def test_make_slices_default_settings(self):
"""Test slicing function with default settings: 500 bp slices"""
for count, i in enumerate(VCF.get_slice_indicies(self.bgzip_path, regions=None, window_size=500)):
if count > 10:
break
self.assertEqual(i, ('Chr01', 5501, 6000))
def test_heterozyogote_outgroup_calling(self):
vcf_line = self.vcf_line
vcf_line['out1']['GT'] = '1/1'
vcf_line['out2']['GT'] = '1/0'
het = VCF.process_outgroup(vcf_line, self.populations)
self.assertEqual(het, None)
def test_diff_homozygotes_outgroups_calling(self):
vcf_line = self.vcf_line
vcf_line['out1']['GT'] = '1/1'
vcf_line['out2']['GT'] = '0/0'
diff = VCF.process_outgroup(vcf_line, self.populations)
self.assertEqual(diff, None)
def test_make_slices_default_with_params_set(self):
"""Test slicing function with window_size set"""
for count, i in enumerate(VCF.get_slice_indicies(self.bgzip_path, regions=None, window_size=1008)):
if count > 10:
break
self.assertEqual(i, ('Chr01', 11089, 12096))
def test_home_alt_outgroup_calling(self):
vcf_line = self.vcf_line
vcf_line['out1']['GT'] = '1/1'
vcf_line['out2']['GT'] = '1/1'
homo_alt = VCF.process_outgroup(vcf_line, self.populations)
self.assertEqual(homo_alt, '1')
def test_header_vs_population_sample_ids(self):
"""Check that the sample IDs parsed from the population arguement
match those in the VCF file.
NOTE: In practice the populations arguement can contain fewer
samples and populations than actually contained in the VCF file.
"""
header = VCF.make_empty_vcf_ordered_dict(self.bgzip_path, )
header_sample_ids = [item for count, item in enumerate(header) if count >= 9]
populations_dict = VCF.parse_populations_list(self.populations_list)
populations_sample_ids = [i for l in populations_dict.values() for i in l]
# Check both unique IDs and equal length
self.assertEqual(set(header_sample_ids), set(populations_sample_ids))
self.assertEqual(len(header_sample_ids), len(populations_sample_ids))
def test_population_string_parsing(self):
populations = VCF.parse_populations_list(self.populations_list)
self.assertEqual(populations, {'melpo': ['m523', 'm524', 'm525',
'm589', 'm675', 'm676', 'm682', 'm683', 'm687', 'm689'],
'pachi': ['p516', 'p517', 'p518', 'p519', 'p520', 'p591',
'p596', 'p690', 'p694', 'p696'], 'cydno': ['c511',
'c512', 'c513', 'c514', 'c515', 'c563', 'c614', 'c630',
'c639', 'c640'], 'outgroups': ['h665', 'i02-210']})
def test_calc_fstats_normal_allele_counts(self):
f_statistics = VCF.calc_fstats(self.normal_allele_counts)
self.assertEqual(
{'G_prime_st_est': 0.9140159767610748,
'D_est': 0.7581699346405228,
'G_double_prime_st_est': 0.9477124183006534,
'Gst_est': 0.6444444444444445,
'Hs_est': 0.1729729729729729,
'Ht_est': 0.48648648648648646},
f_statistics[('pachi', 'outgroups')])
def test_trivial_calc_multilocus_f_statistics(self):
ml_stats = VCF.calc_multilocus_f_statistics(self.trivial_Hs_est_dict, self.trivial_Ht_est_dict)
self.assertEqual({('pop1', 'pop2'):
{'G_prime_st_est': 0.0,
'Gst_est.stdev': 0.0,
'G_double_prime_st_est.stdev': 0.0,
'G_double_prime_st_est': 0.0,
'Gst_est': 0.0,
'D_est.stdev': 0.0,
'G_prime_st_est.stdev': 0.0,
'D_est': 0.0}}, ml_stats)
def test_trivial_2_calc_multilocus_f_statistics(self):
ml_stats = VCF.calc_multilocus_f_statistics(self.trivial_2_Hs_est_dict, self.trivial_2_Ht_est_dict)
self.assertEqual({('pop1', 'pop2'):
