v2 CN/LOH (WIP): cn build-model and cn call
Cyto model (.simurg-cyto: GC 1 kb/100 kb/1 Mb, PFB from the cluster file, optional sex-aware batch reference from normal GTCs; IN-051, CYTO-038); GC-wave correction (CYTO-003); smoothing (CYTO-004); HMM with constitutional, gain-LOH, mosaic and haploid states, forward-backward QUAL and Viterbi segments (CYTO-005/012); event statistics, effective size, post-filters, per-type thresholds, promotion/LowFraction, built-in centromere mask from UCSC cytoBand (CYTO-006..021); sex resolution (CYTO-024), ploidy; CNV VCF with bgzip+tabix (CYTO-028..031), segments parquet, cn_sample_summary.tsv and the cn_call_manifest.json sidecar.
This commit is contained in:
kemal committed
1 parent
f571ad8a2e
commit
724e87dc66
8 files changed
+1452
No files matched your search
@@ -0,0 +1,190 @@
|
||||
"""Genome-wide CN/LOH/mosaic hidden Markov model — spec CYTO-004/005/012/018, plan §10.2. Pure functions, no I/O.
|
||||
|
||||
[LIT: Wang et al. 2007 Genome Res 17:1665 (PennCNV: LRR/BAF emissions weighted by population B-allele frequency,
|
||||
distance-dependent transitions); Loh et al. 2018 Nature 559:350 (MoChA: mosaic BAF split); DOC: cnvPartition
|
||||
technical note (reference LRR state means CN0 −5, CN1 −0.45, CN2 0, CN3 0.3, CN4 0.75)] [OURS: state grid, mixture
|
||||
weights, switch model]
|
||||
|
||||
* Diploid regions: CN0, CN1, CN2, CN2-LOH, CN3, CN3-LOH, CN4 and mosaic loss / gain / CN-LOH at cell fractions
|
||||
0.2, 0.4, 0.6, 0.8. Haploid regions (male X outside PAR, male Y): CN0, CN1, CN2 and mosaic gain/loss relative to
|
||||
the region's median LRR.
|
||||
* LRR ~ (1−ε)·N(µ_state, σ) + ε·U(−5, 3); σ = 1.4826·MAD of the sample's autosomal LRR (floor 0.08); CN0 σ = 2.
|
||||
Mosaic means interpolate linearly between the constitutional means by the cell fraction.
|
||||
* BAF ~ (1−ε)·Σ_g w_g N(b_g, σ_b) + ε·U(0, 1); genotype weights from the probe's PFB p (binomial in the copy
|
||||
number; LOH: {0: 1−p, 1: p}); mosaic heterozygotes split into the two bands 0.5 ± d(f).
|
||||
* Transitions: switch probability 1 − exp(−d / D) for inter-probe distance d, D = 5·10⁸ bp; a switch lands on state
|
||||
j with probability π_j (the same target distribution from every state).
|
||||
* Viterbi path for segmentation; forward–backward posteriors for QUAL.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import math
|
||||
from dataclasses import dataclass, field
|
||||
|
||||
import numpy as np
|
||||
import numpy.typing as npt
|
||||
|
||||
F64 = npt.NDArray[np.float64]
|
||||
FRACTIONS = (0.2, 0.4, 0.6, 0.8)
|
||||
LRR_MEAN = {0: -5.0, 1: -0.45, 2: 0.0, 3: 0.3, 4: 0.75}
|
||||
EPS = 0.01
|
||||
MOSAIC_PRIOR = 0.004 # total switch-target mass of the 12 diploid mosaic states
|
||||
SWITCH_D = 5e8
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class State:
|
||||
name: str
|
||||
cn: int # copy number (baseline-relative for haploid regions: 0, 1, 2)
|
||||
loh: bool
|
||||
mosaic: str # "" | "loss" | "gain" | "cnloh"
|
||||
fraction: float # cell fraction of mosaic states, 1.0 otherwise
|
||||
call: str # "" (baseline) | DEL | DUP | LOH | GAINLOH | MDEL | MDUP | MLOH
|
||||
lrr_mu: float
|
||||
baf: tuple[tuple[str, float], ...] # (genotype-weight key, BAF mean)
