|
6
|
1 #! /usr/bin/env python
|
|
|
2 #
|
|
|
3 # Copyright INRA-URGI 2009-2010
|
|
|
4 #
|
|
|
5 # This software is governed by the CeCILL license under French law and
|
|
|
6 # abiding by the rules of distribution of free software. You can use,
|
|
|
7 # modify and/ or redistribute the software under the terms of the CeCILL
|
|
|
8 # license as circulated by CEA, CNRS and INRIA at the following URL
|
|
|
9 # "http://www.cecill.info".
|
|
|
10 #
|
|
|
11 # As a counterpart to the access to the source code and rights to copy,
|
|
|
12 # modify and redistribute granted by the license, users are provided only
|
|
|
13 # with a limited warranty and the software's author, the holder of the
|
|
|
14 # economic rights, and the successive licensors have only limited
|
|
|
15 # liability.
|
|
|
16 #
|
|
|
17 # In this respect, the user's attention is drawn to the risks associated
|
|
|
18 # with loading, using, modifying and/or developing or reproducing the
|
|
|
19 # software by the user in light of its specific status of free software,
|
|
|
20 # that may mean that it is complicated to manipulate, and that also
|
|
|
21 # therefore means that it is reserved for developers and experienced
|
|
|
22 # professionals having in-depth computer knowledge. Users are therefore
|
|
|
23 # encouraged to load and test the software's suitability as regards their
|
|
|
24 # requirements in conditions enabling the security of their systems and/or
|
|
|
25 # data to be ensured and, more generally, to use and operate it in the
|
|
|
26 # same conditions as regards security.
|
|
|
27 #
|
|
|
28 # The fact that you are presently reading this means that you have had
|
|
|
29 # knowledge of the CeCILL license and that you accept its terms.
|
|
|
30 #
|
|
|
31 """Get the distance between the transcripts of two lists"""
|
|
|
32
|
|
|
33 import os
|
|
|
34 import sys
|
|
|
35 from optparse import OptionParser
|
|
|
36 from SMART.Java.Python.structure.TranscriptListsComparator import TranscriptListsComparator
|
|
|
37 from SMART.Java.Python.structure.TranscriptContainer import TranscriptContainer
|
|
|
38 from SMART.Java.Python.misc.RPlotter import RPlotter
|
|
|
39 from commons.core.writer.Gff3Writer import Gff3Writer
|
|
|
40
|
|
|
41 class GetDistance(object):
|
|
|
42
|
|
|
43 def __init__(self, verbosity = 0):
|
|
|
44 self.verbosity = verbosity
|
|
|
45 self.writer = None
|
|
|
46 self.spearman = False
|
|
|
47 self.tlc = TranscriptListsComparator(None, self.verbosity)
|
|
|
48 self.strands = (0, )
|
|
|
49 self.buckets = None
|
|
|
50 self.title = ""
|
|
|
51 self.xMin = None
|
|
|
52 self.xMax = None
|
|
|
53 self.proportion = False
|
|
|
54 self.outputFileName = None
|
|
|
55 self.keep = False
|
|
|
56
|
|
|
57 def __del__(self):
|
|
|
58 pass
|
|
|
59
|
|
|
60 def setQueryFile(self, fileName, format):
|
|
|
61 self.transcriptContainer1 = TranscriptContainer(fileName, format, self.verbosity)
|
|
|
62
|
|
|
63 def setReferenceFile(self, fileName, format):
|
|
|
64 self.transcriptContainer2 = TranscriptContainer(fileName, format, self.verbosity)
|
|
|
65
|
|
|
66 def setOutputFile(self, fileName):
|
|
|
67 self.outputFileName = fileName
|
|
|
68
|
|
|
69 def setOutputTranscriptFile(self, fileName):
|
|
|
70 if fileName != None:
|
|
|
71 self.writer = Gff3Writer(fileName, self.verbosity)
|
|
|
72
|
|
|
73 def restrictQueryToStart(self, number):
|
|
|
74 self.tlc.restrictToStart(self.tlc.QUERY, number)
|
|
|
75
|
|
|
76 def restrictReferenceToStart(self, number):
