Updated on 2024/04/28

写真a

 
YAMANISHI Yoshihiro
 
Organization
Graduate School of Informatics Department of Complex Systems Science 2 Professor
Graduate School
Graduate School of Informatics
Undergraduate School
School of Informatics Department of Natural Informatics
Title
Professor
Profile
My research interest is in statistical machine learning methods for bioinformatics, chemoinformatics, and genomic drug discovery.
External link

Degree 1

  1. Doctor of Science ( 2005.3   Kyoto University ) 

Research Interests 12

  1. インシリコ創薬

  2. 遺伝子ネットワーク

  3. 統計学

  4. 機械学習

  5. 標的分子

  6. 化学反応

  7. 代謝パスウェイ

  8. バイオインフォマティクス

  9. ドラッグリポジショニング

  10. システム生物学

  11. ケモインフォマティクス

  12. カーネル法

Research Areas 3

  1. Life Science / Pharmaceutical chemistry and drug development sciences

  2. Informatics / Statistical science

  3. Informatics / Life, health and medical informatics

Research History 9

  1. Nagoya University   Department of Complex Systems Science, Graduate School of Informatics   Professor

    2023.4

      More details

    Country:Japan

  2. Kyushu Institute of Technology   Faculty of Computer Science and Systems Engineering Department of Bioscience and Bioinformatics   Professor

    2018.6 - 2023.3

  3. 科学技術振興機構   さきがけ研究者(兼任)

    2015.10 - 2019.3

  4. Kyushu University   Medical Institute of Bioregulation   Associate professor

    2012.3 - 2018.5

  5. キュリー研究所   バイオインフォマティクスユニット   常勤研究員(Principal Investigator)

    2008.1 - 2012.2

  6. パリ国立高等鉱業学校   バイオインフォマティクスセンター   常勤研究員(Principal Investigator)

    2008.1 - 2012.2

  7. Kyoto University   Institute for Chemical Research

    2006.4 - 2007.12

  8. パリ国立高等鉱業学校   バイオインフォマティクスセンター   ポスドク

    2005.4 - 2006.3

  9. Japan Society for Promotion of Science

    2004.4 - 2005.3

▼display all

Professional Memberships 7

  1. THE JAPANESE SOCIETY OF TOXICOLOGY

    2021.7

  2. JAPANESE SOCIETY OF COMPUTATIONAL STATISTICS

  3. Division of Chemoinformatics, The Chemical Society of Japan

  4. 日本メディカルAI学会

  5. JAPANESE SOCIETY FOR BIOINFORMATICS

  6. The Chem-Bio Informatics Society

  7. International Society for Computational Biology (ISCB)

▼display all

Committee Memberships 13

  1. Artificial Intelligence in the Life Sciences   Editorial Board  

    2024.2   

      More details

    Committee type:Academic society

  2. International Society for Computational Biology (ISCB)   Board of Directors  

    2024.1 - 2026.12   

      More details

    Committee type:Academic society

  3. Bioinformatics Advances   Academic Editor  

    2023.8 - 2026.7   

      More details

    Committee type:Academic society

  4. 日本バイオインフォマティクス学会   会長  

    2023.4   

      More details

    Committee type:Academic society

  5. 日本バイオインフォマティクス学会   副会長  

    2021.4 - 2023.3   

      More details

    Committee type:Academic society

  6.   日本化学会ケモインフォマティクス部会 幹事  

    2018.4 - 2023.3   

      More details

    Committee type:Academic society

  7.   日本バイオインフォマティクス学会 幹事  

    2018   

      More details

    Committee type:Academic society

  8.   日本メディカルAI学会 評議員  

    2018   

      More details

    Committee type:Academic society

  9.   Molecular Informatics 編集委員  

    2017   

      More details

    Committee type:Academic society

  10.   Genes & Genetic Systems 編集委員  

    2016   

      More details

    Committee type:Academic society

  11.   日本バイオインフォマティクス学会 理事  

    2016 - 2018   

      More details

    Committee type:Academic society

  12.   BioMed International 編集委員  

    2014.12 - 2018.8   

      More details

    Committee type:Academic society

  13.   PLoS ONE 編集委員  

    2013   

      More details

    Committee type:Academic society

▼display all

Awards 11

  1. 日本薬学会第144年会 学生優秀発表賞(口頭発表)

    2024.4   日本薬学会第144年会   細胞形態画像から医薬品候補化合物の標的分子を予測する機械学習手法の開発

    石原慎也, 岩田通夫, 林広夢, 濱野桃子, 霜古田一優, 木谷晃広, 吹田直政, 山西芳裕

     More details

    Award type:Award from Japanese society, conference, symposium, etc.  Country:Japan

  2. 日本薬学会第144年会 学生優秀発表賞(ポスター発表)

    2024.4   日本薬学会 第144年会   機械学習による薬剤標的分子予測と薬剤組み合わせ効果の検討

    亀淵由乃, 難波里子, 関谷拓海, 大谷則子, 岩田通夫, 山西芳裕

     More details

    Award type:Award from Japanese society, conference, symposium, etc.  Country:Japan

  3. AAAI2024 outstanding paper award

    2024.2   The 38th Annual AAAI Conference on Artificial Intelligence (AAAI2024)   GxVAEs: Two Joint VAEs Generate Hit Molecules from Gene Expression Profiles

    Li, C. and Yamanishi, Y.

     More details

    Award type:Award from international society, conference, symposium, etc. 

  4. 第46回ケモインフォマティクス討論会「優秀講演賞」

    2023.11   第46回ケモインフォマティクス討論会   深層学習モデルによる所望の特性を持つ合成可能な化学構造の生成

    髙田慎之助, 海東和麻, 津田宏治, 山西芳裕

  5. 情報計算化学生物学会2023年大会「口頭発表賞」

    2023.10   情報計算化学生物学会2023年大会   De novo inhibitor and activator design from gene expression profiles via deep learning and Bayesian optimization

    松清優樹、山中知茂, 山西芳裕

  6. 情報計算化学生物学会2023年大会「口頭発表賞」

    2023.10   情報計算化学生物学会2023年大会   Transformer Encoder-based Generative Adversarial Network for Design of Polypharmacological Drugs

    安田花純、李晨、海東和麻, 山西芳裕

  7. 第12回生命医薬情報学連合大会「優秀ポスター賞」

    2023.9   第12回生命医薬情報学連合大会   GWASとTWASの融合による希少疾患に対する治療標的分子の予測

    難波里子、岩田通夫、山西芳裕

  8. 第12回生命医薬情報学連合大会「最優秀ポスター賞」

    2023.9   第12回生命医薬情報学連合大会   シングルセルレベルの細胞変換過程を考慮したダイレクトリプログラミング誘導化合物の予測

    伊藤緑風,濱野桃子, 山西芳裕

  9. 「田邊賞」

    2021.7   日本毒性学会  

    山西芳裕

     More details

    Award type:Award from Japanese society, conference, symposium, etc. 

  10. 文部科学大臣表彰「若手科学者賞」

    2014.4   文部科学省  

    山西芳裕

  11. 京都大学化学研究所「所長賞」奨励賞

    2003.12   京都大学化学研究所  

    山西芳裕

▼display all

 

Papers 133

  1. DIRECTEUR: Transcriptome-based prediction of small molecules that replace transcription factors for direct cell conversion Reviewed

    Momoko Hamano, Toru Nakamura, Ryoku Ito, Yuki Shimada, Michio Iwata, Jun-ichi Takeshita, Ryohei Eguchi, Yoshihiro Yamanishi

    Bioinformatics   Vol. 40 ( 2 ) page: btae048 - btae048   2024.2

     More details

    Authorship:Last author, Corresponding author   Language:English   Publishing type:Research paper (scientific journal)   Publisher:Oxford University Press (OUP)  

    Abstract

    Motivation

    Direct reprogramming (DR) is a process that directly converts somatic cells to target cells. Although DR via small molecules is safer than using transcription factors (TFs) in terms of avoidance of tumorigenic risk, the determination of DR-inducing small molecules is challenging.

    Results

    Here we present a novel in silico method, DIRECTEUR, to predict small molecules that replace TFs for DR. We extracted DR-characteristic genes using transcriptome profiles of cells in which DR was induced by TFs, and performed a variant of simulated annealing to explore small molecule combinations with similar gene expression patterns with DR-inducing TFs. We applied DIRECTEUR to predicting combinations of small molecules that convert fibroblasts into neurons or cardiomyocytes, and were able to reproduce experimentally verified and functionally related molecules inducing the corresponding conversions. The proposed method is expected to be useful for practical applications in regenerative medicine.

    Availability

    The source code and data are available at the following link: https://www.dropbox.com/scl/fo/hhkpc7xspl9ngwo5zv62z/h?rlkey=8ib5jav8sf87uj1j0rkcj1cd6&dl=0

    Supplementary information

    Supplementary data are available at Bioinformatics online.

