Five pharma companies fine-tune OpenFold3 federated, lifting ligand-pose accuracy from 29% to 47%
AllThingsApx · x · 2026-09-15
Five pharmaceutical companies fine-tuned OpenFold3 in a federated setting on 20,000+ structures, raising correct ligand-pose predictions from 29% to 47%. A comment notes that if protein-structure prediction is still in the early fun part of its scaling law, structure-free discovery holds many low-hanging gains — the bottleneck is getting the right data.
More from Research
- DeepMind's Economics of Intelligence: AI reshapes economy via agent coordination, not solo model smarts — Scobleizer · 2026-10-31
- Nesformer: an entire Nintendo crammed into ~1GB of Qwen3.5 weights, following the Qwenputer method — idanbeck · 2026-10-31
- SCOPE workshop proposed for ICLR 2027 asks what counts as an AI scientific discovery — mariyaivasileva · 2026-10-31
- New MolmoSpaces-CommonSense benchmark: no robot policy tops 30% on manipulation tasks — RanjayKrishna · 2026-10-31
- Mischief launches video model trained from lab-grown brain cells at 0.5¢ per second — evilsocket · 2026-10-31
- Stanford CS336 notes: Percy Liang on scaling recipes and hyperparameter transfer — stanfordnlp · 2026-10-31