feat: redesign around phenotype-driven triage, not variant filtering
A table with filters made the user do the work. Rare disease triage is a different task:
which few variants could explain *this* patient's phenotype, and why. The app now answers
that, and lets a reviewer act on the answer.
Domain
- a case is a proband: a VCF plus the HPO terms observed in the patient (samples -> cases)
- HPO's gene-to-phenotype annotations are loaded as reference data (scripts/load-hpo.py)
- each candidate can be shortlisted or dismissed with a reason and a note
Ranking (app/services/triage.py, 21 tests)
- weighted sum of phenotype match, rarity, consequence severity and the model's score,
with every component shown next to the candidate
- rarity and consequence filter; phenotype only ranks, because a real diagnosis can sit in
a gene nobody has annotated yet and filtering on it would hide exactly that case
- ClinVar is deliberately not an input: it appears beside the result as independent
confirmation, so nothing ranks highly merely because ClinVar already said pathogenic
UI
- the funnel is the headline: variants called -> rare -> coding candidates -> phenotype-matched
- ranked candidates with evidence chips, not a grid of everything; filters are demoted
- a variant panel showing the score breakdown, the matched HPO terms, the raw VEP record and
links out to Ensembl/gnomAD/ClinVar, with the decision controls
- a printable case report: phenotype, funnel, shortlisted variants with reasons, provenance
API: /cases with phenotypes, /cases/{id}/candidates (funnel + ranked + weights),
/variants/{id}, /variants/{id}/decision, /cases/{id}/report, /phenotypes for the picker.
Scoring moved under the case and now answers 503 with the reason when no model registry is
reachable, instead of a 500.
Verified end to end on a simulated proband (scripts/make-demo-case.sh: real GIAB HG002
background + one real ClinVar 2-star pathogenic NF2 variant). 13 variants called -> 1 coding
candidate, and the planted variant ranks first at 0.80 on phenotype 1.00, rarity 1.00 and
consequence 1.00, with ClinVar agreeing afterwards.
Tests: api 75, ml 18, loader 16, web 27; ruff, mypy, svelte-check, terraform validate, both
kustomize overlays and the Nextflow stub run all clean.
This commit is contained in:
+52
-49
@@ -1,60 +1,63 @@
|
||||
import uuid
|
||||
|
||||
from fastapi import APIRouter, Query
|
||||
from sqlalchemy import Integer, case, cast, func, select
|
||||
from fastapi import APIRouter, HTTPException
|
||||
from sqlalchemy import func, select
|
||||
from sqlalchemy.dialects.postgresql import insert
|
||||
from sqlalchemy.orm import selectinload
|
||||
|
||||
from app.db import SessionDep
|
||||
from app.models import Prediction, Variant
|
||||
from app.schemas import VariantOut, VariantPage
|
||||
from app.models import Variant, VariantDecision
|
||||
from app.schemas import CandidateOut, DecisionIn, DecisionOut, VariantDetailOut
|
||||
from app.services import candidates as case_view
|
||||
from app.services import triage
|
||||
|
||||
router = APIRouter()
