Sato, Kengo



Faculty of Science and Technology, Department of Biosciences and Informatics (Yagami)


Assistant Professor/Senior Assistant Professor

External Links

Career 【 Display / hide

  • 2003.04

    Instructor, Department of Biosciences and Informatics, Keio University

  • 2006.04

    Researcher, Japan Biological Infomatics Consortium

  • 2006.04

    Visiting Researcher, Computational Biology Research Center, National Institute of Advanced Industrial Science and Technology

  • 2009.11

    Assistant Professor, Department of Computational Biology, Graduate School of Frontier Sciences, University of Tokyo

  • 2011.04

    Assistant Professor, Department of Biosciences and Informatics, Keio University

Academic Background 【 Display / hide

  • 1991.04

    Keio University, Faculty of Science and Technology, Department of Mathematics

    University, Graduated

  • 1995.04

    Keio University, Graduate School of Science and Technology, Department of Computer Science

    Graduate School, Completed, Master's course

  • 1997.04

    Keio University, Graduate School of Science and Technology, School of Science for Open and Environmental Systems

    Graduate School, Completed, Doctoral course

Academic Degrees 【 Display / hide

  • Ph.D., Keio University, Coursework, 2003.03


Research Areas 【 Display / hide

  • Intelligent informatics (Intelligent Informatics)

  • Life / Health / Medical informatics

  • System genome science

Research Keywords 【 Display / hide

  • Data Mining

  • Bioinformatics

  • Machine Learning

  • Computational Biology


Books 【 Display / hide

  • バイオインフォマティクス入門

    Sato Kengo, 慶應義塾大学出版会, 2015.08

    Scope: 第2章

  • Readings in Japanese Natural Language Processing

    Nobesawa, H.S., Sano, T., Sato, K., Saito, H., CSLI Publications, 2015

    Scope: Domain-specific statistical data for morphological analysis

  • Algorithmic Bioprocesses

    Sakakibara, Y., Sato, K., Springer, 2009.08

    Scope: Sequence and Structural Analyses for Functional non-coding RNAs

  • 実験医学増刊「生命科学の最先端に役立つバイオデータベースとウェブツール総集編」

    佐藤健吾, 榊原康文, 羊土社, 2008.08

    Scope: 二次構造に基づく機能性RNAの配列解析

  • Grammatical Inference: Algorithms and Applications, Lecture Notes in Computer Science

    Yasubumi Sakakibara; Satoshi Kobayashi; Kengo Sato; Tetsuro Nishino; Etsuji Tomita, Springer, 2006

Papers 【 Display / hide

  • A web server for designing molecular switches composed of two interacting rnas

    Taneda A., Sato K.

    International Journal of Molecular Sciences (International Journal of Molecular Sciences)  22 ( 5 ) 1 - 12 2021.03

    ISSN  16616596

     View Summary

    The programmability of RNA–RNA interactions through intermolecular base-pairing has been successfully exploited to design a variety of RNA devices that artificially regulate gene expression. An in silico design for interacting structured RNA sequences that satisfies multiple design criteria becomes a complex multi-objective problem. Although multi-objective optimization is a powerful technique that explores a vast solution space without empirical weights between design objectives, to date, no web service for multi-objective design of RNA switches that utilizes RNA–RNA interaction has been proposed. We developed a web server, which is based on a multi-objective design algorithm called MODENA, to design two interacting RNAs that form a complex in silico. By predicting the secondary structures with RactIP during the design process, we can design RNAs that form a joint secondary structure with an external pseudoknot. The energy barrier upon the complex formation is modeled by an interaction seed that is optimized in the design algorithm. We benchmarked the RNA switch design approaches (MODENA+RactIP and MODENA+RNAcofold) for the target structures based on natural RNA-RNA interactions. As a result, MODENA+RactIP showed high design performance for the benchmark datasets.

  • RNA secondary structure prediction using deep learning with thermodynamic integration

    Sato K., Akiyama M., Sakakibara Y.

