def test_max_different_overlappers_get_all(self):
dict_data = {}
dict_data['1'] = {}
dict_data['1']['2'] = {}
dict_data['1']['2']['+'] = []
inter1 = Interval("Test1", 1, 2, "+", 50, 50, 15, 10, 75, 70)
inter2 = Interval("Test2", 1, 2, "+", 50, 50, 115, 110, 175, 170)
inter3 = Interval("Test3", 1, 2, "+", 50, 50, 215, 210, 275, 270)
dict_data['1']['2']['+'].append(inter1)
dict_data['1']['2']['+'].append(inter2)
dict_data['1']['2']['+'].append(inter3)
analysis = CoverageTypeAnalysis()
analysis.analyse_data(dict_data, ["Test1", "Test2", "Test3"], 1, None,
True)
self.assertEqual(3, len(dict_data['1']['2']['+']))
result2 = Interval("Test1", 1, 2, "+", 50, 50, 115, 110, 175, 170)
result3 = Interval("Test1", 1, 2, "+", 50, 50, 215, 210, 275, 270)
self.assertEqual(inter1.toStringInterval(),
dict_data['1']['2']['+'][0].toStringInterval())
self.assertEqual(result2.toStringInterval(),
dict_data['1']['2']['+'][1].toStringInterval())
self.assertEqual(result3.toStringInterval(),
dict_data['1']['2']['+'][2].toStringInterval())
def test_strict_no_fusion_different_overlappers_2_good_overlappers(self):
dict_data = {}
dict_data['1'] = {}
dict_data['1']['2'] = {}
dict_data['1']['2']['+'] = []
inter1 = Interval("Test1", 1, 2, "+", 50, 50, 15, 10, 175, 170)
inter2 = Interval("Test2", 1, 2, "+", 50, 50, 115, 110, 175, 170)
inter3 = Interval("Test3", 1, 2, "+", 50, 50, 215, 210, 275, 270)
dict_data['1']['2']['+'].append(inter1)
dict_data['1']['2']['+'].append(inter2)
dict_data['1']['2']['+'].append(inter3)
analysis = CoverageTypeAnalysis()
analysis.analyse_data(dict_data, ["Test1", "Test2", "Test3"], 0, None,
False)
self.assertEqual(0, len(dict_data['1']['2']['+']))
def test_custom_equals_to_no_accept(self):
dict_data = {}
dict_data['1'] = {}
dict_data['1']['2'] = {}
dict_data['1']['2']['+'] = []
inter1 = Interval("Test1", 1, 2, "+", 50, 50, 115, 110, 175, 170)
inter2 = Interval("Test2", 1, 2, "+", 50, 50, 115, 110, 175, 170)
inter3 = Interval("Test3", 1, 2, "+", 50, 50, 115, 110, 175, 170)
dict_data['1']['2']['+'].append(inter1)
dict_data['1']['2']['+'].append(inter2)
dict_data['1']['2']['+'].append(inter3)
analysis = CoverageTypeAnalysis()
analysis.analyse_data(dict_data, ["Test1", "Test2", "Test3"], 12, 2,
False)
self.assertEqual(0, len(dict_data['1']['2']['+']))
def test_max_same_overlappers(self):
dict_data = {}
dict_data['1'] = {}
dict_data['1']['2'] = {}
dict_data['1']['2']['+'] = []
inter1 = Interval("Test1", 1, 2, "+", 50, 50, 15, 10, 75, 70)
inter2 = Interval("Test1", 1, 2, "+", 50, 50, 115, 110, 175, 170)
inter3 = Interval("Test1", 1, 2, "+", 50, 50, 215, 210, 275, 270)
dict_data['1']['2']['+'].append(inter1)
dict_data['1']['2']['+'].append(inter2)
dict_data['1']['2']['+'].append(inter3)
analysis = CoverageTypeAnalysis()
analysis.analyse_data(dict_data, ["Test1", "Test2", "Test3"], 1, None,
False)
self.assertEqual(1, len(dict_data['1']['2']['+']))
self.assertEqual(inter1.toStringInterval(),
dict_data['1']['2']['+'][0].toStringInterval())
def test_strict_fusion_different_overlappers(self):
dict_data = {}
dict_data['1'] = {}
dict_data['1']['2'] = {}
dict_data['1']['2']['+'] = []
inter1 = Interval("Test1", 1, 2, "+", 50, 50, 15, 10, 175, 170)
