--- /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 Strongylocentrotus purpuratus
+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/S_purpuratus/spurpuratus.genedb" % cisRoot
+
+
+def loadChromosome(db, chromPath, chromOutPath):
+ seqArray = []
+ seqLen = 0
+ spGenome = Genome("spurpuratus", dbFile=db)
+ inFile = open(chromPath, "r")
+ header = inFile.readline()
+ while header != "":
+ seqArray = []
+ seqLen = 0
+ fields = header.split()
+ if "purpuratus" in header:
+ idpart = fields[3]
+ else:
+ idpart = fields[-1].strip()
+
+ parts = idpart.split("_")
+ chromID = parts[-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 < 50000:
+ print "Added contig %s to database" % chromID
+ spGenome.addSequence(("spurpuratus", chromID), seq, "chromosome", str(seqLen))
+ spGenome.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
+ spGenome.addChromosomeEntry(chromID, outFileName, "file")
+
+ header = currentLine
+
+ inFile.close()
+
+
+def createDBFile(db):
+ spGenome = Genome("spurpuratus", version="2.1", dbFile=db)
+ spGenome.createGeneDB(db)
+
+
+def createDBindices(db):
+ spGenome = Genome("spurpuratus", version="2.1", dbFile=db)
+ spGenome.createIndices()
+
+
+def buildSpurpuratusDB(db=geneDB):
+ chromoPath = "%s/download/Spur2.1_Nmasked.txt" % cisRoot
+ chromoOutPath = "/S_purpuratus/"
+
+ print "Creating database %s" % db
+ createDBFile(db)
+
+ 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