Mercurial > repos > yufei-luo > s_mart
view smart_toolShed/commons/core/coord/test/Test_ConvCoord.py @ 0:e0f8dcca02ed
Uploaded S-MART tool. A toolbox manages RNA-Seq and ChIP-Seq data.
| author | yufei-luo |
|---|---|
| date | Thu, 17 Jan 2013 10:52:14 -0500 |
| parents | |
| children |
line wrap: on
line source
import unittest import os import time from commons.core.coord.ConvCoord import ConvCoord from commons.core.utils.FileUtils import FileUtils from commons.core.sql.DbFactory import DbFactory from commons.core.coord.Map import Map class Test_ConvCoord( unittest.TestCase ): def setUp( self ): self._i = ConvCoord() self._uniqId = "%s_%s" % ( time.strftime("%Y%m%d%H%M%S") , os.getpid() ) self._inData = "dummyInData_%s" % ( self._uniqId ) self._mapData = "dummyMapData_%s" % ( self._uniqId ) self._expData = "dummyExpData_%s" % ( self._uniqId ) self._obsData = "dummyObsData_%s" % ( self._uniqId ) self._iDb = DbFactory.createInstance() self._i._iDb = self._iDb def tearDown( self ): self._iDb.close() #TODO: handle duplicated matchs for path # def test_convCoordsChkToChrFromFile_duplicated_matchs( self ): # dChunks2CoordMaps = {"chunk1": Map( "chunk1", "dmel_chr4", 760001, 960000 ), # "chunk2": Map( "chunk2", "dmel_chr4", 950001, 1150000 ) } # tmpPathFileName = "dummyPathCoordOnChr_%s" % self._uniqId # self._writePathFileCoordOnChunk(tmpPathFileName) # # expPathFile = "dummyExpPathFile_%s" % self._uniqId # self._writePathFileCoordOnChrWithOutDoublons(expPathFile) # # outTableName = self._i.convCoordsChkToChrFromFile(tmpPathFileName, "path", dChunks2CoordMaps) # # obsPathFile = "dummyObsPathFile_%s" % self._uniqId # self._iDb.exportDataToFile(outTableName, obsPathFile) # # self.assertTrue(FileUtils.are2FilesIdentical(expPathFile, obsPathFile)) # # for f in [ expPathFile, obsPathFile, tmpPathFileName ]: # os.remove( f ) # self._iDb.dropTable(outTableName) #TODO: handle matchs out of chunk overlap ? For one side (=> path 128, remove path 152) ? For two sides (path 129, fusion with path 154) ? # def test_convCoordsChkToChrFromFile_matchs_out_of_overlap( self ): # dChunks2CoordMaps = {"chunk1": Map( "chunk1", "dmel_chr4", 760001, 960000 ), # "chunk2": Map( "chunk2", "dmel_chr4", 950001, 1150000 ) } # tmpPathFileName = "dummyPathCoordOnChr_%s" % self._uniqId # self._writePathFileCoordOnChunk_outOfOverlap(tmpPathFileName) # # expPathFile = "dummyExpPathFile_%s" % self._uniqId # self._writePathFileCoordOnChrWithOutDoublons_outOfOverlap(expPathFile) # # outTableName = self._i.convCoordsChkToChrFromFile(tmpPathFileName, "path", dChunks2CoordMaps) # # obsPathFile = "dummyObsPathFile_%s" % self._uniqId # self._iDb.exportDataToFile(outTableName, obsPathFile) # # self.assertTrue(FileUtils.are2FilesIdentical(expPathFile, obsPathFile)) # # for f in [ expPathFile, obsPathFile, tmpPathFileName ]: # os.remove( f ) # self._iDb.dropTable(outTableName) def test_mergeCoordsOnChunkOverlaps( self ): dChunks2CoordMaps = { "chunk1": Map( "chunk1", "chromosome1", 1, 100 ), "chunk2": Map( "chunk2", "chromosome1", 91, 190 ), "chunk3": Map( "chunk3", "chromosome2", 1, 100 ) } tmpPathTable = "dummyTmpPathTable" linesToProcess = [ "1" + "\t" + "chromosome1" + "\t" + "21" + "\t" + "37" + "\t" + "TE1" + "\t" + "1" + "\t" + "27" + "\t" + "8e-58" + "\t" + "30" + "\t" + "97.8" + "\n", # hit within the 1st chunk "3" + "\t" + "chromosome1" + "\t" + "92" + "\t" + "99" + "\t" + "TE1" + "\t" + "1" + "\t" + "8" + "\t" + "8e-58" + "\t" + "11" + "\t" + "97.8" + "\n", # hit included within the chunk overlap, on the 2nd chunk "2" + "\t" + "chromosome1" + "\t" + "92" + "\t" + "99" + "\t" + "TE1" + "\t" + "1" + "\t" + "8" + "\t" + "8e-58" + "\t" + "11" + "\t" + "97.8" + "\n", # hit included within the chunk overlap, on the 1st chunk ] FileUtils.writeLineListInFile( tmpPathTable, linesToProcess ) self._iDb.createTable( tmpPathTable, "path", tmpPathTable, True) os.remove( tmpPathTable ) expPathFile = "dummyExpPathFile" linesToProcess = [ "1" + "\t" + "chromosome1" + "\t" + "21" + "\t" + "37" + "\t" + "TE1" + "\t" + "1" + "\t" + "27" + "\t" + "8e-58" + "\t" + "30" + "\t" + "97.8" + "\n", # hit within the 1st chunk "2" + "\t" + "chromosome1" + "\t" + "92" + "\t" + "99" + "\t" + "TE1" + "\t" + "1" + "\t" + "8" + "\t" + "8e-58" + "\t" + "11" + "\t" + "97.8" + "\n", # hit included within the chunk overlap, on the 1st chunk ] FileUtils.writeLineListInFile( expPathFile, linesToProcess ) self._i.mergeCoordsOnChunkOverlaps( dChunks2CoordMaps, tmpPathTable) obsPathFile = "dummyObsPathFile" self._iDb.exportDataToFile( tmpPathTable, obsPathFile ) self.assertTrue( FileUtils.are2FilesIdentical( expPathFile, obsPathFile ) ) for f in [ expPathFile, obsPathFile ]: os.remove( f ) self._iDb.dropTable( tmpPathTable ) def test_mergeCoordsOnChunkOverlaps_withConnectedMatches( self ): dChunks2CoordMaps = { "chunk1": Map( "chunk1", "chromosome1", 1, 100 ), "chunk2": Map( "chunk2", "chromosome1", 91, 190 ), "chunk3": Map( "chunk3", "chromosome2", 1, 100 ) } tmpPathTable = "dummyTmpPathTable" linesToProcess = [ "1" + "\t" + "chromosome1" + "\t" + "21" + "\t" + "37" + "\t" + "TE1" + "\t" + "1" + "\t" + "27" + "\t" + "8e-58" + "\t" + "30" + "\t" + "97.8" + "\n", # hit on the 1st chunk "1" + "\t" + "chromosome1" + "\t" + "92" + "\t" + "99" + "\t" + "TE1" + "\t" + "28" + "\t" + "36" + "\t" + "8e-58" + "\t" + "10" + "\t" + "97.8" + "\n", # hit included