|
6
|
1 #
|
|
|
2 # Copyright INRA-URGI 2009-2010
|
|
|
3 #
|
|
|
4 # This software is governed by the CeCILL license under French law and
|
|
|
5 # abiding by the rules of distribution of free software. You can use,
|
|
|
6 # modify and/ or redistribute the software under the terms of the CeCILL
|
|
|
7 # license as circulated by CEA, CNRS and INRIA at the following URL
|
|
|
8 # "http://www.cecill.info".
|
|
|
9 #
|
|
|
10 # As a counterpart to the access to the source code and rights to copy,
|
|
|
11 # modify and redistribute granted by the license, users are provided only
|
|
|
12 # with a limited warranty and the software's author, the holder of the
|
|
|
13 # economic rights, and the successive licensors have only limited
|
|
|
14 # liability.
|
|
|
15 #
|
|
|
16 # In this respect, the user's attention is drawn to the risks associated
|
|
|
17 # with loading, using, modifying and/or developing or reproducing the
|
|
|
18 # software by the user in light of its specific status of free software,
|
|
|
19 # that may mean that it is complicated to manipulate, and that also
|
|
|
20 # therefore means that it is reserved for developers and experienced
|
|
|
21 # professionals having in-depth computer knowledge. Users are therefore
|
|
|
22 # encouraged to load and test the software's suitability as regards their
|
|
|
23 # requirements in conditions enabling the security of their systems and/or
|
|
|
24 # data to be ensured and, more generally, to use and operate it in the
|
|
|
25 # same conditions as regards security.
|
|
|
26 #
|
|
|
27 # The fact that you are presently reading this means that you have had
|
|
|
28 # knowledge of the CeCILL license and that you accept its terms.
|
|
|
29 #
|
|
|
30 from SMART.Java.Python.structure.Transcript import Transcript
|
|
|
31 from SMART.Java.Python.mySql.MySqlTable import MySqlTable
|
|
|
32 from SMART.Java.Python.structure.Interval import Interval
|
|
|
33 from SMART.Java.Python.misc.Progress import Progress
|
|
|
34
|
|
|
35
|
|
|
36 class TranscriptList(object):
|
|
|
37 """A class that codes for a list of transcript"""
|
|
|
38
|
|
|
39 def __init__(self, verbosity = 0):
|
|
|
40 self.transcripts = dict()
|
|
|
41 self.longestTranscript = 0
|
|
|
42 self.verbosity = verbosity
|
|
|
43
|
|
|
44
|
|
|
45 def getTranscript(self, chromosome, index):
|
|
|
46 return self.transcripts[chromosome][index]
|
|
|
47
|
|
|
48
|
|
|
49 def getChromosomes(self):
|
|
|
50 return self.transcripts.keys()
|
|
|
51
|
|
|
52
|
|
|
53 def getTranscriptsOnChromosome(self, chromosome):
|
|
|
54 if chromosome not in self.transcripts:
|
|
|
55 return []
|
|
|
56 return self.transcripts[chromosome]
|
|
|
57
|
|
|
58
|
|
|
59 def addTranscript(self, transcript):
|
|
|
60 if transcript.getChromosome() in self.transcripts:
|
|
|
61 self.transcripts[transcript.getChromosome()].append(transcript)
|
|
|
62 else:
|
|
|
63 self.transcripts[transcript.getChromosome()] = [transcript]
|
|
|
64 self.longestTranscript = max(self.longestTranscript, transcript.getEnd() - transcript.getStart())
|
|
|
65
|
|
|
66
|
|
|
67 def removeTranscript(self, chromosome, i):
|
|
|
68 del self.transcripts[chromosome][i]
|
|
|
69
|
|
|
70
|
|
|
71 def removeAll(self):
|
|
|
72 self.transcripts = {}
|
|
|
73
|
|
|
74
|
|
|
75 def getNbTranscripts(self):
|
|
|
76 nbTranscripts = 0
|
|
|
77 for chromosome in self.transcripts:
|
|
|
78 nbTranscripts += len(self.transcripts[chromosome])
|
|
|
79 return nbTranscripts
|
|
|
80
|
|
|
81
|
|
|
82 def getSize(self):
|
|
|
83 size = 0
|
|
|
84 for chromosome in self.transcripts:
|
|
|
85 for transcript in self.transcripts[chromosome]:
|
|
|
86 size += transcript.getSize()
|
|
|
87 return size
|
|
|
88
|
|
|
89
|
|
|
90 def sort(self):
|
|
|
91 for chromosome in self.transcripts:
|
|
|
92 self.transcripts[chromosome].sort(lambda x, y: x.getStart() - y.getStart())
|
|
|
93
|
|
|
94
|
|
|
