We are an open science effort focused on improving how the field predicts safety and toxicity for small molecules. By combining high-quality data generation, mechanistic insight, and machine learning, OpenADMET helps create more rigorous and useful ADMET models for the broader scientific community.

Our work includes open datasets, predictive modeling, and community blind challenges designed to benchmark progress on realistic problems in drug discovery. We aim to build shared infrastructure that helps researchers better understand molecular properties and develop stronger predictive tools.