within the chunk overlap, on the 1st chunk, connected to the previous "2" + "\t" + "chromosome1" + "\t" + "92" + "\t" + "99" + "\t" + "TE1" + "\t" + "28" + "\t" + "36" + "\t" + "8e-58" + "\t" + "10" + "\t" + "97.8" + "\n", # hit included within the chunk overlap, on the 2nd chunk "2" + "\t" + "chromosome1" + "\t" + "111" + "\t" + "120" + "\t" + "TE1" + "\t" + "37" + "\t" + "46" + "\t" + "8e-58" + "\t" + "15" + "\t" + "97.8" + "\n", # hit on the 2nd chunk, connected to the previous ] FileUtils.writeLineListInFile( tmpPathTable, linesToProcess ) self._iDb.createTable( tmpPathTable, "path", tmpPathTable, True) os.remove( tmpPathTable ) expPathFile = "dummyExpPathFile" linesToProcess = [ "1" + "\t" + "chromosome1" + "\t" + "21" + "\t" + "37" + "\t" + "TE1" + "\t" + "1" + "\t" + "27" + "\t" + "8e-58" + "\t" + "30" + "\t" + "97.8" + "\n", # hit within the 1st chunk "1" + "\t" + "chromosome1" + "\t" + "92" + "\t" + "99" + "\t" + "TE1" + "\t" + "28" + "\t" + "36" + "\t" + "8e-58" + "\t" + "10" + "\t" + "97.8" + "\n", # hit included within the chunk overlap, on the 1st chunk "1" + "\t" + "chromosome1" + "\t" + "111" + "\t" + "120" + "\t" + "TE1" + "\t" + "37" + "\t" + "46" + "\t" + "8e-58" + "\t" + "15" + "\t" + "97.8" + "\n", # hit on the 2nd chunk, connected to the previous ] FileUtils.writeLineListInFile( expPathFile, linesToProcess ) self._i.mergeCoordsOnChunkOverlaps( dChunks2CoordMaps, tmpPathTable ) obsPathFile = "dummyObsPathFile" self._iDb.exportDataToFile( tmpPathTable, obsPathFile ) self.assertTrue( FileUtils.are2FilesIdentical( expPathFile, obsPathFile ) ) for f in [ expPathFile, obsPathFile ]: os.remove( f ) self._iDb.dropTable( tmpPathTable ) def _writePathFileCoordOnChrWithOutDoublons(self, pathFileName): file = open( pathFileName, "w" ) file.write("123\tdmel_chr4\t868397\t868531\tMariner2_AG_1p:classII:TIR\t53\t97\t8e-19\t28\t35.56\n") file.write("123\tdmel_chr4\t868545\t869120\tMariner2_AG_1p:classII:TIR\t102\t333\t8e-19\t87\t27.97\n") file.write("124\tdmel_chr4\t819607\t819714\tLINER1-2_NVi_2p:classI:?\t502\t537\t3e-20\t30\t36.11\n") file.write("124\tdmel_chr4\t819695\t820156\tLINER1-2_NVi_2p:classI:?\t533\t725\t3e-20\t90\t36.79\n") file.write("125\tdmel_chr4\t953027\t953101\tCR1-8_AG_1p:classI:LINE\t470\t448\t1e-27\t11\t28.57\n") file.write("126\tdmel_chr4\t862131\t862178\tTc1-1_TCa_1p:classII:TIR\t288\t274\t5e-29\t18\t52.5\n") file.write("127\tdmel_chr4\t819520\t819606\tNotoAg1_2p:classI:?