BioEmu2 predicts free-energy surfaces within ~1 kcal/mol in GPU-minutes
FrankNoeBerlin · x · 2026-10-20
BioEmu2's equilibrium sampling mode, trained on vast molecular dynamics (MD) simulations, reproduces MD structure distributions in GPU-minutes that would take GPU-years with MD.
Benchmark highlights:
- Free-energy surfaces predicted with 1 kcal/mol error.
- State coverage of 50–100% of MD structures across single-protein, protein-dimer, and protein-ligand benchmarks.
- Outperforms Boltz-2 (MD), Boltz-2, and Protenix v2 on both free-energy error and state coverage.
- On the protein-peptide complex 2khw, BioEmu2's free-energy surface covers the multiple states seen in MD.
More from Research
- Causal inference tutorial series covers DAG engines for separating correlation from causation — Nasereliver · 2026-10-20
- Google's FireSat constellation uses AI to spot wildfires as small as 5x5 meters from space — GoogleAI · 2026-10-20
- CyberArena benchmarks AI agents in live attack-and-defense combat — 2077AIDataFoundation · 2026-10-20
- Training MOSS-Image LoRAs locally on 8GB VRAM: 500 steps beats 8000, full settings inside — AcademiaSD · 2026-10-20
- PNAS study: brief AI chats drive 17,950 people to sign petitions and donate, attitudes don't predict behavior — _FelixSimon_ · 2026-10-20
- Citrini Used Anthropic's Internal Model to Design Scorpion Antivenom Proteins Overnight — citrini · 2026-10-20