How do you train robust deep learning models when most of the high-quality data is proprietary? Discover how to enrich multitask ADMET predictions using a public proxy for proprietary learnings.
Part 1: Structure Prediction
Living on a prayer (and half a test set): Unblinding the data, freezing the board, and stepping into Phase 2. By Jon Swain, Maria Castellanos, Hugo MacDermott-Opeskin, and Pat Walters We are halfway through the OpenADMET PXR Blind challenge! We have been overwhelmed with the response so far. Thank
Statistical Comparison of Blind Challenge Entries by Jon Swain Benchmarks have become ubiquitous in machine learning, from the MNIST (Modified National Institute of Standards and Technology) dataset for computer vision to the SWE-bench leaderboard for LLM coding tasks. Benchmarks are standardized datasets or tasks used to evaluate models, comparing
Improving 66 Pregnane X Receptor structures from the Protein Data Bank using modern refinement protocols to enhance ligand model quality.
A step-by-step guide to setting up a consumer AMD GPU workstation with ROCm to run the full openadmet-models stack, including dual-boot Linux setup.
Launch details for the PXR induction challenge, including the dataset, rules, and practical guidance for participants.
Lessons and reflections from the OpenADMET-ExpansionRx blind challenge — evaluating whether zero-shot ADMET predictions can be trusted in real drug discovery settings.
An introduction to the next blind challenge and why blinded datasets remain important for realistic benchmarking.
A look at OpenADMET's clearance modeling work and the broader challenge of generalizing across chemical space.
Data
A behind-the-scenes look at the infrastructure and strategy required to generate useful ADMET datasets at scale.
Blind Challenges
Maria Castellanos Hugo MacDermott-Opeskin Jon Ainsley Pat Walters The ExpansionRx challenge, launched on October 27, 2025, closed two weeks ago! We are extremely grateful to everyone who participated and made this incredible learning experience possible for the ML and ADMET communities. After releasing the final leaderboard in our previous
Blind Challenges
Maria Castellanos Hugo MacDermott-Opeskin Absorption, Distribution, Metabolism, Excretion, and Toxicity (ADMET) properties can make or break the preclinical and clinical development of small molecules. At OpenADMET we aim to address the unpredictable nature of these properties through open science, generating high-quality experimental data and building robust predictive models
Models
OpenADMET's first public model release — predictive models for key ADMET properties, built on open data and designed for the drug discovery community.
Blind Challenges
Intermediate leaderboard release Absorption, Distribution, Metabolism, Excretion, and Toxicity (ADMET) properties can make or break the preclinical and clinical development of small molecules. At OpenADMET we address the unpredictable nature of these properties through open science, generating experimental data and building predictive models of ADMET properties. A key component of
Models
How do you know what you don't know? A deep dive into uncertainty quantification for ADMET predictions and why it matters for drug discovery decision-making.
Blind Challenges
Additional details on the coming challenge Absorption, Distribution, Metabolism, Excretion and Toxicity–ADMET–properties can make or break preclinical and clinical development of small molecules. At OpenADMET we address the unpredictable nature of these properties through open science, generating experimental data and building predictive models of ADMET properties. A key
Blind Challenges
Small molecules continue to be the bricks and mortar of drug discovery globally, accounting for ~75% of FDA approvals over the last decade. Oral bioavailability, easily tunable properties, modulation of a wide range of mechanisms, and ease of manufacturing make small molecules highly attractive as therapeutic agents. Moreover, emerging small
General
Author: Pat Walters, Chief Scientist, OpenADMET Originally published on Practical Cheminformatics. Starting today, September 15, 2025, I will assume a new role as Chief Scientist at OpenADMET, an open science initiative that combines high-throughput experimentation, computation, and structural biology to enhance the understanding and prediction of absorption, distribution, metabolism,
General
Small molecule therapies have always been and continue to be the dominant way we treat diseases worldwide. Small molecules have unique advantages such as cost, scalability, convenience, the ability to get into every organ/cell and modulate a wide variety of targets/mechanisms – especially as compared to other modalities like