Lamarr AI Colloquium: Atsushi Yoshimori on “AI Agent for Drug Discovery”

About the Lamarr AI-Colloquium

The AI Colloquia, organized by the Lamarr Institute, the Research Center Trustworthy Data Science and Security (RC Trust) and the Center for Data Science & Simulation at TU Dortmund University (DoDas), provides a platform for leading researchers to present groundbreaking work in the field of Machine Learning and Artificial Intelligence. These 90-minute sessions, which usually take place on Thursdays at 10 a.m. c.t., unlike other colloquia, focus on interactive dialog and international collaboration and include one-hour lectures and 30-minute Q&A sessions. The colloquium will be held mainly in English. The hybrid format of the colloquium ensures that all interested parties can participate in person in the room 3.110 at the University of Bonn or online via this ZOOM-Link .
On November 27th, the Lamarr AI Colloquium welcomes Atsushi Yoshimori as its next speaker with a keynote entitled “AI Agent for Drug Discovery”.

Abstract

The emergence of large language models (LLMs) is drawing increasing attention to the development of AI agents in scientific research. In drug discovery, the development of AI agents requires the seamless integration of LLMs with external tools. Recently, the Model Context Protocol (MCP) has attracted attention as a framework to enable integration. This lecture begins with an introduction of MCP, which is followed by a detailed explanation of its implementation using a simple example. Then, a new MCP-based compound optimization system termed X-DeepSARM, is introduced. This system is characterized by its ability to identify chemical modifications of compounds for potency optimization based on explainable AI (XAI). The underlying theory and exemplary applications are presented

Atushi Yoshimori

Atsushi Yoshimori is the Director of the Institute of Theoretical Medicine, Inc. (Japan) and an Affiliate/Adjunct Professor at Tokyo University of Science and University of Shizuoka. His area of expertise is cheminformatics and drug discovery, with a focus on artificial intelligence and the integration of computational methods into pharmaceutical innovation.

For questions please contact Brendan Balcerak Jackson.