    DOI: 10.1093/bioinformatics/btae048

    DOI: 10.1093/bioinformatics/btae048

    Web of Science

    Scopus

    PubMed

  2. Network-based identification of diagnosis-specific trans-omic biomarkers via integration of multiple omics data Reviewed International coauthorship

    Md Mamunur Rashid, Momoko Hamano, Midori Iida, Michio Iwata, Toshiyuki Ko, Seitaro Nomura, Issei Komuro, Yoshihiro Yamanishi

    Biosystems   Vol. 236   page: 105122 - 105122   2024.1

     More details

    Authorship:Last author, Corresponding author   Language:English   Publishing type:Research paper (scientific journal)   Publisher:Elsevier BV  

    DOI: 10.1016/j.biosystems.2024.105122

    DOI: 10.1016/j.biosystems.2024.105122

    Scopus

    PubMed

  3. Automatic generation of functional peptides with desired bioactivity and membrane permeability using Bayesian optimization. Reviewed

    Fukunaga I, Matsukiyo Y, Kaitoh K, Yamanishi Y

    Molecular informatics   Vol. 43   page: e202300148 - e202300148   2024.1

     More details

    Authorship:Last author, Corresponding author   Language:English   Publishing type:Research paper (scientific journal)  

    DOI: 10.1002/minf.202300148

    DOI: 10.1002/minf.202300148

    PubMed

  4. EarlGAN: An enhanced actor-critic reinforcement learning agent-driven GAN for de novo drug design Reviewed

    Tang, HD; Li, C; Jiang, S; Yu, HC; Kamei, S; Yamanishi, Y; Morimoto, Y

    PATTERN RECOGNITION LETTERS   Vol. 175 ( 4 ) page: 45 - 51   2023.11

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:Pattern Recognition Letters  

    Deep generative models, such as Generative Adversarial Networks (GANs), have attracted the attention of researchers in the denovo drug design field. However, traditional GANs are typically used for image processing. Therefore, they are unsuitable for Simplified Molecular-Input Line-Entry System (SMILES) strings due to their discrete nature. Previous studies addressed this problem by combining Reinforcement Learning (RL) approaches with Monte Carlo tree search. However, for large chemical datasets, the molecule generation process is time-consuming due to the lengthy atom-by-atom sampling process with cumulative reward, an essence of the Monte Carlo tree search-based RL approaches. To address this problem, we propose an enhanced actor–critic RL agent-driven GAN, called EarlGAN, for denovo drug design. Specifically, EarlGAN's generator acts as an actor to generate SMILES strings, and the discriminator acts as a critic to perform discrimination. EarlGAN makes autoregressive predictions at the atomic level. While the generator is based on previously generated atoms, the discriminator discriminates using a bidirectional pass over the atoms, including the current atom that is being predicted. We integrate moment, global-level discrimination rewards, and information entropy maximization. The moment rewards reduce the computation time, and the global-level rewards ensure the consistency of the molecule, whereas the information entropy maximization leads to a more diverse sample generation. Experiments and ablation studies verify the effectiveness of EarlGAN for denovo drug design on the QM9 and ZINC datasets. In addition, the visualization analysis provides insight into EarlGAN and supports our conclusion.

    DOI: 10.1016/j.patrec.2023.10.001

    Web of Science

    Scopus

  5. Myocardial DNA Damage Predicts Heart Failure Outcome in Various Underlying Diseases Reviewed

    Zhehao Dai, Toshiyuki Ko, Kanna Fujita, Seitaro Nomura, Yukari Uemura, Kenji Onoue, Momoko Hamano, Manami Katoh, Shintaro Yamada, Mikako Katagiri, Bo Zhang, Satoshi Hatsuse, Takanobu Yamada, Shunsuke Inoue, Masayuki Kubota, Kosuke Sawami, Tuolisi Heryed, Masamichi Ito, Eisuke Amiya, Masaru Hatano, Norifumi Takeda, Hiroyuki Morita, Yoshihiro Yamanishi, Yoshihiko Saito, Issei Komuro

    JACC: Heart Failure   Vol. S2213-1779 ( 23 ) page: 00680 - 00687   2023.10

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:Elsevier BV  

    DOI: 10.1016/j.jchf.2023.09.027

    DOI: 10.1016/j.jchf.2023.09.027

    Scopus

    PubMed

  6. A community effort in SARS-CoV-2 drug discovery Reviewed International coauthorship

    Schimunek J, Seidl P, Elez K, Hempel T, Le T, Noé F, Olsson S, Raich L, Winter R, Gokcan H, Gusev F, Gutkin EM, Isayev O, Kurnikova MG, Narangoda CH, Zubatyuk R, Bosko IP, Furs KV, Karpenko AD, Kornoushenko YV, Shuldau M, Yushkevich A, Benabderrahmane MB, Bousquet-Melou P, Bureau R, Charton B, Cirou BC, Gil G, Allen WJ, Sirimulla S, Watowich S, Antonopoulos NA, Epitropakis NE, Krasoulis AK, Pitsikalis VP, Theodorakis ST, Kozlovskii I, Maliutin A, Medvedev A, Popov P, Zaretckii M, Eghbal-Zadeh H, Halmich C, Hochreiter S, Mayr A, Ruch P, Widrich M, Berenger F, Kumar A, Yamanishi, Y., Zhang KYJ, Bengio E, Bengio Y, Jain MJ, Korablyov M, Liu CH, Marcou G, Glaab E, Barnsley K, Iyengar SM, Ondrechen MJ, Haupt VJ, Kaiser F, Schroeder M, Pugliese L, Albani S, Athanasiou C, Beccari A, Carloni P, D'Arrigo G, Gianquinto E, Goßen J, Hanke A, Joseph BP, Kokh DB, Kovachka S, Manelfi C, Mukherjee G, Muñiz-Chicharro A, Musiani F, Nunes-Alves A, Paiardi G, Rossetti G, Sadiq SK, Spyrakis F, Talarico C, Tsengenes A, Wade RC, Copeland C, Gaiser J, Olson DR, Roy A, Venkatraman V, Wheeler TJ, Arthanari H, Blaschitz K, Cespugli M, Durmaz V, Fackeldey K, Fischer PD, Gorgulla C, Gruber C, Gruber K, Hetmann M., Kinney, JE, Padmanabha Das, KM, Pandita, S, Singh, A, Steinkellner, G, Tesseyre, G, Wagner, G, Wang Z, Yust RJ, Druzhilovskiy, DS, Filimonov, DA, Pogodin, PV, Poroikov, V, Rudik, AV, Stolbov, LA, Veselovsky, AV, De Rosa, M, De Simone, G, Gulotta, MR, Lombino, J, Mekni, N, Perricone, U, Casini, A, Embree, A, Gordon DB, Lei, D, Pratt, K, Voigt, CA, Chen, K-Y, Jacob, Y, Krischuns, T, Lafaye, P, Zettor, A, Rodríguez, ML, White, KM, Fearon, D, Von Delft, F, Walsh, MA, Horvath, D, Brooks, CL III, Falsafi, B, Ford, B, García-Sastre, A, Lee, SY, Naffakh, N, Varnek, A, Klambauer, G, and Hermans, TM

    Molecular Informatics   Vol. 43 ( 1 ) page: e202300262 - e202300262   2023.10

     More details

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

    DOI: 10.1002/minf.202300262

    DOI: 10.1002/minf.202300262

  7. De Novo Generation of Chemical Structures of Inhibitor and Activator Candidates for Therapeutic Target Proteins by a Transformer-Based Variational Autoencoder and Bayesian Optimization. Reviewed

    Matsukiyo Y, Yamanaka C, Yamanishi Y

    Journal of chemical information and modeling     2023.9

     More details

    Authorship:Last author, Corresponding author   Language:English   Publishing type:Research paper (scientific journal)  

    DOI: 10.1021/acs.jcim.3c00824

    PubMed

  8. Elucidating disease-associated mechanisms triggered by pollutants via the epigenetic landscape using large-scale ChIP-Seq data. Reviewed

    Zou Z, Yoshimura Y, Yamanishi Y, Oki S

    Epigenetics & chromatin   Vol. 16 ( 1 ) page: 34 - 34   2023.9

     More details

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

    DOI: 10.1186/s13072-023-00510-w

    DOI: 10.1186/s13072-023-00510-w

    PubMed

  9. SpotGAN: A Reverse-Transformer GAN Generates Scaffold-Constrained Molecules with Property Optimization. Reviewed

    Chen Li, Yoshihiro Yamanishi

    Proceedings of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD 2023)     page: 323 - 338   2023.9

     More details

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

    DOI: 10.1007/978-3-031-43412-9_19

    Other Link: https://dblp.uni-trier.de/db/conf/pkdd/pkdd2023-1.html#LiY23

  10. Design and structural optimization of thiadiazole derivatives with potent GLS1 inhibitory activity. Reviewed International journal

    Takuya Okada, Kaho Yamabe, Michiko Jo, Yuko Sakajiri, Tomokazu Shibata, Ryusuke Sawada, Yoshihiro Yamanishi, Daisuke Kanayama, Hisashi Mori, Mineyuki Mizuguchi, Takayuki Obita, Yuko Nabeshima, Keiichi Koizumi, Naoki Toyooka

    Bioorganic & medicinal chemistry letters   Vol. 93   page: 129438 - 129438   2023.9

     More details

    Authorship:Corresponding author   Language:English   Publishing type:Research paper (scientific journal)  

    GLS1 is an attractive target not only as anticancer agents but also as candidates for various potential pharmaceutical applications such as anti-aging and anti-obesity treatments. We performed docking simulations based on the complex crystal structure of GLS1 and its inhibitor CB-839 and found that compound A bearing a thiadiazole skeleton exhibits GLS1 inhibition. Furthermore, we synthesized 27 thiadiazole derivatives in an effort to obtain a more potent GLS1 inhibitor. Among the synthesized derivatives, 4d showed more potent GLS1 inhibitory activity (IC50 of 46.7 µM) than known GLS1 inhibitor DON and A. Therefore, 4d is a very promising novel GLS1 inhibitor.