|
||||
prior: float
|
||||
|
||||
|
||||
def _d_split(kind: str, f: float) -> float:
|
||||
if kind == "loss":
|
||||
return f / (2 * (2 - f))
|
||||
if kind == "gain":
|
||||
return f / (2 * (2 + f))
|
||||
return f / 2
|
||||
|
||||
|
||||
def diploid_states() -> list[State]:
|
||||
s = [
|
||||
State("CN0", 0, False, "", 1.0, "DEL", LRR_MEAN[0], (), 0.01),
|
||||
State("CN1", 1, False, "", 1.0, "DEL", LRR_MEAN[1], (("h0", 0.0), ("h1", 1.0)), 0.06),
|
||||
State("CN2", 2, False, "", 1.0, "", 0.0, (("aa", 0.0), ("ab", 0.5), ("bb", 1.0)), 0.60),
|
||||
State("CN2LOH", 2, True, "", 1.0, "LOH", 0.0, (("h0", 0.0), ("h1", 1.0)), 0.06),
|
||||
State("CN3", 3, False, "", 1.0, "DUP", LRR_MEAN[3],
|
||||
(("t0", 0.0), ("t1", 1 / 3), ("t2", 2 / 3), ("t3", 1.0)), 0.06),
|
||||
State("CN3LOH", 3, True, "", 1.0, "GAINLOH", LRR_MEAN[3], (("h0", 0.0), ("h1", 1.0)), 0.02),
|
||||
State("CN4", 4, False, "", 1.0, "DUP", LRR_MEAN[4],
|
||||
(("q0", 0.0), ("q1", 0.25), ("q2", 0.5), ("q3", 0.75), ("q4", 1.0)), 0.03),
|
||||
] # fmt: skip
|
||||
for kind, call, mu_end in (("loss", "MDEL", LRR_MEAN[1]), ("gain", "MDUP", LRR_MEAN[3]), ("cnloh", "MLOH", 0.0)):
|
||||
for f in FRACTIONS:
|
||||
d = _d_split(kind, f)
|
||||
cn = {"loss": 1, "gain": 3, "cnloh": 2}[kind]
|
||||
bands = (("aa", 0.0), ("ab-", 0.5 - d), ("ab+", 0.5 + d), ("bb", 1.0))
|
||||
s.append(State(f"M{kind}{f:.1f}", cn, kind == "cnloh", kind, f, call, mu_end * f, bands, MOSAIC_PRIOR / 12))
|
||||
return s
|
||||
|
||||
|
||||
def haploid_states() -> list[State]:
|
||||
s = [
|
||||
State("H0", 0, False, "", 1.0, "DEL", LRR_MEAN[0], (), 0.02),
|
||||
State("H1", 1, False, "", 1.0, "", 0.0, (("h0", 0.0), ("h1", 1.0)), 0.80),
|
||||
State("H2", 2, False, "", 1.0, "DUP", 0.45, (("h0", 0.0), ("h1", 1.0)), 0.06),
|
||||
]
|
||||
for f in FRACTIONS:
|
||||
s.append(State(f"Hgain{f:.1f}", 2, False, "gain", f, "MDUP", 0.45 * f, (("h0", 0.0), ("h1", 1.0)),
|
||||
MOSAIC_PRIOR / 8)) # fmt: skip
|
||||
s.append(State(f"Hloss{f:.1f}", 0, False, "loss", f, "MDEL", -1.0 * f, (("h0", 0.0), ("h1", 1.0)),
|
||||
MOSAIC_PRIOR / 8)) # fmt: skip
|
||||
return s
|
||||
|
||||
|
||||
def _geno_weights(key: str, p: F64) -> F64:
|
||||
q = 1 - p
|
||||
table = {
|
||||
"aa": q * q, "ab": 2 * p * q, "bb": p * p, "ab-": p * q, "ab+": p * q,
|
||||
"h0": q, "h1": p,
|
||||
"t0": q**3, "t1": 3 * p * q * q, "t2": 3 * p * p * q, "t3": p**3,
|
||||
"q0": q**4, "q1": 4 * p * q**3, "q2": 6 * p * p * q * q, "q3": 4 * p**3 * q, "q4": p**4,
|
||||
} # fmt: skip
|
||||
return table[key]
|
||||
|
||||
|
||||
def _norm(x: F64, mu: float, sd: float) -> F64:
|
||||
return np.exp(-0.5 * ((x - mu) / sd) ** 2) / (sd * math.sqrt(2 * math.pi))
|
||||
|
||||
|
||||
@dataclass
|
||||
class Params:
|
||||
lrr_sd: float
|
||||
baf_sd: float
|
||||
lrr_offset: float = 0.0 # added to every state mean (haploid regions: the region's median LRR)
|
||||
switch_d: float = SWITCH_D
|
||||
eps: float = EPS
|
||||
extra: dict[str, float] = field(default_factory=dict)
|
||||
|
||||
|
||||
def emissions(states: list[State], lrr: F64, baf: F64, pfb: F64, par: Params) -> F64:
|
||||
"""Per-probe, per-state emission likelihood (n × S); missing LRR/BAF contribute 1."""
