Blind Challenges
Woah, we’re halfway there…
We're halfway through the PXR Blind Challenge: unblinding the first data, freezing the leaderboard, and stepping into Phase 2 — plus a look at the response so far and what's next.
Latest
Data
Navigating PXR Chemical Space with High-Throughput Chemistry and Standard-Free Quantification
With Octant, we use direct-to-biology high-throughput chemistry and standard-free quantification to explore PXR chemical space far beyond commercial libraries, part of OpenADMET's effort to map the Avoidome.
Models
Model, take the wheel: active learning with pEC50 data
Synthesizing and assaying compounds is slow and costly. We explore whether active learning can use what a model already knows to guide which pEC50 data to acquire next.
Blind Challenges
Peak Performance or Just Noise?
Benchmarks are everywhere in ML — but when is a leaderboard gap real? Jon Swain on the statistics of comparing blind challenge entries and separating genuine performance from noise.
Data
Pregnane X Receptor PDB structure re-refinement
Improving 66 Pregnane X Receptor structures from the Protein Data Bank using modern refinement protocols to enhance ligand model quality.
Infrastructure
Running the OpenADMET stack on AMD GPUs with ROCm
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.
Blind Challenges
Predicting PXR Induction - We have liftoff
Launch details for the PXR induction challenge, including the dataset, rules, and practical guidance for participants.
Blind Challenges
Lessons Learned from the OpenADMET-ExpansionRx Blind Challenge: Can We Trust Zero-Shot ADMET Predictions?
Lessons and reflections from the OpenADMET-ExpansionRx blind challenge — evaluating whether zero-shot ADMET predictions can be trusted in real drug discovery settings.
Blind Challenges
Announcing the next OpenADMET Blind Challenge: Predicting PXR Induction
An introduction to the next blind challenge and why blinded datasets remain important for realistic benchmarking.
Models
A Hot, Fresh, & New Clearance Model
A look at OpenADMET's clearance modeling work and the broader challenge of generalizing across chemical space.
Data
Building the OpenADMET Data Engine
A behind-the-scenes look at the infrastructure and strategy required to generate useful ADMET datasets at scale.
Blind Challenges
Lessons Learned from the OpenADMET - ExpansionRx Blind Challenge
Authors: Maria Castellanos, Hugo MacDermott-Opeskin, Jon Ainsley, Pat Walters DOI: 10.5281/zenodo.21784567 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