    DOI: 10.1016/j.bmcl.2023.129438

    DOI: 10.1016/j.bmcl.2023.129438

    Web of Science

    Scopus

    PubMed

  11. De novo drug design based on patient gene expression profiles via deep learning. Reviewed International journal

    Chikashige Yamanaka, Shunya Uki, Kazuma Kaitoh, Michio Iwata, Yoshihiro Yamanishi

    Molecular informatics   Vol. 42 ( 8-9 ) page: e2300064   2023.8

     More details

    Authorship:Last author, Corresponding author   Language:English   Publishing type:Research paper (scientific journal)  

    Computational de novo drug design is a challenging issue in medicine, and it is desirable to consider all of the relevant information of the biological systems in a disease state. Here, we propose a novel computational method to generate drug candidate molecular structures from patient gene expression profiles via deep learning, which we call DRAGONET. Our model can generate new molecules that are likely to counteract disease-specific gene expression patterns in patients, which is made possible by exploring the latent space constructed by a transformer-based variational autoencoder and integrating the substructures of disease-correlated molecules. We applied DRAGONET to generate drug candidate molecules for gastric cancer, atopic dermatitis, and Alzheimer's disease, and demonstrated that the newly generated molecules were chemically similar to registered drugs for each disease. This approach is applicable to diseases with unknown therapeutic target proteins and will make a significant contribution to the field of precision medicine.

    DOI: 10.1002/minf.202300064

    DOI: 10.1002/minf.202300064

    Web of Science

    Scopus

    PubMed

  12. Association between immune checkpoint inhibitor-induced myocarditis and concomitant use of thiazide diuretics. Reviewed International coauthorship International journal

    Satoru Mitsuboshi, Hirofumi Hamano, Takahiro Niimura, Aya F Ozaki, Pranav M Patel, Tsung-Jen Lin, Yuta Tanaka, Ikuya Kimura, Naohiro Iwata, Shoya Shiromizu, Masayuki Chuma, Toshihiro Koyama, Yoshihiro Yamanishi, Yasunari Kanda, Keisuke Ishizawa, Yoshito Zamami

    International journal of cancer   Vol. 153 ( 8 ) page: 1472 - 1476   2023.6

     More details

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

    Although an association has been reported between diuretics and myocarditis, it is unclear whether the risk of immune checkpoint inhibitor (ICI)-induced myocarditis is affected by concomitant diuretics. Thus, the aim of this work was to evaluate the impact of concomitant diuretics on ICI-induced myocarditis. This cross-sectional study used disproportionality analysis and a pharmacovigilance database to assess the risk of myocarditis with various diuretics in patients receiving ICIs via the analysis of data entered into the VigiBase database through December 2022. Multiple logistic regression analysis was performed to identify risk factors for myocarditis in patients who received ICIs. A total of 90 611 patients who received ICIs, including 975 cases of myocarditis, were included as the eligible dataset. A disproportionality in myocarditis was observed for loop diuretic use (reporting odds ratio 1.47, 95% confidence interval [CI] 1.02-2.04, P = .03) and thiazide use (reporting odds ratio 1.76, 95% CI 1.20-2.50, P < .01) in patients who received ICIs. The results of the multiple logistic regression analysis showed that the use of thiazides (odds ratio 1.67, 95% CI 1.15-2.34, P < .01) was associated with an increased risk of myocarditis in patients who received ICIs. Our findings may help to predict the risk of myocarditis in patients receiving ICIs.

    DOI: 10.1002/ijc.34616

    DOI: 10.1002/ijc.34616

    Web of Science

    Scopus

    PubMed

  13. TEAD1 trapping by the Q353R-Lamin A/C causes dilated cardiomyopathy. Reviewed International journal

    Shintaro Yamada, Toshiyuki Ko, Masamichi Ito, Tatsuro Sassa, Seitaro Nomura, Hiromichi Okuma, Mayuko Sato, Tsuyoshi Imasaki, Satoshi Kikkawa, Bo Zhang, Takanobu Yamada, Yuka Seki, Kanna Fujita, Manami Katoh, Masayuki Kubota, Satoshi Hatsuse, Mikako Katagiri, Hiromu Hayashi, Momoko Hamano, Norifumi Takeda, Hiroyuki Morita, Shuji Takada, Masashi Toyoda, Masanobu Uchiyama, Masashi Ikeuchi, Kiminori Toyooka, Akihiro Umezawa, Yoshihiro Yamanishi, Ryo Nitta, Hiroyuki Aburatani, Issei Komuro

    Science advances   Vol. 9 ( 15 ) page: eade7047   2023.4

     More details

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

    Mutations in the LMNA gene encoding Lamin A and C (Lamin A/C), major components of the nuclear lamina, cause laminopathies including dilated cardiomyopathy (DCM), but the underlying molecular mechanisms have not been fully elucidated. Here, by leveraging single-cell RNA sequencing (RNA-seq), assay for transposase-accessible chromatin using sequencing (ATAC-seq), protein array, and electron microscopy analysis, we show that insufficient structural maturation of cardiomyocytes owing to trapping of transcription factor TEA domain transcription factor 1 (TEAD1) by mutant Lamin A/C at the nuclear membrane underlies the pathogenesis of Q353R-LMNA-related DCM. Inhibition of the Hippo pathway rescued the dysregulation of cardiac developmental genes by TEAD1 in LMNA mutant cardiomyocytes. Single-cell RNA-seq of cardiac tissues from patients with DCM with the LMNA mutation confirmed the dysregulated expression of TEAD1 target genes. Our results propose an intervention for transcriptional dysregulation as a potential treatment of LMNA-related DCM.

    DOI: 10.1126/sciadv.ade7047

    DOI: 10.1126/sciadv.ade7047

    Web of Science

    Scopus

    PubMed

  14. Discovery of novel biomarkers of small cell lung cancer by proteomics of exosomes

    Suga, Y; Yamamoto, M; Yoshimura, H; Shiroyama, T; Miyake, K; Takeda, Y; Ito, M; Adachi, J; Kamijo, Y; Sawada, R; Yamanishi, Y; Kumanogoh, A

    CANCER SCIENCE   Vol. 114   page: 1979 - 1979   2023.2

     More details

  15. A trial of topiramate for patients with hereditary spinocerebellar ataxia. Reviewed International journal

    Shiroh Miura, Ryusuke Sawada, Akiko Yorita, Hiroshi Kida, Takashi Kamada, Yoshihiro Yamanishi

    Clinical case reports   Vol. 11 ( 2 ) page: e6980   2023.2

     More details

    Authorship:Last author   Language:English   Publishing type:Research paper (scientific journal)  

    In an open pilot trial, six patients with various hereditary forms of spinocerebellar ataxia (SCA) were assigned to topiramate (50 mg/day) for 24 weeks. Four patients completed the protocol without adverse events. Of these four patients, topiramate was effective for three patients. Some patients with SCA could respond to treatment with topiramate.

    DOI: 10.1002/ccr3.6980

    Web of Science

    PubMed

  16. Differential effects of proton pump inhibitors and vonoprazan on vascular endothelial growth factor expression in cancer cells. Reviewed International journal

    Rie Ando-Matsuoka, Kenta Yagi, Mayu Takaoka, Yuko Sakajiri, Tomokazu Shibata, Ryusuke Sawada, Akinori Maruo, Koji Miyata, Fuka Aizawa, Hirofumi Hamano, Takahiro Niimura, Yuki Izawa-Ishizawa, Mitsuhiro Goda, Satoshi Sakaguchi, Yoshito Zamami, Yoshihiro Yamanishi, Keisuke Ishizawa

    Drug development research   Vol. 84 ( 1 ) page: 75 - 83   2023.2

     More details

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

    Proton pump inhibitors (PPIs) are potent inhibitors of gastric acid secretion, used as first-line agents in treating peptic ulcers. However, we have previously reported that PPIs may diminish the therapeutic effect of anti-vascular endothelial growth factor (VEGF) drugs in patients with cancer. In this study, we explored the effects of vonoprazan, a novel gastric acid secretion inhibitor used for the treatment of peptic ulcers, on the secretion of VEGF in cancer cells and attempted to propose it as an alternative PPI for cancer chemotherapy. The effects of PPI and vonoprazan on VEGF expression in cancer cells were compared by real-time reverse transcription-polymerase chain reaction and ELISA. The interaction of vonoprazan and PPIs with transcriptional regulators by docking simulation analysis. In various cancer cell lines, including the human colorectal cancer cell line (LS174T), PPI increased VEGF messenger RNA expression and VEGF protein secretion, while this effect was not observed with vonoprazan. Molecular docking simulation analysis showed that vonoprazan had a lower binding affinity for estrogen receptor alpha (ER-α), one of the transcriptional regulators of VEGF, compared to PPI. Although the PPI-induced increase in VEGF expression was counteracted by pharmacological ER-α inhibition, the effect of vonoprazan on VEGF expression was unchanged. Vonoprazan does not affect VEGF expression in cancer cells, which suggests that vonoprazan might be an alternative to PPIs, with no interference with the therapeutic effects of anti-VEGF cancer chemotherapy.

    DOI: 10.1002/ddr.22013

    Web of Science

    Scopus

    PubMed

  17. Data-driven drug discovery and healthcare by AI

    Yamanishi, Y

    CANCER SCIENCE   Vol. 114   page: 7 - 7   2023.2

     More details

  18. Mode Collapse Alleviation of Reinforcement Learning-based GANs in Drug Design

    Jiang Z., Wang Z., Zhang J., Wub M., Li C., Yamanishi Y.

    Proceedings - 2023 2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023     page: 3045 - 3052   2023

     More details

    Publisher:Proceedings - 2023 2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023  

    De novo drug design is a challenging task that involves understanding the principles of chemistry, chemical properties, and the rules that govern molecular interactions. Deep learning-based generative models, such as MolGAN, offer a promising approach for generating new molecules with the desired chemical properties from molecular graphs. Such models often combine a discrete generative adversarial network (GAN) and reinforcement learning (RL) to produce highly valid and novel molecules. However, the severe mode collapse problem leads to low performance. This study aims to alleviate and investigate the effect of multiple factors on mode collapse. We conducted experiments on different sampling methods, training epochs, and datasets of various volumes and evaluated the experimental results using performance metrics such as validity, uniqueness, novelty, and diversity. The experimental results demonstrate that noise sampling distributions, training epochs, and training data volumes affect performance. The experimental results provide a direction for mitigating the mode collapse problem for RL-based discrete GANs.

