Oncko offers a discovery platform that systematically searches and optimizes multi‑drug cancer regimens. Using high‑throughput screening against its SuperTumor™ model, real‑world patient data, and machine‑learning‑driven optimization, the platform identifies combinations with high efficacy and acceptable toxicity for pharmaceutical, biotech, and academic oncology research.
Funding
Funding not disclosed
Founders
Product
Problem
Cancer cells rapidly develop resistance, and the most effective therapies often require combinations of multiple drugs. Identifying the optimal set of agents, doses, and schedules is a combinatorial problem that quickly becomes intractable as the number of candidate drugs grows.
Solution
Oncko provides a discovery platform that systematically searches the space of multi‑drug regimens to find combinations with high efficacy and acceptable toxicity. The workflow begins by screening candidate combos against SuperTumor™, an experimental model that captures roughly one million resistance mechanisms. Results are then integrated with real‑world patient data and in‑silico simulations to quantify both therapeutic activity and expected side effects. Machine‑learning algorithms guide the search toward regimens that improve the therapeutic index, iterating between experimental validation and computational optimization. The platform delivers preclinical candidates—such as four‑drug orthogonal mechanisms for second‑line NSCLC—ready for further development.
Target Audience
Primary customers are pharmaceutical and biotech R&D teams, as well as academic cancer research groups, that need systematic methods to discover and optimize multi‑drug regimens for oncology indications.
Features
- High‑throughput screening of drug combos using the SuperTumor™ model, representing ~1 million resistance pathways
- Integrated efficacy and toxicity quantification that combines in‑vivo results with real‑world patient data
- Machine‑learning driven optimization engine that navigates combinatorial spaces (e.g., 5 000 two‑drug combos, 4 billion four‑drug dose‑schedule permutations)
- Automated pipeline that iterates between experimental testing and computational modeling to refine therapeutic index
- Generation of preclinical multi‑drug candidates with documented orthogonal mechanisms of action