def _calc_stat(self, variations):
vars_for_stat = self._filter_samples_for_stats(variations)
assert len(vars_for_stat.samples) == self.sample_dp_means.shape[0]
dps = vars_for_stat[DP_FIELD]
if dps.shape[0] == 0:
# No SNPs
raise ValueError('No SNPs to filter')
if is_dataset(dps):
dps = dps[:]
num_no_miss_calls = numpy.sum(dps > 0, axis=1)
high_dp_calls = dps > self._too_high_dps
het_calls = call_is_het(vars_for_stat[GT_FIELD])
het_and_high_dp_calls = numpy.logical_and(high_dp_calls, het_calls)
num_high_dp_and_het_calls = numpy.sum(het_and_high_dp_calls, axis=1)
with numpy.errstate(all='ignore'):
# This is the stat
freq_high_dp_and_het_calls = (num_high_dp_and_het_calls /
num_no_miss_calls)
return freq_high_dp_and_het_calls
def _calc_sample_missing_rates(variations, chunk_size, min_called_rate,
max_het):
if chunk_size is None:
chunks = [variations]
else:
chunks = variations.iterate_chunks(kept_fields=[GT_FIELD],
chunk_size=chunk_size)
missing = None
het_counts = None
for chunk in chunks:
chunk_missing = calc_called_gt(chunk, rates=False, axis=0)
if min_called_rate is not None:
if missing is None:
missing = chunk_missing
else:
missing += chunk_missing
if max_het is not None:
is_het = call_is_het(chunk[GT_FIELD])
chunk_het_counts = numpy.sum(is_het, axis=0)
if het_counts is None:
het_counts = chunk_het_counts
else:
het_counts += chunk_het_counts
res = {}
if min_called_rate is not None:
rates = missing / variations.num_variations
res['missing_rates'] = rates
if max_het is not None:
obs_hets = het_counts / variations.num_variations
res['obs_hets'] = obs_hets
return res
def __call__(self, variations):
vars_for_stat = self._filter_samples_for_stats(variations)
assert len(vars_for_stat.samples) == self.sample_dp_means.shape[0]
dps = vars_for_stat[DP_FIELD]
if is_dataset(dps):
dps = dps[:]
num_no_miss_calls = numpy.sum(dps > 0, axis=1)
high_dp_calls = dps > self._too_high_dps
num_high_dp_calls = numpy.sum(high_dp_calls, axis=1)
with numpy.errstate(all='ignore'):
# This is the stat
freq_high_dp = num_high_dp_calls / num_no_miss_calls
result = {}
if self.do_histogram:
counts, edges = histogram(freq_high_dp,
n_bins=self.n_bins,
range_=self.range)
result[COUNTS] = counts
result[EDGES] = edges
if self.do_filtering or self.report_selection:
het_call = call_is_het(vars_for_stat[GT_FIELD])
with numpy.errstate(all='ignore'):
obs_het = numpy.sum(het_call, axis=1) / num_no_miss_calls
with numpy.errstate(all='ignore'):
too_much_het = numpy.greater(obs_het, self.max_obs_het)
with numpy.errstate(all='ignore'):
snps_too_high = numpy.greater(freq_high_dp,
self.max_high_dp_freq)
to_remove = numpy.logical_and(too_much_het, snps_too_high)
selected_snps = numpy.logical_not(to_remove)
if self.report_selection:
result[SELECTED_VARS] = selected_snps
if self.do_filtering:
flt_vars = variations.get_chunk(selected_snps)
n_kept = numpy.count_nonzero(selected_snps)
tot = selected_snps.shape[0]
n_filtered_out = tot - n_kept
result[FLT_VARS] = flt_vars
result[FLT_STATS] = {
N_KEPT: n_kept,
N_FILTERED_OUT: n_filtered_out,
TOT: tot
}
return result
def __call__(self, variations):
vars_for_stat = self._filter_samples_for_stats(variations)
assert len(vars_for_stat.samples) == self.sample_dp_means.shape[0]
dps = vars_for_stat[DP_FIELD]
if is_dataset(dps):
dps = dps[:]
num_no_miss_calls = numpy.sum(dps > 0, axis=1)
high_dp_calls = dps > self._too_high_dps
num_high_dp_calls = numpy.sum(high_dp_calls, axis=1)
with numpy.errstate(all='ignore'):
# This is the stat
freq_high_dp = num_high_dp_calls / num_no_miss_calls
result = {}
if self.do_histogram:
counts, edges = histogram(freq_high_dp, n_bins=self.n_bins,
range_=self.range)
result[COUNTS] = counts
result[EDGES] = edges
if self.do_filtering or self.report_selection:
het_call = call_is_het(vars_for_stat[GT_FIELD])
with numpy.errstate(all='ignore'):
obs_het = numpy.sum(het_call, axis=1) / num_no_miss_calls
with numpy.errstate(all='ignore'):
too_much_het = numpy.greater(obs_het, self.max_obs_het)
with numpy.errstate(all='ignore'):
snps_too_high = numpy.greater(freq_high_dp,
self.max_high_dp_freq)
to_remove = numpy.logical_and(too_much_het, snps_too_high)
selected_snps = numpy.logical_not(to_remove)
if self.report_selection:
result[SELECTED_VARS] = selected_snps
if self.do_filtering:
flt_vars = variations.get_chunk(selected_snps)
n_kept = numpy.count_nonzero(selected_snps)
tot = selected_snps.shape[0]
n_filtered_out = tot - n_kept
result[FLT_VARS] = flt_vars
result[FLT_STATS] = {N_KEPT: n_kept,
N_FILTERED_OUT: n_filtered_out,
TOT: tot}
return result
def _calc_stat(self, variations):
vars_for_stat = self._filter_samples_for_stats(variations)
assert len(vars_for_stat.samples) == self.sample_dp_means.shape[0]
dps = vars_for_stat[DP_FIELD]
if is_dataset(dps):
dps = dps[:]
num_no_miss_calls = numpy.sum(dps > 0, axis=1)
high_dp_calls = dps > self._too_high_dps
het_calls = call_is_het(vars_for_stat[GT_FIELD])
het_and_high_dp_calls = numpy.logical_and(high_dp_calls, het_calls)
num_high_dp_and_het_calls = numpy.sum(het_and_high_dp_calls, axis=1)
with numpy.errstate(all='ignore'):
# This is the stat
freq_high_dp_and_het_calls = (num_high_dp_and_het_calls /
num_no_miss_calls)
return freq_high_dp_and_het_calls