|
||||
|
||||
# Karyotype order (1..22, X, Y, MT) instead of text order, where "10" sorts before "2".
|
||||
_chrom = func.regexp_replace(Variant.chrom, "^chr", "", "i")
|
||||
CHROM_ORDER = case(
|
||||
(_chrom.regexp_match("^[0-9]+$"), cast(_chrom, Integer)),
|
||||
(_chrom == "X", 23),
|
||||
(_chrom == "Y", 24),
|
||||
(_chrom.in_(["M", "MT"]), 25),
|
||||
else_=26,
|
||||
)
|
||||
|
||||
|
||||
@router.get("", response_model=VariantPage)
|
||||
async def list_variants(
|
||||
job_id: uuid.UUID,
|
||||
session: SessionDep,
|
||||
gene: str | None = None,
|
||||
impact: str | None = Query(None, pattern="^(HIGH|MODERATE|LOW|MODIFIER)$"),
|
||||
max_af: float | None = Query(None, ge=0, le=1),
|
||||
min_score: float | None = Query(None, ge=0, le=1),
|
||||
limit: int = Query(50, ge=1, le=500),
|
||||
offset: int = Query(0, ge=0),
|
||||
) -> VariantPage:
|
||||
stmt = select(Variant).where(Variant.job_id == job_id)
|
||||
if gene:
|
||||
stmt = stmt.where(Variant.gene == gene.upper())
|
||||
if impact:
|
||||
stmt = stmt.where(Variant.impact == impact)
|
||||
if max_af is not None:
|
||||
stmt = stmt.where((Variant.gnomad_af.is_(None)) | (Variant.gnomad_af <= max_af))
|
||||
if min_score is not None:
|
||||
stmt = stmt.join(Prediction, Prediction.variant_id == Variant.id).where(
|
||||
Prediction.score >= min_score
|
||||
@router.get("/{variant_id}", response_model=VariantDetailOut)
|
||||
async def get_variant(variant_id: int, session: SessionDep) -> VariantDetailOut:
|
||||
"""Every piece of evidence for one variant, including the raw VEP record."""
|
||||
variant = await session.scalar(
|
||||
select(Variant)
|
||||
.where(Variant.id == variant_id)
|
||||
.options(
|
||||
selectinload(Variant.prediction),
|
||||
selectinload(Variant.decision),
|
||||
selectinload(Variant.job),
|
||||
)
|
||||
)
|
||||
if variant is None:
|
||||
raise HTTPException(404, "variant not found")
|
||||
case = await case_view.get_case(session, variant.job.case_id)
|
||||
terms = [p.hpo_id for p in case.phenotypes] if case else []
|
||||
gene_terms = await case_view.gene_terms_for(session, {variant.gene} if variant.gene else set())
|
||||
|
||||
total = await session.scalar(select(func.count()).select_from(stmt.subquery()))
|
||||
rows = await session.scalars(
|
||||
stmt.options(selectinload(Variant.prediction))
|
||||
# id breaks ties between split multiallelics at one position, keeping pages stable.
|
||||
.order_by(CHROM_ORDER, Variant.chrom, Variant.pos, Variant.id)
|
||||
.limit(limit)
|
||||
.offset(offset)
|
||||
# evaluate, not rank: the panel must work for a variant that did not make the candidate list.
|
||||
scored = triage.evaluate(variant, terms, gene_terms)
|
||||
labels = {p.hpo_id: p.label for p in case.phenotypes} if case else {}
|
||||
base = CandidateOut.from_candidate(scored, labels).model_dump()
|
||||
return VariantDetailOut(**base, annotations=variant.annotations or {})
|
||||
|
||||
|
||||
@router.post("/{variant_id}/decision", response_model=DecisionOut)
|
||||
async def decide(variant_id: int, payload: DecisionIn, session: SessionDep) -> DecisionOut:
|
||||
if await session.get(Variant, variant_id) is None:
|
||||
raise HTTPException(404, "variant not found")
|
||||
stmt = insert(VariantDecision).values(
|
||||
variant_id=variant_id, state=payload.state, reason=payload.reason, note=payload.note
|
||||
)
|
||||
return VariantPage(
|
||||
items=[VariantOut.model_validate(v) for v in rows],
|
||||
total=total or 0,
|
||||
limit=limit,
|
||||
offset=offset,
|
||||
# Changing your mind replaces the call rather than failing on the unique constraint.
|
||||
await session.execute(
|
||||
stmt.on_conflict_do_update(
|
||||
index_elements=[VariantDecision.variant_id],
|
||||
set_={
|
||||
"state": stmt.excluded.state,
|
||||
"reason": stmt.excluded.reason,
|
||||
"note": stmt.excluded.note,
|
||||
"decided_at": func.now(),
|
||||
},
|
||||
)
|
||||
)
|
||||
await session.commit()
|
||||
decision = await session.scalar(
|
||||
select(VariantDecision).where(VariantDecision.variant_id == variant_id)
|
||||
)
|
||||
return DecisionOut.model_validate(decision)
|
||||
|
||||
Reference in New Issue
Block a user