Recursion Releases Nesso-1 for Accelerating Open-Source Binding Affinity Predictions

Francesco_dgv · x · 2026-08-11

Recursion Pharmaceuticals recently released Nesso-1, an open-source model designed to predict binding affinity more efficiently than existing cofolding-based models.

Binding affinity is a key challenge in small molecule drug design, evaluating the strength of a compound's binding to a specific target and the concentration required for a biological response. Accurate predictions help identify effective binders and mitigate off-target toxicity.

Drug discovery is a complex multi-objective optimization problem. Nesso-1 aims to disrupt the Pareto front of traditional physics-based models using AI and data, accelerating large-scale searches during early stages like Hit-Identification.

Original post →

More from Research

Research channel →