Updated on 2025/06/09

写真a

 
SAIGO HIROTO
 
Organization
Faculty of Information Science and Electrical Engineering Department of Informatics Associate Professor
Joint Graduate School of Mathematics for Innovation (Concurrent)
School of Sciences Department of Physics(Concurrent)
Graduate School of Information Science and Electrical Engineering Department of Information Science and Technology(Concurrent)
Title
Associate Professor
Contact information
メールアドレス
Tel
0928023783
Profile
His research interest is in developing methods for data mining and artificial intelligence, and applying them to problems in biology and chemistry. He also serves as a program committee member for international conferences in bioinformatics and machine learning.
External link

Research Areas

  • Informatics / Life, health and medical informatics

  • Informatics / Statistical science

  • Informatics / Intelligent informatics

Degree

  • Doctor of Informatics

Research History

  • 2010-2015 九州工業大学(准教授) 2008-2010 Max Planck Institute for Informatics, Germany (Research Scientist) 2006-2008 Max Planck Institute for Biological Cybernetics, Germany (Research Scientist)   

Education

  • Kyoto University   情報学研究科  

    2001.4 - 2006.3

Research Interests・Research Keywords

  • Research theme: Machine Learning for High-Level Radioactive Waste Management: An Approach Based on Control of High-Temperature Multiphase Melts

    Keyword: machine learning, high-level radioactive waste, high-temperature multiphase melts

    Research period: 2023.4

  • Research theme: A machine learning approach to automatic design of genes, proteins and chemical compounds

    Keyword: machine learning, protein squence, chemical compound, design

    Research period: 2022.9

  • Research theme: Development of machine learning methods towards manufacturing informatics

    Keyword: machine learning, data mining, statistics

    Research period: 2018.4

  • Research theme: Development of a GWAS method that considers interaction among genetic factors and environmental factors

    Keyword: GWAS, interaction

    Research period: 2013.3

  • Research theme: Development and application of statistical learning methods to the problems associated with Human Immunodeficiency Virus (HIV).

    Keyword: HIV, statistical learning, pattern mining

    Research period: 2008.6

  • Research theme: Integration of frequent pattern mining with machine learning algorithms

    Keyword: 頻出パターンマイニング、ブースティング、線形計画法、SVM

    Research period: 2006.6

  • Research theme: Development of kernel methods for detecting remote homology between protein sequences.

    Keyword: kernel methods, protein homology detection, alignment, SVM

    Research period: 2002.4 - 2006.3

Awards

  • 奨励賞

    2007.6   人工知能学会   奨励賞

  • Best Paper Award

    2006.6   Mining and Learning with Graphs Committee   論文賞

Papers

  • Einstein-Roscoe regression for the slag viscosity prediction problem in steelmaking Reviewed International journal

    @Saigo, H., Bahadur, K.C.D, @Saito, N.

    Scientific Reports   12   2022.4

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

    Other Link: https://www.nature.com/articles/s41598-022-10278-w

  • Automatically mining relevant variable interactions via sparse Bayesian learning Reviewed International journal

    #Yafune, R., #Sakuma, D., Tabei, Y., @Saito, N., @Saigo, H.

    International Conference on Pattern Recognition   2021.1

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

  • KDE: a Kernel-based approach to detecting high-order genetic Epistasis Reviewed International journal

    Kodama, K., Saigo, H.

    The 27th International Conference on Genome Informatics (GIW2016)   2016.10

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)  

  • Protein Structure Comparison Based on 3D Molecular Visualization Images Reviewed International journal

    Suryanto, C. H., Saigo, H., Fukui, K.

    2016.8

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

  • Extracting sets of chemical substructures and protein domains governing drug-target interactions Reviewed International journal

    Yamanishi, Y., Pauwels, E., Saigo, H., Stoven, V.

