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
- NVIDIA's AVO Achieves 100% on ARC-AGI-3, Outperforms FlashAttention-4 — daniel_mac8 · 2026-08-22
- NeurIPS 2026 Workshop on Long Context Foundation Models (LCFM) Opens CFP — danqi_chen · 2026-08-22
- Researcher Joins Burning Glass Institute to Focus on Economics of AI — soumitrashukla9 · 2026-08-22
- 个性化癌症疫苗受热议，自动化生物分析助力研发 — matt_slotnick · 2026-08-22
- AI-assisted math lowers bound for de Bruijn–Newman constant to 0.1787854 — ctjlewis · 2026-08-22
- Machine learning studies techniques that don't work in theory but do in practice — pmddomingos · 2026-08-22