Sakakibara, Yasubumi



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



E-mail Address

E-mail address

Related Websites

External Links

Career 【 Display / hide

  • 1985.04

    (株)富士通研究所情報社会科学研究所 ,研究員

  • 1992.06

    兼 米国カリフォルニア大学サンタクルーズ校 ,客員研究員

  • 1996.04

    東京電機大学理工学部情報科学科 ,助教授

  • 2001.10

    東京電機大学理工学部情報科学科 ,教授

  • 2002.04

    慶應義塾大学理工学部生命情報学科 ,助教授

display all >>

Academic Background 【 Display / hide

  • 1983.03

    Tokyo Institute of Technology, Faculty of Science, 情報科学科

    University, Graduated

  • 1985.03

    Tokyo Institute of Technology, Graduate School, Division of Science and Engineeri, 情報科学専攻

    Graduate School, Completed, Master's course

Academic Degrees 【 Display / hide

  • 理学, Tokyo Institute of Technology, 1991.10


Research Areas 【 Display / hide

  • Life / Health / Medical informatics

  • Life / Health / Medical informatics (Bioinformatics)

  • System genome science

Research Keywords 【 Display / hide

  • cancer genome

  • Bioinformatics

Research Themes 【 Display / hide

  • Big daya analysis, 


  • Cancer genmome analysis, 


  • functional RNA sequence analysis, 



Books 【 Display / hide

  • 情報数理シリーズ「計算論的学習」

    榊原康文,小林聡,横森貴, 培風館, 2001.10

     View Summary


  • DNAコンピューティング

    Paun, Rozenberg, Salomaa 著,横森貴, 榊原康文, 小林聡 訳, シュプリンガー・フェアラーク東京, 1999.12

     View Summary


  • 新版 情報処理ハンドブック

    情報処理学会偏,13編6章の「学習」に関する節を分担執筆, オーム社, 1995.11

     View Summary


Papers 【 Display / hide

  • Convolutional neural network based on SMILES representation of compounds for detecting chemical motif

    Hirohara M., Saito Y., Koda Y., Sato K., Sakakibara Y.

    BMC Bioinformatics (BMC Bioinformatics)  19 2018.12

     View Summary

    © 2018 The Author(s). Background: Previous studies have suggested deep learning to be a highly effective approach for screening lead compounds for new drugs. Several deep learning models have been developed by addressing the use of various kinds of fingerprints and graph convolution architectures. However, these methods are either advantageous or disadvantageous depending on whether they (1) can distinguish structural differences including chirality of compounds, and (2) can automatically discover effective features. Results: We developed another deep learning model for compound classification. In this method, we constructed a distributed representation of compounds based on the SMILES notation, which linearly represents a compound structure, and applied the SMILES-based representation to a convolutional neural network (CNN). The use of SMILES allows us to process all types of compounds while incorporating a broad range of structure information, and representation learning by CNN automatically acquires a low-dimensional representation of input features. In a benchmark experiment using the TOX 21 dataset, our method outperformed conventional fingerprint methods, and performed comparably against the winning model of the TOX 21 Challenge. Multivariate analysis confirmed that the chemical space consisting of the features learned by SMILES-based representation learning adequately expressed a richer feature space that enabled the accurate discrimination of compounds. Using motif detection with the learned filters, not only important known structures (motifs) such as protein-binding sites but also structures of unknown functional groups were detected. Conclusions: The source code of our SMILES-based convolutional neural network software in the deep learning framework Chainer is available at , and the dataset used for performance evaluation in this work is available at the same URL.

  • A max-margin training of RNA secondary structure prediction integrated with the thermodynamic model

    Akiyama M., Sato K., Sakakibara Y.

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

    ISSN  02197200

     View Summary

    © 2018 World Scientific Publishing Europe Ltd. A popular approach for predicting RNA secondary structure is the thermodynamic nearest-neighbor model that finds a thermodynamically most stable secondary structure with minimum free energy (MFE). For further improvement, an alternative approach that is based on machine learning techniques has been developed. The machine learning-based approach can employ a fine-grained model that includes much richer feature representations with the ability to fit the training data. Although a machine learning-based fine-grained model achieved extremely high performance in prediction accuracy, a possibility of the risk of overfitting for such a model has been reported. In this paper, we propose a novel algorithm for RNA secondary structure prediction that integrates the thermodynamic approach and the machine learning-based weighted approach. Our fine-grained model combines the experimentally determined thermodynamic parameters with a large number of scoring parameters for detailed contexts of features that are trained by the structured support vector machine (SSVM) with the ℓ1 regularization to avoid overfitting. Our benchmark shows that our algorithm achieves the best prediction accuracy compared with existing methods, and heavy overfitting cannot be observed. The implementation of our algorithm is available at

  • Time-Series Analysis of Tumorigenesis in a Murine Skin Carcinogenesis Model

    Aoto Y., Okumura K., Hachiya T., Hase S., Wakabayashi Y., Ishikawa F., Sakakibara Y.

