def get_gnomad_v3_mt(
split=False,
key_by_locus_and_alleles: bool = False,
remove_hard_filtered_samples: bool = True,
release_only: bool = False,
samples_meta: bool = False,
) -> hl.MatrixTable:
"""
Wrapper function to get gnomAD data with desired filtering and metadata annotations
:param split: Perform split on MT - Note: this will perform a split on the MT rather than grab an already split MT
:param key_by_locus_and_alleles: Whether to key the MatrixTable by locus and alleles (only needed for v3)
:param remove_hard_filtered_samples: Whether to remove samples that failed hard filters (only relevant after sample QC)
:param release_only: Whether to filter the MT to only samples available for release (can only be used if metadata is present)
:param samples_meta: Whether to add metadata to MT in 'meta' column
:return: gnomAD v3 dataset with chosen annotations and filters
"""
mt = gnomad_v3_genotypes.mt()
if key_by_locus_and_alleles:
mt = hl.MatrixTable(
hl.ir.MatrixKeyRowsBy(
mt._mir, ["locus", "alleles"], is_sorted=True
) # Prevents hail from running sort on genotype MT which is already sorted by a unique locus
)
if remove_hard_filtered_samples:
mt = mt.filter_cols(
hl.is_missing(hard_filtered_samples.ht()[mt.col_key]))
if samples_meta:
mt = mt.annotate_cols(meta=meta.ht()[mt.col_key])
if release_only:
mt = mt.filter_cols(mt.meta.release)
elif release_only:
mt = mt.filter_cols(meta.ht()[mt.col_key].release)
if split:
mt = mt.annotate_rows(
n_unsplit_alleles=hl.len(mt.alleles),
mixed_site=(hl.len(mt.alleles) > 2)
& hl.any(lambda a: hl.is_indel(mt.alleles[0], a), mt.alleles[1:])
& hl.any(lambda a: hl.is_snp(mt.alleles[0], a), mt.alleles[1:]),
)
mt = hl.experimental.sparse_split_multi(mt, filter_changed_loci=True)
return mt
def run_mendel_errors() -> hl.Table:
meta_ht = meta.ht()
ped = pedigree.versions[f"{CURRENT_RELEASE}_raw"].pedigree()
logger.info(f"Running Mendel errors for {len(ped.trios)} trios.")
fake_ped = create_fake_pedigree(
n=100,
sample_list=list(
meta_ht.aggregate(
hl.agg.filter(
hl.rand_bool(0.01)
& ((hl.len(meta_ht.qc_metrics_filters) == 0)
& hl.or_else(hl.len(meta_ht.hard_filters) == 0, False)),
hl.agg.collect_as_set(meta_ht.s),
))),
real_pedigree=ped,
)
merged_ped = hl.Pedigree(trios=ped.trios + fake_ped.trios)
ped_samples = hl.literal(
set([
s for trio in merged_ped.trios
for s in [trio.s, trio.pat_id, trio.mat_id]
]))
mt = get_gnomad_v3_mt(key_by_locus_and_alleles=True)
mt = mt.filter_cols(ped_samples.contains(mt.s))
mt = hl.filter_intervals(
mt, [hl.parse_locus_interval("chr20", reference_genome='GRCh38')])
mt = hl.experimental.sparse_split_multi(mt, filter_changed_loci=True)
mt = mt.select_entries("GT", "END")
mt = hl.experimental.densify(mt)
mt = mt.filter_rows(hl.len(mt.alleles) == 2)
mendel_errors, _, _, _ = hl.mendel_errors(mt["GT"], merged_ped)
