first pass cleanup of cistematic/genomes; change bamPreprocessing
[erange.git] / cistematic / genomes / spurpuratus.py
1 ###########################################################################
2 #                                                                         #
3 # C O P Y R I G H T   N O T I C E                                         #
4 #  Copyright (c) 2003-13 by:                                              #
5 #    * California Institute of Technology                                 #
6 #                                                                         #
7 #    All Rights Reserved.                                                 #
8 #                                                                         #
9 # Permission is hereby granted, free of charge, to any person             #
10 # obtaining a copy of this software and associated documentation files    #
11 # (the "Software"), to deal in the Software without restriction,          #
12 # including without limitation the rights to use, copy, modify, merge,    #
13 # publish, distribute, sublicense, and/or sell copies of the Software,    #
14 # and to permit persons to whom the Software is furnished to do so,       #
15 # subject to the following conditions:                                    #
16 #                                                                         #
17 # The above copyright notice and this permission notice shall be          #
18 # included in all copies or substantial portions of the Software.         #
19 #                                                                         #
20 # THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,         #
21 # EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF      #
22 # MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND                   #
23 # NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS     #
24 # BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN      #
25 # ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN       #
26 # CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE        #
27 # SOFTWARE.                                                               #
28 ###########################################################################
29 #
30 # data for Strongylocentrotus purpuratus
31 import string
32 from cistematic.genomes import Genome
33 from os import environ
34
35 if environ.get("CISTEMATIC_ROOT"):
36     cisRoot = environ.get("CISTEMATIC_ROOT")
37 else:
38     cisRoot = "/proj/genome"
39
40 geneDB = "%s/S_purpuratus/spurpuratus.genedb" % cisRoot
41
42
43 def buildSpurpuratusDB(db=geneDB):
44     chromoPath = "%s/download/Spur2.1_Nmasked.txt" % cisRoot
45     chromoOutPath = "/S_purpuratus/"
46
47     print "Creating database %s" % db
48     createDBFile(db)
49
50     print "Loading genomic sequence"
51     loadChromosome(db, chromoPath, chromoOutPath)
52
53     print "Creating Indices"
54     createDBindices(db)
55
56     print "Finished creating database %s" % db
57
58 def createDBFile(db):
59     spGenome = Genome("spurpuratus", version="2.1",  dbFile=db)
60     spGenome.createGeneDB(db)
61
62
63 def loadChromosome(db, chromPath, chromOutPath):
64     seqArray = []
65     seqLen = 0
66     spGenome = Genome("spurpuratus", dbFile=db)
67     inFile = open(chromPath, "r")
68     header = inFile.readline()
69     while header != "":
70         seqArray = []
71         seqLen = 0
72         fields = header.split()
73         if "purpuratus" in header:
74             idpart = fields[3]
75         else:
76             idpart = fields[-1].strip()
77
78         parts = idpart.split("_")
79         chromID = parts[-1]
80         currentLine = inFile.readline()
81         while currentLine != "" and currentLine[0] != ">":
82             lineSeq = currentLine.strip()
83             seqLen += len(lineSeq)
84             seqArray.append(lineSeq)
85             currentLine = inFile.readline()
86
87         seq = string.join(seqArray, "")
88         if seqLen < 50000:
89             print "Added contig %s to database" % chromID
90             spGenome.addSequence(("spurpuratus", chromID), seq, "chromosome", str(seqLen))
91             spGenome.addChromosomeEntry(chromID, chromID, "db")
92         else:
93             outFileName = "%s%s.bin" % (chromOutPath, chromID)
94             outFile = open("%s%s" % (cisRoot, outFileName), "w")
95             outFile.write(seq)
96             outFile.close()
97             print "Added contig file %s to database" % outFileName
98             spGenome.addChromosomeEntry(chromID, outFileName, "file")
99
100         header = currentLine
101
102     inFile.close()
103
104
105 def createDBindices(db):
106     spGenome = Genome("spurpuratus", version="2.1", dbFile=db)
107     spGenome.createIndices()