Model Card for Nesso-1

Nesso-1 is a fast, structure-based protein–ligand binding-affinity model. Given a protein sequence and a ligand (SMILES / CCD code / SDF), it predicts a binding affinity scalar along with a binder/non-binder score.

• Developed by: Valence Labs (Recursion)
• Input modality: Protein Amino-Acid sequence + Ligand (SMILES, CCD code, or SDF)
• License: Apache License 2.0
• Paper: Technical Report

For full method details and evaluations, see the Technical Report and Github

Documentation

Install the package, run predictions, and explore examples from the GitHub repository:

• README — installation, quick start, and development setup
• docs/prediction.md — CLI options, input YAML schema, and output format
• tutorial/ — runnable YAML examples and feature extraction
• Issues - For questions related to weights, model code, please raise issues here.