Toshiaki Sunazuka
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Toshiaki Sunazuka has a total of 43 co-authors. Here are the top co-authors by number of shared publications:
Akira Katsuyama
Center for Research and Education on Drug Discovery, Faculty of Pharmaceutical Science, Hokkaido University, Kita 12, Nishi 6, Kita ku, Sapporo 060 0812, Japan; Faculty of Pharmaceutical Sciences, Hokkaido University, Kita-12, Nishi-6, Kita-ku, Sapporo 060-0812, Japan
1 shared publicationAkira Matsuda
Faculty of Pharmaceutical Sciences, Hokkaido University, Kita-12, Nishi-6, Kita-ku, Sapporo 060-0812, Japan
1 shared publicationEri Watanabe
Lead Exploration Unit, Drug Discovery Initiative, The University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo 113-0033, Japan
1 shared publicationFumika Yakushiji
Center for Research and Education on Drug Discovery, Faculty of Pharmaceutical Science, Hokkaido University, Kita 12, Nishi 6, Kita ku, Sapporo 060 0812, Japan; Faculty of Pharmaceutical Sciences, Hokkaido University, Kita-12, Nishi-6, Kita-ku, Sapporo 060-0812, Japan
1 shared publication- Hideaki Kakeya
Kyoto University
1 shared publication - Hirotaka Matsuo
Kitasato Institute for Life Sciences, Kitasato University, 5-9-1 Shirokane, Minato-ku, Tokyo 108-8641, Japan
1 shared publication
Latest Publications
- Open Access
- 29 May 2023
- Published by American Chemical Society (ACS) in ChemRxiv
Deep generative model of constructing chemical latent space for large molecular structures with 3D complexity
The structural diversity of chemical libraries, which are systematic collections of compounds that have potential to bind to biomolecules, can be represented by chemical latent space. A chemical latent space is a projection of a compound structure into a mathematical space based on several molecular features, and it can express structural diversity within a compound library in order to explore a broader chemical space and generate novel compound structures for drug candidates. Many of the natural compounds produced by living organisms have complicated structures and are highly biologically active. However, no deep learning models exist that can effectively construct chemical latent spaces to handle large and complex compound structures, such as those found in natural compounds, and furthermore manage chirality, which is an essential factor in the 3D complexity of compounds. In this study, we developed a new deep-learning method, called NP-VAE, based on variational autoencoder for handling natural compounds, and constructed a chemical latent space that projected large and complex compound structures including chirality. NP-VAE was successful in construction of the chemical latent space that showed higher accuracy with respect to reconstruction and generalization than the state-of-the-art deep learning methods. Furthermore, by exploring the acquired latent space, we succeeded in comprehensively analyzing a compound library containing natural compounds and generating novel compound structures with optimized functions.
- 29 May 2023
- Published by American Chemical Society (ACS) in ChemRxiv
Open AccessDeep generative model of constructing chemical latent space for large molecular structures with 3D complexity
The structural diversity of chemical libraries, which are systematic collections of compounds that have potential to bind to biomolecules, can be represented by chemical latent space. A chemical latent space is a projection of a compound structure into a mathematical space based on several molecular features, and it can express structural diversity within a compound library in order to explore a broader chemical space and generate novel compound structures for drug candidates. Many of the natural compounds produced by living organisms have complicated structures and are highly biologically active. However, no deep learning models exist that can effectively construct chemical latent spaces to handle large and complex compound structures, such as those found in natural compounds, and furthermore manage chirality, which is an essential factor in the 3D complexity of compounds. In this study, we developed a new deep-learning method, called NP-VAE, based on variational autoencoder for handling natural compounds, and constructed a chemical latent space that projected large and complex compound structures including chirality. NP-VAE was successful in construction of the chemical latent space that showed higher accuracy with respect to reconstruction and generalization than the state-of-the-art deep learning methods. Furthermore, by exploring the acquired latent space, we succeeded in comprehensively analyzing a compound library containing natural compounds and generating novel compound structures with optimized functions.
- 1 April 2021
- Published by Elsevier in Bioorganic & Medicinal Chemistry Letters
- Vol. 37, 127847
Structure, solubility, and permeability relationships in a diverse middle molecule library
- 1 April 2021
- Published by Elsevier in Bioorganic & Medicinal Chemistry Letters
- Vol. 37, 127847
Structure, solubility, and permeability relationships in a diverse middle molecule library
- Open Access
- 7 May 2020
- Published by MDPI AG in Antibiotics
- Vol. 9 (5) , 236
Thioporidiols A and B: Two New Sulfur Compounds Discovered by Molybdenum-Catalyzed Oxidation Screening from Trichoderma polypori FKI-7382
Two new sulfur compounds, designated thioporidiol A (1) and B (2), were discovered by the MoS-screening program from a culture broth of Trichoderma polypori FKI-7382. The structures of 1 and 2 were determined as C13 lipid structures with an N-acetylcysteine moiety. The relative configuration at the C-5 and C-6 position of 1 was determined by the derivatives of α-methoxy-α-phenylacetic acid diesters, and the absolute configuration of the N-acetylcysteine moiety was determined by advanced Marfey’s analysis. Compounds 1 and 2 were evaluated for anti-microbial, cytotoxic and anti-malarial activities. Compound 2 exhibited anti-microbial activity against Candida albicans ATCC 64548.
- 7 May 2020
- Published by MDPI AG in Antibiotics
- Vol. 9 (5) , 236
Open AccessThioporidiols A and B: Two New Sulfur Compounds Discovered by Molybdenum-Catalyzed Oxidation Screening from Trichoderma polypori FKI-7382
Two new sulfur compounds, designated thioporidiol A (1) and B (2), were discovered by the MoS-screening program from a culture broth of Trichoderma polypori FKI-7382. The structures of 1 and 2 were determined as C13 lipid structures with an N-acetylcysteine moiety. The relative configuration at the C-5 and C-6 position of 1 was determined by the derivatives of α-methoxy-α-phenylacetic acid diesters, and the absolute configuration of the N-acetylcysteine moiety was determined by advanced Marfey’s analysis. Compounds 1 and 2 were evaluated for anti-microbial, cytotoxic and anti-malarial activities. Compound 2 exhibited anti-microbial activity against Candida albicans ATCC 64548.