def test_add_hit(self):
self.th.add_hit('a', 'b', 0.1, 20)
self.th.add_hit('a', 'c', 0.1, 10)
self.th.add_hit('x', 'y', 0.1, 20)
self.th.add_hit('x', 'z', 0.0, 20)
expected = {('a', Hit('a', 'b', 0.1, 20)),
('x', Hit('x', 'z', 0.0, 20))}
self.assertSetEqual(expected, set(self.th.iter_hits()))
def test_add_hit(self):
self.th.add_hit('a', 'b', 0.1, 10)
self.th.add_hit('a', 'b', 0.1, 20)
self.th.add_hit('a', 'c', 0.1, 10)
self.th.add_hit('x', 'y', 0.1, 10)
self.th.add_hit('x', 'y', 0.2, 10)
self.assertEqual(Hit('a', 'b', 0.1, 20), self.th.get_top_hit('a'))
self.assertEqual(Hit('x', 'y', 0.1, 10), self.th.get_top_hit('x'))
def test_ordering(self):
expected = [
Hit('a', 'a', 0.05, 50),
Hit('a', 'b', 0.99, 50),
Hit('a', 'x', 0.01, 10),
Hit('a', 'y', 0.01, 10)
]
test = [expected[2], expected[1], expected[0], expected[3]]
self.assertListEqual(expected, sorted(test, reverse=True))
def test_read(self):
with open(self.path, 'w') as fh:
fh.write('Gene Id Top hits (Family id,e-value,bitscore)\n')
fh.write('a\tc,0.1,20;b,0.1,10\n')
fh.write('x\ty,0.1,10\n')
self.th.read()
self.assertEqual(Hit('a', 'c', 0.1, 20), self.th.get_hmm_hit('a', 'c'))
self.assertEqual(Hit('a', 'b', 0.1, 10), self.th.get_hmm_hit('a', 'b'))
self.assertEqual(Hit('x', 'y', 0.1, 10), self.th.get_hmm_hit('x', 'y'))
def test___hash__(self):
self.assertEqual(hash(Hit('a', 'b', 0.1, 10)),
hash(Hit('a', 'b', 0.1, 10)))
self.assertNotEqual(hash(Hit('a', 'b', 0.1, 10)),
hash(Hit('a', 'b', 0.1, 20)))
self.assertNotEqual(hash(Hit('a', 'b', 0.1, 10)),
hash(Hit('a', 'b', 0.2, 10)))
self.assertNotEqual(hash(Hit('a', 'b', 0.1, 10)),
hash(Hit('a', 'c', 0.1, 10)))
self.assertNotEqual(hash(Hit('a', 'b', 0.1, 10)),
hash(Hit('c', 'b', 0.1, 10)))
def test__merge_hit_files(self):
pfam_th = TopHitPfamFile(os.path.join(self.dir_tmp), 'genome_1')
pfam_th.add_hit('gene_a', 'PFAM_1', 0.05, 100)
pfam_th.add_hit('gene_b', 'PFAM_2', 0.05, 200)
pfam_th.add_hit('gene_c', 'PFAM_2', 0.05, 100)
tigr_th = TopHitTigrFile(os.path.join(self.dir_tmp), 'genome_1')
tigr_th.add_hit('gene_x', 'TIGR_1', 0.05, 100)
expected = {'TIGR_1': [Hit('gene_x', 'TIGR_1', 0.05, 100)],
'PFAM_1': [Hit('gene_a', 'PFAM_1', 0.05, 100)],
'PFAM_2': [Hit('gene_b', 'PFAM_2', 0.05, 200),
Hit('gene_c', 'PFAM_2', 0.05, 100)]}
self.assertDictEqual(expected, CopyNumberFile._merge_hit_files(pfam_th, tigr_th))
def test___lt__(self):
self.assertLess(Hit('gene_id', 'hmm_id', 1e-100, 10),
Hit('gene_id', 'hmm_id', 1e-100, 20))
self.assertLess(Hit('gene_id', 'hmm_id', 1e-100, 10),
Hit('gene_id', 'hmm_id', 1e-200, 10))
self.assertLess(Hit('gene_id', 'z', 1e-100, 10),
Hit('gene_id', 'a', 1e-100, 10))
self.assertLess(Hit('z', 'hmm_id', 1e-100, 10),
Hit('a', 'hmm_id', 1e-100, 10))
def test___eq___not_equal(self):
self.assertNotEqual(Hit('gene_id', 'hmm_id', 0.01, 100),