\t482\t508\t1e-13\t14\t30.61\n") # file.write("128\tdmel_chr4\t953866\t953889\tCR1-19_HM_1p:classI:LINE\t898\t891\t5e-21\t4\t34.98\n") # file.write("129\tdmel_chr4\t953866\t953889\tCR1-83_HM_1p:classI:LINE\t912\t905\t3e-21\t4\t34.62\n") file.write("150\tdmel_chr4\t971176\t971250\tTc1-1_TCa_1p:classII:TIR\t135\t109\t8e-32\t21\t41.57\n") file.write("151\tdmel_chr4\t1066603\t1066698\tMARWOLEN1_1p:classII:TIR\t285\t320\t7e-25\t28\t41.67\n") file.write("152\tdmel_chr4\t953866\t953889\tCR1-19_HM_1p:classI:LINE\t898\t891\t5e-21\t4\t34.98\n") file.write("153\tdmel_chr4\t953951\t954343\tCR1-1_DWil_1p:classI:LINE\t127\t2\t4e-18\t92\t37.59\n") file.write("154\tdmel_chr4\t953866\t953889\tCR1-83_HM_1p:classI:LINE\t912\t905\t3e-21\t4\t34.62\n") file.write("155\tdmel_chr4\t953102\t953199\tCR1-1_DWil_2p:classI:LINE\t869\t837\t2e-26\t38\t57.89\n") file.close() def _writePathFileCoordOnChunk(self, pathFileName): pathFile = open( pathFileName, "w" ) pathFile.write("123\tchunk1\t108397\t108531\tMariner2_AG_1p:classII:TIR\t53\t97\t8e-19\t28\t35.56\n") pathFile.write("123\tchunk1\t108545\t109120\tMariner2_AG_1p:classII:TIR\t102\t333\t8e-19\t87\t27.97\n") pathFile.write("124\tchunk1\t59607\t59714\tLINER1-2_NVi_2p:classI:?\t502\t537\t3e-20\t30\t36.11\n") pathFile.write("124\tchunk1\t59695\t60156\tLINER1-2_NVi_2p:classI:?\t533\t725\t3e-20\t90\t36.79\n") pathFile.write("125\tchunk1\t193027\t193101\tCR1-8_AG_1p:classI:LINE\t470\t448\t1e-27\t11\t28.57\n") pathFile.write("126\tchunk1\t102131\t102178\tTc1-1_TCa_1p:classII:TIR\t288\t274\t5e-29\t18\t52.5\n") pathFile.write("127\tchunk1\t59520\t59606\tNotoAg1_2p:classI:?\t482\t508\t1e-13\t14\t30.61\n") pathFile.write("128\tchunk1\t193866\t193889\tCR1-19_HM_1p:classI:LINE\t898\t891\t5e-21\t4\t34.98\n") pathFile.write("129\tchunk1\t193866\t193889\tCR1-83_HM_1p:classI:LINE\t912\t905\t3e-21\t4\t34.62\n") pathFile.write("150\tchunk2\t21176\t21250\tTc1-1_TCa_1p:classII:TIR\t135\t109\t8e-32\t21\t41.57\n") pathFile.write("151\tchunk2\t116603\t116698\tMARWOLEN1_1p:classII:TIR\t285\t320\t7e-25\t28\t41.67\n") pathFile.write("152\tchunk2\t3866\t3889\tCR1-19_HM_1p:classI:LINE\t898\t891\t5e-21\t4\t34.98\n") pathFile.write("153\tchunk2\t3951\t4343\tCR1-1_DWil_1p:classI:LINE\t127\t2\t4e-18\t92\t37.59\n") pathFile.write("154\tchunk2\t3866\t3889\tCR1-83_HM_1p:classI:LINE\t912\t905\t3e-21\t4\t34.62\n") pathFile.write("155\tchunk2\t3102\t3199\tCR1-1_DWil_2p:classI:LINE\t869\t837\t2e-26\t38\t57.89\n") pathFile.close() # def _writePathFileCoordOnChunk_outOfOverlap(self, pathFileName): # pathFile = open( pathFileName, "w" ) # pathFile.write("123\tchunk1\t108397\t108531\tMariner2_AG_1p:classII:TIR\t53\t97\t8e-19\t28\t35.56\n") # pathFile.write("123\tchunk1\t108545\t109120\tMariner2_AG_1p:classII:TIR\t102\t333\t8e-19\t87\t27.97\n") # pathFile.write("124\tchunk1\t59607\t59714\tLINER1-2_NVi_2p:classI:?\t502\t537\t3e-20\t30\t36.11\n") # pathFile.write("124\tchunk1\t59695\t60156\tLINER1-2_NVi_2p:classI:?