95 def removeOverlapWith(self, transcriptList):
|
|
|
96 transcriptList.sort()
|
|
|
97 for chromosome in self.transcripts:
|
|
|
98 progress = Progress(len(self.transcripts[chromosome]), "Handling chromosome %s" % (chromosome), self.verbosity)
|
|
|
99 for thisTranscriptId in range(len(self.transcripts[chromosome])):
|
|
|
100 progress.inc()
|
|
|
101 for thatTranscriptId in range(len(transcriptList.transcripts[chromosome])):
|
|
|
102 if self.transcripts[chromosome][thisTranscriptId].overlapWith(transcriptList.transcripts[chromosome][thatTranscriptId]):
|
|
|
103 self.transcripts[chromosome][thisTranscriptId] = None
|
|
|
104 break
|
|
|
105 if self.transcripts[chromosome][thisTranscriptId].getEnd() > transcriptList.transcripts[chromosome][thatTranscriptId]:
|
|
|
106 break
|
|
|
107 self.transcripts[chromosome] = [transcript for transcript in self.transcripts[chromosome] if transcript != None]
|
|
|
108 progress.done()
|
|
|
109
|
|
|
110
|
|
|
111 def removeOverlapWithExon(self, transcriptList):
|
|
|
112 transcriptList.sort()
|
|
|
113 for chromosome in self.transcripts:
|
|
|
114 progress = Progress(len(self.transcripts[chromosome]), "Handling chromosome %s" % (chromosome), self.verbosity)
|
|
|
115 for thisTranscriptId in range(len(self.transcripts[chromosome])):
|
|
|
116 progress.inc()
|
|
|
117 for thatTranscriptId in range(len(transcriptList.transcripts[chromosome])):
|
|
|
118 if self.transcripts[chromosome][thisTranscriptId].overlapWithExon(transcriptList.transcripts[chromosome][thatTranscriptId]):
|
|
|
119 self.transcripts[chromosome][thisTranscriptId] = None
|
|
|
120 break
|
|
|
121 if self.transcripts[chromosome][thisTranscriptId].getEnd() > transcriptList.transcripts[chromosome][thatTranscriptId]:
|
|
|
122 break
|
|
|
123 self.transcripts[chromosome] = [transcript for transcript in self.transcripts[chromosome] if transcript != None]
|
|
|
124 progress.done()
|
|
|
125
|
|
|
126
|
|
|
127 def setDefaultTagValue(self, name, value):
|
|
|
128 for transcript in self.getIterator():
|
|
|
129 transcript.setTag(name, value)
|
|
|
130
|
|
|
131
|
|
|
132 def storeDatabase(self, mySqlConnection):
|
|
|
133 transcriptsTable = MySqlTable("TmpTranscriptsTable", mySqlConnection)
|
|
|
134 transcriptsTable.create(Transcript.getSqlVariables(), Transcript.getSqlTypes())
|
|
|
135 intervalsVariables = Interval.getSqlVariables()
|
|
|
136 intervalsVariables.append("idTranscript")
|
|
|
137 intervalsTypes = Interval.getSqlTypes()
|
|
|
138 intervalsTypes["idTranscript"] = "int"
|
|
|
139 intervalsTable = MySqlTable("TmpIntervalsTable", mySqlConnection)
|
|
|
140 intervalsTable.create(intervalsVariables, intervalsTypes)
|
|
|
141 for chromosome in self.transcripts:
|
|
|
142 for transcript in self.transcripts[chromosome]:
|
|
|
143 idTranscript = transcriptsTable.addLine(transcript.getSqlValues())
|
|
|
144 for exon in transcript.getExons():
|
|
|
145 intervalValues = exon.getSqlValues()
|
|
|
146 intervalValues["idTranscript"] = idTranscript
|
|
|
147 intervalsTable.addLine(intervalValues)
|
|
|
148
|
|
|
149
|
|
|
150 def getIterator(self):
|
|
|
151 chromosomes = self.transcripts.keys()
|
|
|
152 currentChromosome = 0
|
|
|
153 currentTranscript = 0
|
|
|
154 while True:
|
|
|
155 if currentChromosome >= len(chromosomes):
|
|
|
156 return
|
|
|
157 elif currentTranscript >= len(self.transcripts[chromosomes[currentChromosome]]):
|
|
|
158 currentTranscript = 0
|
|
|
159 currentChromosome += 1
|
|
|
160 elif self.transcripts[chromosomes[currentChromosome]][currentTranscript] == None:
|
|
|
161 currentTranscript += 1
|
|
|
162 else:
|
|
|
163 yield self.transcripts[chromosomes[currentChromosome]][currentTranscript]
|
|
|
164 currentTranscript += 1
|
|
|
165
|
|
|
166
|
|
|
167 def __str__(self):
|
|
|
168 string = ""
|
|
|
169 for transcript in self.getIterator():
|
|
|
170 string += str(transcript)
|
|
|
171 return string
|
|
|
172
|
