Tatsuya Yoshizawa 🐤

Tatsuya Yoshizawa

Ph.D. Student / Junior Research Associate

Yokohama City University / RIKEN

About Me

I am currently conducting research on machine-learning applications to drug discovery at the Computational Life Science Laboratory, Graduate School of Medical Life Science, Yokohama City University, and the Laboratory for Structure-Based Molecular Design, RIKEN Center for Integrated Medical Sciences.

Interests
  • Cheminformatics
  • Artificial Intelligence
  • In Silico Drug Discovery
Education
  • Doctoral Program, Graduate School of Medical Life Science

    Yokohama City University

  • Master's Program, Graduate School of Medical Life Science

    Yokohama City University

  • International College of Arts and Sciences

    Yokohama City University

Publications
Generalizing molecular design via flexible search space control. Communications Chemistry, 2026.
A data-driven generative strategy to avoid reward hacking in multi-objective molecular design. Nature Communications, 16, 2409, 2025.
ChemTSv2: Functional molecular design using de novo molecule generator. WIREs Computational Molecular Science, 13, e1680, 2023.
Selective Inhibitor Design for Kinase Homologs Using Multiobjective Monte Carlo Tree Search. Journal of Chemical Information and Modeling, 62(22), 5351–5360, 2022.
Talks
Multi-Objective Optimization of Molecular Properties Integrating Boltz-2 and Pharmacokinetic Prediction. 146th Annual Meeting of the Pharmaceutical Society of Japan. 2026/3/27, 2026.
A generative strategy for reliable data-driven design of functional molecules. The International Chemical Congress of Pacific Basin Societies 2025 2025/12/17, 2025.
Molecule Generation with Boltz-2: A Case Study on Kinase Inhibitor Design. CBI Annual Meeting 2025. 2025/10/28, 2025.
Molecular Generation Using a Diffusion Model-Based Binding Affinity Prediction Method. 53rd Symposium on Structure–Activity Relationships. 2025/9/5, 2025.
Introduction to DyRAMO: A Strategy for Reliable Data-Driven Molecular Design. 15th CBI Young Researchers Meeting. 2025/8/21, 2025.