Advanced General Intelligence for Science Program Polymeromics Team
Team Director: Ryo Yoshida (Ph.D.)
Research Summary

Our team leverages a large-scale database from both real-world experiments and computational simulations to develop foundation models for polymer material systems. By utilizing automation technologies for computational experiments based on molecular dynamics simulations and first-principles calculations, we are building one of the world’s largest polymer material databases. Furthermore, we are advancing technologies such as "Sim2Real machine learning", which enables the integrated analysis of simulation and experimental data, and developing AI- and robotics-driven autonomous material discovery systems.
Main Research Fields
- Complex Systems
Related Research Fields
- Chemistry
- Informatics
- Intelligent informatics-related
- Polymer materials-related
Keywords
- Machine learning
- Polymer materials
- Simulation
- Automated experiments
- Materials database
Selected Publications
Papers with an asterisk(*) are based on research conducted outside of RIKEN.
- 1.
*Hayashi, Y., Shiomi, J., Morikawa, J., Yoshida, R.
"RadonPy: automated physical property calculation using all-atom classical molecular dynamics simulations for polymer informatics"
npj Computational Materials 8(1), 222 (2022) - 2.
*Aoki, Y., Wu, S., Tsurimoto, T., Hayashi, Y., Minami, S., Okubo, T., Shiratori, K., Yoshida, R.
"Multitask machine learning to predict polymer-solvent miscibility using Flory-Huggins interaction parameters"
Macromolecules 56(14), 5446–5456 (2023) - 3.
*Minami, S., Fukumizu, K., Hayashi, Y., Yoshida, R.
"Transfer learning with affine model transformation"
Advance in Neural Information Processing Systems 36 (2023) - 4.
*Kusaba, M., Liu, C., Yoshida, R.
"Crystal structure prediction with machine learning-based element substitution"
Computational Materials Science 211, 111496 (2022) - 5.
*Ohno, M., Hayashi, Y., Zhang, Q., Kaneko, Y., & Yoshida, R.
"SMiPoly: generation of synthesizable polymer virtual library using rule-based polymerization reactions"
Journal of Chemical Information and Modeling 63(17), 5539–5548 (2023) - 6.
*Kusaba, M., Hayashi, Y., Liu, C., Wakiuchi, A., Yoshida, R.
"Representation of materials by kernel mean embedding"
Physical Review B 108(13), 134107 (2023) - 7.
*Liu, C., Tamaki, H., Yokoyama, T., Wakasugi, K., Yotsuhashi, S., Kusaba, M., Oganov, A.R, Yoshida, R.
"Shotgun crystal structure prediction using machine-learned formation energies"
npj Computational Materials 10, 298 (2024) - 8.
*Noda, K., Wakiuchi, A., Hayashi, Y., Yoshida. R.
"Advancing extrapolative predictions of material properties through learning to learn using extrapolative episodic training"
Communications Materials 6, 36 (2025) - 9.
*Minami, S., Hayashi, Y., Wu, S., Fukumizu, K., Sugisawa, H., Ishii, M., Kuwajima, I., Shiratori, K., Yoshida, R.
"Scaling law of Sim2Real transfer learning in expanding computational materials databases for real-world predictions"
npj Computational Materials (2025). (in press) - 10.
*Nanjo, S., Maeda, H., Hayashi, Y., Hatakeyama-Sato, K., Himeno, R., Hayakawa, T., Yoshida, R.
"SPACIER: on-demand polymer design with fully automated all-atom classical molecular dynamics integrated into machine learning pipelines"
npj Computational Materials 11, 16 (2025)
Related Links
Lab Members
Principal investigator
- Ryo Yoshida
- Team Director
Contact Information
2-1 Hirosawa, Wako,
Saitama 351-0198, Japan
CONTACT | TRIP Headquarters