RIKEN Center for Advanced Intelligence Project Chemical Reaction Informatics Team

Team Director: Ichigaku Takigawa (D.Eng.)

Japanese Page

Research Summary

Chemical reactions are processes that convert one substance into another, forming the foundation of life itself while also playing a vital role in everything from consumer products and pharmaceuticals to electronics and energy. At the same time, because the molecular structures and its rearrangements involve combinatorial aspects, and chemical reactions are inherently non-equilibrium processes—from equilibrium to transition states and back—they pose many unresolved questions and technical challenges for machine learning. Our team is working on machine learning research that contributes to the discovery and design of chemical reactions across multiple levels.

Main Research Fields

Informatics

Related Research Fields

Chemistry
Mathematical & Physical Sciences
Biological Sciences
Intelligent informatics-related
Life, health and medical informatics-related

Keywords

Machine Learning
Machine Discovery
Geometric Learning
Combinatorial Generalization

Selected Publications

Papers with an asterisk(*) are based on research conducted outside of RIKEN.

1. *Wang G, Mine S, Chen D, Jing Y, Ting KW, Yamaguchi T, Takao M, Maeno Z, Takigawa I*, Matsushita K, Shimizu K*, Toyao T*.
"Accelerated discovery of multi-elemental reverse water-gas shift catalysts using extrapolative machine learning approach"
Nature Communications, 14, 5861. (2023)
2. *Ide Y*, Shirakura H, Sano T, Murugavel M, Inaba Y, Hu S, Takigawa I*, Inokuma Y*
"Machine Learning-Based Analysis of Molar and Enantiomeric Ratios and Reaction Yields Using Images of Solid Mixtures"
Ind. Eng. Chem. Res., 62(35): 13790–1379. (2023)
3. *Katsuno H, Kimura Y, Yamazaki T, Takigawa I
"Machine Learning Refinement of In Situ Images Acquired by Low Electron Dose LC-TEM"
Microscopy and Microanalysis, 30(1), 77-84. (2024)
4. *Katsuno H, Kimura Y, Yamazaki T, Takigawa I
"Early detection of nucleation events from solution in LC-TEM by machine learning"
Frontiers in Chemistry 2022; 10:818230.
5. *Katsuno H, Kimura Y, Yamazaki T, Takigawa I
"Fast improvement of TEM image with low-dose electrons by deep learning"
Microscopy and Microanalysis 28(1), 138-144. (2022)
6. *Toyao T, Maeno Z, Takakusagi S, Kamachi T, Takigawa I*, Shimizu K*
"Machine learning for catalysis informatics: Recent applications and prospects."
ACS Catalysis. 10: 2260-2297. (2020)
7. *Suzuki K, Toyao T, Maeno Z, Takakusagi S, Shimizu K, Takigawa I
"Statistical analysis and discovery of heterogeneous catalysts based on machine learning from diverse published data."
ChemCatChem. 11(18): 4537-4547. (2019)
8. *Toyao T*, Suzuki K, Kikuchi S, Takakusagi S, Shimizu K, Takigawa I*
"Toward effective utilization of methane: machine learning prediction of adsorption energies on metal alloys"
The Journal of Physical Chemistry C. 122(15): 8315-8326. (2018)
9. *Takigawa I, Mamitsuka H
"Generalized sparse learning of linear models over the complete subgraph feature set"
IEEE Transactions on Pattern Analysis and Machine Intelligence. 39(3): 617-624. (2017)
10. *Takigawa I, Mamitsuka H
"Efficiently mining delta-tolerance closed frequent subgraphs"
Machine Learning. 82(2): 95-121. (2011)

Lab Members

Principal investigator

Ichigaku Takigawa: Team Director

Contact Information

Nihonbashi 1-chome Mitsui Building, 15th floor,
1-4-1 Nihonbashi,
Chuo-ku, Tokyo
103-0027, Japan
Email: ichigaku.takigawa@riken.jp