KIN66 benchmark shows AIMNet2(2025) reaches 3 kcal/mol RMSE on ~1,000-atom kinase sites
olexandr · x · 2026-07-24
KIN66 benchmark shows AIMNet2(2025) transfers to 1,000-atom kinase sites
The authors say they built KIN66, a kinase benchmark with 1,000-atom active sites evaluated at three DFT levels.
- AIMNet2(2025) reproduces the benchmark’s B97-3c reference with about 3 kcal/mol RMSE.
- The model also transfers to systems larger than anything seen in training.
- The claim is that one MLIP can provide DFT-level interaction energies at protein–ligand scale.
Related event: AIMNet2(Score) Enables Label-Free Protein-Ligand Binding Scoring(3 posts)→
More from Research
- YC Startup School panel says biology foundation models must simulate cells, not just describe them — david_van_dijk · 2026-07-27
- Yaqi Xie joins UIUC as assistant professor and starts recruiting for AI agents and robots — dhruv2038 · 2026-07-27
- Kimi K3 may be strong on cyber, but token efficiency keeps it off UK AISIS — teortaxesTex · 2026-07-27
- ARC AGI 3 should have stayed private, with no examples or public dataset — flowersslop · 2026-07-27
- ExploitGym may have only 60–70% solvable tasks, fueling the OpenAI cheating debate — max_paperclips · 2026-07-27
- RTX 5090 local tests show Qwen Q6 can drop to 15 tok/s at 80k context — LFAdvice7984 · 2026-07-27