inter2 = Interval("Test2", 1, 2, "+", 50, 50, 115, 110, 215, 225)
inter3 = Interval("Test3", 1, 2, "+", 50, 50, 150, 160, 275, 270)
dict_data['1']['2']['+'].append(inter1)
dict_data['1']['2']['+'].append(inter2)
dict_data['1']['2']['+'].append(inter3)
analysis = CoverageTypeAnalysis()
analysis.analyse_data(dict_data, ["Test1", "Test2", "Test3"], 0, None,
False)
result1 = Interval("Test1", 1, 2, "+", 50, 50, 150, 160, 175, 170)
self.assertEqual(1, len(dict_data['1']['2']['+']))
self.assertEqual(result1.toStringInterval(),
dict_data['1']['2']['+'][0].toStringInterval())
def test_custom_less_than_accept(self):
dict_data = {}
dict_data['1'] = {}
dict_data['1']['2'] = {}
dict_data['1']['2']['+'] = []
inter1 = Interval("Test1", 1, 2, "+", 50, 50, 15, 10, 75, 70)
inter2 = Interval("Test2", 1, 2, "+", 50, 50, 115, 110, 175, 170)
inter3 = Interval("Test3", 1, 2, "+", 50, 50, 215, 210, 275, 270)
dict_data['1']['2']['+'].append(inter1)
dict_data['1']['2']['+'].append(inter2)
dict_data['1']['2']['+'].append(inter3)
analysis = CoverageTypeAnalysis()
analysis.analyse_data(dict_data, ["Test1", "Test2", "Test3"], 12, 2,
False)
self.assertEqual(1, len(dict_data['1']['2']['+']))
result1 = Interval("Test1", 1, 2, "+", 50, 50, 215, 210, 275, 270)
self.assertEqual(result1.toStringInterval(),
dict_data['1']['2']['+'][0].toStringInterval())
def main(args):
"""Main function of the program"""
parameters = Parameters()
readFiles = ReadFiles()
parser = parameters.complete_analyze(sys.argv[1:])
parameters.additionnalAnalysis(parser)
outputWriter = OutputWriter(parser.analysis)
dict_data = readFiles.readAllFiles(parser.files, "../allowed_files.csv")
count = 0
for id_a in dict_data:
for id_b in dict_data[id_a]:
for strand in dict_data[id_a][id_b]:
count = count + len(dict_data[id_a][id_b][strand])
if parser.stats is False:
tools = AnalysisTools()
print("=============================")
if parser.analysis == "gentle":
analysis = GentleTypeAnalysis()
dict_data = analysis.analyse_data(dict_data)
else:
analysis = CoverageTypeAnalysis()
if parser.analysis == "strict":
dict_data = analysis.analyse_data(dict_data, parser.files, 0,
None, parser.get_all)
elif parser.analysis == "max":
dict_data = analysis.analyse_data(dict_data, parser.files, 1,
None, parser.get_all)
elif parser.analysis == "custom":
if parser.moreThan is not None:
dict_data = analysis.analyse_data(dict_data, parser.files,
11, int(parser.moreThan),
parser.get_all)
elif parser.lessThan is not None:
dict_data = analysis.analyse_data(dict_data, parser.files,
12, int(parser.lessThan),
parser.get_all)
else:
dict_data = analysis.analyse_data(dict_data, parser.files,
13, int(parser.equalsTo),
parser.get_all)
print("=============================")
if parser.no_output is False:
if parser.output == "mhap":
outputWriter.outputMhap(dict_data)
elif parser.output == "paf":
outputWriter.outputPaf(dict_data)
else:
print("Hisea output not implemented yet.")
exit(0)
else:
print("No writing in an output file")
# If the stat option is enabled, print some statistics about the files
else:
statAnalyser = StatisticsTypeAnalysis()
print(statAnalyser.statistics(dict_data, parser.files))