    Scientific Reports (Scientific Reports)  8 ( 1 )  2018.12

     View Summary

    © 2018, The Author(s). Recent years have witnessed substantial progress in understanding tumor heterogeneity and the process of tumor progression; however, the entire process of the transition of tumors from a benign to metastatic state remains poorly understood. In the present study, we performed a prospective cancer genome-sequencing analysis by employing an experimental carcinogenesis mouse model of squamous cell carcinoma to systematically understand the evolutionary process of tumors. We surgically collected a part of a lesion of each tumor and followed the progression of these tumors in vivo over time. Comparative time-series analysis of the genomes of tumors with different fates, i.e., those that eventually metastasized and regressed, suggested that these tumors acquired and inherited different mutations. These findings suggest that despite the occurrence of an intra-tumor selection event for malignant alteration during the transformation from early- to late-stage papilloma, the fate determination of tumors might be determined at an even earlier stage.

  • Convolutional neural networks for classification of alignments of non-coding RNA sequences

    Aoki G., Sakakibara Y.

    Bioinformatics (Bioinformatics)  34 ( 13 ) i237 - i244 2018.07

    ISSN  13674803

     View Summary

    © The Author(s) 2018. Published by Oxford University Press. All rights reserved. Motivation: The convolutional neural network (CNN) has been applied to the classification problem of DNA sequences, with the additional purpose of motif discovery. The training of CNNs with distributed representations of four nucleotides has successfully derived position weight matrices on the learned kernels that corresponded to sequence motifs such as protein-binding sites. Results: We propose a novel application of CNNs to classification of pairwise alignments of sequences for accurate clustering of sequences and show the benefits of the CNN method of inputting pairwise alignments for clustering of non-coding RNA (ncRNA) sequences and for motif discovery. Classification of a pairwise alignment of two sequences into positive and negative classes corresponds to the clustering of the input sequences. After we combined the distributed representation of RNA nucleotides with the secondary-structure information specific to ncRNAs and furthermore with mapping profiles of next-generation sequence reads, the training of CNNs for classification of alignments of RNA sequences yielded accurate clustering in terms of ncRNA families and outperformed the existing clustering methods for ncRNA sequences. Several interesting sequence motifs and secondary-structure motifs known for the snoRNA family and specific to microRNA and tRNA families were identified.

  • DEclust: A statistical approach for obtaining differential expression profiles of multiple conditions

    Y. Aoto, T. Hachiya, K. Okumura, S. Hase, K. Sato, Y. Wakabayashi, SAKAKIBARA YASUBUMI

    PLoS One 12-11   e0188285 2017

    Research paper (scientific journal), Joint Work, Accepted

display all >>

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

display all >>

Reviews, Commentaries, etc. 【 Display / hide

Presentations 【 Display / hide

  • MetaVelvet : An extension of Velvet assembler to de novo metagenome assembly from short sequence reads

    Namiki, T., Hachiya, T., Tanaka, H., and SAKAKIBARA YASUBUMI

    ACM Conference on Bioinformatics, Computational Biology and Biomedicine 2011 (Chicago, USA) , 2011.08, Oral Presentation(general)

  • Comprehensive analysis of small non-coding RNAs in medaka transcriptome by deep RNA-seq approach

    Abe, M., Hase, S., Ogawa, M., Okada, Y., Sato, K., Saito, Y., and SAKAKIBARA YASUBUMI

    RNA 2011 Sixteenth Annual Meeting of the RNA Society (Kyoto, Japan) , 2011.06, Oral Presentation(general)

  • Genome-wide detections of non-coding RNAs on Ciona intestinalis genome: from in silico search of snoRNA to full-length sequencing and expression analysis

    Kawarama, J., Hase, S., Hachiya, T., Hotta, K., Sakakibara, Y.