\t533\t725\t3e-20\t90\t36.79\n") # pathFile.write("125\tchunk1\t193027\t193101\tCR1-8_AG_1p:classI:LINE\t470\t448\t1e-27\t11\t28.57\n") # pathFile.write("126\tchunk1\t102131\t102178\tTc1-1_TCa_1p:classII:TIR\t288\t274\t5e-29\t18\t52.5\n") # pathFile.write("127\tchunk1\t59520\t59606\tNotoAg1_2p:classI:?\t482\t508\t1e-13\t14\t30.61\n") # pathFile.write("128\tchunk1\t183866\t193889\tCR1-19_HM_1p:classI:LINE\t898\t1891\t5e-21\t4\t34.98\n") # pathFile.write("129\tchunk1\t183866\t200000\tCR1-83_HM_1p:classI:LINE\t912\t905\t3e-21\t4\t34.62\n") # pathFile.write("150\tchunk2\t21176\t21250\tTc1-1_TCa_1p:classII:TIR\t135\t109\t8e-32\t21\t41.57\n") # pathFile.write("151\tchunk2\t116603\t116698\tMARWOLEN1_1p:classII:TIR\t285\t320\t7e-25\t28\t41.67\n") # pathFile.write("152\tchunk2\t1\t3889\tCR1-19_HM_1p:classI:LINE\t898\t1891\t5e-21\t4\t34.98\n") # pathFile.write("153\tchunk2\t3951\t4343\tCR1-1_DWil_1p:classI:LINE\t127\t2\t4e-18\t92\t37.59\n") # pathFile.write("154\tchunk2\t1\t13889\tCR1-83_HM_1p:classI:LINE\t912\t905\t3e-21\t4\t34.62\n") # pathFile.write("155\tchunk2\t3102\t3199\tCR1-1_DWil_2p:classI:LINE\t869\t837\t2e-26\t38\t57.89\n") # pathFile.close() # # def _writePathFileCoordOnChrWithOutDoublons_outOfOverlap(self, pathFileName): # file = open( pathFileName, "w" ) # file.write("123\tdmel_chr4\t868397\t868531\tMariner2_AG_1p:classII:TIR\t53\t97\t8e-19\t28\t35.56\n") # file.write("123\tdmel_chr4\t868545\t869120\tMariner2_AG_1p:classII:TIR\t102\t333\t8e-19\t87\t27.97\n") # file.write("124\tdmel_chr4\t819607\t819714\tLINER1-2_NVi_2p:classI:?\t502\t537\t3e-20\t30\t36.11\n") # file.write("124\tdmel_chr4\t819695\t820156\tLINER1-2_NVi_2p:classI:?\t533\t725\t3e-20\t90\t36.79\n") # file.write("125\tdmel_chr4\t953027\t953101\tCR1-8_AG_1p:classI:LINE\t470\t448\t1e-27\t11\t28.57\n") # file.write("126\tdmel_chr4\t862131\t862178\tTc1-1_TCa_1p:classII:TIR\t288\t274\t5e-29\t18\t52.5\n") # file.write("127\tdmel_chr4\t819520\t819606\tNotoAg1_2p:classI:?\t482\t508\t1e-13\t14\t30.61\n") # file.write("128\tdmel_chr4\t943866\t953889\tCR1-19_HM_1p:classI:LINE\t898\t1891\t5e-21\t4\t34.98\n") # file.write("129\tdmel_chr4\t943866\t963889\tCR1-83_HM_1p:classI:LINE\t912\t905\t3e-21\t4\t34.62\n") # file.write("150\tdmel_chr4\t971176\t971250\tTc1-1_TCa_1p:classII:TIR\t135\t109\t8e-32\t21\t41.57\n") # file.write("151\tdmel_chr4\t1066603\t1066698\tMARWOLEN1_1p:classII:TIR\t285\t320\t7e-25\t28\t41.67\n") # file.write("153\tdmel_chr4\t953951\t954343\tCR1-1_DWil_1p:classI:LINE\t127\t2\t4e-18\t92\t37.59\n") # file.write("155\tdmel_chr4\t953102\t953199\tCR1-1_DWil_2p:classI:LINE\t869\t837\t2e-26\t38\t57.89\n") # file.close() if __name__ == "__main__": unittest.main()