Advancing Explainable AI in Drug Discovery

Sano Researchers at MLSSD 2025

Two researchers from the Structural and Functional Genomics Group brought their expertise in AI-driven biomedical research to the Machine Learning Summer School for Drug and Materials Discovery (MLSSD 2025), contributing to the vibrant exchange of ideas between computational science and pharmaceutical innovation.

Tomasz Kościółek, Research Team Leader, delivered a talk on the role of machine learning in drug design, offering a clear and insightful perspective on how advanced algorithms are reshaping early-stage drug discovery. His presentation blended technical depth with accessible delivery, drawing strong interest from participants across disciplines.

Adam Sułek, Postdoctoral Researcher, showcased a poster titled “Challenges in Explainable Machine Learning for Drug Discovery”, co-authored with Jakub Klimczak, Jakub Jończyk, Tomasz Kościółek, Tomasz Danel, and Barbara Pucelik. Their work addressed the growing demand for transparency in machine learning models applied to molecular and pharmacological research, outlining both current obstacles and future directions.

The summer school served as a fertile ground for interdisciplinary dialogue — linking machine learning with real-world challenges in drug and materials development. From hands-on sessions to informal discussions, it created space for both technical learning and collaborative inspiration.