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
- Diamandis: AI Cancer Navigator and $100 Genome Sequencing Close the Care Gap — PeterDiamandis · 2026-10-27
- EMNLP Oral: training-free Nexus Sampling cuts KV-cache memory 10x; OpenResearcher tops BrowseComp-Plus at 54.8% — yuz9yuz · 2026-10-27
- ICML 2026 position paper: LLM 'thinking traces' are a harmful anthropomorphism — rao2z · 2026-10-27
- Forking gap follows a power law in context frequency; masking rare n-grams shrinks it — ZimingLiu11 · 2026-10-27
- How forking happens: n-gram tables split logits into non-interacting subspaces — ZimingLiu11 · 2026-10-27
- The best LoRA explainer video yet: rank constraints meet intrinsic dimension — sophiamyang · 2026-10-27