    DOI: 10.1109/BIBM58861.2023.10385948

    Scopus

  19. Characterization of Immune Checkpoint Inhibitor-Induced Myasthenia Gravis Using the US Food and Drug Administration Adverse Event Reporting System. Reviewed International journal

    Takahiro Niimura, Yoshito Zamami, Koji Miyata, Takahisa Mikami, Mizuho Asada, Keijo Fukushima, Masaki Yoshino, Satoru Mitsuboshi, Naoto Okada, Hirofumi Hamano, Takumi Sakurada, Rie Matsuoka-Ando, Fuka Aizawa, Kenta Yagi, Mitsuhiro Goda, Masayuki Chuma, Toshihiro Koyama, Yuki Izawa-Ishizawa, Hiroaki Yanagawa, Hiromichi Fujino, Yoshihiro Yamanishi, Keisuke Ishizawa

    Journal of clinical pharmacology   Vol. 63 ( 4 ) page: 473 - 479   2022.12

     More details

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

    Myasthenia gravis (MG) is a rare but fatal adverse event of immune checkpoint inhibitors (ICIs). We assessed whether patient characteristics differed between those with ICI-related myasthenia gravis and those with idiopathic myasthenia gravis. Reports from the US Food and Drug Administration Adverse Event Reporting System were analyzed. Multivariate analyses were conducted to evaluate the associations between age, sex, and ICI treatment and the reporting rate of myasthenia gravis. Among 5 464 099 cases between 2011 and 2019, 53 447 were treated with ICIs. Myasthenia gravis was reported more often in ICI users. Multiple logistic regression analyses showed that the reporting rate of ICI-related myasthenia gravis did not differ significantly between men and women; however, it was higher in older people than in younger people (adjusted odds ratio, 2.4 [95%CI, 1.84-3.13]). We also investigated useful signs for the early detection of myositis and myocarditis, which are fatal when overlapping with ICI-related myasthenia gravis. Patients with elevated serum creatine kinase or troponin levels were more likely to have concurrent myositis and myocarditis. Unlike idiopathic myasthenia gravis, there was no sex difference in the development of ICI-related myasthenia gravis, which may be more common in older people. Considering the physiological muscle weakness that occurs in the elderly, it may be necessary to monitor ICI-related myasthenia gravis more closely in older people.

    DOI: 10.1002/jcph.2187

    DOI: 10.1002/jcph.2187

    Web of Science

    Scopus

    PubMed

  20. Regulome-based characterization of drug activity across the human diseasome Reviewed International journal

    Michio Iwata, Keisuke Kosai, Yuya Ono, Shinya Oki, Koshi Mimori, Yoshihiro Yamanishi

    npj Systems Biology and Applications   Vol. 8 ( 1 ) page: 44 - 44   2022.11

     More details

    Authorship:Last author, Corresponding author   Language:English   Publishing type:Research paper (scientific journal)   Publisher:Springer Science and Business Media LLC  

    Abstract

    Drugs are expected to recover the cell system away from the impaired state to normalcy through disease treatment. However, the understanding of gene regulatory machinery underlying drug activity or disease pathogenesis is far from complete. Here, we perform large-scale regulome analysis for various diseases in terms of gene regulatory machinery. Transcriptome signatures were converted into regulome signatures of transcription factors by integrating publicly available ChIP-seq data. Regulome-based correlations between diseases and their approved drugs were much clearer than the transcriptome-based correlations. For example, an inverse correlation was observed for cancers, whereas a positive correlation was observed for immune system diseases. After demonstrating the usefulness of the regulome-based drug discovery method in terms of accuracy and applicability, we predicted new drugs for nonsmall cell lung cancer and validated the anticancer activity in vitro. The proposed method is useful for understanding disease–disease relationships and drug discovery.

    DOI: 10.1038/s41540-022-00255-4

    Web of Science

    Scopus

    PubMed

    Other Link: https://www.nature.com/articles/s41540-022-00255-4

  21. Pathway trajectory analysis with tensor imputation reveals drug-induced single-cell transcriptomic landscape Reviewed

    Michio Iwata, Hiroaki Mutsumine, Yusuke Nakayama, Naomasa Suita, Yoshihiro Yamanishi

    NATURE COMPUTATIONAL SCIENCE   Vol. 2 ( 11 ) page: 758 - 770   2022.11

     More details

    Authorship:Last author, Corresponding author   Language:English   Publishing type:Research paper (scientific journal)   Publisher:SPRINGERNATURE  

    Genome-wide identification of single-cell transcriptomic responses of drugs in various human cells is a challenging issue in medical and pharmaceutical research. Here we present a computational method, tensor-based imputation of gene-expression data at the single-cell level (TIGERS), which reveals the drug-induced single-cell transcriptomic landscape. With this algorithm, we predict missing drug-induced single-cell gene-expression data with tensor imputation, and identify trajectories of regulated pathways considering intercellular heterogeneity. Tensor imputation outperformed existing imputation methods for data completion, and provided cell-type-specific transcriptomic responses for unobserved drugs. For example, TIGERS correctly predicted the cell-type-specific expression of maker genes for pancreatic islets. Pathway trajectory analysis of the imputed gene-expression profiles of all combinations of drugs and human cells identified single-cell-specific drug activities and pathway trajectories that reflect drug-induced changes in pathway regulation. The proposed method is expected to expand our understanding of the single-cell mechanisms of drugs at the pathway level.

    DOI: 10.1038/s43588-022-00352-8

    Web of Science

    Scopus

  22. Small compound-based direct cell conversion with combinatorial optimization of pathway regulations. Reviewed International journal

    Toru Nakamura, Michio Iwata, Momoko Hamano, Ryohei Eguchi, Jun-Ichi Takeshita, Yoshihiro Yamanishi

    Bioinformatics (Oxford, England)   Vol. 38 ( Suppl_2 ) page: ii99 - ii105   2022.9

     More details

    Authorship:Last author, Corresponding author   Language:English   Publishing type:Research paper (scientific journal)  

    MOTIVATION: Direct cell conversion, direct reprogramming (DR), is an innovative technology that directly converts source cells to target cells without bypassing induced pluripotent stem cells. The use of small compounds (e.g. drugs) for DR can help avoid carcinogenic risk induced by gene transfection; however, experimentally identifying small compounds remains challenging because of combinatorial explosion. RESULTS: In this article, we present a new computational method, COMPRENDRE (combinatorial optimization of pathway regulations for direct reprograming), to elucidate the mechanism of small compound-based DR and predict new combinations of small compounds for DR. We estimated the potential target proteins of DR-inducing small compounds and identified a set of target pathways involving DR. We identified multiple DR-related pathways that have not previously been reported to induce neurons or cardiomyocytes from fibroblasts. To overcome the problem of combinatorial explosion, we developed a variant of a simulated annealing algorithm to identify the best set of compounds that can regulate DR-related pathways. Consequently, the proposed method enabled to predict new DR-inducing candidate combinations with fewer compounds and to successfully reproduce experimentally verified compounds inducing the direct conversion from fibroblasts to neurons or cardiomyocytes. The proposed method is expected to be useful for practical applications in regenerative medicine. AVAILABILITY AND IMPLEMENTATION: The code supporting the current study is available at the http://labo.bio.kyutech.ac.jp/~yamani/comprendre. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

    DOI: 10.1093/bioinformatics/btac475

    Web of Science

    Scopus

    PubMed

  23. Transformer-based Objective-reinforced Generative Adversarial Network to Generate Desired Molecules. Reviewed

    Chen Li, Chikashige Yamanaka, Kazuma Kaitoh, Yoshihiro Yamanishi

    Proceedings of the 31st International Joint Conference on Artificial Intelligence and the 25th European Conference on Artificial Intelligence (IJCAI-ECAI 2022)     page: 3884 - 3890   2022.7

     More details

    Authorship:Last author   Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:ijcai.org  

    DOI: 10.24963/ijcai.2022/539

    Other Link: https://dblp.uni-trier.de/db/conf/ijcai/ijcai2022.html#LiYKY22

  24. From drug repositioning to target repositioning: prediction of therapeutic targets using genetically perturbed transcriptomic signatures. Reviewed International journal

    Satoko Namba, Michio Iwata, Yoshihiro Yamanishi

    Bioinformatics (Oxford, England)   Vol. 38 ( SUPPL 1 ) page: 68 - 76   2022.6

     More details

    Authorship:Last author, Corresponding author   Language:English   Publishing type:Research paper (scientific journal)  

    MOTIVATION: A critical element of drug development is the identification of therapeutic targets for diseases. However, the depletion of therapeutic targets is a serious problem. RESULTS: In this study, we propose the novel concept of target repositioning, an extension of the concept of drug repositioning, to predict new therapeutic targets for various diseases. Predictions were performed by a trans-disease analysis which integrated genetically perturbed transcriptomic signatures (knockdown of 4345 genes and overexpression of 3114 genes) and disease-specific gene transcriptomic signatures of 79 diseases. The trans-disease method, which takes into account similarities among diseases, enabled us to distinguish the inhibitory from activatory targets and to predict the therapeutic targetability of not only proteins with known target-disease associations but also orphan proteins without known associations. Our proposed method is expected to be useful for understanding the commonality of mechanisms among diseases and for therapeutic target identification in drug discovery. AVAILABILITY AND IMPLEMENTATION: Supplemental information and software are available at the following website [http://labo.bio.kyutech.ac.jp/~yamani/target_repositioning/]. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

    DOI: 10.1093/bioinformatics/btac240

    Web of Science

    Scopus

    PubMed

  25. Corrigendum: A Web Server for GPCR-GPCR Interaction Pair Prediction. Reviewed International coauthorship International journal

    Wataru Nemoto, Yoshihiro Yamanishi, Vachiranee Limviphuvadh, Shunsuke Fujishiro, Sakie Shimamura, Aoi Fukushima, Hiroyuki Toh

    Frontiers in endocrinology   Vol. 13   page: 944910 - 944910   2022.6

     More details

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

    [This corrects the article DOI: 10.3389/fendo.2022.825195.].

