def test_to_vcf_row_instantiated_variant_numeric_chrom(self):
factory = variant.VariantFactory()
v1 = factory.from_edit(1,2093,'TGG','CCC')
row = str(self.writer.get_row(v1))
row2 = str(v1)
self.assertIn('TGG', row)
self.assertIn('TGG', row2)
def test_get_vcf_row_instantiated_variant(self):
factory = variant.VariantFactory()
v1 = factory.from_edit('chr24',2093,'TGG','CCC')
row = self.writer.get_row(v1)
self.assertEqual(row.REF, 'TGG')
self.assertEqual(row.POS, 2094)
self.assertEqual(str(row), 'chr24\t2094\t.\tTGG\tCCC\t.\t.\t.')
gv = GenomVariant(v1, attrib={'id':'vrtid', 'filter':'LOWQUAL',
'qual':100})
row = self.writer.get_row(gv)
self.assertEqual(
str(row),'chr24\t2094\tvrtid\tTGG\tCCC\t100\tLOWQUAL\t.')
vrt = factory.from_edit('chr20', 1253922,'TGT','G')
row = self.writer.get_row(vrt)
self.assertEqual(str(row), 'chr20\t1253923\t.\tTGT\tG\t.\t.\t.')
# vf = VariantFactory(reference=ref,
# normindel=True)
vrt = factory.from_edit('chr1',13957,'TCCCCCA','TCCCCA')
with self.assertRaises(ValueError) as cm:
row = self.writer.get_row(vrt)
self.assertIn('Reference is required',cm.exception.args[0])
def test_haplotype_edit_equality(self):
factory = variant.VariantFactory()
v1 = factory.from_edit('chr24',2093,'TGG','CCC')
v2 = factory.from_edit('chr24',2098,'TT','GG')
v3 = factory.from_edit('chr24',2098,'TT','CC')
h1 = variant.Haplotype.from_variants([v1,v2])
h1_ = variant.Haplotype.from_variants([v1,v2])
h2 = variant.Haplotype.from_variants([v1,v3])
self.assertTrue(h1.edit_equal(h1_))
self.assertFalse(h1.edit_equal(h2))
def test_ambig_difference_snp_in_locus(self):
# 10043
# Ref TC-ACA--G
# v1 s1 CA
# v1 s2 G
# v2 s2 T
fac = variant.VariantFactory(reference=self.chr24, normindel=True)
s1 = VariantSet.from_variants(
[fac.from_edit('chr24', 10047, 'A', 'ACA')])
s2 = VariantSet.from_variants([
fac.from_edit('chr24', 10044, 'C', 'G'),
fac.from_edit('chr24', 10044, 'C', 'CT')
])
self.assertEqual(len(list(s1.comm(s2, match_ambig=True).iter_vrt())),
0)
def test_from_variants_to_records(self):
fac = variant.VariantFactory(reference=self.chr24, normindel=True)
hap = Haplotype.from_variants([
fac.from_edit('chr24', 1207, 'G', 'C'),
fac.from_edit('chr24', 1207, 'G', 'T')
])
vs = VariantSet.from_variants([
fac.from_edit('chr24', 10043, 'T', 'TCA'),
fac.from_edit('chr24', 10045, 'ACA', 'A'), hap
])
recs = vs.to_records()
self.assertEqual(recs.shape, (4, ))
self.assertEqual(list(recs.dtype.fields), [
'chrom', 'start', 'end', 'ref', 'alt', 'vartype', 'phase_group',
'attrib'
])
def test_strip_order_dependent_Ambig(self):
# 10043
# R T--CA--CAG
# v1 TCACA--CAG
# v2 T--CACACAG
factory = variant.VariantFactory(reference=pkg_file(
'genomvar.test', 'data/chr24.fna'),
normindel=True)
v1 = factory.from_edit('chr24', 10043, 'T', 'TCA')
v2 = factory.from_edit('chr24', 10045, 'A', 'ACA')
s1 = VariantSet.from_variants([v1])
s2 = VariantSet.from_variants([v2])
diff = s1.diff(s2, match_ambig=True)
self.assertEqual(len(list(diff.iter_vrt())), 0)
diff = s1.diff(s2, match_ambig=False)
self.assertEqual(len(list(diff.iter_vrt())), 1)
def test_ambig_difference_different_ambig(self):
# 10043
# Ref T--CA--CA--G
# v1 s1 T--CA--CACAG ins CA right
# v2 s1 T------CA--G del CA left
# v1 s2 TCACA--CA--G ins CA left
# v2 s2 T--CA------G del CA right
fac = variant.VariantFactory(reference=self.chr24, normindel=True)
s1 = VariantSet.from_variants([
fac.from_edit('chr24', 10047, 'A', 'ACA'),
fac.from_edit('chr24', 10043, 'TCA', 'T')
])
s2 = VariantSet.from_variants([
fac.from_edit('chr24', 10043, 'T', 'TCA'),
fac.from_edit('chr24', 10045, 'ACA', 'A')
])
self.assertEqual(len(list(s1.diff(s2, match_ambig=True).iter_vrt())),
0)
def test_no_ovlp(self):
# REF TGG TT
# 2093 2099
# CCC GG
# CG
factory = variant.VariantFactory()
variants = [
factory.from_edit('1', 2093, 'TGG', 'CCC'),
factory.from_edit('1', 2098, 'TT', 'GG'),
factory.from_edit('1', 2098, 'TT', 'CG'),
factory.from_edit('2', 3200, 'G', 'GG')
]
for ind, chunk in enumerate(no_ovlp(variants)):
if ind == 0:
self.assertEqual(len(chunk), 1)
elif ind == 1:
self.assertEqual(len(chunk), 2)
if ind == 2:
self.assertEqual(len(chunk), 1)
def setUp(self):
self.chr24 = Reference(
pkg_file(__name__,'data/chr24.fna'))
self.nvf = variant.VariantFactory(self.chr24,normindel=True)
# Factory not normalizing indels
self.svf = variant.VariantFactory()
def test_min_mnps(self):
factory = variant.VariantFactory()
v1 = factory.from_edit('1', 1, 'AAA', 'GGG')
v2 = factory.from_edit('1', 1, 'AAA', 'GGC')
v3 = factory.from_edit('1', 1, 'AAA', 'CGG')
self.assertEqual(nof_snp_vrt([v1, v2, v3]), 5)
from genomvar import OverlappingHaplotypeVars,\
UnsortedVariantFileError,VCFSampleMismatch,NoIndexFoundError
from genomvar.vcf import VCFRow, VCFReader, RESERVED_FORMAT
from genomvar import variant
from genomvar.test import MyTestCase
# Representation of an example used here a lot (example1.vcf)
#
# REF AG T| T| C G TGG TT G| T T CACAGTTCCAC
# 22 154 165 453 1206 2093 2099 3200 4754 6145 10044
# varset1 A TT TG CT C CCC GG GG TCG C T----------
# AGG TT TG T CCC GG GG T G G----------
# AG -------- ------ phased
# FILT h h;n n n
factory = variant.VariantFactory()
class TestVariantSetCase(MyTestCase):
def test_empty_vcf(self):
buf = io.StringIO()
with open(pkg_file('genomvar.test', 'data/example1.vcf')) as fh:
for line in itertools.takewhile(lambda l: l.startswith('#'), fh):
buf.write(line)
buf.seek(0)
vs = VariantSet.from_vcf(buf)
self.assertEqual(vs.nof_unit_vrt(), 0)
def test_random_sample(self):
vs = VariantSet.from_vcf(pkg_file('genomvar.test',
'data/example1.vcf'))
