Mercurial > repos > yufei-luo > s_mart
comparison commons/tools/TEclassifierPE.py @ 18:94ab73e8a190
Uploaded
author | m-zytnicki |
---|---|
date | Mon, 29 Apr 2013 03:20:15 -0400 |
parents | |
children |
comparison
equal
deleted
inserted
replaced
17:b0e8584489e6 | 18:94ab73e8a190 |
---|---|
1 #!/usr/bin/env python | |
2 | |
3 # Copyright INRA (Institut National de la Recherche Agronomique) | |
4 # http://www.inra.fr | |
5 # http://urgi.versailles.inra.fr | |
6 # | |
7 # This software is governed by the CeCILL license under French law and | |
8 # abiding by the rules of distribution of free software. You can use, | |
9 # modify and/ or redistribute the software under the terms of the CeCILL | |
10 # license as circulated by CEA, CNRS and INRIA at the following URL | |
11 # "http://www.cecill.info". | |
12 # | |
13 # As a counterpart to the access to the source code and rights to copy, | |
14 # modify and redistribute granted by the license, users are provided only | |
15 # with a limited warranty and the software's author, the holder of the | |
16 # economic rights, and the successive licensors have only limited | |
17 # liability. | |
18 # | |
19 # In this respect, the user's attention is drawn to the risks associated | |
20 # with loading, using, modifying and/or developing or reproducing the | |
21 # software by the user in light of its specific status of free software, | |
22 # that may mean that it is complicated to manipulate, and that also | |
23 # therefore means that it is reserved for developers and experienced | |
24 # professionals having in-depth computer knowledge. Users are therefore | |
25 # encouraged to load and test the software's suitability as regards their | |
26 # requirements in conditions enabling the security of their systems and/or | |
27 # data to be ensured and, more generally, to use and operate it in the | |
28 # same conditions as regards security. | |
29 # | |
30 # The fact that you are presently reading this means that you have had | |
31 # knowledge of the CeCILL license and that you accept its terms. | |
32 | |
33 import os | |
34 import sys | |
35 | |
36 if not "REPET_PATH" in os.environ.keys(): | |
37 print "ERROR: no environment variable REPET_PATH" | |
38 sys.exit(1) | |
39 sys.path.append(os.environ["REPET_PATH"]) | |
40 if not "PYTHONPATH" in os.environ.keys(): | |
41 os.environ["PYTHONPATH"] = os.environ["REPET_PATH"] | |
42 else: | |
43 os.environ["PYTHONPATH"] = "%s:%s" % (os.environ["REPET_PATH"], os.environ["PYTHONPATH"]) | |
44 | |
45 from commons.core.LoggerFactory import LoggerFactory | |
46 from commons.core.utils.RepetOptionParser import RepetOptionParser | |
47 from commons.core.checker.ConfigChecker import ConfigRules | |
48 from commons.core.checker.ConfigChecker import ConfigChecker | |
49 from commons.core.seq.FastaUtils import FastaUtils | |
50 from denovo_pipe.ReverseComplementAccordingToClassif import ReverseComplementAccordingToClassif | |
51 from denovo_pipe.RenameHeaderClassif import RenameHeaderClassif | |
52 from denovo_pipe.DetectTEFeatures import DetectTEFeatures | |
53 from denovo_pipe.LaunchPASTEC import LaunchPASTEC | |
54 from PASTEC.StatPastec import StatPastec | |
55 | |
56 LOG_DEPTH = "repet.tools" | |
57 #LOG_FORMAT = "%(message)s" | |
58 | |
59 ####TEclassifier PASTEC Edition | |
60 # | |
61 class TEclassifierPE(object): | |
62 | |
63 def __init__(self, fastaFileName = "", configFileName = "", addWickerCode = False, reverseComp = False, doClean = False, verbosity = 0): | |
64 self._fastaFileName = fastaFileName | |
65 self._addWickerCode = addWickerCode | |
66 self._reverseComp = reverseComp | |
67 self._configFileName = configFileName | |
68 self._doClean = doClean | |
69 self._verbosity = verbosity | |
70 self._projectName = "" | |
71 self._log = LoggerFactory.createLogger("%s.%s" % (LOG_DEPTH, self.__class__.__name__), self._verbosity) | |
72 | |
73 def setAttributesFromCmdLine(self): | |
74 description = "TE classifier PASTEC Edition.\n" | |
75 description += "Detect TE features on consensus and classify them. Give some classification statistics.\n" | |
76 description += "Can rename headers with classification info and Wicker's code at the beginning.\n" | |
77 description += "Can reverse-complement consensus if they are detected in reverse strand.\n" | |
78 description += "Warning : it's highly advised to use sequences in upper case.\n" | |
79 epilog = "\n" | |
80 epilog += "Example 1: launch and clean temporary files\n" | |
81 epilog += "\t$ python TEclassifierPE.py -i consensus.fa -C TEclassifier.cfg -c\n" | |
82 epilog += "\n" | |
83 epilog += "Example 2: launch with 'rename headers' and 'reverse-complement' options\n" | |
84 epilog += "\t$ python TEclassifierPE.py -i consensus.fa -C TEclassifier.cfg -c -w -r\n" | |
85 parser = RepetOptionParser(description = description, epilog = epilog) | |
86 parser.add_option("-i", "--fasta", dest = "fastaFileName", action = "store", type = "string", help = "input fasta file name [compulsory] [format: fasta]", default = "") | |