    DOI: 10.3389/fendo.2022.944910

    Web of Science

    Scopus

    PubMed

  26. Scaffold-Retained Structure Generator to Exhaustively Create Molecules in an Arbitrary Chemical Space. Reviewed International journal

    Kazuma Kaitoh, Yoshihiro Yamanishi

    Journal of Chemical Information and Modeling   Vol. 62 ( 9 ) page: 2212 - 2225   2022.5

     More details

    Authorship:Last author, Corresponding author   Language:English   Publishing type:Research paper (scientific journal)  

    The construction of a virtual library (VL) consisting of novel molecules based on structure-activity relationships is crucial for lead optimization in rational drug design. In this study, we propose a novel scaffold-retained structure generator, EMPIRE (Exhaustive Molecular library Production In a scaffold-REtained manner), to create novel molecules in an arbitrary chemical space. By combining a deep learning model-based generator and a building block-based generator, the proposed method efficiently provides a VL consisting of molecules that retain the input scaffold and contain unique arbitrary substructures. The proposed method enables us to construct rational VLs located in unexplored chemical spaces containing molecules with unique skeletons (e.g., bicyclo[1.1.1]pentane and cubane) or elements (e.g., boron and silicon). We expect EMPIRE to contribute to efficient drug design with unique substructures by virtual screening.

    DOI: 10.1021/acs.jcim.1c01130

    Web of Science

    Scopus

    PubMed

  27. TRANSDIRE: data-driven direct reprogramming by a pioneer factor-guided trans-omics approach. Reviewed International journal

    Ryohei Eguchi, Momoko Hamano, Michio Iwata, Toru Nakamura, Shinya Oki, Yoshihiro Yamanishi

    Bioinformatics(Bioinform.)   Vol. 38 ( 10 ) page: 2839 - 2846   2022.4

     More details

    Authorship:Last author, Corresponding author   Language:English   Publishing type:Research paper (scientific journal)   Publisher:Oxford University Press (OUP)  

    Abstract

    Motivation

    Direct reprogramming involves the direct conversion of fully differentiated mature cell types into various other cell types while bypassing an intermediate pluripotent state (e.g., induced pluripotent stem cells). Cell differentiation by direct reprogramming is determined by two types of transcription factors (TFs): pioneer factors (PFs) and cooperative TFs. PFs have the distinct ability to open chromatin aggregations, assemble a collective of cooperative TFs, and activate gene expression. The experimental determination of two types of TFs is extremely difficult and costly.

    Results

    In this study, we developed a novel computational method, TRANSDIRE (TRANS-omics-based approach for DIrect REprogramming), to predict the TFs that induce direct reprogramming in various human cell types using multiple omics data. In the algorithm, potential PFs were predicted based on low signal chromatin regions, and the cooperative TFs were predicted through a trans-omics analysis of genomic data (e.g., enhancers), transcriptome data (e.g., gene expression profiles in human cells), epigenome data (e.g., chromatin immunoprecipitation sequencing data), and interactome data. We applied the proposed methods to the reconstruction of TFs that induce direct reprogramming from fibroblasts to six other cell types: hepatocytes, cartilaginous cells, neurons, cardiomyocytes, pancreatic cells, and Paneth cells. We demonstrated that the methods successfully predicted TFs for most cell conversions with high accuracy. Thus, the proposed methods are expected to be useful for various practical applications in regenerative medicine.

    Availability

    The source code and data are available at the following website: http://figshare.com/s/b653781a5b9e6639972b

    DOI: 10.1093/bioinformatics/btac209

    Web of Science

    Scopus

    PubMed

  28. A Web Server for GPCR-GPCR Interaction Pair Prediction. Reviewed International coauthorship International journal

    Wataru Nemoto, Yoshihiro Yamanishi, Vachiranee Limviphuvadh, Shunsuke Fujishiro, Sakie Shimamura, Aoi Fukushima, Hiroyuki Toh

    Frontiers in endocrinology   Vol. 13   page: 825195 - 825195   2022.3

     More details

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

    The GGIP web server (https://protein.b.dendai.ac.jp/GGIP/) provides a web application for GPCR-GPCR interaction pair prediction by a support vector machine. The server accepts two sequences in the FASTA format. It responds with a prediction that the input GPCR sequence pair either interacts or not. GPCRs predicted to interact with the monomers constituting the pair are also shown when query sequences are human GPCRs. The server is simple to use. A pair of amino acid sequences in the FASTA format is pasted into the text area, a PDB ID for a template structure is selected, and then the 'Execute' button is clicked. The server quickly responds with a prediction result. The major advantage of this server is that it employs the GGIP software, which is presently the only method for predicting GPCR-interaction pairs. Our web server is freely available with no login requirement. In this article, we introduce some application examples of GGIP for disease-associated mutation analysis.

    DOI: 10.3389/fendo.2022.825195

    Web of Science

    Scopus

    PubMed

  29. Epigenetic landscape of drug responses revealed through large-scale ChIP-seq data analyses. Reviewed International journal

    Zhaonan Zou, Michio Iwata, Yoshihiro Yamanishi, Shinya Oki

    BMC Bioinformatics   Vol. 23 ( 1 ) page: 51 - 51   2022.1

     More details

    Authorship:Corresponding author   Language:English   Publishing type:Research paper (scientific journal)   Publisher:Springer Science and Business Media LLC  

    Abstract

    Background

    Elucidating the modes of action (MoAs) of drugs and drug candidate compounds is critical for guiding translation from drug discovery to clinical application. Despite the development of several data-driven approaches for predicting chemical–disease associations, the molecular cues that organize the epigenetic landscape of drug responses remain poorly understood.

    Results

    With the use of a computational method, we attempted to elucidate the epigenetic landscape of drug responses, in terms of transcription factors (TFs), through large-scale ChIP-seq data analyses. In the algorithm, we systematically identified TFs that regulate the expression of chemically induced genes by integrating transcriptome data from chemical induction experiments and almost all publicly available ChIP-seq data (consisting of 13,558 experiments). By relating the resultant chemical–TF associations to a repository of associated proteins for a wide range of diseases, we made a comprehensive prediction of chemical–TF–disease associations, which could then be used to account for drug MoAs. Using this approach, we predicted that: (1) cisplatin promotes the anti-tumor activity of TP53 family members but suppresses the cancer-inducing function of MYCs; (2) inhibition of RELA and E2F1 is pivotal for leflunomide to exhibit antiproliferative activity; and (3) CHD8 mediates valproic acid-induced autism.

    Conclusions

    Our proposed approach has the potential to elucidate the MoAs for both approved drugs and candidate compounds from an epigenetic perspective, thereby revealing new therapeutic targets, and to guide the discovery of unexpected therapeutic effects, side effects, and novel targets and actions.

    DOI: 10.1186/s12859-022-04571-8

    Web of Science

    Scopus

    PubMed

    Other Link: https://link.springer.com/article/10.1186/s12859-022-04571-8/fulltext.html

  30. TRIOMPHE: Transcriptome-Based Inference and Generation of Molecules with Desired Phenotypes by Machine Learning. Reviewed International journal

    Kazuma Kaitoh, Yoshihiro Yamanishi

    Journal of Chemical Information and Modeling   Vol. 61 ( 9 ) page: 4303 - 4320   2021.9

     More details

    Authorship:Last author, Corresponding author   Language:English   Publishing type:Research paper (scientific journal)  

    One of the most challenging tasks in the drug-discovery process is the efficient identification of small molecules with desired phenotypes. In this study, we propose a novel computational method for omics-based de novo drug design, which we call TRIOMPHE (transcriptome-based inference and generation of molecules with desired phenotypes). We investigated the correlation between chemically induced transcriptome profiles (reflecting cellular responses to compound treatment) and genetically perturbed transcriptome profiles (reflecting cellular responses to gene knock-down or gene overexpression of target proteins) in terms of ligand-target interactions. Subsequently, we developed novel machine learning methods to generate the chemical structures of new molecules with desired transcriptome profiles in the framework of a variational autoencoder. The use of desired transcriptome profiles enables the automatic design of molecules that are likely to have bioactivities for target proteins of interest. We showed that our methods can generate chemically valid molecules that are likely to have biological activities on 10 target proteins; moreover, they can outperform previous methods that had the same objective. Our omics-based structure generator is expected to be useful for the de novo design of drugs for a variety of target proteins.

    DOI: 10.1021/acs.jcim.1c00967

    Web of Science

    Scopus

    PubMed

  31. Plasma amino acids in patients with essential tremor. International journal

    Shiroh Miura, Takashi Kamada, Ryuta Fujioka, Yoshihiro Yamanishi

    Clinical case reports   Vol. 9 ( 8 ) page: e04580   2021.8

     More details

    Language:English  

    Essential tremor (ET) is one of the most common movement disorders. However, there are currently no accepted biomarkers for ET. This report suggested that concentration of plasma glutamic acid, aspartic acid, and taurine could be biomarkers for ET.

