def sor_from_sb(
sb: Union[hl.expr.ArrayNumericExpression, hl.expr.ArrayExpression]
) -> hl.expr.Float64Expression:
"""
Computes `SOR` (Symmetric Odds Ratio test) annotation from the `SB` (strand balance table) field.
.. note::
This function can either take
- an array of length four containing the forward and reverse strands' counts of ref and alt alleles: [ref fwd, ref rev, alt fwd, alt rev]
- a two dimensional array with arrays of length two, containing the counts: [[ref fwd, ref rev], [alt fwd, alt rev]]
GATK code here: https://github.com/broadinstitute/gatk/blob/master/src/main/java/org/broadinstitute/hellbender/tools/walkers/annotator/StrandOddsRatio.java
:param sb: Count of ref/alt reads on each strand
:return: SOR value
"""
if not isinstance(sb, hl.expr.ArrayNumericExpression):
sb = hl.bind(lambda x: hl.flatten(x), sb)
sb = sb.map(lambda x: hl.float64(x) + 1)
ref_fw = sb[0]
ref_rv = sb[1]
alt_fw = sb[2]
alt_rv = sb[3]
symmetrical_ratio = ((ref_fw * alt_rv) / (alt_fw * ref_rv)) + (
(alt_fw * ref_rv) / (ref_fw * alt_rv)
)
ref_ratio = hl.min(ref_rv, ref_fw) / hl.max(ref_rv, ref_fw)
alt_ratio = hl.min(alt_fw, alt_rv) / hl.max(alt_fw, alt_rv)
sor = hl.log(symmetrical_ratio) + hl.log(ref_ratio) - hl.log(alt_ratio)
return sor
def compute_same_hap_log_like(n, p, q, x):
res = (
hl.cond(
q > 0,
hl.fold(
lambda i, j: i + j[0] * j[1], 0.0,
hl.zip(gt_counts, [
hl.log10(x) * 2,
hl.log10(2 * x * e),
hl.log10(e) * 2,
hl.log10(2 * x * p),
hl.log10(2 * (p * e + x * q)),
hl.log10(2 * q * e),
hl.log10(p) * 2,
hl.log10(2 * p * q),
hl.log10(q) * 2
])),
-1e31 # Very large negative value if no q is present
))
# If desired, add distance posterior based on value derived from regression
if distance is not None:
res = res + hl.max(-6,
hl.log10(0.97 - 0.03 * hl.log(distance + 1)))
return res
def test(self):
schema = hl.tstruct(a=hl.tint32, b=hl.tint32, c=hl.tint32, d=hl.tint32, e=hl.tstr,
f=hl.tarray(hl.tint32),
g=hl.tarray(
hl.tstruct(x=hl.tint32, y=hl.tint32, z=hl.tstr)),
h=hl.tstruct(a=hl.tint32, b=hl.tint32, c=hl.tstr),
i=hl.tbool,
j=hl.tstruct(x=hl.tint32, y=hl.tint32, z=hl.tstr))
rows = [{'a': 4, 'b': 1, 'c': 3, 'd': 5,
'e': "hello", 'f': [1, 2, 3],
'g': [hl.Struct(x=1, y=5, z='banana')],
'h': hl.Struct(a=5, b=3, c='winter'),
'i': True,
'j': hl.Struct(x=3, y=2, z='summer')}]
kt = hl.Table.parallelize(rows, schema)
result = convert_struct_to_dict(kt.annotate(
chisq=hl.chisq(kt.a, kt.b, kt.c, kt.d),
ctt=hl.ctt(kt.a, kt.b, kt.c, kt.d, 5),
dict=hl.dict(hl.zip([kt.a, kt.b], [kt.c, kt.d])),
dpois=hl.dpois(4, kt.a),
drop=kt.h.drop('b', 'c'),
exp=hl.exp(kt.c),
fet=hl.fisher_exact_test(kt.a, kt.b, kt.c, kt.d),
hwe=hl.hardy_weinberg_p(1, 2, 1),
index=hl.index(kt.g, 'z'),
is_defined=hl.is_defined(kt.i),
is_missing=hl.is_missing(kt.i),
is_nan=hl.is_nan(hl.float64(kt.a)),
json=hl.json(kt.g),
log=hl.log(kt.a, kt.b),
log10=hl.log10(kt.c),
or_else=hl.or_else(kt.a, 5),
or_missing=hl.or_missing(kt.i, kt.j),
pchisqtail=hl.pchisqtail(kt.a, kt.b),
pcoin=hl.rand_bool(0.5),
pnorm=hl.pnorm(0.2),
pow=2.0 ** kt.b,
ppois=hl.ppois(kt.a, kt.b),
qchisqtail=hl.qchisqtail(kt.a, kt.b),
range=hl.range(0, 5, kt.b),
rnorm=hl.rand_norm(0.0, kt.b),
rpois=hl.rand_pois(kt.a),
runif=hl.rand_unif(kt.b, kt.a),
select=kt.h.select('c', 'b'),
sqrt=hl.sqrt(kt.a),
to_str=[hl.str(5), hl.str(kt.a), hl.str(kt.g)],
where=hl.cond(kt.i, 5, 10)
).take(1)[0])
def compute_chet_log_like(n, p, q, x):
res = (hl.cond((p > 0) & (q > 0),
hl.fold(
lambda i, j: i + j[0] * j[1], 0,
hl.zip(gt_counts, [
hl.log10(x) * 2,
hl.log10(2 * x * q),
hl.log10(q) * 2,
hl.log10(2 * x * p),
hl.log10(2 * (p * q + x * e)),
hl.log10(2 * q * e),
hl.log10(p) * 2,
hl.log10(2 * p * e),
hl.log10(e) * 2
])), -1e-31))
# If desired, add distance posterior based on value derived from regression
if distance is not None:
res = res + hl.max(-6,
hl.log10(0.03 + 0.03 * hl.log(distance - 1)))
return res