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 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 calc_ld_random_pairs_from_different_chroms(variations, num_pairs,
max_maf=0.95, min_num_gts=10,
silence_runtime_warnings=False):
chroms = va.make_sure_array_is_in_memory(variations[CHROM_FIELD],
silence_runtime_warnings=silence_runtime_warnings)
different_chroms = np.unique(chroms)
if different_chroms.size < 2:
raise ValueError('Only one chrom in variations')
max_alleles = variations[ALT_FIELD].shape[1]
mafs = calc_maf_by_gt(variations, max_alleles, min_num_gts)
mafs = va.make_sure_array_is_in_memory(mafs,
silence_runtime_warnings=silence_runtime_warnings)
if va.any(va.isnan(mafs)) or va.any(mafs > max_maf):
msg = 'Not enough genotypes or MAF below allowed maximum, Rogers Huff calculations known to go wrong for very high maf'
raise RuntimeError(msg)
gts = va.make_sure_array_is_in_memory(variations[GT_FIELD],
silence_runtime_warnings=silence_runtime_warnings)
num_variations = gts.shape[0]
pairs_computed = 0
while True:
snp_idx1 = random.randrange(num_variations)
snp_idx2 = random.randrange(num_variations)
chrom1 = chroms[snp_idx1]
chrom2 = chroms[snp_idx2]
if chrom1 == chrom2:
continue
gts_snp1 = gts[snp_idx1]
gts_snp2 = gts[snp_idx2]
r2_ld = _calc_rogers_huff_r_for_snp_pair(gts_snp1, gts_snp2,
min_num_gts=min_num_gts)
if not math.isnan(r2_ld):
yield chrom1, snp_idx1, chrom2, snp_idx2, r2_ld
pairs_computed += 1
if pairs_computed >= num_pairs:
break
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
def _calc_obs_het_counts(variations, axis, min_call_dp_for_het_call,
max_call_dp_for_het_call=None):
is_missing = va.any(variations[GT_FIELD] == MISSING_INT, axis=2)
if min_call_dp_for_het_call is not None or max_call_dp_for_het_call is not None:
dps = variations[DP_FIELD]
if min_call_dp_for_het_call is not None:
low_dp = dps < min_call_dp_for_het_call
is_missing = va.logical_or(is_missing, low_dp)
if max_call_dp_for_het_call is not None:
high_dp = dps > max_call_dp_for_het_call
is_missing = va.logical_or(is_missing, high_dp)
is_het = _call_is_het(variations, is_missing=is_missing)
return (va.sum(is_het, axis=axis),
va.sum(va.logical_not(is_missing), axis=axis))