Hit('gene+id', 'hmm_id', 0.01, 100))
self.assertNotEqual(Hit('gene_id', 'hmm_id', 0.01, 100),
Hit('gene_id', 'hmm+id', 0.01, 100))
self.assertNotEqual(Hit('gene_id', 'hmm_id', 1e-100, 100),
Hit('gene_id', 'hmm_id', 1e-101, 100))
self.assertNotEqual(Hit('gene_id', 'hmm_id', 0.01, 1e-100),
Hit('gene_id', 'hmm_id', 0.01, 1e-101))
def test_get_single_copy_hits(self):
g1_expected = {
'PFAM_1': {
'hit': Hit('gene_a', 'PFAM_1', 0.05, 100),
'seq': 'VVVVVV'
},
'TIGR_1': {
'hit': Hit('gene_x', 'TIGR_1', 0.05, 100),
'seq': 'AAAAAA'
},
'PFAM_2': {
'hit': Hit('gene_b', 'PFAM_2', 0.05, 200),
'seq': 'AAVVPP'
}
}
g2_expected = {
'PFAM_2': {
'hit': Hit('gene_a', 'PFAM_2', 0.05, 100),
'seq': 'VVVVVV'
},
'TIGR_1': {
'hit': Hit('gene_x', 'TIGR_1', 0.05, 200),
'seq': 'AAAVVV'
},
'TIGR_2': {
'hit': Hit('gene_y', 'TIGR_2', 0.01, 100),
'seq': 'VVVAAA'
}
}
self.assertDictEqual(g1_expected,
self.cn.get_single_copy_hits('genome_1'))
self.assertDictEqual(g2_expected,
self.cn.get_single_copy_hits('genome_2'))
def test_add_genome(self):
genome_1_truth = {
'unq': {
'PFAM_1': {
'hit': Hit('gene_a', 'PFAM_1', 0.05, 100),
'seq': 'VVVVVV'
},
'TIGR_1': {
'hit': Hit('gene_x', 'TIGR_1', 0.05, 100),
'seq': 'AAAAAA'
}
},
'muq': {
'PFAM_2': {
'hit': Hit('gene_b', 'PFAM_2', 0.05, 200),
'seq': 'AAVVPP'
}
},
'mul': {},
'mis': {
'PFAM_3': None,
'TIGR_2': None
}
}
genome_2_truth = {
'unq': {
'PFAM_2': {
'hit': Hit('gene_a', 'PFAM_2', 0.05, 100),
'seq': 'VVVVVV'
}
},
'muq': {
'TIGR_1': {
'hit': Hit('gene_x', 'TIGR_1', 0.05, 200),
'seq': 'AAAVVV'
},
'TIGR_2': {
'hit': Hit('gene_y', 'TIGR_2', 0.01, 100),
'seq': 'VVVAAA'
}
},
'mul': {
'PFAM_1': None,
'PFAM_3': None
},
'mis': {}
}
self.assertDictEqual(genome_1_truth, self.cn.genomes['genome_1'])
self.assertDictEqual(genome_2_truth, self.cn.genomes['genome_2'])
def test_hmm_str(self):
hit = Hit('gene_id', 'hmm_id', 0.05, 100)
self.assertEqual('hmm_id,0.05,100', hit.hmm_str())
def test___eq___equal(self):
self.assertEqual(Hit('gene_id', 'hmm_id', 1e-100, 1e-100),
Hit('gene_id', 'hmm_id', 1e-100, 1e-100))
def test___repr__(self):
hit = Hit('a', 'b', 0.05, 100)
self.assertEqual(f'a b (0.05/100)', repr(hit))
def test___init__(self):
hit = Hit('gene_id', 'hmm_id', 0.05, 100)
self.assertEqual('gene_id', hit.gene_id)
self.assertEqual('hmm_id', hit.hmm_id)
self.assertAlmostEqual(0.05, hit.e_val, 2)
self.assertAlmostEqual(100, hit.bit_score, 0)
def test_get_hmm_hit(self):
self.th.add_hit('a', 'b', 0.1, 10)
self.th.add_hit('a', 'c', 0.1, 20)
self.assertEqual(Hit('a', 'b', 0.1, 10), self.th.get_hmm_hit('a', 'b'))
def test_get_top_hit(self):
self.th.add_hit('a', 'b', 0.1, 10)
self.th.add_hit('a', 'c', 0.1, 20)
self.th.add_hit('a', 'd', 0.1, 5)
self.assertEqual(Hit('a', 'c', 0.1, 20), self.th.get_top_hit('a'))
self.assertIsNone(self.th.get_top_hit('x'))