|
||||
n = len(lrr)
|
||||
out = np.ones((n, len(states)), dtype=np.float64)
|
||||
lok = np.isfinite(lrr)
|
||||
bok = np.isfinite(baf)
|
||||
x = np.where(lok, lrr, 0.0)
|
||||
b = np.clip(np.where(bok, baf, 0.5), 0.0, 1.0)
|
||||
p = np.clip(np.where(np.isfinite(pfb), pfb, 0.5), 0.01, 0.99)
|
||||
for j, st in enumerate(states):
|
||||
sd = 2.0 if st.cn == 0 and not st.mosaic else par.lrr_sd
|
||||
le = (1 - par.eps) * _norm(x, st.lrr_mu + par.lrr_offset, sd) + par.eps / 8.0
|
||||
if st.baf:
|
||||
be = np.zeros(n)
|
||||
for key, mean in st.baf:
|
||||
be += _geno_weights(key, p) * _norm(b, mean, par.baf_sd)
|
||||
be = (1 - par.eps) * be + par.eps
|
||||
else:
|
||||
be = np.ones(n)
|
||||
out[:, j] = np.where(lok, le, 1.0) * np.where(bok, be, 1.0)
|
||||
return out
|
||||
|
||||
|
||||
def switch_probs(pos: npt.NDArray[np.int64], switch_d: float = SWITCH_D) -> F64:
|
||||
"""Switch probability before each probe (the first probe gets 1: it draws from the prior)."""
|
||||
d = np.diff(np.asarray(pos, dtype=np.float64), prepend=np.nan)
|
||||
p = 1.0 - np.exp(-np.maximum(d, 0.0) / switch_d)
|
||||
p[0] = 1.0
|
||||
return np.clip(np.nan_to_num(p, nan=1.0), 1e-12, 1.0)
|
||||
|
||||
|
||||
def forward_backward(e: F64, sw: F64, prior: F64) -> F64:
|
||||
"""Posterior state probabilities (n × S) under the switch model."""
|
||||
n, s = e.shape
|
||||
alpha = np.empty((n, s))
|
||||
c = np.empty(n)
|
||||
a = prior * e[0]
|
||||
c[0] = a.sum() or 1e-300
|
||||
alpha[0] = a / c[0]
|
||||
for t in range(1, n):
|
||||
a = ((1 - sw[t]) * alpha[t - 1] + sw[t] * prior) * e[t]
|
||||
c[t] = a.sum() or 1e-300
|
||||
alpha[t] = a / c[t]
|
||||
beta = np.ones(s)
|
||||
post = np.empty((n, s))
|
||||
post[n - 1] = alpha[n - 1]
|
||||
for t in range(n - 1, 0, -1):
|
||||
eb = e[t] * beta
|
||||
beta = ((1 - sw[t]) * eb + sw[t] * float(prior @ eb)) / c[t]
|
||||
g = alpha[t - 1] * beta
|
||||
post[t - 1] = g / (g.sum() or 1e-300)
|
||||
return post
|
||||
|
||||
|
||||
def viterbi(e: F64, sw: F64, prior: F64) -> npt.NDArray[np.int32]:
|
||||
"""Most likely state path under the switch model (log space)."""
|
||||
n, s = e.shape
|
||||
le = np.log(np.maximum(e, 1e-300))
|
||||
lp = np.log(np.maximum(prior, 1e-300))
|
||||
back = np.empty((n, s), dtype=np.int32)
|
||||
ld = lp + le[0]
|
||||
idx = np.arange(s, dtype=np.int32)
|
||||
for t in range(1, n):
|
||||
stay = np.log(np.maximum(1 - sw[t] + sw[t] * prior, 1e-300)) + ld
|
||||
best = int(np.argmax(ld))
|
||||
jump = math.log(max(sw[t], 1e-300)) + lp + ld[best]
|
||||
take_jump = jump > stay
|
||||
back[t] = np.where(take_jump, best, idx)
|
||||
ld = np.where(take_jump, jump, stay) + le[t]
|
||||
path = np.empty(n, dtype=np.int32)
|
||||
path[-1] = int(np.argmax(ld))
|
||||
for t in range(n - 1, 0, -1):
|
||||
path[t - 1] = back[t, path[t]]
|
||||
return path
|
||||
Reference in new issue
Block a user