Five pharma firms federated-finetune OpenFold3 on 20,000+ private structures, lifting ligand-pose accuracy from 29% to 47%

AllThingsApx · x · 2026-09-14

Five pharmaceutical companies fine-tuned OpenFold3 in a federated setting across 20,000+ private structures, with no data leaving their local environments, raising correct ligand-pose predictions from 29% to 47%.

It's a landmark use of federated learning in drug discovery: companies improve a shared protein-ligand co-folding model without exposing sensitive proprietary data.

Related event: Five Pharma Firms Federated-Tune OpenFold3 on 20,167 Private Structures, Beating Public-Data Models(5 posts)→

Original post →

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

Research channel →