def test_king_filtered_entries_no_error():
plink_path = resource('balding-nichols-1024-variants-4-samples-3-populations')
mt = hl.import_plink(bed=f'{plink_path}.bed',
bim=f'{plink_path}.bim',
fam=f'{plink_path}.fam')
mt = mt.filter_entries(hl.rand_bool(0.5))
hl.king(mt.GT)._force_count_rows()
def query():
"""Query script entry point."""
hl.init(default_reference='GRCh38')
mt = hl.read_matrix_table(HGDP1KG_TOBWGS)
mt = mt.filter_cols(
(mt.hgdp_1kg_metadata.population_inference.pop == 'nfe')
| (mt.s.contains('TOB'))
)
# Remove related samples (at the 2nd degree or closer)
king = hl.king(mt.GT)
king_path = output_path('king_kinship_estimate_NFE.ht')
king.write(king_path)
ht = king.entries()
related_samples = ht.filter((ht.s_1 != ht.s) & (ht.phi > 0.125), keep=True)
struct = hl.struct(i=related_samples.s_1, j=related_samples.s)
struct = struct.annotate(phi=related_samples.phi)
related_samples_to_remove = hl.maximal_independent_set(
struct.i, struct.j, False # pylint: disable=E1101
)
n_related_samples = related_samples_to_remove.count()
print(f'related_samples_to_remove.count() = {n_related_samples}')
# save as html
html = pd.DataFrame(
{'related_individual': related_samples_to_remove.node.collect()}
).to_html()
plot_filename_html = output_path(f'related_samples.html', 'web')
with hl.hadoop_open(plot_filename_html, 'w') as f:
f.write(html)
def test_king_large():
plink_path = resource('fastlmmTest')
mt = hl.import_plink(bed=f'{plink_path}.bed',
bim=f'{plink_path}.bim',
fam=f'{plink_path}.fam',
reference_genome=None)
kinship = hl.king(mt.GT)
assert_c_king_same_as_hail_king(resource('fastlmmTest.kin0.bgz'), kinship)
def test_king_small():
plink_path = resource('balding-nichols-1024-variants-4-samples-3-populations')
mt = hl.import_plink(bed=f'{plink_path}.bed',
bim=f'{plink_path}.bim',
fam=f'{plink_path}.fam')
kinship = hl.king(mt.GT)
assert_c_king_same_as_hail_king(
resource('balding-nichols-1024-variants-4-samples-3-populations.kin0'),
kinship)
def relatedness_check(in_mt: hl.MatrixTable = None,
method: str = 'pc_relate',
outdir: str = None,
kin_estimate: float = 0.98):
global mt, samples_to_remove
in_mt = hl.variant_qc(in_mt)
in_mt = hl.sample_qc(in_mt)
# _localize=False means don't put this in Python, keep it as a Hail expr
call_rate_dict = in_mt.aggregate_cols(hl.dict(
hl.agg.collect((in_mt.s, in_mt.sample_qc.call_rate))),
_localize=False)
if method == 'pc_relate':
print("\nUsing PC-Relate for relatedness checks")
relatedness_ht = hl.pc_relate(in_mt.GT,
0.01,
k=10,
min_kinship=0.1,
statistics='kin')
samples_to_remove_ht = relatedness_ht.filter(
relatedness_ht.kin > kin_estimate)
# get call rates for both samples so we remove the one with lower call rate between the two
samples_to_remove = samples_to_remove_ht.annotate(
cr_s1=call_rate_dict[samples_to_remove_ht.i.s],
cr_s2=call_rate_dict[samples_to_remove_ht.j.s])
samples_list = samples_to_remove.annotate(sample_to_remove=hl.cond(
samples_to_remove.cr_s1 <= samples_to_remove.cr_s2,
samples_to_remove.i, samples_to_remove.j))
elif method == 'ibd':
print("\nUsing PLINK-style identity by descent for relatedness checks")
in_mt = in_mt.annotate_rows(maf=hl.min(in_mt.variant_qc.AF))
relatedness_ht = hl.identity_by_descent(
in_mt, maf=in_mt['maf']
) # this returns a Hail Table with the sample pairs
samples_to_remove_ht = relatedness_ht.filter(
relatedness_ht.ibd.PI_HAT > kin_estimate)
# get call rates for both samples so we remove the one with lower call rate between the two
samples_to_remove = samples_to_remove_ht.annotate(
cr_s1=call_rate_dict[samples_to_remove_ht.i],
cr_s2=call_rate_dict[samples_to_remove_ht.j])
samples_list = samples_to_remove.annotate(sample_to_remove=hl.cond(
samples_to_remove.cr_s1 <= samples_to_remove.cr_s2,
samples_to_remove.i, samples_to_remove.j))
else:
print("\nUsing KING for relatedness checks")
if kin_estimate > 0.5:
raise Exception(
"\nThe maximum kinship coefficient is for KING 0.5")
relatedness_mt = hl.king(in_mt.GT)
filtered_relatedness_mt = relatedness_mt.filter_entries(
(relatedness_mt.s_1 != relatedness_mt.s) &
(relatedness_mt.phi >= kin_estimate),
keep=True)
samples_to_remove_ht = filtered_relatedness_mt.entries()
samples_to_remove = samples_to_remove_ht.annotate(
cr_s1=call_rate_dict[samples_to_remove_ht.s_1],
cr_s2=call_rate_dict[samples_to_remove_ht.s])
samples_list = samples_to_remove.annotate(sample_to_remove=hl.cond(
samples_to_remove.cr_s1 <= samples_to_remove.cr_s2,
samples_to_remove.s_1, samples_to_remove.s))
samples = samples_list.sample_to_remove.collect()
if len(samples) > 0:
in_mt = in_mt.filter_cols(hl.literal(samples).contains(in_mt['s']),
keep=False)
print("\nNumber of samples that fail relatedness checks: {}".format(
len(samples)))
with open(outdir + 'relatedness_removed_samples.tsv', 'w') as f:
for sample in samples:
f.write(sample + "\n")
else:
print("\nNo samples failed the relatedness check")
return in_mt
def king():
mt = hl.balding_nichols_model(6, n_variants=10000, n_samples=4096)
path = hl.utils.new_temp_file(extension='mt')
hl.king(mt.GT).write(path, overwrite=True)