    Nature Communications (Nature Communications)  12 ( 1 )  2021.02

     View Summary

    Accurate predictions of RNA secondary structures can help uncover the roles of functional non-coding RNAs. Although machine learning-based models have achieved high performance in terms of prediction accuracy, overfitting is a common risk for such highly parameterized models. Here we show that overfitting can be minimized when RNA folding scores learnt using a deep neural network are integrated together with Turner’s nearest-neighbor free energy parameters. Training the model with thermodynamic regularization ensures that folding scores and the calculated free energy are as close as possible. In computational experiments designed for newly discovered non-coding RNAs, our algorithm (MXfold2) achieves the most robust and accurate predictions of RNA secondary structures without sacrificing computational efficiency compared to several other algorithms. The results suggest that integrating thermodynamic information could help improve the robustness of deep learning-based predictions of RNA secondary structure.

  • Prediction of RNA secondary structure including pseudoknots for long sequences

    Sato, K., Kato, Y.

    Briefings in Bioinformatics  2021

    Research paper (scientific journal), Joint Work, Accepted

  • An improved de novo genome assembly of the common marmoset genome yields improved contiguity and increased mapping rates of sequence data

    Jayakumar V., Ishii H., Seki M., Kumita W., Inoue T., Hase S., Sato K., Okano H., Sasaki E., Sakakibara Y.

    BMC Genomics (BMC Genomics)  21 2020.04

     View Summary

    Background: The common marmoset (Callithrix jacchus) is one of the most studied primate model organisms. However, the marmoset genomes available in the public databases are highly fragmented and filled with sequence gaps, hindering research advances related to marmoset genomics and transcriptomics. Results: Here we utilize single-molecule, long-read sequence data to improve and update the existing genome assembly and report a near-complete genome of the common marmoset. The assembly is of 2.79 Gb size, with a contig N50 length of 6.37 Mb and a chromosomal scaffold N50 length of 143.91 Mb, representing the most contiguous and high-quality marmoset genome up to date. Approximately 90% of the assembled genome was represented in contigs longer than 1 Mb, with approximately 104-fold improvement in contiguity over the previously published marmoset genome. More than 98% of the gaps from the previously published genomes were filled successfully, which improved the mapping rates of genomic and transcriptomic data on to the assembled genome. Conclusions: Altogether the updated, high-quality common marmoset genome assembly provide improvements at various levels over the previous versions of the marmoset genome assemblies. This will allow researchers working on primate genomics to apply the genome more efficiently for their genomic and transcriptomic sequence data.

  • Efficient generation of Knock-in/Knock-out marmoset embryo via CRISPR/Cas9 gene editing

    Kumita W., Sato K., Suzuki Y., Kurotaki Y., Harada T., Zhou Y., Kishi N., Sato K., Aiba A., Sakakibara Y., Feng G., Okano H., Sasaki E.

    Scientific Reports (Scientific Reports)  9 ( 1 )  2019.12

     View Summary

    Genetically modified nonhuman primates (NHP) are useful models for biomedical research. Gene editing technologies have enabled production of target-gene knock-out (KO) NHP models. Target-gene-KO/knock-in (KI) efficiency of CRISPR/Cas9 has not been extensively investigated in marmosets. In this study, optimum conditions for target gene modification efficacies of CRISPR/mRNA and CRISPR/nuclease in marmoset embryos were examined. CRISPR/nuclease was more effective than CRISPR/mRNA in avoiding mosaic genetic alteration. Furthermore, optimal conditions to generate KI marmoset embryos were investigated using CRISPR/Cas9 and 2 different lengths (36 nt and 100 nt) each of a sense or anti-sense single-strand oligonucleotide (ssODN). KIs were observed when CRISPR/nuclease and 36 nt sense or anti-sense ssODNs were injected into embryos. All embryos exhibited mosaic mutations with KI and KO, or imprecise KI, of c-kit. Although further improvement of KI strategies is required, these results indicated that CRISPR/Cas9 may be utilized to produce KO/KI marmosets via gene editing.

display all >>

Papers, etc., Registered in KOARA 【 Display / hide

Reviews, Commentaries, etc. 【 Display / hide

  • Introduction to Selected Papers from GIW2018

    Li J., Nakai K., Zheng Y., Sato K., Wong L.