return mendel_errors
def get_gnomad_v3_mt(key_by_locus_and_alleles: bool = False,
remove_hard_filtered_samples: bool = True,
release_only: bool = False,
samples_meta: bool = False) -> hl.MatrixTable:
mt = gnomad_v3_genotypes.mt()
if key_by_locus_and_alleles:
mt = hl.MatrixTable(
hl.ir.MatrixKeyRowsBy(mt._mir, ['locus', 'alleles'],
is_sorted=True))
if remove_hard_filtered_samples:
mt = mt.filter_cols(
hl.is_missing(hard_filtered_samples.ht()[mt.col_key]))
if samples_meta:
mt = mt.annotate_cols(meta=meta.ht()[mt.col_key])
if release_only:
mt = mt.filter_cols(mt.meta.release)
elif release_only:
mt = mt.filter_cols(meta.ht()[mt.col_key].release)
return mt
def run_infer_families() -> hl.Pedigree:
logger.info("Inferring families")
ped = infer_families(get_relatedness_annotated_ht(), sex.ht(),
duplicates.ht())
# Remove all trios containing any QC-filtered sample
meta_ht = meta.ht()
filtered_samples = meta_ht.aggregate(
hl.agg.filter(
(hl.len(meta_ht.qc_metrics_filters) > 0)
| hl.or_else(hl.len(meta_ht.hard_filters) > 0, False),
hl.agg.collect_as_set(meta_ht.s),
))
return hl.Pedigree(trios=[
trio for trio in ped.trios
if trio.s not in filtered_samples and trio.pat_id not in
filtered_samples and trio.mat_id not in filtered_samples
])
def main(args):
if args.join_qc_mt:
v2_qc_mt_liftover = get_liftover_v2_qc_mt('exomes', ld_pruned=True, release_only=True)
v2_qc_mt_liftover = v2_qc_mt_liftover.key_cols_by(s=v2_qc_mt_liftover.s, data_type="v2_exomes")
v3_qc_mt = qc.mt()
v3_qc_mt = v3_qc_mt.filter_cols(meta.ht()[v3_qc_mt.col_key].release)
v3_qc_mt = v3_qc_mt.select_rows().select_cols()
v3_qc_mt = v3_qc_mt.key_cols_by(s=v3_qc_mt.s, data_type="v3_genomes")
joint_qc_mt = v2_qc_mt_liftover.union_cols(v3_qc_mt)
joint_qc_mt.write("gs://gnomad-tmp/v2_exomes_v3_joint_qc.mt", overwrite=args.overwrite)
if args.run_pc_relate:
logger.info('Running PC-Relate')
logger.warning("PC-relate requires SSDs and doesn't work with preemptible workers!")
joint_qc_mt = hl.read_matrix_table("gs://gnomad-tmp/v2_exomes_v3_joint_qc.mt")
joint_qc_mt = joint_qc_mt.sample_rows(0.1)
eig, scores, _ = hl.hwe_normalized_pca(joint_qc_mt.GT, k=10, compute_loadings=False)
scores = scores.checkpoint(v2_v3_pc_relate_pca_scores.path, overwrite=args.overwrite, _read_if_exists=not args.overwrite)
relatedness_ht = hl.pc_relate(joint_qc_mt.GT, min_individual_maf=0.01, scores_expr=scores[joint_qc_mt.col_key].scores,
block_size=4096, min_kinship=0.1, statistics='all')
relatedness_ht.write(v2_v3_relatedness.path, args.overwrite)
def main(args):
hl.init(default_reference='GRCh38')
coverage_version = args.coverage_version if args.coverage_version else CURRENT_GENOME_COVERAGE_RELEASE
logger = logging.getLogger("gnomad_qc.v3.load_data.compute_coverage")
logger.warning(
"Last time this was run (July 2020), this script required high-mem machines."
