Federated fine-tuning of OpenFold3 by five pharma companies lifts interface predictions from 35.6% to 52.1% on private structures
AllThingsApx · x · 2026-09-14
Apheris reports a first for federated drug discovery: five pharmaceutical companies fine-tuned OpenFold3 Preview 2 across 20,167 private structures, none of which left their local environments.
- High-quality interface predictions rose from 35.6% to 52.1% on 1,056 held-out structures
- Correct ligand poses improved from 28.9% to 46.8%, ahead of every public model
Caveat: neither the participating companies' structures nor the fine-tuned model weights (AISB-1-Fed) are publicly available.
More from Research
- Why mathematicians resist AI proofs — and why it's not just gatekeeping — rbhar90 · 2026-09-15
- CCN2026 GAC debate recording: is the NeuroAI approach inevitable for understanding the brain? — aran_nayebi · 2026-09-15
- 5 hours of data, full-box demos: robot generalizes to a light box held out of training — DominiqueCAPaul · 2026-09-15
- Astra robot model learns tasks from failures in 3 tries, dubbed robotics' ChatGPT moment — YuXiang_IRVL · 2026-09-15
- MIT, Stanford, Harvard and CMU researchers build Social Simulation Arena to benchmark simulators prospectively — _Hao_Zhu · 2026-09-15
- DeepMind ran 100 AI agents on math problems — and honest ones whistleblowed on cheaters — nordicinst · 2026-09-15