    51 ( 5 )   1183 - 1194   2011.5

     More details

    Language:English   Publishing type:Research paper (scientific journal)  

▼display all

Books

  • Matrix Decomposition-based Dimensionality Reduction on Graph Data In Sakr, S. and Pardede, E. editors Graph Data Management: Techniques and Applications

    Saigo, H., Tsuda, K.(Role:Joint author)

    IGI Global  2011.1 

     More details

    Responsible for pages:260-284   Language:English   Book type:Scholarly book

  • Graph Mining for Chemoinformatics In Lodhi, H and Yamanishi, Y. editors Chemoinformatics and Advanced Machine Learning Perspectives: Complex Computational Method and Collaborative Technique

    Saigo, H., Tsuda, K.(Role:Joint author)

    2010.1 

     More details

    Responsible for pages:95-128   Language:English   Book type:Scholarly book

  • Graph Classification  In Sakr, C.C.C. and Wang, H. editors Managing and Mining Graph Data

    Saigo, H., Tsuda, K.(Role:Joint author)

    Springer  2010.1 

     More details

    Responsible for pages:337-364   Language:English   Book type:Scholarly book

  • Graph Kernels for Chemoinformatics In Lodhi, H and Yamanishi, Y. editors Chemoinformatics and Advanced Machine Learning Perspectives: Complex Computational Method and Collaborative Techniques

    Kashima, H., Saigo, H., Hattori, M., Tsuda, K.(Role:Joint author)

    IGI Global  2010.1 

     More details

    Responsible for pages:1-15   Language:English   Book type:Scholarly book

  • Deep Learning-Based Advances In Protein Posttranslational Modification Site and Protein Cleavage Prediction in "Methods in Molecular Biology"

    Subash C Pakhrin, Suresh Pokharel, @Hiroto Saigo, Dukka B Kc(Role:Joint author)

    Springer  2022.6    ISSN:10643745

     More details

    Language:English   Book type:Scholarly book

    Posttranslational modification (PTM) is a ubiquitous phenomenon in both eukaryotes and prokaryotes which gives rise to enormous proteomic diversity. PTM mostly comes in two flavors: covalent modification to polypeptide chain and proteolytic cleavage. Understanding and characterization of PTM is a fundamental step toward understanding the underpinning of biology. Recent advances in experimental approaches, mainly mass-spectrometry-based approaches, have immensely helped in obtaining and characterizing PTMs. However, experimental approaches are not enough to understand and characterize more than 450 different types of PTMs and complementary computational approaches are becoming popular. Recently, due to the various advancements in the field of Deep Learning (DL), along with the explosion of applications of DL to various fields, the field of computational prediction of PTM has also witnessed the development of a plethora of deep learning (DL)-based approaches. In this book chapter, we first review some recent DL-based approaches in the field of PTM site prediction. In addition, we also review the recent advances in the not-so-studied PTM, that is, proteolytic cleavage predictions. We describe advances in PTM prediction by highlighting the Deep learning architecture, feature encoding, novelty of the approaches, and availability of the tools/approaches. Finally, we provide an outlook and possible future research directions for DL-based approaches for PTM prediction.

    DOI: 10.1007/978-1-0716-2317-6_15

    Scopus

    PubMed

▼display all

Presentations

  • Automatically mining relevant variable interactions via sparse Bayesian learning International conference

    #Yafune, R., #Sakuma, D., Tabei, Y., @Saito, N., @Saigo, H.

    International Conference on Pattern Recognition  2021.1 

     More details

    Event date: 2021.1

    Language:English   Presentation type:Oral presentation (general)  

    Venue:Online (originally Milan)   Country:Italy  

  • Entire regularization path for sparse nonnegative interaction model International conference

    #Takayanagi, M., Tabei, Y., Saigo, H.

    International Conference on Data Mining (ICDM)  2018.11 

     More details

    Event date: 2017.9

    Language:English   Presentation type:Oral presentation (general)  

    Venue:Singapore   Country:Japan  

    本研究では相互作用を考慮した非負値最小二乗法に対する正則化パス追跡アルゴリズムを提案した。
    組み合わせ空間の効率的な探索のための枝刈りを実装した本手法は、LASSOよりも大幅に小さい解集合を得られることを計算機実験で示した。
    HIVデータを用いた実験では、重要な遺伝子要因の組み合わせを自動的に探索することにより、薬剤耐性モデルを正確に推定出来ることを示した。

  • Towards predicting the epistasis in genome wide association study International conference

    Saigo, H.