|
|
|
77 self.tlc.restrictToStart(self.tlc.REFERENCE, number)
|
|
|
78
|
|
|
79 def restrictQueryToEnd(self, number):
|
|
|
80 self.tlc.restrictToEnd(self.tlc.QUERY, number)
|
|
|
81
|
|
|
82 def restrictReferenceToEnd(self, number):
|
|
|
83 self.tlc.restrictToEnd(self.tlc.REFERENCE, number)
|
|
|
84
|
|
|
85 def setAbsolute(self, boolean):
|
|
|
86 self.tlc.setAbsolute(boolean)
|
|
|
87
|
|
|
88 def setProportion(self, boolean):
|
|
|
89 self.proportion = boolean
|
|
|
90
|
|
|
91 def setColinear(self, boolean):
|
|
|
92 self.tlc.getColinearOnly(boolean)
|
|
|
93
|
|
|
94 def setAntisense(self, boolean):
|
|
|
95 self.tlc.getAntisenseOnly(boolean)
|
|
|
96
|
|
|
97 def setDistances(self, minDistance, maxDistance):
|
|
|
98 self.tlc.setMinDistance(minDistance)
|
|
|
99 self.tlc.setMaxDistance(maxDistance)
|
|
|
100
|
|
|
101 def setStrands(self, boolean):
|
|
|
102 self.tlc.setStrandedDistance(boolean)
|
|
|
103 if boolean:
|
|
|
104 self.strands = (-1, 1)
|
|
|
105
|
|
|
106 def setUpstream(self, number):
|
|
|
107 self.tlc.setUpstream(self.tlc.REFERENCE, number)
|
|
|
108
|
|
|
109 def setDownstream(self, number):
|
|
|
110 self.tlc.setDownstream(self.tlc.REFERENCE, number)
|
|
|
111
|
|
|
112 def setBuckets(self, number):
|
|
|
113 self.buckets = number
|
|
|
114
|
|
|
115 def setTitle(self, title):
|
|
|
116 self.title = title
|
|
|
117
|
|
|
118 def setXValues(self, xMin, xMax):
|
|
|
119 self.xMin, self.xMax = xMin, xMax
|
|
|
120
|
|
|
121 def keepTmpValues(self, boolean):
|
|
|
122 self.keep = boolean
|
|
|
123
|
|
|
124 def getSpearman(self, boolean):
|
|
|
125 self.spearman = True
|
|
|
126
|
|
|
127 def compare(self):
|
|
|
128 self.tlc.setInputTranscriptContainer(self.tlc.QUERY, self.transcriptContainer1)
|
|
|
129 self.tlc.setInputTranscriptContainer(self.tlc.REFERENCE, self.transcriptContainer2)
|
|
|
130 self.tlc.setOutputWriter(self.writer)
|
|
|
131 self.distances = self.tlc.compareTranscriptListDistance()
|
|
|
132
|
|
|
133 def checkEmptyDistances(self):
|
|
|
134 return (sum([len(self.distances[strand].keys()) for strand in self.strands]) == 0)
|
|
|
135
|
|
|
136 def setPlotterMinusStrand(self):
|
|
|
137 if -1 in self.strands:
|
|
|
138 for x, y in self.distances[-1].iteritems():
|
|
|
139 self.distances[-1][x] = -y
|
|
|
140
|
|
|
141 def setPlotterProportion(self):
|
|
|
142 if not self.proportion:
|
|
|
143 return
|
|
|
144 self.nbElements = sum([abs(sum(self.distances[strand].values())) for strand in self.strands])
|
|
|
145 for strand in self.strands:
|
|
|
146 self.distances[strand] = dict([(distance, float(nb) / self.nbElements * 100) for distance, nb in self.distances[strand].iteritems()])
|
|
|
147
|
|
|
148 def setPlotter(self):
|
|
|
149 self.plotter = RPlotter(self.outputFileName, self.verbosity, self.keep)
|
|
|
150 if self.buckets != None:
|
|
|
151 self.plotter.setBarplot(True)
|
|
|
152 self.plotter.setFill(0)
|
|
|
153 self.plotter.setXLabel("distance")
|
|
|
154 self.plotter.setYLabel("# elements")
|
|
|
155 if self.proportion:
|
|
|
156 self.plotter.setYLabel("%% elements (%d in toto)" % (self.nbElements))
|
|
|
157 self.plotter.setBuckets(self.buckets)
|
|
|
158 self.plotter.setMinimumX(self.xMin)
|
|
|
159 self.plotter.setMaximumX(self.xMax)
|
|
|
160 self.plotter.setTitle(self.title)
|
|
|
161
|
|
|
162 def plot(self):
|
|
|
163 if len(self.strands) == 1:
|
|
|
164 self.distances = {0: self.distances}
|
|
|
165 if self.checkEmptyDistances():
|
|
|
166 print "No output."
