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
- Harry Collins: LLMs can't do frontier science because they can't invent new language — whoamisri · 2026-09-11
- The Waymo effect: how AI is quietly making research less collaborative — JohnHammersley · 2026-09-11
- Causal-only attention for non-generative tasks is wasteful, argues HF engineer — antoine_chaffin · 2026-09-11
- Catholic University of Chile researcher: scaling AI feedback is key to sustainable medical education — julianvarascom · 2026-09-11
- Nature paper images cellular activity across all organs, revealing body-wide circuits — arjunrajlab · 2026-09-11
- SignNet 1M Dataset Released for Sign Language Research — ducha_aiki · 2026-09-11