Recursion releases Nesso: 10x faster binding affinity model for drug discovery
anshulkundaje · x · 2026-08-22
Recursion Pharmaceuticals has released Nesso, a new affinity prediction model that matches or beats Boltz but utilizes a much simpler architecture. This efficiency results in predictions that are 10x faster and cheaper, running at 1 second per prediction on a single GPU. Binding affinity is critical in small molecule drug design for determining compound-target interaction strength. Nesso's speed aims to disrupt the physics-based Pareto front in drug discovery, particularly beneficial for the broad search phase of Hit-Identification and for mitigating off-target toxicity risks through large-scale prediction.
More from Research
- Quotient Recurrent Reasoners hit 97.9% on Sudoku-Extreme with 78% fewer loops — burny_tech · 2026-10-16
- Mathematicians publish explainer for the Egyptian fraction proof in OpenAI's proofs collection — burny_tech · 2026-10-16
- Robin Hanson: a neural network is almost 'a fractal of explanations' — burny_tech · 2026-10-16
- 'Neural networks really are super simple': a takes on features, concepts and connectionism — burny_tech · 2026-10-16
- Sim data can't cover the humanoid long tail: the sim2real debate, mapped — herbiebradley · 2026-10-16
- SJTU AutoLab releases Drive3R, a streaming geometric foundation model for long-horizon driving 3D reconstruction — AutoLab-SJTU · 2026-10-16