Takuto Koyama

Kyoto University — Japan

Computer Science · Physical Sciences

4h-index46citations17works1.72yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Computational Drug Discovery Methods(14), Machine Learning in Materials Science(8), Bioinformatics and Genomic Networks(4), Chemistry and Chemical Engineering(4), Protein Structure and Dynamics(2)

Publications17 total

Chemical genomics language model toward reliable and explainable compound-protein interaction exploration
Journal of Cheminformatics·2026Open Access
Empowering federated learning for robust compound-protein interaction prediction across heterogeneous cross-pharma domains
Journal of Cheminformatics·2026Open Access
Improving ADME Prediction with Multitask Graph Neural Networks and Assessing Explainability in Lead Optimization
Journal of Chemical Information and Modeling·2025Open Access
Improving ADME Prediction with Multitask Graph Neural Networks and Assessing Explainability in Lead Optimization
2025
Empowering Federated Learning for Robust Compound-Protein Interaction Prediction across Heterogeneous Cross-Pharma Domains
2025
Improving ADME Prediction with Multitask Graph Neural Networks and Assessing Explainability in Lead Optimization
2025
kMoL: an open-source machine and federated learning library for drug discovery
Journal of Cheminformatics·2025· 9 citedOpen Access
Synergistic involvement of the NZF domains of the LUBAC accessory subunits HOIL-1L and SHARPIN in the regulation of LUBAC function
Cell Death and Disease·2024· 1 citedOpen Access
Chemical Genomics Language Model toward Reliable and Explainable Compound-Protein Interaction Exploration
2024· 4 citedOpen Access
Feature extraction of particle morphologies of pharmaceutical excipients from scanning electron microscope images using convolutional neural networks
International Journal of Pharmaceutics·2024· 5 citedOpen Access
The AI Trends in Chemical Space for Drug Discovery
2024
VGAE-MCTS: A New Molecular Generative Model Combining the Variational Graph Auto-Encoder and Monte Carlo Tree Search
Journal of Chemical Information and Modeling·2023· 21 citedOpen Access
VGAE-MCTS: A New Molecular Generative Model Combining Variational Graph Auto-Encoder and Monte Carlo Tree Search
Research Square (Research Square)·2023· 2 citedOpen Access
Improving Compound–Protein Interaction Prediction by Self-Training with Augmenting Negative Samples
Journal of Chemical Information and Modeling·2023· 3 citedOpen Access
VGAE-MCTS: a New Molecular Generative Model combining Variational Graph Auto-Encoder and Monte Carlo Tree Search
2023Open Access
VGAE-MCTS: a New Molecular Generative Model combining Variational Graph Auto-Encoder and Monte Carlo Tree Search
2023· 1 citedOpen Access
Improving Compound-Protein Interaction Prediction by Self-Training with Augmenting Negative Samples
2023Open Access

Frequent Co-authors

Yasushi Okuno(15), Shigeyuki Matsumoto(14), Ryosuke Kojima(12), Hiroaki Iwata(9), Taichi Nakai(3), Yuji Okamoto(3), Masataka Kuroda(3), Hitoshi Kawashima(3), Reiko Watanabe(3), Tomoki Yonezawa(3), Takaaki Sumiyoshi(3), Kazuyoshi Ikeda(3), Kenji Mizuguchi(3), Hiroaki Iwata(3), Takao Otsuka(2), Aki Hasegawa(2), Hayato Tsumura(2), Takehiko Morimoto(2), Rei Sasaki(2), Manabu Tojo(2)