    DOI: 10.1002/ccr3.4580

    Web of Science

    PubMed

  32. Lean-Docking: Exploiting Ligands' Predicted Docking Scores to Accelerate Molecular Docking. International journal

    Francois Berenger, Ashutosh Kumar 0001, Kam Y. J. Zhang, Yoshihiro Yamanishi

    Journal of Chemical Information and Modeling   Vol. 61 ( 5 ) page: 2341 - 2352   2021.5

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:American Chemical Society (ACS)  

    In structure-based virtual screening (SBVS), a binding site on a protein structure is used to search for ligands with favorable nonbonded interactions. Because it is computationally difficult, docking is time-consuming and any docking user will eventually encounter a chemical library that is too big to dock. This problem might arise because there is not enough computing power or because preparing and storing so many three-dimensional (3D) ligands requires too much space. In this study, however, we show that quality regressors can be trained to predict docking scores from molecular fingerprints. Although typical docking has a screening rate of less than one ligand per second on one CPU core, our regressors can predict about 5800 docking scores per second. This approach allows us to focus docking on the portion of a database that is predicted to have docking scores below a user-chosen threshold. Herein, usage examples are shown, where only 25% of a ligand database is docked, without any significant virtual screening performance loss. We call this method "lean-docking". To validate lean-docking, a massive docking campaign using several state-of-the-art docking software packages was undertaken on an unbiased data set, with only wet-lab tested active and inactive molecules. Although regressors allow the screening of a larger chemical space, even at a constant docking power, it is also clear that significant progress in the virtual screening power of docking scores is desirable.

    DOI: 10.1021/acs.jcim.0c01452

    Web of Science

    Scopus

    PubMed

  33. Prediction of single-cell mechanisms for disease progression in hypertrophic remodelling by a trans-omics approach International journal

    Momoko Hamano, Seitaro Nomura, Midori Iida, Issei Komuro, Yoshihiro Yamanishi

    Scientific Reports   Vol. 11 ( 1 ) page: 8112 - 8112   2021.4

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:Springer Science and Business Media LLC  

    <title>Abstract</title>Heart failure is a heterogeneous disease with multiple risk factors and various pathophysiological types, which makes it difficult to understand the molecular mechanisms involved. In this study, we proposed a trans-omics approach for predicting molecular pathological mechanisms of heart failure and identifying marker genes to distinguish heterogeneous phenotypes, by integrating multiple omics data including single-cell RNA-seq, ChIP-seq, and gene interactome data. We detected a significant increase in the expression level of natriuretic peptide A (<italic>Nppa</italic>), after stress loading with transverse aortic constriction (TAC), and showed that cardiomyocytes with high <italic>Nppa</italic> expression displayed specific gene expression patterns. Multiple NADH ubiquinone complex family, which are associated with the mitochondrial electron transport system, were negatively correlated with <italic>Nppa</italic> expression during the early stages of cardiac hypertrophy. Large-scale ChIP-seq data analysis showed that Nkx2-5 and Gtf2b were transcription factors characteristic of high-<italic>Nppa-</italic>expressing cardiomyocytes. <italic>Nppa</italic> expression levels may, therefore, represent a useful diagnostic marker for heart failure.

    DOI: 10.1038/s41598-021-86821-y

    Web of Science

    Scopus

    PubMed

    Other Link: http://www.nature.com/articles/s41598-021-86821-y

  34. The novel driver gene ASAP2 is a potential druggable target in pancreatic cancer International journal

    Atsushi Fujii, Takaaki Masuda, Michio Iwata, Taro Tobo, Hiroaki Wakiyama, Kensuke Koike, Keisuke Kosai, Takafumi Nakano, Shotaro Kuramitsu, Akihiro Kitagawa, Kuniaki Sato, Yuta Kouyama, Dai Shimizu, Yoshihiro Matsumoto, Tohru Utsunomiya, Takao Ohtsuka, Yoshihiro Yamanishi, Masafumi Nakamura, Koshi Mimori

    Cancer Science   Vol. 112 ( 4 ) page: 1655 - 1668   2021.4

     More details

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

    Targeting mutated oncogenes is an effective approach for treating cancer. The 4 main driver genes of pancreatic ductal adenocarcinoma (PDAC) are KRAS, TP53, CDKN2A, and SMAD4, collectively called the "big 4" of PDAC, however they remain challenging therapeutic targets. In this study, ArfGAP with SH3 domain, ankyrin repeat and PH domain 2 (ASAP2), one of the ArfGAP family, was identified as a novel driver gene in PDAC. Clinical analysis with PDAC datasets showed that ASAP2 was overexpressed in PDAC cells based on increased DNA copy numbers, and high ASAP2 expression contributed to a poor prognosis in PDAC. The biological roles of ASAP2 were investigated using ASAP2-knockout PDAC cells generated with CRISPR-Cas9 technology or transfected PDAC cells. In vitro and in vivo analyses showed that ASAP2 promoted tumor growth by facilitating cell cycle progression through phosphorylation of epidermal growth factor receptor (EGFR). A repositioned drug targeting the ASAP2 pathway was identified using a bioinformatics approach. The gene perturbation correlation method showed that niclosamide, an antiparasitic drug, suppressed PDAC growth by inhibition of ASAP2 expression. These data show that ASAP2 is a novel druggable driver gene that activates the EGFR signaling pathway. Furthermore, niclosamide was identified as a repositioned therapeutic agent for PDAC possibly targeting ASAP2.

    DOI: 10.1111/cas.14858

    Web of Science

    Scopus

    PubMed

  35. Novel driver gene ASAP2 is a potentially druggable target in pancreatic cancer

    Masuda Takaaki, Fujii Atsushi, Iwata Michio, Matsumoto Yoshihiro, Otsu Hajime, Takeishi Kazuki, Yonemura Yusuke, Yamanishi Yoshihiro, Mimori Koshi

    CANCER SCIENCE   Vol. 112   page: 276 - 276   2021.2

     More details

  36. Ranking Molecules with Vanishing Kernels and a Single Parameter: Active Applicability Domain Included. International journal

    Francois Berenger, Yoshihiro Yamanishi

    Journal of Chemical Information and Modeling   Vol. 60 ( 9 ) page: 4376 - 4387   2020.9

     More details

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

    In ligand-based virtual screening, high-throughput screening (HTS) data sets can be exploited to train classification models. Such models can be used to prioritize yet untested molecules, from the most likely active (against a protein target of interest) to the least likely active. In this study, a single-parameter ranking method with an Applicability Domain (AD) is proposed. In effect, Kernel Density Estimates (KDE) are revisited to improve their computational efficiency and incorporate an AD. Two modifications are proposed: (i) using vanishing kernels (i.e., kernel functions with a finite support) and (ii) using the Tanimoto distance between molecular fingerprints as a radial basis function. This construction is termed "Vanishing Ranking Kernels" (VRK). Using VRK on 21 HTS assays, it is shown that VRK can compete in performance with a graph convolutional deep neural network. VRK are conceptually simple and fast to train. During training, they require optimizing a single parameter. A trained VRK model usually defines an active AD. Exploiting this AD can significantly increase the screening frequency of a VRK model. Software: https://github.com/UnixJunkie/rankers. Data sets: https://zenodo.org/record/1320776 and https://zenodo.org/record/3540423.

    DOI: 10.1021/acs.jcim.9b01075

    Web of Science

    Scopus

    PubMed

    Other Link: https://dblp.uni-trier.de/db/journals/jcisd/jcisd60.html#BerengerY20

  37. Network-based characterization of disease-disease relationships in terms of drugs and therapeutic targets. International journal

    Midori Iida, Michio Iwata, Yoshihiro Yamanishi

    Bioinformatics(Bioinform.)   Vol. 36 ( Supplement-1 ) page: 516 - 524   2020.7

     More details

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

    MOTIVATION: Disease states are distinguished from each other in terms of differing clinical phenotypes, but characteristic molecular features are often common to various diseases. Similarities between diseases can be explained by characteristic gene expression patterns. However, most disease-disease relationships remain uncharacterized. RESULTS: In this study, we proposed a novel approach for network-based characterization of disease-disease relationships in terms of drugs and therapeutic targets. We performed large-scale analyses of omics data and molecular interaction networks for 79 diseases, including adrenoleukodystrophy, leukaemia, Alzheimer's disease, asthma, atopic dermatitis, breast cancer, cystic fibrosis and inflammatory bowel disease. We quantified disease-disease similarities based on proximities of abnormally expressed genes in various molecular networks, and showed that similarities between diseases could be explained by characteristic molecular network topologies. Furthermore, we developed a kernel matrix regression algorithm to predict the commonalities of drugs and therapeutic targets among diseases. Our comprehensive prediction strategy indicated many new associations among phenotypically diverse diseases. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

    DOI: 10.1093/bioinformatics/btaa439

    Web of Science

    Scopus

    PubMed

    Other Link: https://dblp.uni-trier.de/db/journals/bioinformatics/bioinformatics36.html#IidaIY20

  38. Dual graph convolutional neural network for predicting chemical networks. International journal

    Shonosuke Harada, Hirotaka Akita, Masashi Tsubaki, Yukino Baba, Ichigaku Takigawa, Yoshihiro Yamanishi, Hisashi Kashima

    BMC bioinformatics   Vol. 21 ( Suppl 3 ) page: 94 - 94   2020.4

     More details

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

    BACKGROUND: Predicting of chemical compounds is one of the fundamental tasks in bioinformatics and chemoinformatics, because it contributes to various applications in metabolic engineering and drug discovery. The recent rapid growth of the amount of available data has enabled applications of computational approaches such as statistical modeling and machine learning method. Both a set of chemical interactions and chemical compound structures are represented as graphs, and various graph-based approaches including graph convolutional neural networks have been successfully applied to chemical network prediction. However, there was no efficient method that can consider the two different types of graphs in an end-to-end manner. RESULTS: We give a new formulation of the chemical network prediction problem as a link prediction problem in a graph of graphs (GoG) which can represent the hierarchical structure consisting of compound graphs and an inter-compound graph. We propose a new graph convolutional neural network architecture called dual graph convolutional network that learns compound representations from both the compound graphs and the inter-compound network in an end-to-end manner. CONCLUSIONS: Experiments using four chemical networks with different sparsity levels and degree distributions shows that our dual graph convolution approach achieves high prediction performance in relatively dense networks, while the performance becomes inferior on extremely-sparse networks.

