Blind Challenges

Events
Events

ExpansionRx × OpenADMET Blind Challenge

Blind challenges are a cornerstone for benchmarking and improving predictive modeling in molecular sciences. Following in the tradition of community efforts like CASP and other open benchmarking initiatives, this challenge invites researchers to test and refine AI-driven ADMET modeling approaches on a high-quality experimental dataset.

OpenADMET, in collaboration with Expansion Therapeutics and Collaborative Drug Discovery (CDD Vault), is launching the ExpansionRx–OpenADMET Blind Challenge on October 27th, 2025, focused on predicting key ADMET properties for small molecules using both traditional and machine learning approaches. Participants will gain access to carefully curated data through CDD Vault Public and Hugging Face, enabling transparent, reproducible evaluation of predictive performance. Submissions close on January 19th, 2026.

This challenge exemplifies the OpenADMET mission: accelerating open, community-driven progress in the modeling of the “avoidome” — the molecular features that drive toxicity, metabolic instability, and off-target effects. We welcome participants from academia, biotech, pharma, and beyond to join this collaborative experiment in open science.

If you missed our live announcement webinar or want to hear more from the organizers, you can visit our blog and YouTube for updates.

ASAP x Polaris x OpenADMET Blind Challenge

Blind challenges are a critical tool to evaluate and advance the current state of the art in computational molecular sciences, see here for some recent blind challenges in drug discovery. Sharing of these sorts of learnings has led to innovations such as AlphaFold2 as with the CASP sequence of folding challenges.

OpenADMET is proud to collaborate with the ASAP Discovery Consortium and Polaris benchmarking platform to launch an exciting computational blind challenge in small molecule drug discovery. This challenge represents a unique opportunity for researchers to tackle real-world drug discovery problems and demonstrate cutting-edge approaches in molecular modeling and prediction. This challenge aligns perfectly with OMSF’s and OpenADMET’s missions, leveraging the expertise and data from the ASAP Discovery Consortium to foster community-driven innovation in open science and evaluate models on ADMET endpoints

If you missed the event or want to hear from some participants in the challenge, you can watch our recording below.

Videos: visit our YouTube Playlist to hear from the challenge winners.