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 Federally Fine-Tune OpenFold3 on Private Structures, Beating Public-Data Models(6 posts)→

Original post →

More from Research

• Aligning image and text embeddings without paired data: Wasserstein Procrustes and rotation papers — phillip_isola · 2026-10-31
• Phillip Isola demos aligning image and text embeddings with just a single rotation — phillip_isola · 2026-10-31
• Arena Offers Up to $50,000 Per Project for Academic Research on AI Evaluation — arena · 2026-10-31
• StudentBench: AI tutoring matches human GRE gains at 918x lower cost — gharik · 2026-10-31
• WISD: Distill Training Signal from Weaker Quantized Copies of Reasoning Models — jet-ai · 2026-10-31
• Albert Gu: H-Net learns to segment Chinese characters from raw bytes mid-training — niloofar_mire · 2026-10-31

Research channel →