    DOI: 10.1186/s12859-020-3378-0

    Web of Science

    Scopus

    PubMed

    Other Link: https://dblp.uni-trier.de/db/journals/bmcbi/bmcbi21S.html#HaradaATBTYK20

  39. Omics‐based Identification of Glycan Structures as Biomarkers for a Variety of Diseases International journal

    Sayaka Akiyoshi, Michio Iwata, Francois Berenger, Yoshihiro Yamanishi

    Molecular Informatics   Vol. 39 ( 1-2 ) page: 1900112 - 1900112   2020.1

     More details

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

    Glycans play important roles in cell communication, protein interaction, and immunity, and structural changes in glycans are associated with the regulation of a range of biological pathways involved in disease. However, our understanding of the detailed relationships between specific diseases and glycans is very limited. In this study, we proposed an omics-based method to investigate the correlations between glycans and a wide range of human diseases. We analyzed the gene expression patterns of glycogenes (glycosyltransferases and glycosidases) for 79 different diseases. A biological pathway-based glycogene signature was constructed to identify the alteration in glycan biosynthesis and the associated glycan structures for each disease state. The degradation of N-glycan and keratan sulfate, for example, may promote the growth or metastasis of multiple types of cancer, including endometrial, gastric, and nasopharyngeal. Our results also revealed that commonalities between diseases can be interpreted using glycogene expression patterns, as well as the associated glycan structure patterns at the level of the affected pathway. The proposed method is expected to be useful for understanding the relationships between glycans, glycogenes, and disease and identifying disease-specific glycan biomarkers.

    DOI: 10.1002/minf.201900112

    Web of Science

    Scopus

    PubMed

    Other Link: https://onlinelibrary.wiley.com/doi/full-xml/10.1002/minf.201900112

  40. Prediction of the Health Effects of Food Peptides and Elucidation of the Mode‐of‐action Using Multi‐task Graph Convolutional Neural Network International journal

    Itsuki Fukunaga, Ryusuke Sawada, Tomokazu Shibata, Kazuma Kaitoh, Yukie Sakai, Yoshihiro Yamanishi

    Molecular Informatics   Vol. 39 ( 1-2 ) page: 1900134 - 1900134   2020.1

     More details

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

    Food proteins work not only as nutrients but also modulators for the physiological functions of the human body. The physiological functions of food proteins are basically regulated by peptides encrypted in food protein sequences (food peptides). In this study, we propose a novel deep learning-based method to predict the health effects of food peptides and elucidate the mode-of-action. In the algorithm, we estimate potential target proteins of food peptides using a multi-task graph convolutional neural network, and predict its health effects using information about therapeutic targets for diseases. We constructed predictive models based on 21,103 peptide-protein interactions involving 10,950 peptides and 2,533 proteins, and applied the models to food peptides (e. g., lactotripeptide, isoleucyltyrosine and sardine peptide) defined in food for specified health use. The models suggested potential effects such as blood-pressure lowering effects, blood glucose level lowering effects, and anti-cancer effects for several food peptides. The interactions of food peptides with target proteins were confirmed by docking simulations.

    DOI: 10.1002/minf.201900134

    Web of Science

    Scopus

    PubMed

    Other Link: https://onlinelibrary.wiley.com/doi/full-xml/10.1002/minf.201900134

  41. <i>In silico</i> systems for predicting chemical-induced side effects using known and potential chemical protein interactions, enabling mechanism estimation

    Amano Yuto, Honda Hiroshi, Sawada Ryusuke, Nukada Yuko, Yamane Masayuki, Ikeda Naohiro, Morita Osamu, Yamanishi Yoshihiro

    The Journal of Toxicological Sciences   Vol. 45 ( 3 ) page: 137 - 149   2020

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:The Japanese Society of Toxicology  

    <p><i>In silico</i> models for predicting chemical-induced side effects have become increasingly important for the development of pharmaceuticals and functional food products. However, existing predictive models have difficulty in estimating the mechanisms of side effects in terms of molecular targets or they do not cover the wide range of pharmacological targets. In the present study, we constructed novel <i>in silico</i> models to predict chemical-induced side effects and estimate the underlying mechanisms with high general versatility by integrating the comprehensive prediction of potential chemical-protein interactions (CPIs) with machine learning. First, the potential CPIs were comprehensively estimated by chemometrics based on the known CPI data (1,179,848 interactions involving 3,905 proteins and 824,143 chemicals). Second, the predictive models for 61 side effects in the cardiovascular system (CVS), gastrointestinal system (GIS), and central nervous system (CNS) were constructed by sparsity-induced classifiers based on the known and potential CPI data. The cross validation experiments showed that the proposed CPI-based models had a higher or comparable performance than the traditional chemical structure-based models. Moreover, our enrichment analysis indicated that the highly weighted proteins derived from predictive models could be involved in the corresponding functions of the side effects. For example, in CVS, the carcinogenesis-related pathways (e.g., prostate cancer, PI3K-Akt signal pathway), which were recently reported to be involved in cardiovascular side effects, were enriched. Therefore, our predictive models are biologically valid and would be useful for predicting side effects and novel potential underlying mechanisms of chemical-induced side effects.</p>

    DOI: 10.2131/jts.45.137

    Web of Science

    Scopus

    PubMed

    CiNii Research

  42. Space-Efficient Feature Maps for String Alignment Kernels.

    Yasuo Tabei, Yoshihiro Yamanishi, Rasmus Pagh

    Data Science and Engineering   Vol. 5 ( 2 ) page: 168 - 179   2020

     More details

    Publishing type:Research paper (scientific journal)  

    DOI: 10.1007/s41019-020-00120-6

    Scopus

  43. Data-driven drug discovery and medical treatment by machine learning

    Yamanishi, Y

    ABSTRACTS OF PAPERS OF THE AMERICAN CHEMICAL SOCIETY   Vol. 258   2019.8

     More details

  44. Predicting drug-induced transcriptome responses of a wide range of human cell lines by a novel tensor-train decomposition algorithm. International journal

    Michio Iwata, Longhao Yuan, Qibin Zhao, Yasuo Tabei, Francois Berenger, Ryusuke Sawada, Sayaka Akiyoshi, Momoko Hamano, Yoshihiro Yamanishi

    Bioinformatics(Bioinform.)   Vol. 35 ( 14 ) page: I191 - I199   2019.7

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:Oxford University Press (OUP)  

    <title>Abstract</title>
    <sec>
    <title>Motivation</title>
    Genome-wide identification of the transcriptomic responses of human cell lines to drug treatments is a challenging issue in medical and pharmaceutical research. However, drug-induced gene expression profiles are largely unknown and unobserved for all combinations of drugs and human cell lines, which is a serious obstacle in practical applications.


    </sec>
    <sec>
    <title>Results</title>
    Here, we developed a novel computational method to predict unknown parts of drug-induced gene expression profiles for various human cell lines and predict new drug therapeutic indications for a wide range of diseases. We proposed a tensor-train weighted optimization (TT-WOPT) algorithm to predict the potential values for unknown parts in tensor-structured gene expression data. Our results revealed that the proposed TT-WOPT algorithm can accurately reconstruct drug-induced gene expression data for a range of human cell lines in the Library of Integrated Network-based Cellular Signatures. The results also revealed that in comparison with the use of original gene expression profiles, the use of imputed gene expression profiles improved the accuracy of drug repositioning. We also performed a comprehensive prediction of drug indications for diseases with gene expression profiles, which suggested many potential drug indications that were not predicted by previous approaches.


    </sec>
    <sec>
    <title>Supplementary information</title>
    Supplementary data are available at Bioinformatics online.


    </sec>

    DOI: 10.1093/bioinformatics/btz313

    Web of Science

    Scopus

    PubMed

  45. Network-based characterization of drug-protein interaction signatures with a space-efficient approach. International journal

    Yasuo Tabei, Masaaki Kotera, Ryusuke Sawada, Yoshihiro Yamanishi

    BMC Systems Biology   Vol. 13 ( 2 ) page: 39 - 15   2019.4

     More details

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

    BACKGROUND: Characterization of drug-protein interaction networks with biological features has recently become challenging in recent pharmaceutical science toward a better understanding of polypharmacology. RESULTS: We present a novel method for systematic analyses of the underlying features characteristic of drug-protein interaction networks, which we call "drug-protein interaction signatures" from the integration of large-scale heterogeneous data of drugs and proteins. We develop a new efficient algorithm for extracting informative drug-protein interaction signatures from the integration of large-scale heterogeneous data of drugs and proteins, which is made possible by space-efficient representations for fingerprints of drug-protein pairs and sparsity-induced classifiers. CONCLUSIONS: Our method infers a set of drug-protein interaction signatures consisting of the associations between drug chemical substructures, adverse drug reactions, protein domains, biological pathways, and pathway modules. We argue the these signatures are biologically meaningful and useful for predicting unknown drug-protein interactions and are expected to contribute to rational drug design.

