def test_005_check_trim_ref(self):
v_orig = Variant('20', 14369, 'ATCGG', alt=['ATAGG', 'ATGGG'])
v_expt = Variant('20', 14371, 'C', alt=['A', 'G'])
v_trim = v_orig.trim()
self.assertEqual(v_expt, v_trim,
'Trimming failed for {}.'.format(v_expt))
def test_006_check_trim_ref(self):
v_orig = Variant('20', 14369, 'CCTG', alt=['C'])
v_expt = v_orig
v_trim = v_orig.trim()
self.assertEqual(v_expt, v_trim,
'Trimming failed for {}.'.format(v_expt))
def test_001_check_trim_start(self):
v_orig = Variant('20', 14369, 'GGC', alt=['GGA'])
v_expt = Variant('20', 14371, 'C', alt=['A'])
v_trim = v_orig.trim()
self.assertEqual(v_expt, v_trim,
'Trimming failed for {}.'.format(v_expt))
def test_002_check_trim_end(self):
v_orig = Variant('20', 14369, 'CGG', alt=['AGG'])
v_expt = Variant('20', 14369, 'C', alt=['A'])
v_trim = v_orig.trim()
self.assertEqual(v_expt, v_trim,
'Trimming failed for {}.'.format(v_expt))
def test_raises(self):
chrom = 'my_chrom'
ref_seq = 'ATGCTACTGC'
var = Variant(chrom, 2, 'GT', 'G') # ref should be GC
with self.assertRaises(ValueError):
get_padded_haplotypes(var, ref_seq, 2)
def test_003_check_merge_multi(self):
ref_seq = 'ATGGTATGCGATTGACC'
chrom = 'chrom1'
h1 = [
Variant(chrom,
0,
'ATG',
alt='G',
qual=5,
genotype_data={'GT': '1/1'}),
Variant(chrom,
4,
'T',
alt='G',
qual=5,
genotype_data={'GT': '1/1'}),
Variant(chrom,
7,
'G',
alt='GG',
qual=5,
genotype_data={'GT': '1/1'}),
Variant(chrom,
9,
ref_seq[9],
alt=ref_seq[9] + 'T',
qual=5,
genotype_data={'GT': '1/1'}),
]
h2 = [
Variant(chrom,
1,
'T',
alt='TT',
qual=10,
genotype_data={'GT': '1/1'}),
Variant(chrom,
2,
ref_seq[2:10],
alt=ref_seq[2],
qual=10,
genotype_data={'GT': '1/1'}),
]
# POS 0 1 2 3 4 5 6 7 8 9 10
# REF A T G G T A T G C G A
# H1 - - G G g A T Gg C Gt A
# H2 A Tt G - - - - - - - A
# expected merged variants
ref_expt = "ATGGTATGCG"
alt1_expt = "GGGATGGCGT"
alt2_expt = "ATTG"
expt = Variant(chrom,
0,
ref_expt,
alt=[alt1_expt, alt2_expt],
qual=7.5,
genotype_data={'GT': '1|2'})
comb_interval, trees = self.intervaltree_prep(h1, h2, ref_seq)
# preserve phase otherwise alts could be switched around
got = _merge_variants(comb_interval,
trees,
ref_seq,
discard_phase=False)
for key in ('chrom', 'pos', 'ref', 'qual', 'alt', 'gt', 'phased'):
expected = getattr(expt, key)
result = getattr(got, key)
self.assertEqual(
expected, result,
'Merging failed for {}:{} {}.'.format(expt.chrom, expt.pos + 1,
key))
def test_050_check_variant_contents(self):
expected = [
Variant(
'chr1',
14369,
'G',
alt=['A'],
ident='rs6054257',
qual=29,
filt='PASS',
info={
'NS': 3,
'DP': 14,
'AF': 0.5,
'DB': True,
'H2': True
},
genotype_data=OrderedDict([('GT', '1|0'), ('GQ', '48'),
('DP', '8'), ('HQ', '51,51')]),
),
Variant(
'chr2',
17329,
'T',
alt=['A'],
ident='.',
qual=3,
filt='q10',
info={
'NS': 3,
'DP': 11,
'AF': 0.017
},
genotype_data=OrderedDict([('GT', '0|0'), ('GQ', '49'),
('DP', '3'), ('HQ', '58,50')]),
),
Variant(
'chr10',
1110695,
'A',
alt=['G', 'T'],
ident='rs6040355',
qual=67,
filt='PASS',
info={
'NS': 2,
'DP': 10,
'AF': [0.333, 0.667],
'AA': 'T',
'DB': True
},
genotype_data=OrderedDict([('GT', '1|2'), ('GQ', '21'),
('DP', '6'), ('HQ', '23,27')]),
),
Variant(
'chr20',
1230236,
'T',
alt=['.'],
ident='.',
qual=47,
filt='PASS',
info={
'NS': 3,
'DP': 13,
'AA': 'T'
},
genotype_data=OrderedDict([('GT', '0|0'), ('GQ', '54'),
('DP', '7'), ('HQ', '56,60')]),
),
Variant(
'chrX',
1234566,
'GTCT',
alt=['G', 'GTACT'],
ident='microsat1',
qual=50,
filt='PASS',
info={
'NS': 3,
'DP': 9,
'AA': 'G'
},
genotype_data=OrderedDict([('GT', '1/1'), ('GQ', '40'),
('DP', '3')]),
)
]
result = list(self.vcf_reader.fetch())
self.assertSequenceEqual(result, expected)
def test_015_empty_info(self):
params = deepcopy(self.base_parameters)
del params['info']
variant = Variant(**params)
self.assertEqual(variant.info_string, ".")
def _make_variant(self, pos, ref, alt, gt):
return Variant(self.chrom, pos, ref, alt,
genotype_data={'GT': '{}|{}'.format(*gt),
'GQ': self.qual},
info=self.info)