def test_bad_peptide_attribute(self):
self.proteins = self.spi.readInputFile(
self.runner.pcssConfig['fasta_file'])
startAtt = self.runner.pfa.getAttribute('peptide_start')
startAtt.name = "peptide_start_fake"
afw = pcssIO.AnnotationFileWriter(self.runner)
with self.assertRaises(pcssErrors.PcssGlobalException) as e:
afw.writeAllOutput(self.proteins)
self.handleTestException(e)
def test_bad_protein_attribute(self):
self.proteins = self.spi.readInputFile(
self.runner.pcssConfig['fasta_file'])
badAtt = self.runner.pfa.getColumnSortedInputAttributes()[0]
badAtt.name = "seq_id_fake"
afw = pcssIO.AnnotationFileWriter(self.runner)
with self.assertRaises(pcssErrors.PcssGlobalException) as e:
afw.writeAllOutput(self.proteins)
self.handleTestException(e)
def read_write_annotation_file(self, inputFile):
reader = pcssIO.AnnotationFileReader(self.runner)
reader.readAnnotationFile(inputFile)
proteins = reader.getProteins()
afw = pcssIO.AnnotationFileWriter(self.runner)
afw.writeAllOutput(proteins)
self.compareFiles(
inputFile,
self.runner.pdh.getFullOutputFile(
self.runner.internalConfig["annotation_output_file"]), True)
def mergeTrainingAnnotationResults(self):
fastaFile = self.pcssRunner.pcssConfig['fasta_file']
seqGroupList = self.getFastaGroupList(fastaFile)
seqBatchDirectory = self.pdh.getSeqBatchDirectory()
allProteins = []
for (i, nextGroup) in enumerate(seqGroupList):
subDirName = self.pdh.getSeqBatchSubDirectoryName(i)
subOutputFile = os.path.join(
subDirName,
self.pcssRunner.internalConfig["annotation_output_file"])
reader = pcssIO.AnnotationFileReader(self.pcssRunner)
reader.readAnnotationFile(subOutputFile)
proteins = reader.getProteins()
allProteins += proteins
afw = pcssIO.AnnotationFileWriter(self.pcssRunner)
afw.writeAllOutput(allProteins)
def test_write_normal_output(self):
self.proteins = self.spi.readInputFile(
self.runner.pcssConfig['fasta_file'])
modelColumns = pcssModels.PcssModelTableColumns(
self.runner.internalConfig['model_table_column_file'])
self.modelTable = pcssModels.PcssModelTable(self.runner, modelColumns)
pcssProtein = self.getProtein(
"76c3a409540532138c6b44bde9e4d248MDDRDENQ", self.proteins)
disopredFileHandler = pcssFeatureHandlers.DisopredFileHandler(
self.pcssConfig, self.runner.pdh)
disopredReader = pcssFeatureHandlers.DisopredReader(
disopredFileHandler)
disopredRunner = pcssFeatureHandlers.SequenceFeatureRunner(
disopredFileHandler)
pcssProtein.processDisopred(disopredReader, disopredRunner)
psipredFileHandler = pcssFeatureHandlers.PsipredFileHandler(
self.pcssConfig, self.runner.pdh)
psipredReader = pcssFeatureHandlers.PsipredReader(psipredFileHandler)
psipredRunner = pcssFeatureHandlers.SequenceFeatureRunner(
psipredFileHandler)
pcssProtein.processPsipred(psipredReader, psipredRunner)
pcssProtein.addModels(self.modelTable)
pcssProtein.processDssp()
rankedModels = pcssProtein.getRankedModels()
afw = pcssIO.AnnotationFileWriter(self.runner)
afw.writeAllOutput(self.proteins)
annotationFileName = self.runner.pdh.getFullOutputFile(
"annotationOutput.txt")
reader = pcssIO.AnnotationFileReader(self.runner)
reader.readAnnotationFile(annotationFileName)
newProteins = reader.getProteins()
for newProtein in newProteins:
oldProtein = self.getProtein(newProtein.modbaseSequenceId,
self.proteins)
self.assertTrue(oldProtein.isEqual(newProtein))
def mergeSvmApplicationResults(self):
fastaFile = self.pcssRunner.pcssConfig['fasta_file']
seqGroupList = self.getFastaGroupList(fastaFile)
print "merging application results"
seqBatchDirectory = self.pdh.getSeqBatchDirectory()
allProteins = []
for (i, nextGroup) in enumerate(seqGroupList):
subDirName = self.pdh.getSeqBatchSubDirectoryName(i)
self.seqBatchErrorExists(subDirName)
subOutputFile = os.path.join(
subDirName,
self.pcssRunner.internalConfig["annotation_output_file"])
if (not os.path.exists(subOutputFile)):
raise pcssErrors.PcssGlobalException(
"Seq batch error: did not get annotation output file in directory %s"
% subDirName)
reader = pcssIO.AnnotationFileReader(self.pcssRunner)
reader.readAnnotationFile(subOutputFile)
proteins = reader.getProteins()
allProteins += proteins
afw = pcssIO.AnnotationFileWriter(self.pcssRunner)
afw.writeAllOutput(allProteins)
def writeOutput(self):
afw = pcssIO.AnnotationFileWriter(self)
afw.writeAllOutput(self.proteins)