def vep_protein_domain_filter_expr(
d: hl.expr.DictExpression) -> hl.expr.BooleanExpression:
"""
Return True of False if any protein domain source(s) are contained within pre-defined protein domain sources.
Expected as input dict<k,v> where keys (k) represent source/database and values (v) the annotated domain_id.
:param d: hl.DictExpression
:return: hl.BoolExpression
"""
domain_dbs = hl.set(PROTEIN_DOMAIN_DB)
return (d.key_set().intersection(domain_dbs).length() >= 1)
def get_group_to_counts_expr(k: hl.expr.StructExpression, counts: hl.expr.DictExpression) -> hl.expr.ArrayExpression:
return hl.range(1, k.snv - 1, step=-1).flatmap(
lambda snv: hl.range(0, k.all + 1).flatmap(
lambda af: hl.range(0, k.csq + 1).map(
lambda csq: hl.struct(snv=hl.bool(snv), all=hl.bool(af), csq=csq)
)
)
).filter(
lambda key: counts.contains(key)
).map(
lambda key: counts[key]
)
def inbreeding_coeff(
gt_counts: hl.expr.DictExpression,
) -> hl.expr.Float32Expression:
n = gt_counts.get(0, 0) + gt_counts.get(1, 0) + gt_counts.get(2, 0)
p = (2 * gt_counts.get(0, 0) + gt_counts.get(1, 0)) / (2 * n)
q = (2 * gt_counts.get(2, 0) + gt_counts.get(1, 0)) / (2 * n)
return 1 - (gt_counts.get(1, 0) / (2 * p * q * n))