onco-os DomainOS

Status: Graduated (production, ADR-009)
Engine: onco-os
Domain: Cancer genomics (somatic variants, neoantigen, TMB, DepMap dependencies)

Cancer-genomics DomainOS: somatic variant calling, mutational burden, neoantigen prediction, cancer-panel QC, and DepMap cell-line dependency / drug-sensitivity analysis. Graduated 2026-04-12 (ADR-009) with ~20 skills on disk; 5-artifact compliance is inherited debt tracked under Wave 3C.

Field	Value
Product	onco-os
Engine id	onco-os
Intent key	onco_os
Repository	Hordago-Labs/onco-os
Plugin	onco-os
Maturity (registry)	Graduated (production, ADR-009)

Overview

Cancer-genomics DomainOS: somatic variant calling, mutational burden, neoantigen prediction, cancer-panel QC, and DepMap cell-line dependency / drug-sensitivity analysis. Graduated 2026-04-12 (ADR-009) with ~20 skills on disk; 5-artifact compliance is inherited debt tracked under Wave 3C.

Scientific approach

onco-os structures every run as 5 phases. Gates marked HITL require an explicit human-in-the-loop approval before the run advances.

#	Phase	Gate	HITL
1	Panel QC	Validate sequencing panel and tumor/normal pairing.	No
2	Somatic Calling	Call somatic variants.	No
3	Mutational Burden	Compute TMB and mutational signatures.	No
4	Neoantigen Prediction	Predict candidate neoantigens.	No
5	Dependency Mapping	Attach DepMap dependency / drug sensitivity.	Yes

Capabilities & evidence objects

Domain tools / skills

• somatic-calling
• tmb
• neoantigen-prediction
• panel-qc
• depmap-wrapper

Evidence objects

Object	Role	Consumer
result.json	produces	co-writer
provenance.json	produces	evidence-audit

Canonical artifacts (5-artifact contract)

Planned

The 5-artifact contract below is the target shape. Canonical-artifact emission is tracked as inherited debt (Wave 3C) and is not yet guaranteed.

Artifact	Description
result.json	Structured primary result payload for the domain run.
report.md	Human-readable narrative summary of the analysis.
provenance.json	Tool versions, reference data, and algorithm lineage for reproducibility.
gate_status.json	Per-phase gate pass/fail decisions.
session_summary.json	Session metadata for replay and audit.

Standalone quickstart

Zero platform dependency

This quickstart runs the DomainOS standalone. The Hordago platform is not required; platform composition is opt-in (see Composition below).

1. Install the standalone onco-os plugin (Hordago-Labs/onco-os) -- no Hordago platform required.
2. Invoke the domain skill with a onco-os intent (see the intent keywords below).
3. Review the emitted artifacts under the run's output directory.

Intent keywords (route to this engine):

somatic tumor oncology neoantigen cancer genomics mutational burden tumor mutational somatic variant cancer sequencing depmap dependency map cancer cell line drug sensitivity gene dependency

Worked example

TMB + DepMap dependencies for a tumor panel

A user submits a cancer sequencing panel. onco-os runs panel QC, calls somatic variants, computes tumor mutational burden, predicts neoantigens, then queries DepMap for cell-line gene dependencies and drug sensitivity.

Validation & benchmarks

Benchmarks

• Somatic-calling truth-set concordance
• TMB reproducibility

Reproducibility. provenance.json pins reference build and DepMap release; 5-artifact emission is Wave 3C follow-up.

Reference

MCP fallback servers (used when the plugin is unavailable): pubmed, open-targets, clinical-trials

Source documents

• Scaffold-domains ledger (onco-os): references/scaffold-domains.md
• ADR-009 scaffold drift resolution: references/engine-catalog.md

Composition

Platform opt-in

onco-os runs standalone. When composed under the Hordago platform it gains cross-domain routing, the Shared Compiler gate, and evidence-audit provenance enforcement. Platform composition is opt-in; the quickstart above has zero platform dependency.

Cross-domain dependencies

Engine	Relationship
gwas-os	Shares Open Targets / ChEMBL / clinical-trials MCP context.
aiDevops	Consumes variant-effect-prediction models from MLos.