    BMIRC2015  2015.3 

     More details

    Language:English  

    Venue:Iizuka   Country:Japan  

  • Towards predicting the epistasis in genome wide association study International conference

    Saigo, H.

    BMIRC2015  2015.3 

     More details

    Language:English  

    Venue:Iizuka   Country:Japan  

  • Mining and learning with structured data International conference

    Saigo, H.

    BIT2016  2016.3 

     More details

    Language:English  

    Venue:Taipei   Country:Taiwan, Province of China  

▼display all

MISC

  • QSARモデルの構築; 機械学習と部分構造マイニングによるアプローチ

    西郷 浩人

    日本化学会情報化学部会誌   2013.7

     More details

    Language:Japanese   Publishing type:Article, review, commentary, editorial, etc. (scientific journal)  

  • 局所アラインメントカーネルを用いたアミノ酸置換行列の最適化

    西郷 浩人, ジャンフィリップ・ヴェール, 阿久津 達也

    情報処理学会研究報告数理モデル化と問題解決(MPS)   2006.3

     More details

    Language:English  

    Optimizing amino acid substitution matrices with local alignment kernels
    Detecting similarity between protein sequence is one of the core problems in bioinformatics, and detecting weak similarities is known as a hard problem. We have proposed a local alignmnet kernel for this purpose and showed good performance in the previous research. The local alignment kernel depdends on amino acid substitution matrices. We show that we can analytically calculate the derivatives of the local alignment kernels with respect to amino acid substitution matrix as well as their efficient calculation through dynamic programming. Then we plug them into the gradient based optimization procedure which is designed to discriminate true homologs from non-homologs. The local alignment kernel exhibits better performance when it uses the matrices and gap parameters optimized by this procedure than when it uses the matrices optimized for the Smith-Waterman algorithm. Furthermore, the matrices and gap parameters optimized for the local alignment kernel can also be used successfully by the Smith-Waterman algorithm.

Professional Memberships

  • Japanese Society of Bioinformatics (JSBi)

  • Japanese Society of Artificial Intelligence (JSAI)

  • Japanese Society of Statistics (JSS)

  • The Iron and Steel Institute of Japan (ISIJ)

  • THE JAPAN STATISTICAL SOCIETY

Academic Activities

  • 学術論文等の審査 International contribution

    Role(s): Peer review

    2024

     More details

    Type:Peer review 

    Number of peer-reviewed articles in foreign language journals:10

  • Pattern Recognition International contribution

    2023.12 - Present

     More details

    Type:Academic society, research group, etc. 

  • Screening of academic papers

    Role(s): Peer review

    2023

     More details

    Type:Peer review 

    Number of peer-reviewed articles in foreign language journals:2

    Number of peer-reviewed articles in Japanese journals:1

    Proceedings of International Conference Number of peer-reviewed papers:10

  • Screening of academic papers

    Role(s): Peer review

    2022

     More details

    Type:Peer review 

    Number of peer-reviewed articles in foreign language journals:2

    Number of peer-reviewed articles in Japanese journals:2

    Proceedings of International Conference Number of peer-reviewed papers:9

    Proceedings of domestic conference Number of peer-reviewed papers:0

  • プログラム編集委員長

    電気・情報関係学会九州支部連合大会  ( Online Japan ) 2021.9

     More details

    Type:Competition, symposium, etc. 

▼display all

Research Projects

  • 高レベル放射性廃棄物処理のための機械学習:高温多相融体の制御によるアプローチ

    2023.4

      More details

    Authorship:Principal investigator 

  • 高レベル放射性廃棄物処理のための機械学習:高温多相融体の制御によるアプローチ研究

    Grant number:23H03356  2023 - 2027

    Japan Society for the Promotion of Science  Grants-in-Aid for Scientific Research  Grant-in-Aid for Scientific Research (B)

      More details

    Authorship:Principal investigator  Grant type:Scientific research funding

  • 高炉操業の診断・予測方法の開発

    2023

      More details

    Grant type:Donation

  • A machine learning approach to automatic design of genes, proteins and chemical compounds