87 parser.add_option("-C", "--config", dest = "configFileName",action = "store", type = "string", help = "configuration file name (e.g. TEclassifier.cfg) [compulsory]", default = "") | |
88 parser.add_option("-w", "--wicker", dest = "addWickerCode", action = "store_true", help = "add classification info and Wicker's code at the beginning of the headers [optional] [default: False]", default = False) | |
89 parser.add_option("-r", "--reverse", dest = "reverseComp", action = "store_true", help = "reverse-complement consensus if they are detected in reverse strand [optional] [default: False]", default = False) | |
90 parser.add_option("-c", "--clean", dest = "doClean", action = "store_true", help = "clean temporary files [optional] [default: False]", default = False) | |
91 parser.add_option("-v", "--verbosity", dest = "verbosity", action = "store", type = "int", help = "verbosity [optional] [default: 3, from 1 to 4]", default = 3) | |
92 options = parser.parse_args()[0] | |
93 self._setAttributesFromOptions(options) | |
94 | |
95 def _setAttributesFromOptions(self, options): | |
96 self.setFastaFileName(options.fastaFileName) | |
97 self.setAddWickerCode(options.addWickerCode) | |
98 self.setReverseComp(options.reverseComp) | |
99 self.setConfigFileName(options.configFileName) | |
100 self.setDoClean(options.doClean) | |
101 self.setVerbosity(options.verbosity) | |
102 | |
103 def _checkConfig(self): | |
104 iConfigRules = ConfigRules() | |
105 iConfigRules.addRuleOption(section="project", option ="project_name", mandatory=True, type="string") | |
106 sectionName = "classif_consensus" | |
107 iConfigRules.addRuleOption(section=sectionName, option ="clean", mandatory=True, type="bool") | |
108 iConfigChecker = ConfigChecker(self._configFileName, iConfigRules) | |
109 iConfig = iConfigChecker.getConfig() | |
110 self._setAttributesFromConfig(iConfig) | |
111 | |
112 def _setAttributesFromConfig(self, iConfig): | |
113 self.setProjectName(iConfig.get("project", "project_name")) | |
114 sectionName = "classif_consensus" | |
115 self.setDoClean(iConfig.get(sectionName, "clean")) | |
116 | |
117 def setFastaFileName(self, fastaFileName): | |
118 self._fastaFileName = fastaFileName | |
119 | |
120 def setConfigFileName(self, configFileName): | |
121 self._configFileName = configFileName | |
122 | |
123 def setAddWickerCode(self, addWickerCode): | |
124 self._addWickerCode = addWickerCode | |
125 | |
126 def setReverseComp(self, reverseComp): | |
127 self._reverseComp = reverseComp | |
128 | |
129 def setDoClean(self, doClean): | |
130 self._doClean = doClean | |
131 | |
132 def setVerbosity(self, verbosity): | |
133 self._verbosity = verbosity | |
134 | |
135 def setProjectName(self, projectName): | |
136 self._projectName = projectName | |
137 | |
138 def _checkOptions(self): | |
139 if self._fastaFileName == "": | |
140 self._logAndRaise("ERROR: Missing input fasta file name") | |
141 | |
142 def _logAndRaise(self, errorMsg): | |
143 self._log.error(errorMsg) | |
144 raise Exception(errorMsg) | |
145 | |
146 def run(self): | |
147 LoggerFactory.setLevel(self._log, self._verbosity) | |
148 if self._configFileName: | |
149 self._checkConfig() | |
150 self._checkOptions() | |
151 self._log.info("START TEclassifier PASTEC Edition") | |
152 self._log.debug("Fasta file name: %s" % self._fastaFileName) | |
153 nbSeq = FastaUtils.dbSize(self._fastaFileName) | |
154 self._log.debug("Total number of sequences: %i)" % nbSeq) | |
155 | |
156 #TODO: add step => avoid to re-launch DetectTEFeatures, if error with PASTEC (e.g. wrong bank format) | |
157 #step 1 | |
158 iDF = DetectTEFeatures(self._fastaFileName, self._projectName, self._configFileName, self._doClean, self._verbosity) | |
159 iDF.run() | |
160 | |
161 #step 2 | |
162 iLP = LaunchPASTEC(configFileName = self._configFileName, inputFileName = self._fastaFileName, projectName = self._projectName, verbose = self._verbosity) | |
163 iLP.run() | |
164 | |
165 classifFileName = "%s.classif" % self._projectName | |
166 | |
167 iSP = StatPastec(classifFileName) | |
168 iSP.run() | |
169 | |
170 if self._reverseComp: | |
171 self._log.info("Reverse complement...") | |
172 iRevComplAccording2Classif = ReverseComplementAccordingToClassif() | |
173 iRevComplAccording2Classif.setFastaFile(self._fastaFileName) | |
174 iRevComplAccording2Classif.setClassifFile(classifFileName) | |
175 iRevComplAccording2Classif.run() | |
176 tmpFastaFileName = "%s_negStrandReversed.fa" % os.path.splitext(self._fastaFileName)[0] | |
177 else: | |
178 tmpFastaFileName = self._fastaFileName | |
179 | |
180 if self._addWickerCode: | |
181 self._log.info("Rename headers according to Wicker's code...") | |
182 iRHC = RenameHeaderClassif(classifFileName, tmpFastaFileName, self._projectName) | |
183 iRHC.setOutputFileName("") | |
184 iRHC.run() | |
185 if self._doClean: | |
186 os.remove(tmpFastaFileName) | |
187 | |
188 self._log.info("END TEclassifier PASTEC Edition") | |
189 | |
190 if __name__ == "__main__": | |
191 iLaunch = TEclassifierPE() | |
192 iLaunch.setAttributesFromCmdLine() | |
193 iLaunch.run() |