{'G_prime_st_est': 0.8333333333333334,
'Gst_est.stdev': 0.09999999999999998,
'G_double_prime_st_est.stdev': 0.060586734693877375,
'G_double_prime_st_est': 0.8888888888888888,
'Gst_est': 0.5,
'D_est.stdev': 0.08928571428571419,
'G_prime_st_est.stdev': 0.07857142857142851,
'D_est': 0.6488650338184054}}, ml_stats)
def test_calc_multilocus_f_statistics(self):
ml_stats = VCF.calc_multilocus_f_statistics(self.Hs_est_dict, self.Ht_est_dict)
self.assertEqual({('pop1', 'pop2'):
{'Gst_est': 0.30312672938572266,
'Gst_est.stdev': 1.3360742705570265,
'G_double_prime_st_est': 0.5003506191636901,
'G_double_prime_st_est.stdev': 2.394045897494315,
'G_prime_st_est': 0.34889353651117816,
'G_prime_st_est.stdev': 1.6091544573608876,
'D_est': 0.0015629851350084287,
'D_est.stdev': 0.25110803099568757}}, ml_stats)
def test_calc_fstats_trivial_allele_counts(self):
f_statistics = VCF.calc_fstats(self.trivial_allele_counts)
self.assertEqual(
{('pop2', 'pop1'):
{'G_prime_st_est': 0.6803049722304385,
'D_est': 0.517460317460318,
'G_double_prime_st_est': 0.7609710550887027,
'Gst_est': 0.33747412008281613,
'Hs_est': 0.3368421052631577,
'Ht_est': 0.508421052631579}},
f_statistics)
def callSNPs(current_base, numb_of_seqs):
"""Call the SNPs. Duh!"""
blanks = np.zeros(numb_of_seqs, np.string0)
if current_base.FILTER == 'LowQual':
blanks.fill("-")
if current_base.FORMAT == 'GT':
blanks.fill("-")
for count, snp_call in enumerate(current_base[9:]):
base = VCF.process_snp_call(snp_call, current_base.REF, current_base.ALT)
blanks[count] = base
return blanks
def callSNPs(current_base, numb_of_seqs, IUPAC_ambiguities=True):
"""Call the SNPs. Duh!"""
blanks = np.zeros(numb_of_seqs, np.string0)
#print current_base.REF, current_base.ALT
if current_base.FILTER == 'LowQual':
blanks.fill("-")
#elif current_base.FORMAT == 'GT':
# blanks.fill("-")
elif len(current_base.ALT) > 1 or len(current_base.REF) > 1:
blanks.fill("-")
else:
for count, snp_call in enumerate(current_base[9:]):
base = VCF.process_snp_call(snp_call, current_base.REF, current_base.ALT, IUPAC_ambiguities=True)
blanks[count] = base
return blanks
def test_homo_alt_genotype_calling(self):
homo_alt = VCF.process_snp_call('1/1:10,9:19:99:254,0,337', 'A', 'T', IUPAC_ambiguities=True)
self.assertEqual(homo_alt, 'T')
def test_double_alt_genotype_calling(self):
double_alt = VCF.process_snp_call('1/2:10,9:19:99:254,0,337', 'A', 'T,G', IUPAC_ambiguities=True)
self.assertEqual(double_alt, 'K')
def test_header_to_ordered_dict_parsing(self):
header = VCF.make_empty_vcf_ordered_dict(self.bgzip_path)
self.assertEqual(header, self.header_dict)
def test_heterozygote_as_N_genotype_calling(self):
heterozygote_as_N = VCF.process_snp_call('0/1:10,9:19:99:254,0,337', 'A', 'T', IUPAC_ambiguities=False)
self.assertEqual(heterozygote_as_N, 'N')
def test_double_alt_het_as_N_genotype_calling(self):
double_alt_het_as_N = VCF.process_snp_call('1/2:10,9:19:99:254,0,337', 'A', 'T,G', IUPAC_ambiguities=False)
self.assertEqual(double_alt_het_as_N, 'N')
def test_home_ref_outgroup_calling(self):
homo_ref = VCF.process_outgroup(self.vcf_line, self.populations)
self.assertEqual(homo_ref, '0')
def test_second_alt_genotype_calling(self):
second_alt = VCF.process_snp_call('0/2:10,9:19:99:254,0,337', 'A', 'T,G', IUPAC_ambiguities=True)
self.assertEqual(second_alt, 'R')
