BioEmu2 simulates peptide folding and binding 100,000x faster than MD: 5ms in 40 minutes
FrankNoeBerlin · x · 2026-10-20
Frank Noe demonstrates BioEmu2 simulating the folding and binding of an intrinsically disordered peptide to its protein receptor via an intermediate state. The same 5-millisecond process would take over 10 GPU years with MD simulation, but BioEmu2 completes it at 5-microsecond steps in just 40 minutes on a single GPU—a >100,000x speedup.
Peter Eastman, whose repost amplified the demo, calls it one of those tech-bio advances that is both expected and yet still surprising to see working for real. Generative protein dynamics models are now displacing portions of traditional MD simulation, compressing year-scale compute into hours, with implications for drug discovery and protein interaction research.
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