OpenADMET is building open models and datasets for absorption, distribution, metabolism, excretion, and toxicity to make therapeutic development more reliable, affordable, and effective.
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.
OpenADMET runs community blind challenges to benchmark predictive models on realistic drug discovery datasets. These challenges create rigorous, transparent tests of performance while helping release valuable datasets and methods to the broader community.
Our current blind challenge focuses on human PXR induction, an important ADMET liability associated with drug-drug interactions, hepatotoxicity, and late-stage development risk. The challenge includes both an activity prediction track and a structure prediction track, built on a large OpenADMET-generated dataset designed to resemble realistic lead-optimization workflows.
A growing archive of community challenges built around realistic experimental datasets.
A lead-optimization-style blind challenge based on real-world ADMET data from Expansion Therapeutics. Participants predicted nine ADMET endpoints using earlier-stage molecules to forecast late-stage compounds.
An earlier OpenADMET-associated community blind challenge focused on pan-coronavirus drug discovery data, bringing together participants to evaluate computational methods on realistic potency and structure tasks.
Updates on blind challenges, new models, datasets, and lessons learned from the OpenADMET community.
Launch details for the PXR induction challenge, including the dataset, rules, and practical guidance for participants.
Read MoreReflections on the ExpansionRx challenge and what the results suggest about zero-shot ADMET prediction in practice.
Read more →An introduction to the next blind challenge and why blinded datasets remain important for realistic benchmarking.
Read more →A look at OpenADMET’s clearance modeling work and the broader challenge of generalizing across chemical space.
Read more →A behind-the-scenes look at the infrastructure and strategy required to generate useful ADMET datasets at scale.
Read more →Early takeaways from the ExpansionRx challenge, including what participants and organizers learned from the first round.
Read more →
Publications and related resources from the OpenADMET community.