Example notebooks for the 2025 Polaris x ASAP x OpenADMET blind challenge in computational approaches to drug discovery. See the blog post and competition page for more.
The goal of this blind challenge is to improve our shared understanding of the strengths and pitfalls of computational methods for potency, ADMET and pose prediction.
We encourage everyone participating in this challenge to share a preprint - we will track these during the challenge so that participants can compare learnings on-the-fly - that describes their approach, results, performance and learnings from comparing their approach with other groups. We are working with the editors of Journal of Chemical Information and Modeling (JCIM; a high-impact journal in chemical informatics and molecular modeling) on a collection of papers/ special issue that will report on the breadth of learnings and outcomes from this challenge.
If you have any suggestions on how we could evaluate the submitted predictions to further improve our shared understanding, we'd love to hear it! Please open a Github issue or discussion in this repository to share your ideas with the community.