    Journal of Bioinformatics and Computational Biology (Journal of Bioinformatics and Computational Biology)  16 ( 6 )  2018.12

    ISSN  02197200

  • 機能性RNAの配列解析と構造解析


    人工知能学会誌 22 ( 1 ) 54 - 62 2007.01

    Introduction and explanation (scientific journal), Joint Work

Presentations 【 Display / hide

  • 深層学習に基づく RNA グアニン4重鎖構造識別法の検討

    加藤有己, 佐藤健吾, Jakob Hull Havgaard, 河原行郎

    第20回日本RNA学会年会, 2018.07, Poster (general)

  • RNA secondary structure prediction using deep learning

    Akiyama, M., Sakakibara, Y., Sato, K.

    第6回生命医薬情報学連合大会,日本バイオインフォマティクス学会2017年年会, 2017.09, Poster (general)

  • がん細胞株における derived RNA のプロファイル解析


    第19回日本RNA学会年会, 2017.07, Oral Presentation(general)

  • 深層学習によるRNA二次構造予測


    第19回日本RNA学会年会, 2017.07, Poster (general)

  • 医師国家試験自動解答プログラムの治療薬問題への拡張


    第31回人工知能学会全国大会, 2017.05, Oral Presentation(general)

display all >>

Research Projects of Competitive Funds, etc. 【 Display / hide

  • GenomeGAN: 敵対的生成ネットワークによるインシリコゲノム合成


    MEXT,JSPS, Grant-in-Aid for Scientific Research, 佐藤 健吾, Grant-in-Aid for Challenging Research (Exploratory) , Principal Investigator

  • RNA secondary structure prediction using nanopore sequencers


    MEXT,JSPS, Grant-in-Aid for Scientific Research, 佐藤 健吾, Grant-in-Aid for Scientific Research (B), Principal Investigator

  • 次世代シークエンシングデータを利用した機械学習によるRNA二次構造予測の高精度化


    MEXT,JSPS, Grant-in-Aid for Scientific Research, 佐藤 健吾, Grant-in-Aid for Scientific Research (C), Principal Investigator

Awards 【 Display / hide

  • ポスター賞

    Akiyama, M., Sakakibara, Y., Sato, K., 2017.09, 日本バイオインフォマティクス学会, RNA secondary structure prediction using deep learning

    Type of Award: Awards of National Conference, Council and Symposium

  • 研究奨励賞

    Akiyama, M., Sakakibara, Y., Sato, K., 2016.10, 日本バイオインフォマティクス学会, Improving RNA secondary structure prediction with weak label learning from NGS data

    Type of Award: Awards of National Conference, Council and Symposium

  • IPSJ Yamashita SIG Research Award

    Sato Kengo, 2013.03, 情報処理学会, RNA structural alignments via dual decomposition

    Type of Award: Awards of National Conference, Council and Symposium

  • Oxford University Press JSBi Prize

    Sato Kengo, 2008.12, 日本バイオインフォマティクス学会, A non-parametric Bayesian approach for predicting RNA secondary structures

    Type of Award: Awards of National Conference, Council and Symposium


Courses Taught 【 Display / hide











display all >>


Memberships in Academic Societies 【 Display / hide

  • Japan Society of Marmoset Research, 

  • The RNA Society of Japan, 

  • The Molecular Biology Society of Japan, 


  • International Society for Computational Biology, 


display all >>

Committee Experiences 【 Display / hide

  • 2021.04

    Co-Editor in Chief, IPSJ Transactions on Bioinformatics

  • 2018.04

    Steering Committee Member, IPSJ SIGBIO

  • 2018.04

    Program Committee Co-Chair, International Conference on Genome Informatics (GIW) 2018

  • 2017.04

    Editor, IPSJ Transactions on Bioinformatics

  • 2016.10

    Local Organizing Committee Co-Chair, Asia Pacific Bioinformatics Conference (APBC) 2018

display all >>