def test_02(self):
args_a = CLI(['-m','subset','-s',''])
args_b = CLI(['-m','subset','--strand-specific-matching','-s',''])
## First test the matches if strand-specific-matching is disabled (all 4 fusions should be identical)
experiment_a = ReadChimeraScanAbsoluteBEDPE("tests/data/test_CompareFusionsBySpanningGenes.TestCompareFusionsBySpanningGenes.test_02_a.bedpe","TestExperimentA")
experiment_b = ReadChimeraScanAbsoluteBEDPE("tests/data/test_CompareFusionsBySpanningGenes.TestCompareFusionsBySpanningGenes.test_02_b.bedpe","TestExperimentB")
self.assertEqual(len(experiment_a), 4)
self.assertEqual(len(experiment_b), 4)
genes = ParseBED("tests/data/test_CompareFusionsBySpanningGenes.TestCompareFusionsBySpanningGenes.test_02.bed","hg18",200000)
self.assertEqual(len(genes), 8)
experiment_a.annotate_genes(genes)
experiment_b.annotate_genes(genes)
## @todo -> remove duplicates should be done separately
experiment_a.remove_duplicates(args_a)
experiment_b.remove_duplicates(args_a)
overlap = CompareFusionsBySpanningGenes(experiment_a,experiment_b,args_a)# No EGM, no strand-specific-matching
overlapping_fusions = overlap.find_overlap()
self.assertLessEqual(len(overlapping_fusions[0]), 4)
## Second, test the matches if strand-specific-matching is disabled (only the first fusion should be identical)
overlap = CompareFusionsBySpanningGenes(experiment_a,experiment_b,args_b)# No EGM, but strand-specific-matching
overlapping_fusions = overlap.find_overlap()
self.assertLessEqual(len(overlapping_fusions[0]), 1)
def test_01(self):
args = CLI(['-m', 'subset', '--no-strand-specific-matching', '-s', ''])
experiment_a = ReadChimeraScanAbsoluteBEDPE(
"tests/data/test_CompareFusionsBySpanningGenes.TestCompareFusionsBySpanningGenes.test_01.bedpe",
"TestExperimentA")
experiment_b = ReadChimeraScanAbsoluteBEDPE(
"tests/data/test_CompareFusionsBySpanningGenes.TestCompareFusionsBySpanningGenes.test_01.bedpe",
"TestExperimentB")
self.assertEqual(len(experiment_a), 690)
self.assertEqual(len(experiment_b), 690)
genes = ParseBED(
"tests/data/test_CompareFusionsBySpanningGenes.TestCompareFusionsBySpanningGenes.test_01.bed",
"hg18", 200000)
self.assertEqual(len(genes), 47790)
experiment_a.annotate_genes(genes)
experiment_b.annotate_genes(genes)
experiment_a.remove_duplicates(args)
experiment_b.remove_duplicates(args)
overlap = CompareFusionsBySpanningGenes(experiment_a, experiment_b,
args)
overlapping_fusions = overlap.find_overlap()
self.assertLessEqual(len(overlapping_fusions[0]), 538)
self.assertLessEqual(538, len(experiment_a))
def test_01(self):
args = CLI(['-m','subset','--no-strand-specific-matching','-s',''])
experiment = ReadChimeraScanAbsoluteBEDPE("tests/data/test_FusionDetectionExperiment.TestFusionDetectionExperiment.test_01.bedpe","TestExperiment")
genes = ParseBED("tests/data/test_FusionDetectionExperiment.TestFusionDetectionExperiment.test_01.bed","hg18", 200000)
length_before_duplication_removal = len(experiment)
experiment.annotate_genes(genes)
experiment.remove_duplicates(args)
length_after_duplication_removal = len(experiment)
self.assertTrue(length_before_duplication_removal > length_after_duplication_removal)
def test_01(self):
args = CLI(['-m','subset','--no-strand-specific-matching','-s',''])
experiment = ReadChimeraScanAbsoluteBEDPE("tests/data/test_FusionDetectionExperiment.TestFusionDetectionExperiment.test_01.bedpe","TestExperiment")
genes = ParseBED("tests/data/test_FusionDetectionExperiment.TestFusionDetectionExperiment.test_01.bed","hg18", 200000)
length_before_duplication_removal = len(experiment)
experiment.annotate_genes(genes)
experiment.remove_duplicates(args)
length_after_duplication_removal = len(experiment)
self.assertTrue(length_before_duplication_removal > length_after_duplication_removal)
def test_02(self):
experiment = ReadChimeraScanAbsoluteBEDPE("tests/data/test_FusionDetectionExperiment.TestFusionDetectionExperiment.test_02.bedpe","TestExperiment")
