Takuto Koyama, Hayato Tsumura, Shigeyuki Matsumoto, Ryunosuke Okita, Ryosuke Kojima, and Yasushi Okuno. (2024). ChemGLaM: Chemical-Genomics Language Models for Compound-Protein Interaction Prediction. bioRxiv. [PREPRINT]

Romeo Cozac, Haris Hasic, Jun Jin Choong, Vincent Richard, Loic Beheshti, Cyrille Froehlich, Takuto Koyama, Shigeyuki Matsumoto, Ryunosuke Kojima, Hiroaki Iwata, Aki Hasegawa, Takao Otsuka, and Yasushi Okuno. (2025). kMoL: an open-source machine and federated learning library for drug discovery. J. Cheminform. [ARTICLE]

Yusuke Toda, Hiroaki Fujita, Koshiki Mino, Takuto Koyama, Seiji Matsuoka, Toshie Kaizuka, Mari Agawa, Shigeyuki Matsumoto, Akiko Idei, Momoko Nishikori, Yasushi Okuno, Hiroyuki Osada, Minoru Yoshida, Akifumi Takaori-Kondo, and Kazuhiro Iwai (2024). Synergistic involvement of the NZF domains of the LUBAC accessory subunits HOIL-1L and SHARPIN in the regulation of LUBAC function. Cell Death & Disease. [ARTICLE]

Hiroaki Iwata, Yoshihiro Hayashi, Takuto Koyama, Aki Hasegawa, Kosuke Ohgi, Ippei Kobayashi, and Yasushi Okuno. (2024). Feature extraction of particle morphologies of pharmaceutical excipients from scanning electron microscope images using convolutional neural networks. Int. J. Pharm. [ARTICLE]

Hiroaki Iwata, Taichi Nakai, Takuto Koyama, Shigeyuki Matsumoto, Ryosuke Kojima, and Yasushi Okuno. (2023). VGAE-MCTS: a New Molecular Generative Model combining Variational Graph Auto-Encoder and Monte Carlo Tree Search. J. Chem. Inf. Model. [ARTICLE]

Takuto Koyama, Shigeyuki Matsumoto, Hiroaki Iwata, Ryosuke Kojima, and Yasushi Okuno. (2023). Improving Compound–Protein Interaction Prediction by Self-Training with Augmenting Negative Samples. J. Chem. Inf. Model. [ARTICLE]

Takuto Koyama, Hayato Tsumura, Ryunosuke Okita, Kimiya Yamazaki, Takashi Kawahigashi, Aki Hasegawa, Hiroaki Iwata, Ryosuke Kojima, Atsuyuki Matsumoto, and Yasushi Okuno.
“Large-scale Prediction of Compound-Protein Interactions Using a Chemical-Genomics Language Model”,
47th Chemoinformatics Symposium, Kanazawa, December 2024. [ORAL]

Takuto Koyama, Hayato Tsumura, Ryunosuke Okita, Ryosuke Kojima, Shigeyuki Matsumoto, Yasushi Okuno.
ChemGLaM: Chemical Genomics Language Models for Compound-Protein Interaction Prediction,
ISMB 2024 MLCSB, Montreal, Canada, July 2024. [POSTER]

Takuto Koyama, Hayato Tsumura, Atsuyuki Matsumoto, Ryunosuke Okita, Ryosuke Kojima, Yasushi Okuno.
“ChemGLaM: Compound-Protein Interaction Prediction Using Large Language Models”,
24th Annual Meeting of the Protein Society, Sapporo, June 2024. [POSTER] Awarded Poster Prize

Takuto Koyama, Hiroaki Iwata, Atsuyuki Matsumoto, Ryosuke Kojima, Takao Otsuka, Aki Hasegawa, and Yasushi Okuno.
“Insight into Federated Learning for Compound-Protein Interaction Prediction”,
CBI Society 2023 Annual Meeting, Tokyo, October 2023. [ORAL]

Akira Ito, Takuto Koyama, Hiroaki Iwata, Atsuyuki Matsumoto, and Yasushi Okuno.
“Exploring Chemical Structural Insights of ADME Properties via Interpretable Deep Learning”,
CBI Society 2023 Annual Meeting, Tokyo, October 2023. [POSTER]

Hiroaki Iwata, Daichi Nakai, Takuto Koyama, Atsuyuki Matsumoto, Ryosuke Kojima, and Yasushi Okuno.
“A New Molecular Generation Method Combining Deep Learning and Reinforcement Learning”,
CBI Society 2023 Annual Meeting, Tokyo, October 2023. [POSTER]

Takuto Koyama, Shigeyuki Matsumoto, Hiroaki Iwata, Ryosuke Kojima, Yasushi Okuno.
Iterative Data Augmentation of Near-Boundary Negative Samples Improves the Model Generalizability in Compound-Protein Interaction Prediction,
ISMB/ECCB 2023 MLCSB, Lyon, France, July 2023. [POSTER]

Hiroaki Iwata, Yoshihiro Hayashi, Takuto Koyama, Aki Hasegawa, Satoshi Terayama, and Yasushi Okuno.
“Clustering of Pharmaceutical Excipients Using Pretrained Convolutional Neural Networks”,
38th Annual Meeting of the Japanese Pharmaceutical Association, Aichi, May 2023. [POSTER]

Takuto Koyama, Atsuyuki Matsumoto, Hiroaki Iwata, Ryosuke Kojima, and Yasushi Okuno.
“Improvement of Compound-Protein Interaction Prediction with Semi-supervised Learning”,
CBI Society 2022 Annual Meeting, Tokyo, October 2022. [POSTER]

Poster Award Winner at the 24th Annual Meeting of the Protein Society

Takuto Koyama, Yasushi Okuno,
“Chapter 6: AI, Big Data, and Drug Discovery” in Utilization of Information and AI in Chemistry (CSJ Current Review: 50), Kagaku Dōjin

Takuto Koyama, Yasushi Okuno,
The AI Trends in Chemical Space for Drug Discovery, Drug Development Supported by Informatics, Springer

2020–2022: Tokyo Pharmaceutical Association Scholarship Recipient

2022–2024: Nōshisha Public Interest Incorporated Foundation Scholarship Recipient

2022–2024: Japan Student Services Organization – Full Loan Scholarship Exemption

2024–2027: JSPS Special Researcher (DC1)