    Grant number:22K19834  2022 - 2024

    Japan Society for the Promotion of Science  Grants-in-Aid for Scientific Research  Challenging Research(Exploratory)

    西郷 浩人

      More details

    Authorship:Principal investigator  Grant type:Scientific research funding

    科学の基本的なプロセスは仮説を立てて実験を行い、それを検証することの繰り返してである。近年は実験装置の機械化や測定装置の高精度化と高速化などにより、実験の質や量が急激に増える傾向にある。しかしながら、次にどのような実験を行うかを決定する実験計画は人間の勘に頼ったままである。そこで本研究課題が目指すのは機械学習を用いた実験計画の自動化である。
    本提案課題では特に、タンパク質・化合物をターゲットとし、類似度の指標に滑らかな近似を導入することで局所解の効率的な探索を目指す。この結果として、次に実験を行うべきタンパク質や化合物を逐次的かつ効率的に行うことが可能となる。

    CiNii Research

  • スラグみえる化研究会

    2022

      More details

    Grant type:Donation

▼display all

Class subject

  • 【通年】情報理工学研究Ⅰ

    2024.4 - 2025.3   Full year

  • 【通年】情報理工学講究

    2024.4 - 2025.3   Full year

  • 【通年】情報理工学演習

    2024.4 - 2025.3   Full year

  • データ科学

    2024.4 - 2024.9   First semester

  • 情報理工学論議Ⅰ

    2024.4 - 2024.9   First semester

▼display all

FD Participation

  • 2023.5   Role:Participation   Title:【シス情FD】農学研究院で進めているDX教育について

    Organizer:[Undergraduate school/graduate school/graduate faculty]

  • 2023.3   Role:Participation   Title:【シス情FD】独・蘭・台湾での産学連携を垣間見る-Industy 4.0・量子コンピューティング・先端半導体-

    Organizer:[Undergraduate school/graduate school/graduate faculty]

  • 2022.6   Role:Participation   Title:【シス情FD】電子ジャーナル等の今後について

    Organizer:[Undergraduate school/graduate school/graduate faculty]

  • 2022.5   Role:Participation   Title:【シス情FD】若手教員による研究紹介④「量子コンピュータ・システム・アーキテクチャの研究~道具になることを目指して~」

    Organizer:[Undergraduate school/graduate school/graduate faculty]

  • 2022.3   Role:Participation   Title:全学FD:メンタルヘルス講演会

    Organizer:University-wide

▼display all

Visiting, concurrent, or part-time lecturers at other universities, institutions, etc.

  • 2024  理化学研究所革新的人工知能研究センター  Classification:Affiliate faculty  Domestic/International Classification:Japan 

  • 2024  九州工業大学  Classification:Part-time lecturer  Domestic/International Classification:Japan 

  • 2023  九州工業大学  Classification:Part-time lecturer  Domestic/International Classification:Japan 

  • 2023  理化学研究所革新的人工知能研究センター  Classification:Affiliate faculty  Domestic/International Classification:Japan 

  • 2022  理化学研究所革新的人工知能研究センター  Classification:Affiliate faculty  Domestic/International Classification:Japan 

▼display all

Participation in international educational events, etc.

  • 2018.9

    工学系国際教育支援センター

    豪州クイーンズランド大学(UQ)におけるSTEM科目英語教育研修

Other educational activity and Special note

  • 2024  Class Teacher  学部

  • 2023  Class Teacher  学部

  • 2022  Class Teacher  学部

  • 2021  Class Teacher  学部

  • 2020  Class Teacher  学部

▼display all

Acceptance of Foreign Researchers, etc.

  • North Carolina A&T State Univeristy

    Acceptance period: 2018.6 - 2018.7   (Period):1 month or more

    Nationality:United States

    Business entity:Japan Society for the Promotion of Science

Travel Abroad

  • 2008.7 - 2010.3

    Staying countory name 1:Germany   Staying institution name 1:Max Planck Institute for Informatics

  • 2006.6 - 2008.6

    Staying countory name 1:Germany   Staying institution name 1:Max Planck Institute for Biological Cybernetics

  • 2003.8 - 2004.8

    Staying countory name 1:United States   Staying institution name 1:University of California, Irvine