    5th International Tunicate Meeting (Okinawa, Japan) , 2009.06, Oral Presentation(general)

  • Discriminative Detection of Cis-acting Regulatory Variation from Location Data

    Yuji Kawada, Yasubumi Sakakibara

    The 4th Asia-Pacific Bioinformatics Conference (APBC2006), Taiwan (Taiwan) , 2006.02, Oral Presentation(general)

  • Intensive in vitro experiments of implementing and executing finite automata in test tube

    Junna Kuramochi and Yasubumi Sakakibara

    The 11th International Meeting on DNA Based Computers (DNA11), London, Ontario (London, Ontario) , 2005.06, Oral Presentation(general)

display all >>

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

  • 非コードRNA遺伝子をゲノムワイドに発見する汎用システム


    MEXT,JSPS, Grant-in-Aid for Scientific Research, 榊原 康文, Grant-in-Aid for Scientific Research (A) , Principal Investigator

  • Deep analysis of chemical communication space using artificial intelligence technology


    MEXT,JSPS, Grant-in-Aid for Scientific Research, 榊原 康文, Grant-in-Aid for Scientific Research on Innovative Areas, Principal Investigator

  • ビッグデータ駆動型創薬システム研究拠点


    戦略的研究基盤形成支援事業, 榊原康文, Principal Investigator

  • 発がんゲノムにおける非コードRNAの網羅的機能解析


    Grant-in-Aid for Scientific Research, 榊原康文, Principal Investigator

  • ゲノム科学の総合的推進に向けた大規模ゲノム情報生産・高度情報解析支援


    Grant-in-Aid for Scientific Research, 小原雄治, Co-investigator

display all >>

Intellectual Property Rights, etc. 【 Display / hide

  • 核酸分子を用いた新規な情報解析方法およびそれを用いた核酸の解析方法

    Application No.: 特願2000-382449  2000.12 


  • Data Sorting,Data Sorting Tree Creating,Derivative

    Registration No.: United State Patent,No.5787426  1998.07

    Patent, PCT international application

Awards 【 Display / hide

  • 東京電機大学研究振興会 教育奨励賞

    榊原 康文, 1999, 東京電機大学研究振興会, 「プログラム言語のマルチメディア教育」


Courses Taught 【 Display / hide











display all >>

Courses Previously Taught 【 Display / hide

  • Bioinformatics

    Keio University, 2015, Spring Semester, Major subject, Lecture, Lecturer outside of Keio, 50people

  • 基礎生命実験

    Keio University, 2015, Autumn Semester, Major subject, Laboratory work/practical work/exercise, Outside own faculty (within Keio), 50people

  • システムバイオロジー特論

    Keio University, 2015, Autumn Semester, Major subject, Lecture, Outside own faculty (within Keio), 50people

  • BioProgramming 2

    Keio University, 2015, Autumn Semester, Major subject, Lecture, Lecturer outside of Keio, 50people

  • Algorithm and Information processing

    Keio University, 2015, Autumn Semester, Major subject, Lecture, Within own faculty, 50people

display all >>


Social Activities 【 Display / hide

  • 第8回 新しい RNA/RNP を見つける会

  • 6th International Workshop on Algorithmic Learning

  • (財)新世代コンピュータ技術開発機構 蛋白質立体構造予測タスクグループ

  • 2nd,3rd,4th,5th,6th International Colloquium on Gr

  • 5th,7th,8th,9th,11th International Workshop on Alg


display all >>

Memberships in Academic Societies 【 Display / hide

  • 16th International Conference on DNA Computing and Molecular Programming, 

  • 20th International Conference on Genome Informatics(GIW2009), 

  • 人工知能学会 人工知能基礎論研究会, 

  • 情報処理学会 論文誌編集委員会, 

  • 第44回情報処理学会全国大会 チュートリアルセッション 機械学習入門, 


display all >>

Committee Experiences 【 Display / hide

  • 2010.07

    Program Committee Co-Chairman, 16th International Conference on DNA Computing and Molecular Programming

  • 2009.12

    organizing chairman, 20th International Conference on Genome Informatics(GIW2009)

  • 2009.09

    Committee Chair, 第8回 新しい RNA/RNP を見つける会

  • 1998.04

    幹事, 人工知能学会 人工知能基礎論研究会

  • 1998.04

    委員, 情報処理学会 論文誌編集委員会

display all >>