The set of protein anti-targets that comprise the Avoid-ome
New Publication
May 25, 2026 · Nature Communications

Mapping the avoid-ome: a systematic open-science approach to predictive ADMET

A Perspective introducing the "Avoid-ome" — a finite set of anti-target proteins driving drug safety liabilities — and how OpenADMET combines high-throughput structural biology, active learning, and community challenges to build mechanistically grounded predictive models.

Read More →

About

Building open ADMET models for drug discovery

An open science effort to improve prediction of safety and toxicity for small molecules through high-quality data, mechanistic insight, and machine learning.

Blind Challenges

Current Challenge
Predicting PXR Induction

Benchmarking activity and structure prediction on a large dataset of human PXR-active compounds, with both an activity track and a structure track.

Datasets & Models

HuggingFace
4 open models and 7 curated ADMET datasets

Predictive models and experimental datasets from OpenADMET blind challenges and data generation efforts.

Blog

July 16, 2026
OpenADMET Quarterly Newsletter Q2 2026

Our quarterly newsletter detailing our progress, goals and priorities.

Videos

June 4, 2026
Leveraging Public Data in the OpenADMET ExpansionRx Blind Challenge

Science seminars, challenge webinars, and workshop recordings from the OpenADMET community.

People

Our Team
Get to Know the OpenADMET Team

Meet the OMSF staff, Governing Board, and our collaborators from Octant and UCSF.

Publications

PubMed Central
Blind Challenges Let Us See the Path Forward for Predictive Models

A perspective on how blind challenges can help the field honestly evaluate and advance predictive modeling in drug discovery.