Polaris: An industry-led initiative to critically assess ML in drug discovery
Year: 2025
Type: article
Abstract: Machine learning (ML) is driving exciting innovations in drug discovery, but we need to be mindful of the circumstances that set this application apart. The absence of standardized, domain-appropriate datasets, guidelines and tools for the evaluation and comparison of methods has led to a growing gap between perceived progress and real-world impact, which is delaying the adoption of ML in drug discovery. To bridge this gap, we formed Polaris: An open-science, cross-industry and interdisciplinary collaboration to develop benchmarking protocols tailored to drug discovery. With Polaris, we are working on three main pillars: First of all, we leverage the unique expertise of scientists in the industry through steering committees to propose guidelines that reflect the real-world context. Then we simplify the adoption of these best practices through a set of open-source software tools, centered around the multimodal Polaris Hub benchmarking platform. Finally, we create incentives to adopt these practices through community initiatives. Jointly, we believe these three pillars will accelerate and amplify the effects of ML methods in drug discovery.
Author: Wognum, Cas
Institution: Recursion (United States)
Language: English
Subfield: Computational Theory and Mathematics
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W6893289487