mt = mt.annotate_rows(
main_transcript=
get_expr_for_worst_transcript_consequence_annotations_struct(
vep_sorted_transcript_consequences_root=mt.sortedTranscriptConsequences
))
mt = mt.annotate_rows(gene_ids=get_expr_for_vep_gene_ids_set(
vep_transcript_consequences_root=mt.sortedTranscriptConsequences), )
review_status_str = hl.delimit(
hl.sorted(hl.array(hl.set(mt.info.CLNREVSTAT)),
key=lambda s: s.replace("^_", "z")))
mt = mt.select_rows(
allele_id=mt.info.ALLELEID,
alt=get_expr_for_alt_allele(mt),
chrom=get_expr_for_contig(mt.locus),
clinical_significance=hl.delimit(
hl.sorted(hl.array(hl.set(mt.info.CLNSIG)),
key=lambda s: s.replace("^_", "z"))),
domains=get_expr_for_vep_protein_domains_set(
vep_transcript_consequences_root=mt.vep.transcript_consequences),
gene_ids=mt.gene_ids,
gene_id_to_consequence_json=get_expr_for_vep_gene_id_to_consequence_map(
vep_sorted_transcript_consequences_root=mt.
sortedTranscriptConsequences,
gene_ids=mt.gene_ids),
gold_stars=CLINVAR_GOLD_STARS_LOOKUP[review_status_str],
**{
f"main_transcript_{field}": mt.main_transcript[field]
for field in mt.main_transcript.dtype.fields
)
for histogram in [
"ab_hist_alt",
"dp_hist_all",
"dp_hist_alt",
"gq_hist_all",
"gq_hist_alt",
"gnomad_age_hist_het",
"gnomad_age_hist_hom",
]
}
)
# Derived top level fields
ds = ds.annotate(
alt=get_expr_for_alt_allele(ds),
chrom=get_expr_for_contig(ds),
pos=get_expr_for_start_pos(ds),
ref=get_expr_for_ref_allele(ds),
variant_id=get_expr_for_variant_id(ds),
xpos=get_expr_for_xpos(ds),
)
###########
# Subsets #
###########
all_subsets = ["gnomad", "controls", "non_cancer", "non_neuro", "non_topmed"]
# There is no separate non-cancer subset for genome data. All genome samples are non-cancer.
subsets = [s for s in all_subsets if f"{s}_AC_adj" in ds.row_value.dtype.fields]
p = argparse.ArgumentParser()
p.add_argument("--variant-results-url", required=True)
p.add_argument("--variant-annotations-url", required=True)
p.add_argument("--output-url", required=True)
args = p.parse_args()
hl.init(log="/tmp/hail.log")
variants = hl.read_table(args.variant_annotations_url)
variants = variants.annotate(
variant_id=get_expr_for_variant_id(variants),
chrom=get_expr_for_contig(variants.locus),
pos=variants.locus.position,
xpos=get_expr_for_xpos(variants.locus),
alt=get_expr_for_alt_allele(variants),
ref=get_expr_for_ref_allele(variants),
)
variants = variants.transmute(
transcript_id=hl.delimit(variants.transcript_id, ","),
hgvsc=hl.delimit(
variants.hgvsc.keys().map(lambda k: k + ":" + variants.hgvsc[k]), ","),
hgvsp=hl.delimit(
variants.hgvsp.keys().map(lambda k: k + ":" + variants.hgvsp[k]), ","),
)
variants = variants.annotate(flags="PASS")
variants = variants.drop("v")
results = hl.read_table(args.variant_results_url)
results = results.annotate(analysis_group=results.analysis_group.lower().
replace("[^a-z0-9]+", "_").replace("_+$", ""))