def main(args):
# init hail
hl.init(default_reference=args.default_ref_genome)
# input MT
mt = hl.read_matrix_table(args.mt_input_path)
# filter high-quality genotype
# mt = filter_genotypes_ab(mt)
# import capture interval table (intersect)
intervals = hl.read_table(args.ht_intervals)
# generate an interval x sample MT by computing per intervals callrate
mt_callrate = compute_callrate_mt(mt=mt, intervals_ht=intervals)
# run pca
eigenvalues, ht_pca, _ = run_platform_pca(
callrate_mt=mt_callrate,
binarization_threshold=args.binarization_threshold)
# normalize eigenvalues (0-100)
eigenvalues_norm = [x / sum(eigenvalues) * 100 for x in eigenvalues]
# compute eigenvalues cumulative sum
ev_cumsum = hl.array_scan(lambda i, j: i + j, 0,
hl.array(eigenvalues_norm))
# getting optimal number of PCs (those which explain 99% of the variance)
n_optimal_pcs = hl.eval(hl.len(ev_cumsum.filter(lambda x: x < 99.0)))
logger.info(
f"Keep only principal components which explain up to 99% of the variance. Number of optimal PCs found: {n_optimal_pcs}"
)
# filter out uninformative PCs
ht_pca = ht_pca.annotate(scores=ht_pca.scores[:n_optimal_pcs])
# apply unsupervised clustering on PCs to infer samples platform
ht_platform = assign_platform_from_pcs(
platform_pca_scores_ht=ht_pca,
pc_scores_ann='scores',
hdbscan_min_cluster_size=args.hdbscan_min_cluster_size,
hdbscan_min_samples=args.hdbscan_min_cluster_size)
ht_platform.show()
# write HT
ht_platform.write(output=args.ht_output_path, overwrite=args.overwrite)
# export to file if true
if args.write_to_file:
(ht_platform.export(f'{args.ht_output_path}.tsv.bgz'))
hl.stop()
def gnomad_coverage_stats_optimized(mt_path):
mt = hl.read_matrix_table(mt_path)
mt = mt.annotate_rows(
mean=hl.agg.mean(mt.x),
count_array=hl.rbind(
hl.agg.counter(hl.min(100, mt.x)),
lambda c: hl.range(0, 100).map(lambda i: c.get(i, 0))))
mt = mt.annotate_rows(median=hl.rbind(
hl.sum(mt.count_array) / 2, lambda s: hl.find(
lambda x: x > s,
hl.array_scan(lambda i, j: i + j, 0, mt.count_array))),
**{
f'above_{x}': hl.sum(mt.count_array[x:])
for x in [1, 5, 10, 15, 20, 25, 30, 50, 100]
})
mt.rows()._force_count()