AIMNet2(Score) matches or beats docking and SQM on FEP+ and HiQBind sets
olexandr · x · 2026-07-24
On FEP+ and HiQBind, AIMNet2(Score) matches or beats several baselines
The thread adds evaluation results on FEP+ series and HiQBind co-crystals:
- With no affinity labels, AIMNet2(Score) ranks affinities on par with or ahead of docking, SQM, and deep-learning baselines.
- On raw docked poses, the methods largely tie, suggesting the bottleneck is pose fidelity rather than scoring physics.
- The takeaway is that better scoring may matter less than getting a higher-quality bound pose.
Related event: AIMNet2(Score) Enables Label-Free Protein-Ligand Binding Scoring(3 posts)→
More from Research
- 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
- Noahpinion quotes Chollet: intelligence may hit a hard ceiling — binarybits · 2026-07-27
- Paper argues graph topology can become the core operating system for AI agents — theomitsa · 2026-07-27