--- /dev/null
+###########################################################################
+# #
+# C O P Y R I G H T N O T I C E #
+# Copyright (c) 2003-10 by: #
+# * California Institute of Technology #
+# #
+# All Rights Reserved. #
+# #
+# Permission is hereby granted, free of charge, to any person #
+# obtaining a copy of this software and associated documentation files #
+# (the "Software"), to deal in the Software without restriction, #
+# including without limitation the rights to use, copy, modify, merge, #
+# publish, distribute, sublicense, and/or sell copies of the Software, #
+# and to permit persons to whom the Software is furnished to do so, #
+# subject to the following conditions: #
+# #
+# The above copyright notice and this permission notice shall be #
+# included in all copies or substantial portions of the Software. #
+# #
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, #
+# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF #
+# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND #
+# NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS #
+# BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN #
+# ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN #
+# CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE #
+# SOFTWARE. #
+###########################################################################
+#
+# data for Caenorhaditis briggsae
+import string
+from cistematic.genomes import Genome
+from os import environ
+
+if environ.get("CISTEMATIC_ROOT"):
+ cisRoot = environ.get("CISTEMATIC_ROOT")
+else:
+ cisRoot = "/proj/genome"
+
+geneDB = "%s/C_briggsae/cbriggsae.genedb" % cisRoot
+
+
+def loadChromosome(db, chromPath, chromOutPath):
+ seqArray = []
+ seqLen = 0
+ cbGenome = Genome("cbriggsae", dbFile=db)
+ inFile = open(chromPath, "r")
+ header = inFile.readline()
+ while header != "":
+ seqArray = []
+ seqLen = 0
+ chromID = header.strip()[1:]
+ currentLine = inFile.readline()
+ while currentLine != "" and currentLine[0] != ">":
+ lineSeq = currentLine.strip()
+ seqLen += len(lineSeq)
+ seqArray.append(lineSeq)
+ currentLine = inFile.readline()
+
+ seq = string.join(seqArray, "")
+ if seqLen < 900000:
+ print "Added contig %s to database" % chromID
+ cbGenome.addSequence(("cbriggsae", 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")
+
+ header = currentLine
+
+ inFile.close()
+
+
+def loadGeneEntries(db, gffFile):
+ cbGenome = Genome("cbriggsae", dbFile=db)
+ geneFile = open(gffFile, "r")
+ geneEntries = []
+ geneAnnotations = []
+ for line in geneFile:
+ field = line[:-1].split("\t")
+ if field[1] != "hybrid":
+ continue
+
+ if field[2] != "CDS":
+ continue
+
+ annot = field[8].split('"')
+ gid = annot[1]
+ geneID = ("cbriggsae", gid)
+ annotation = string.join(annot[3:], "")
+ gidVersion = 1
+ try:
+ gidVersion = giddots[2]
+ except:
+ pass
+
+ start = int(field[3]) - 1
+ stop = int(field[4]) - 1
+ sense = field[6]
+ chrom = field[0].strip()
+ if sense == "+":
+ sense = "F"
+ else:
+ sense = "R"
+
+ if (geneID, chrom, start, stop, sense, "CDS", gidVersion) not in geneEntries:
+ geneEntries.append((geneID, chrom, start, stop, sense, "CDS", gidVersion))
+ if (geneID, annotation) not in geneAnnotations:
+ geneAnnotations.append((geneID, annotation))
+
+ print "Adding %d gene entries" % len(geneEntries)
+ cbGenome.addGeneEntryBatch(geneEntries)
+
+ print "Adding %d annotations" % len(geneAnnotations)
+ cbGenome.addAnnotationBatch(geneAnnotations)
+
+
+def loadFeatureEntries(db, gffFile):
+ cbGenome = Genome("cbriggsae", dbFile=db)
+ featureFile = open(gffFile, "r")
+ featureEntries = []
+ seenFeatures = {}
+ featureTranslation = {"coding_exon": "CDS",
+ "three_prime_UTR": "3UTR",
+ "five_prime_UTR": "5UTR"
+ }
+
+ for line in featureFile:
+ field = line.split("\t")
+ if field[1] != "hybrid":
+ continue
+
+ if field[2].strip() not in featureTranslation:
+ continue
+
+ featureType = featureTranslation[field[2].strip()]
+ gidrev = field[8].split('"')
+ gid = gidrev[1]
+ geneID = ("cbriggsae", gid)
+ gidVersion = 1
+ start = int(field[3]) - 1
+ stop = int(field[4]) - 1
+ sense = field[6]
+ chrom = field[0].strip()
+ if sense == "+":
+ sense = "F"
+ else:
+ sense = "R"
+
+ if geneID not in seenFeatures:
+ seenFeatures[geneID] = []
+ if (gidVersion, start, stop, featureType) not in seenFeatures[geneID]:
+ featureEntries.append((geneID, gidVersion, chrom, start, stop, sense, featureType))
+ seenFeatures[geneID].append((gidVersion, start, stop, featureType))
+
+ print "Adding %d feature entries" % len(featureEntries)
+ cbGenome.addFeatureEntryBatch(featureEntries)
+
+
+def createDBFile(db):
+ cbGenome = Genome("cbriggsae", version="CB25", dbFile=db)
+ cbGenome.createGeneDB(db)
+
+
+def createDBindices(db):
+ cbGenome = Genome("cbriggsae", version="CB25", dbFile=db)
+ cbGenome.createIndices()
+
+
+def buildCbriggsaeDB(db=geneDB):
+ gffPath = "%s/download/briggsae_25.WS132.gff" % cisRoot
+ chromoPath = "%s/download/briggsae_25.fa" % cisRoot
+ chromoOutPath = "/C_briggsae/"
+
+ print "Creating database %s" % db
+ createDBFile(db)
+
+ print "Adding gene entries"
+ loadGeneEntries(db, gffPath)
+
+ print "Adding feature entries"
+ loadFeatureEntries(db, gffPath)
+
+ print "Loading genomic sequence"
+ loadChromosome(db, chromoPath, chromoOutPath)
+
+ print "Creating Indices"
+ createDBindices(db)
+
+ print "Finished creating database %s" % db
\ No newline at end of file