)
if args.compute_coverage_ht:
print("Building reference context HT")
ref_ht = get_reference_ht(
hl.get_reference('GRCh38'),
contigs=[f'chr{x}' for x in range(1, 23)] + ['chrX', 'chrY'],
excluded_intervals=telomeres_and_centromeres.ht().interval.collect(
))
ref_ht = ref_ht.checkpoint("gs://gnomad-tmp/ref_context.ht",
overwrite=True)
logger.info("Done building reference context HT")
mt = get_gnomad_v3_mt()
mt = mt.filter_cols(meta.ht()[mt.col_key].release)
coverage_ht = compute_coverage_stats(mt, ref_ht)
coverage_ht = coverage_ht.checkpoint(
'gs://gnomad-tmp/gnomad.genomes_v3.coverage.summary.ht',
overwrite=True)
coverage_ht = coverage_ht.naive_coalesce(5000)
coverage_ht.write(coverage('genomes').versions[coverage_version].path,
overwrite=args.overwrite)
if args.export_coverage:
ht = coverage('genomes').versions[coverage_version].ht()
if 'count_array' in ht.row_value: # Note that count_array isn't computed any more, so this is v3.0-specific
ht = ht.drop('count_array')
ht.export(coverage_tsv_path('genomes', coverage_version))
def main(args):
hl.init(log='/frequency_data_generation.log', default_reference='GRCh38')
logger.info("Reading sparse MT and metadata table...")
mt = get_gnomad_v3_mt(key_by_locus_and_alleles=True)
meta_ht = meta.ht().select('pop', 'sex', 'project_id', 'release', 'sample_filters')
if args.test:
logger.info("Filtering to chr20:1-1000000")
mt = hl.filter_intervals(mt, [hl.parse_locus_interval('chr20:1-1000000')])
mt = hl.experimental.sparse_split_multi(mt, filter_changed_loci=True)
logger.info("Annotating sparse MT with metadata...")
mt = mt.annotate_cols(meta=meta_ht[mt.s])
mt = mt.filter_cols(mt.meta.release)
samples = mt.count_cols()
logger.info(f"Running frequency table prep and generation pipeline on {samples} samples")
logger.info("Computing adj and sex adjusted genotypes.")
mt = mt.annotate_entries(
GT=adjusted_sex_ploidy_expr(mt.locus, mt.GT, mt.meta.sex),
adj=get_adj_expr(mt.GT, mt.GQ, mt.DP, mt.AD)
)
logger.info("Densify-ing...")
mt = hl.experimental.densify(mt)
mt = mt.filter_rows(hl.len(mt.alleles) > 1)
logger.info("Setting het genotypes at sites with >1% AF (using v3.0 frequencies) and > 0.9 AB to homalt...")
# hotfix for depletion of homozygous alternate genotypes
# Using v3.0 AF to avoid an extra frequency calculation
# TODO: Using previous callset AF works for small incremental changes to a callset, but we need to revisit for large increments
freq_ht = freq.versions["3"].ht()
freq_ht = freq_ht.select(AF=freq_ht.freq[0].AF)
mt = mt.annotate_entries(
GT=hl.cond(
(freq_ht[mt.row_key].AF > 0.01)
& mt.GT.is_het()
& (mt.AD[1] / mt.DP > 0.9),
hl.call(1, 1),
mt.GT,
)
)
logger.info("Calculating InbreedingCoefficient...")
# NOTE: This is not the ideal location to calculate this, but added here to avoid another densify
mt = mt.annotate_rows(InbreedingCoeff=bi_allelic_site_inbreeding_expr(mt.GT))
logger.info("Generating frequency data...")
mt = annotate_freq(
mt,
sex_expr=mt.meta.sex,
pop_expr=mt.meta.pop
)
# Select freq, FAF and popmax
faf, faf_meta = faf_expr(mt.freq, mt.freq_meta, mt.locus, POPS_TO_REMOVE_FOR_POPMAX)
mt = mt.select_rows(
'InbreedingCoeff',
'freq',
faf=faf,
popmax=pop_max_expr(mt.freq, mt.freq_meta, POPS_TO_REMOVE_FOR_POPMAX)
)
mt = mt.annotate_globals(faf_meta=faf_meta)
# Annotate quality metrics histograms, as these also require densifying
mt = mt.annotate_rows(
**qual_hist_expr(mt.GT, mt.GQ, mt.DP, mt.AD)
)
logger.info("Writing out frequency data...")
if args.test:
mt.rows().write("gs://gnomad-tmp/gnomad_freq/chr20_1_1000000_freq.ht", overwrite=True)
else:
mt.rows().write(freq.path, overwrite=args.overwrite)
