--- /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 Equus Caballus
+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/E_caballus/ecaballus.genedb" % cisRoot
+
+
+def loadChromosome(db, chromID, chromPath, chromOut):
+ seqArray = []
+ ecGenome = Genome("ecaballus", dbFile=db)
+ inFile = open(chromPath, "r")
+ line = inFile.readline()
+ for line in inFile:
+ seqArray.append(line.strip())
+
+ seq = string.join(seqArray, "")
+ seqLen = len(seq)
+ if seqLen < 1:
+ print "Problems reading sequence from file"
+
+ print "writing to file %s" % chromOut
+ outFile = open("%s%s" % (cisRoot, chromOut), "w")
+ outFile.write(seq)
+ outFile.close()
+ ecGenome.addChromosomeEntry(chromID, chromOut, "file")
+
+
+def loadGeneEntries(db, gFile):
+ """ FIXME - NEED TO DEAL WITH ALTERNATIVE SPLICING ENTRIES
+ """
+ geneEntries = []
+ alreadySeen = []
+ ecGenome = Genome("ecaballus", dbFile=db)
+ geneFile = open(gFile, "r")
+ geneFile.readline()
+ for line in geneFile:
+ cols = line.split("\t")
+ if cols[11].strip() != "GENE":
+ continue
+
+ name = cols[10].split(":")
+ gid = name[1]
+ if gid == "" or gid in alreadySeen:
+ continue
+
+ alreadySeen.append(gid)
+ start = int(cols[2]) - 1
+ stop = int(cols[3]) - 1
+ sense = cols[4]
+ chrom = cols[1].strip()
+ if sense == "+":
+ sense = "F"
+ else:
+ sense = "R"
+
+ geneID = ("ecaballus", gid)
+ gidVersion = 1
+ geneEntries.append((geneID, chrom, start, stop, sense, "gene", gidVersion))
+
+ print "Adding %d gene entries" % len(geneEntries)
+ ecGenome.addGeneEntryBatch(geneEntries)
+
+
+def loadGeneFeatures(db, gFile):
+ """ Load gene features such as CDS, UTR, and PSEUDO from the gene file.
+ """
+ featureEntries = []
+ ecGenome = Genome("ecaballus", dbFile=db)
+ featureFile = open(gFile, "r")
+ featureFile.readline()
+ for line in featureFile:
+ cols = line.split("\t")
+ if cols[11].strip() not in ["CDS", "UTR", "PSEUDO"]:
+ continue
+
+ fType = cols[11]
+ name = cols[10].split(":")
+ gid = name[1]
+ if gid == "":
+ continue
+
+ start = int(cols[2]) - 1
+ stop = int(cols[3]) - 1
+ sense = cols[4]
+ chrom = cols[1].strip()
+ if sense == "+":
+ sense = "F"
+ else:
+ sense = "R"
+
+ geneID = ("ecaballus", gid)
+ gidVersion = 1
+ featureEntries.append((geneID, gidVersion, chrom, start, stop, sense, fType))
+
+ print "Adding %d feature entries" % len(featureEntries)
+ ecGenome.addFeatureEntryBatch(featureEntries)
+
+
+def createDBFile(db):
+ ecGenome = Genome("ecaballus", dbFile=db)
+ ecGenome.createGeneDB(db)
+
+
+def createDBindices(db):
+ ecGenome = Genome("ecaballus", dbFile=db)
+ ecGenome.createIndices()
+
+
+def buildHorseDB(db=geneDB):
+ genePath = "%s/download/seq_gene.md" % cisRoot
+ chromos = {"1": "%s/download/chr1.fa" % cisRoot,
+ "2": "%s/download/chr2.fa" % cisRoot,
+ "3": "%s/download/chr3.fa" % cisRoot,
+ "4": "%s/download/chr4.fa" % cisRoot,
+ "5": "%s/download/chr5.fa" % cisRoot,
+ "6": "%s/download/chr6.fa" % cisRoot,
+ "7": "%s/download/chr7.fa" % cisRoot,
+ "8": "%s/download/chr8.fa" % cisRoot,
+ "9": "%s/download/chr9.fa" % cisRoot,
+ "10": "%s/download/chr10.fa" % cisRoot,
+ "11": "%s/download/chr11.fa" % cisRoot,
+ "12": "%s/download/chr12.fa" % cisRoot,
+ "13": "%s/download/chr13.fa" % cisRoot,
+ "14": "%s/download/chr14.fa" % cisRoot,
+ "15": "%s/download/chr15.fa" % cisRoot,
+ "16": "%s/download/chr16.fa" % cisRoot,
+ "17": "%s/download/chr17.fa" % cisRoot,
+ "18": "%s/download/chr18.fa" % cisRoot,
+ "19": "%s/download/chr19.fa" % cisRoot,
+ "20": "%s/download/chr20.fa" % cisRoot,
+ "21": "%s/download/chr21.fa" % cisRoot,
+ "22": "%s/download/chr22.fa" % cisRoot,
+ "23": "%s/download/chr23.fa" % cisRoot,
+ "24": "%s/download/chr24.fa" % cisRoot,
+ "25": "%s/download/chr25.fa" % cisRoot,
+ "26": "%s/download/chr26.fa" % cisRoot,
+ "27": "%s/download/chr27.fa" % cisRoot,
+ "28": "%s/download/chr28.fa" % cisRoot,
+ "29": "%s/download/chr29.fa" % cisRoot,
+ "30": "%s/download/chr30.fa" % cisRoot,
+ "31": "%s/download/chr31.fa" % cisRoot,
+ "M": "%s/download/chrM.fa" % cisRoot,
+ "X": "%s/download/chrX.fa" % cisRoot,
+ "Un": "%s/download/chrUn.fa" % cisRoot
+ }
+
+ print "Creating database %s" % db
+ createDBFile(db)
+
+ print "Adding gene entries"
+ loadGeneEntries(db, genePath)
+
+ print "Adding gene features"
+ loadGeneFeatures(db, genePath)
+
+ for chromID in chromos.keys():
+ print "Loading chromosome %s" % chromID
+ loadChromosome(db, chromID, chromos[chromID], "/E_caballus/chromo%s.bin" % chromID)
+
+ print "Creating Indices"
+ createDBindices(db)
+
+ print "Finished creating database %s" % db
\ No newline at end of file
projects / erange.git / blobdiff