|
|
|
167 sys.exit()
|
|
|
168 self.setPlotterMinusStrand()
|
|
|
169 self.setPlotterProportion()
|
|
|
170 if self.outputFileName == None:
|
|
|
171 return
|
|
|
172 self.setPlotter()
|
|
|
173 for strand in self.strands:
|
|
|
174 self.plotter.addLine(self.distances[strand])
|
|
|
175 self.plotter.plot()
|
|
|
176
|
|
|
177 def printSpearman(self):
|
|
|
178 if self.spearman:
|
|
|
179 print "Spearman's rho: %.5f" % (self.plotter.getSpearmanRho())
|
|
|
180
|
|
|
181 def run(self):
|
|
|
182 self.compare()
|
|
|
183 self.plot()
|
|
|
184 self.printSpearman()
|
|
|
185
|
|
|
186 if __name__ == "__main__":
|
|
|
187
|
|
|
188 # parse command line
|
|
|
189 description = "Get Distance v1.0.3: Compute the distance of a set of transcript with respect to a reference set. [Category: Visualization]"
|
|
|
190
|
|
|
191 parser = OptionParser(description = description)
|
|
|
192 parser.add_option("-i", "--input1", dest="inputFileName1", action="store", type="string", help="input file 1 [compulsory] [format: file in transcript format given by -f]")
|
|
|
193 parser.add_option("-f", "--format1", dest="format1", action="store", type="string", help="format of file 1 [compulsory] [format: transcript file format]")
|
|
|
194 parser.add_option("-j", "--input2", dest="inputFileName2", action="store", type="string", help="input file 2 [compulsory] [format: file in transcript format given by -g]")
|
|
|
195 parser.add_option("-g", "--format2", dest="format2", action="store", type="string", help="format of file 2 [compulsory] [format: transcript file format]")
|
|
|
196 parser.add_option("-o", "--output", dest="outputFileName", action="store", type="string", help="plot output file [format: output file in PNG format]")
|
|
|
197 parser.add_option("-O", "--outputDistances", dest="outputDistances", action="store", default=None, type="string", help="output file containing the distance for each element of the query [format: output file in GFF3 format] [default: None]")
|
|
|
198 parser.add_option("-c", "--colinear", dest="colinear", action="store_true", default=False, help="only consider features on the same strand [format: bool] [default: false]")
|
|
|
199 parser.add_option("-a", "--antisense", dest="antisense", action="store_true", default=False, help="only consider features on the opposite strand [format: bool] [default: false]")
|
|
|
200 parser.add_option("-b", "--absolute", dest="absolute", action="store_true", default=False, help="give the absolute value of the distance [format: bool] [default: false]")
|
|
|
201 parser.add_option("-p", "--proportion", dest="proportion", action="store_true", default=False, help="give the proportion on the y-axis instead of the number of distances [format: bool] [default: false]")
|
|
|
202 parser.add_option("-s", "--start1", dest="start1", action="store", default=None, type="int", help="only consider the n first 5' nucleotides for list 1 [format: int]")
|
|
|
203 parser.add_option("-S", "--start2", dest="start2", action="store", default=None, type="int", help="only consider the n first 5' nucleotides for list 2 [format: int]")
|
|
|
204 parser.add_option("-e", "--end1", dest="end1", action="store", default=None, type="int", help="only consider the n last 3' nucleotides for list 1 [format: int]")
|
|
|
205 parser.add_option("-E", "--end2", dest="end2", action="store", default=None, type="int", help="only consider the n last 3' nucleotides for list 2 [format: int]")
