dbFile=db)
+ mmGenome.createGeneDB(db)
def loadGeneEntries(db, gFile, cDict):
- """ FIXME - NEED TO DEAL WITH ALTERNATIVE SPLICING ENTRIES
- """
+ #TODO: - NEED TO DEAL WITH ALTERNATIVE SPLICING ENTRIES
+
geneEntries = []
alreadySeen = []
mmGenome = Genome("mmusculus", dbFile=db)
synonyms = idb.geneIDSynonyms(gID)
if len(synonyms) >0:
for entry in synonyms:
- gene_name += ","
+ gene_name += ","
gene_name += entry
else:
gene_name = " "
mmGenome.addGoInfoBatch(goArray)
-def createDBFile(db):
- mmGenome = Genome("mmusculus", dbFile=db)
- mmGenome.createGeneDB(db)
-
-
-def createDBindices(db):
+def loadChromosome(db, chromID, chromPath, chromOut):
+ seqArray = []
mmGenome = Genome("mmusculus", dbFile=db)
- mmGenome.createIndices()
-
-
-def buildMmusculusDB(db=geneDB, downloadDir="%s/download" % cisRoot):
- genePath = "%s/seq_gene.md" % downloadDir # ftp://ftp.ncbi.nih.gov/genomes/M_musculus/mapview/seq_gene.md
- goDefPath = "%s/GO.terms_and_ids" % downloadDir # ftp://ftp.geneontology.org/pub/go/doc/GO.terms_and_ids
- goPath = "%s/gene2go" % downloadDir # ftp://ftp.ncbi.nih.gov/gene/DATA/gene2go.gz
- # chromosomes are from ftp://hgdownload.cse.ucsc.edu/goldenPath/mm9/chromosomes
- # but ignoring all random chromosomes
- chromDict = {"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,
- "X": "%s/chrX.fa" % downloadDir,
- "Y": "%s/chrY.fa" % downloadDir,
- "M": "%s/chrM.fa" % downloadDir
- }
-
- print "Creating database %s" % db
- createDBFile(db)
-
- print "Adding gene entries"
- loadGeneEntries(db, genePath, chromDict)
-
- print "Adding gene features"
- loadGeneFeatures(db, genePath, chromDict)
-
- 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 chromDict.keys():
- print "Loading chromosome %s" % chromID
- loadChromosome(db, chromID, chromDict[chromID], "/M_musculus/chromo%s.bin" % chromID)
+ print "writing to file %s" % chromOut
+ outFile = open("%s%s" % (cisRoot, chromOut), "w")
+ outFile.write(seq)
+ outFile.close()
+ mmGenome.addChromosomeEntry(chromID, chromOut, "file")
- print "Creating Indices"
- createDBindices(db)
- print "Finished creating database %s" % db
\ No newline at end of file
+def createDBindices(db):
+ mmGenome = Genome("mmusculus", dbFile=db)
+ mmGenome.createIndices()