Chemoinformatics / Materials Science
Discover new materials/drugs with computational science.
Finding new materials by deep learning and computational simulations*
Material analysis based on computational simulation can be a promising solution to reduce experimental costs and promote new material developments. Current simulation technology is, however, not mature enough to handle tremendous numbers of candidate compounds and materials thoroughly because of its computational cost.
Our goal is to accelerate the process of material developments by high-performance material analysis system based on state-of-the-art deep learning and computational simulation technologies.
Especially, we are engaging R&D activities to achieve such material analysis technology for application to drug and material discovery.
Publications
Nature Communications, 2022
By : So Takamoto, Chikashi Shinagawa, Daisuke Motoki, Kosuke Nakago, Wenwen Li, Iori Kurata, Taku Watanabe, Yoshihiro Yayama, Hiroki Iriguchi, Yusuke Asano, Tasuku Onodera, Takafumi Ishii, Takao Kudo, Hideki Ono, Ryohto Sawada, Ryuichiro Ishitani, Marc Ong, Taiki Yamaguchi, Toshiki Kataoka, Akihide Hayashi, Nontawat Charoenphakdee, Takeshi Ibuka
Population-based De Novo Molecule Generation, Using Grammatical Evolution
Chemistry Letters, 47, 1431-1434, 2018
By : Naruki Yoshikawa, Kei Terayama, Masato Sumita, Teruki Homma, Kenta Oono, Koji Tsuda
Semi-supervised learning of hierarchical representations of molecules with neural message passing
Machine Learning for Molecules and Materials in NIPS 2017
By : Hai Nguyen, Shin-ichi Maeda, Kenta Oono