enFoldX gains accuracy as AF3 ensemble disagreement rises for non-binders
quaidmorris · x · 2026-07-22
enFoldX uses ensemble disagreement as a signal
The post says enFoldX summarizes an AlphaFold3 ensemble instead of trusting one prediction. Non-cognate pairs show larger structural disagreement — higher RMSD and higher iPAE — and performance improves as more ensemble members are added.
That behavior differs from single-structure models, which do not benefit as much from additional samples.
Related event: enFoldX Turns AlphaFold3 Noise into TCR Recognition Signals(11 posts)→
More from Research
- DeepMind paper: LLMs can't sample randomly on their own, only convert given seeds — rohanpaul_ai · 2026-10-27
- DeepMind paper: LLMs can't sample randomly on their own — pass random numbers from code instead — rohanpaul_ai · 2026-10-27
- World Model Assigns Weight and Friction to Objects, Then Simulates with a Physics Engine — jonstephens85 · 2026-10-27
- Token Collapse: Study Finds Graph Soft Prompting Tokens in LLMs Fail to Encode Structure — Sapienza · 2026-10-27
- Mathathon 2.0 launches with Terence Tao's SAIR, $1.5M in compute for teams — _sathvikr · 2026-10-27
- The 'sweet lesson' is real: two kinds of ML problems need opposite strategies — mike64_t · 2026-10-27