MAEDA Artificial Intelligence in Chemical Reaction Design and Discovery

Maeda_portrait

Research Director: Satoshi MAEDA
(Director, WPI-ICReDD / Professor, Faculty of Science, Hokkaido University)
Research Term: Oct 2019 - Mar 2025
Grant Number: JPMJER1903

Iwata_portrait

Research Director: Satoru IWATA
(Professor, Graduate School of Information Science and Technology, The University of Tokyo / Specially Appointed Professor, WPI-ICReDD, Hokkaido University)

This project aims to generate “Artificial Intelligence in Chemical Reaction Design Discovery” (AICReDD) that predicts “the whole picture of the behavior of atoms” in chemical reactions and suggests useful and unknown chemical reactions one after another. This will be done by integrating technologies in computational chemistry, information science, and materials informatics. Particularly, our highly versatile automated reaction path method called the Artificial Force Induced Reaction (AFIR) method and combinatorial optimization theory and algorithms are the bases of the AICReDD.

Specifically, we will use the AFIR method to calculate “reaction path network” for combinations of various reactants and catalysts and construct a system to quickly design and suggest chemical reactions appropriate for the synthesis of target substances from the obtained reaction path database. In this case, combinatorial optimization is applied to derive combinations of reactants that maximize the yield of the target product. We will further try to implement AICReDD in synthesis robots and aim to greatly accelerate the speed of discovering the most favorable chemical reaction producing the target substance.

fig_en1

Research Groups

・Project management Group
・Quantum Chemistry Group
・Materials Informatics Group
・Organic synthesis Group
・Robot synthesis Group
・Optimization Group
・Machine learning Group