|
|
|
206 parser.add_option("-m", "--minDistance", dest="minDistance", action="store", default=None, type="int", help="minimum distance considered between two transcripts [format: int] [default: None]")
|
|
|
207 parser.add_option("-M", "--maxDistance", dest="maxDistance", action="store", default=1000, type="int", help="maximum distance considered between two transcripts [format: int] [default: 1000]")
|
|
|
208 parser.add_option("-5", "--fivePrime", dest="fivePrime", action="store_true", default=False, help="consider the elements from list 1 which are upstream of elements of list 2 [format: bool] [default: False]")
|
|
|
209 parser.add_option("-3", "--threePrime", dest="threePrime", action="store_true", default=False, help="consider the elements from list 1 which are downstream of elements of list 2 [format: bool] [default: False]")
|
|
|
210 parser.add_option("-u", "--buckets", dest="buckets", action="store", default=None, type="int", help="plot histogram instead of line plot with given interval size [format: int] [default: None]")
|
|
|
211 parser.add_option("-2", "--2strands", dest="twoStrands", action="store_true", default=False, help="plot the distributions of each strand separately [format: bool] [default: False]")
|
|
|
212 parser.add_option("-r", "--spearman", dest="spearman", action="store_true", default=False, help="compute Spearman rho [format: bool] [default: False]")
|
|
|
213 parser.add_option("-x", "--xMin", dest="xMin", action="store", default=None, type="int", help="minimum value on the x-axis to plot [format: int] [default: None]")
|
|
|
214 parser.add_option("-X", "--xMax", dest="xMax", action="store", default=None, type="int", help="maximum value on the x-axis to plot [format: int] [default: None]")
|
|
|
215 parser.add_option("-t", "--title", dest="title", action="store", default=None, type="string", help="title for the graph [format: int] [default: None]")
|
|
|
216 parser.add_option("-v", "--verbosity", dest="verbosity", action="store", default=1, type="int", help="trace level [format: int]")
|
|
|
217 parser.add_option("-k", "--keep", dest="keep", action="store_true", default=False, help="keep temporary files [format: bool]")
|
|
|
218 (options, args) = parser.parse_args()
|
|
|
219
|
|
|
220 gd = GetDistance(options.verbosity)
|
|
|
221 gd.setQueryFile(options.inputFileName1, options.format1)
|
|
|
222 gd.setReferenceFile(options.inputFileName2, options.format2)
|
|
|
223 gd.setOutputFile(options.outputFileName)
|
|
|
224 gd.setOutputTranscriptFile(options.outputDistances)
|
|
|
225 gd.setColinear(options.colinear)
|
|
|
226 gd.setAntisense(options.antisense)
|
|
|
227 gd.setAbsolute(options.absolute)
|
|
|
228 gd.setProportion(options.proportion)
|
|
|
229 gd.restrictQueryToStart(options.start1)
|
|
|
230 gd.restrictReferenceToStart(options.start2)
|
|
|
231 gd.restrictQueryToEnd(options.end1)
|
|
|
232 gd.restrictReferenceToEnd(options.end2)
|
|
|
233 gd.setDistances(options.minDistance, options.maxDistance)
|
|
|
234 gd.setUpstream(options.fivePrime)
|
|
|
235 gd.setDownstream(options.threePrime)
|
|
|
236 gd.setStrands(options.twoStrands)
|
|
|
237 gd.setBuckets(options.buckets)
|
|
|
238 gd.setTitle(options.title)
|
|
|
239 gd.setXValues(options.xMin, options.xMax)
|
|
|
240 gd.keepTmpValues(options.keep)
|
|
|
241 gd.run()
|
