def keep_variable_variations(variations,
max_alleles,
filter_id='variable_variations'):
gts = variations[GT_FIELD]
some_not_missing_gts = va.any(gts != MISSING_INT, axis=2)
selected_vars1 = va.any(some_not_missing_gts, axis=1)
allele_counts = count_alleles(gts,
max_alleles=max_alleles,
count_missing=False)
num_alleles_per_snp = va.sum(allele_counts > 0, axis=1)
selected_vars2 = num_alleles_per_snp > 1
selected_vars = va.logical_and(selected_vars1, selected_vars2)
selected_variations = variations.get_vars(selected_vars)
num_selected_vars = va.count_nonzero(selected_vars)
num_filtered = va.count_nonzero(va.logical_not(selected_vars))
flt_stats = {N_KEPT: num_selected_vars, N_FILTERED_OUT: num_filtered}
return {
FLT_VARS: selected_variations,
FLT_ID: filter_id,
FLT_STATS: flt_stats
}
def _call_is_hom_in_memory(gts):
is_hom = va.create_full_array_in_memory(gts.shape[:-1],
True,
dtype=numpy.bool)
for idx in range(1, gts.shape[2]):
is_hom = va.logical_and(gts[:, :, idx] == gts[:, :, idx - 1], is_hom)
return is_hom
def gts_as_mat012(gts):
'''It transforms the GT matrix into 0 (major allele h**o), 1 (het),
2(other hom)'''
gts012 = va.sum(gts, axis=2)
gts012[va.any(gts == MISSING_INT, axis=2)] = MISSING_INT
gts012[gts012 >= 1 ] = 2
gts012[va.logical_and(gts012 == 2, va.any(gts == 0, axis=2))] = 1
return gts012
def _select_variations_in_region(variations, regions):
chroms = variations[CHROM_FIELD]
poss = variations[POS_FIELD]
in_any_region = None
for region in regions:
desired_chrom = region[0]
if isinstance(desired_chrom, (tuple, list)):
raise ValueError('Malformed region: ' + str(region))
in_this_region = chroms[:] == desired_chrom
if len(region) > 1:
in_this_region = va.logical_and(
in_this_region,
va.logical_and(region[1] <= poss, poss < region[2]))
if in_any_region is None:
in_any_region = in_this_region
else:
in_any_region = va.logical_or(in_any_region, in_this_region)
return in_any_region
def _kosman(vars1, vars2):
indi1, indi2 = _get_gts_non_missing_in_both(vars1, vars2)
if indi1.shape[1] != 2:
raise ValueError('Only diploid are allowed')
alleles_comparison1 = indi1 == indi2.transpose()[:, :, None]
alleles_comparison2 = indi2 == indi1.transpose()[:, :, None]
result = va.add(va.any(alleles_comparison2, axis=2).sum(axis=0),
va.any(alleles_comparison1, axis=2).sum(axis=0),
dtype=np.float64)
result[result == 0] = 1
result[result == 4] = 0
mask = va.logical_and(result != 1, result != 0)
result[mask] = 0.5
return result