genes = ParseBED("tests/data/test_FusionDetectionExperiment.TestFusionDetectionExperiment.test_02.bed","hg18", 200000)
self.assertEqual(len(experiment), 1)
experiment.annotate_genes(genes)
for fusion in experiment:
left_genes = fusion.get_annotated_genes_left(False)
right_genes = fusion.get_annotated_genes_right(False)
self.assertEqual(len(left_genes), 8)
self.assertEqual(len(right_genes), 8)
# Ensure all annotated gene names do NOT contain substring '_invalid'
self.assertEqual(min([str(gene_name).find("_invalid") for gene_name in left_genes]) , -1)
self.assertEqual(min([str(gene_name).find("_invalid") for gene_name in right_genes]) , -1)
def test_02(self):
experiment = ReadChimeraScanAbsoluteBEDPE("tests/data/test_FusionDetectionExperiment.TestFusionDetectionExperiment.test_02.bedpe","TestExperiment")
genes = ParseBED("tests/data/test_FusionDetectionExperiment.TestFusionDetectionExperiment.test_02.bed","hg18", 200000)
self.assertEqual(len(experiment), 1)
experiment.annotate_genes(genes)
for fusion in experiment:
left_genes = fusion.get_annotated_genes_left(False)
right_genes = fusion.get_annotated_genes_right(False)
self.assertEqual(len(left_genes), 8)
self.assertEqual(len(right_genes), 8)
# Ensure all annotated gene names do NOT contain substring '_invalid'
self.assertEqual(min([str(gene_name).find("_invalid") for gene_name in left_genes]) , -1)
self.assertEqual(min([str(gene_name).find("_invalid") for gene_name in right_genes]) , -1)
def test_02(self):
args_a = CLI(['-m', 'subset', '-s', ''])
args_b = CLI(['-m', 'subset', '--strand-specific-matching', '-s', ''])
## First test the matches if strand-specific-matching is disabled (all 4 fusions should be identical)
experiment_a = ReadChimeraScanAbsoluteBEDPE(
"tests/data/test_CompareFusionsBySpanningGenes.TestCompareFusionsBySpanningGenes.test_02_a.bedpe",
"TestExperimentA")
experiment_b = ReadChimeraScanAbsoluteBEDPE(
"tests/data/test_CompareFusionsBySpanningGenes.TestCompareFusionsBySpanningGenes.test_02_b.bedpe",
"TestExperimentB")
self.assertEqual(len(experiment_a), 4)
self.assertEqual(len(experiment_b), 4)
genes = ParseBED(
"tests/data/test_CompareFusionsBySpanningGenes.TestCompareFusionsBySpanningGenes.test_02.bed",
"hg18", 200000)
self.assertEqual(len(genes), 8)
experiment_a.annotate_genes(genes)
experiment_b.annotate_genes(genes)
## @todo -> remove duplicates should be done separately
experiment_a.remove_duplicates(args_a)
experiment_b.remove_duplicates(args_a)
overlap = CompareFusionsBySpanningGenes(
experiment_a, experiment_b,
args_a) # No EGM, no strand-specific-matching
overlapping_fusions = overlap.find_overlap()
self.assertLessEqual(len(overlapping_fusions[0]), 4)
## Second, test the matches if strand-specific-matching is disabled (only the first fusion should be identical)
overlap = CompareFusionsBySpanningGenes(
experiment_a, experiment_b,
args_b) # No EGM, but strand-specific-matching
overlapping_fusions = overlap.find_overlap()
self.assertLessEqual(len(overlapping_fusions[0]), 1)
def test_01(self):
args = CLI(['-m','subset','--no-strand-specific-matching','-s',''])
experiment_a = ReadChimeraScanAbsoluteBEDPE("tests/data/test_CompareFusionsBySpanningGenes.TestCompareFusionsBySpanningGenes.test_01.bedpe","TestExperimentA")
experiment_b = ReadChimeraScanAbsoluteBEDPE("tests/data/test_CompareFusionsBySpanningGenes.TestCompareFusionsBySpanningGenes.test_01.bedpe","TestExperimentB")
self.assertEqual(len(experiment_a), 690)
self.assertEqual(len(experiment_b), 690)
genes = ParseBED("tests/data/test_CompareFusionsBySpanningGenes.TestCompareFusionsBySpanningGenes.test_01.bed","hg18",200000)
self.assertEqual(len(genes), 47790)
experiment_a.annotate_genes(genes)
experiment_b.annotate_genes(genes)
experiment_a.remove_duplicates(args)
experiment_b.remove_duplicates(args)
overlap = CompareFusionsBySpanningGenes(experiment_a,experiment_b,args)
overlapping_fusions = overlap.find_overlap()
self.assertLessEqual(len(overlapping_fusions[0]), len(experiment_a))
