Models
Cofolding? I hardly know her! - Cofolding Methods on ADMET Targets
Part 1: Structure Prediction
OpenADMET
Blind Challenges
Woah, we’re halfway there…
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 you
Data
Navigating PXR Chemical Space with High-Throughput Chemistry and Standard-Free Quantification
Models
Model, take the wheel: active learning with pEC50 data
Blind Challenges
Peak Performance or Just Noise?
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 metrics
Data
Pregnane X Receptor PDB Structure Rerefinement
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.