    DOI: 10.1186/s12918-019-0691-1

    Web of Science

    Scopus

    PubMed

    Other Link: https://dblp.uni-trier.de/db/journals/bmcsb/bmcsb13S.html#TabeiKSY19

  46. Chemoinformatics and structural bioinformatics in OCaml. International journal

    Francois Berenger, Kam Y. J. Zhang, Yoshihiro Yamanishi

    Journal of Cheminformatics   Vol. 11 ( 1 ) page: 10 - 13   2019.2

     More details

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

    BACKGROUND: OCaml is a functional programming language with strong static types, Hindley-Milner type inference and garbage collection. In this article, we share our experience in prototyping chemoinformatics and structural bioinformatics software in OCaml. RESULTS: First, we introduce the language, list entry points for chemoinformaticians who would be interested in OCaml and give code examples. Then, we list some scientific open source software written in OCaml. We also present recent open source libraries useful in chemoinformatics. The parallelization of OCaml programs and their performance is also shown. Finally, tools and methods useful when prototyping scientific software in OCaml are given. CONCLUSIONS: In our experience, OCaml is a programming language of choice for method development in chemoinformatics and structural bioinformatics.

    DOI: 10.1186/s13321-019-0332-0

    Web of Science

    Scopus

    PubMed

    Other Link: https://dblp.uni-trier.de/db/journals/jcheminf/jcheminf11.html#BerengerZY19

  47. MIBG myocardial scintigraphy in progressive supranuclear palsy Reviewed International journal

    Takashi Kamada, Shiroh Miura, Hiroshi Kida, Ken ichi Irie, Yoshihiro Yamanishi, Tomoaki Hoshino, Takayuki Taniwaki

    Journal of the Neurological Sciences   Vol. 396   page: 3 - 7   2019.1

     More details

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

    © 2018 Elsevier B.V. Background and objectives: Meta-iodobenzylguanidine (MIBG) myocardial scintigraphy is an effective tool for distinguishing Parkinson&#039;s disease (PD) from other diseases accompanied by parkinsonism. Unlike other Parkinsonian diseases, in PD, MIBG accumulation in the heart tends to decrease. However, previous studies have reported that a decrease in MIBG accumulation also occurs in progressive supranuclear palsy (PSP). Thus, we analyzed the relationship between the degree of MIBG accumulation decrease, clinical symptoms, and brainstem atrophy in PSP. Methods: We retrospectively collected data from patients who underwent MIBG myocardial scintigraphy and compared MIBG indices (heart to mediastinum [H/M] ratio, washout rate) between subjects with PSP and other diseases including PD. In addition, we evaluated the relationship between clinical characteristics, MIBG accumulation, and brainstem atrophy in patients with PSP. Results: Patients with PSP had a significantly lower early H/M ratio compared with multiple system atrophy with predominant parkinsonism (MSA-P) patients, and a control group. In PSP patients there was a correlation between the decrease in delay H/M ratio, atrophy of the pons, and clinical severity as evaluated by Hoehn and Yahr score. Conclusion: Unlike in PD, PSP patients exhibited a mild decrease in MIBG accumulation in MIBG myocardial scintigraphy, which may be related to brainstem atrophy.

    DOI: 10.1016/j.jns.2018.10.019

    Web of Science

    Scopus

    PubMed

  48. A Distance-Based Boolean Applicability Domain for Classification of High Throughput Screening Data. Reviewed International journal

    Francois Berenger, Yoshihiro Yamanishi

    Journal of Chemical Information and Modeling   Vol. 59 ( 1 ) page: 463 - 476   2019.1

     More details

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

    In Quantitative Structure-Activity Relationship (QSAR) modeling, one must come up with an activity model but also with an applicability domain for that model. Some existing methods to create an applicability domain are complex, hard to implement, and/or difficult to interpret. Also, they often require the user to select a threshold value, or they embed an empirical constant. In this work, we propose a trivial to interpret and fully automatic Distance-Based Boolean Applicability Domain (DBBAD) algorithm for category QSAR. In retrospective experiments on High Throughput Screening data sets, this applicability domain improves the classification performance and early retrieval of support vector machine and random forest based classifiers, while improving the scaffold diversity among top-ranked active molecules.

    DOI: 10.1021/acs.jcim.8b00499

    Web of Science

    Scopus

    PubMed

    Other Link: https://dblp.uni-trier.de/db/journals/jcisd/jcisd59.html#BerengerY19

  49. Space-Efficient Feature Maps for String Alignment Kernels.

    Yasuo Tabei, Yoshihiro Yamanishi, Rasmus Pagh

    2019 IEEE International Conference on Data Mining(ICDM)   Vol. 2019-November   page: 1312 - 1317   2019

     More details

    Publishing type:Research paper (international conference proceedings)   Publisher:IEEE  

    DOI: 10.1109/ICDM.2019.00166

    Scopus

    Other Link: https://dblp.uni-trier.de/db/conf/icdm/icdm2019.html#TabeiYP19

  50. The use of large-scale chemically-induced transcriptome data acquired from lincs to study small molecules Reviewed International journal

    Michio Iwata, Yoshihiro Yamanishi

    Methods in Molecular Biology   Vol. 1888   page: 189 - 203   2019

     More details

    Language:English   Publishing type:Part of collection (book)   Publisher:Springer New York  

    © Springer Science+Business Media, LLC, part of Springer Nature 2019. Identification of the modes of action of bioactive compounds is an important issue in chemical systems biology. In this chapter we review a recently developed data-driven approach using large-scale chemically induced transcriptome data acquired from the Library of Integrated Network-based Cellular Signatures to elucidate the modes of action of bioactive compounds. First, we present a method for pathway enrichment analyses of regulated genes to reveal biological pathways activated by compounds. Next, we present a method using the pre-knowledge on chemical–protein interactome for predicting potential target proteins, including primary targets and off-targets, with transcriptional similarity. Finally, we present a method based on the target proteins for predicting new therapeutic indications for a variety of diseases. These approaches are expected to be useful for mode-of-action analysis, drug discovery, and drug repositioning.

    DOI: 10.1007/978-1-4939-8891-4_11

    Web of Science

    Scopus

    PubMed

  51. Pathway-Based Drug Repositioning for Cancers: Computational Prediction and Experimental Validation Reviewed International journal

    Iwata M, Hirose L, Kohara H, Liao J, Sawada R, Akiyoshi S, Tani K, Yamanishi Y

    Journal of Medicinal Chemistry   Vol. 61 ( 21 ) page: 9583 - 9595   2018.11

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:American Chemical Society (ACS)  

    © 2018 American Chemical Society. Developing drugs with anticancer activity and low toxic side-effects at low costs is a challenging issue for cancer chemotherapy. In this work, we propose to use molecular pathways as the therapeutic targets and develop a novel computational approach for drug repositioning for cancer treatment. We analyzed chemically induced gene expression data of 1112 drugs on 66 human cell lines and searched for drugs that inactivate pathways involved in the growth of cancer cells (cell cycle) and activate pathways that contribute to the death of cancer cells (e.g., apoptosis and p53 signaling). Finally, we performed a large-scale prediction of potential anticancer effects for all the drugs and experimentally validated the prediction results via three in vitro cellular assays that evaluate cell viability, cytotoxicity, and apoptosis induction. Using this strategy, we successfully identified several potential anticancer drugs. The proposed pathway-based method has great potential to improve drug repositioning research for cancer treatment.

    DOI: 10.1021/acs.jmedchem.8b01044

    Web of Science

    Scopus

    PubMed

  52. Cervical dystonia in Parkinson’s disease: Retrospective study of later-stage clinical features

    Hideki Kida, Tomoaki Hoshino, Takayuki Taniwaki

    Neurology Asia   Vol. 23 ( 3 ) page: 245 - 251   2018.9

     More details

    © 2018, ASEAN Neurological Association. All rights reserved. Objective: Cervical dystonia (CD) is a clinically under-recognized symptom occurring at the later-to end-stages of Parkinson’s disease (PD). The frequency of CD and its influence on prognosis have not been well studied. Here, we conducted an in-depth examination of CD incidence and impact on disease progression in later-stage PD. Methods: We retrospectively reviewed the clinical features of 22 deceased patients with sporadic PD treated at a hospital in Japan from 1983 to 2008. Results: The most common cause of death in PD was pneumonia. CD, in particular retrocollis, was frequent in the later stages of the disease in elderly patients (9/22, 40.9%). Pneumonia incidence increased sharply in the later period with CD. There was a positive trend between CD duration and duration of pergolide use. Conclusion: Analysis revealed that CD increases markedly in late-to end-stage PD, which may be associated with aspiration pneumonia due to dysphagia. Pathological mechanisms underlying CD might be influenced by treatments including dopamine agonists. Prevention of CD may increase quality of life and prolong survival of PD patients.

    Scopus

  53. Cervical dystonia in Parkinson's disease: Retrospective study of later-stage clinical features

    Kida Hiroshi, Miura Shiroh, Yamanishi Yoshihiro, Takahashi Tomoyuki, Kamada Takashi, Yorita Akiko, Ayabe Mitsuyoshi, Kida Hideki, Hoshino Tomoaki, Taniwaki Takayuki

    NEUROLOGY ASIA   Vol. 23 ( 3 ) page: 245 - 251   2018.9

     More details

  54. Data-driven drug discovery and repositioning by machine learning methods

    Yamanishi Yoshihiro

    ABSTRACTS OF PAPERS OF THE AMERICAN CHEMICAL SOCIETY   Vol. 256   2018.8

     More details

  55. KampoDB, database of predicted targets and functional annotations of natural medicines Reviewed International journal

    Ryusuke Sawada, Michio Iwata, Masahito Umezaki, Yoshihiko Usui, Toshikazu Kobayashi, Takaki Kubono, Shusaku Hayashi, Makoto Kadowaki, Yoshihiro Yamanishi

    SCIENTIFIC REPORTS   Vol. 8 ( 1 ) page: 11216 - 11216   2018.7

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:NATURE PUBLISHING GROUP  

    Natural medicines (i.e., herbal medicines, traditional formulas) are useful for treatment of multifactorial and chronic diseases. Here, we present KampoDB (http://wakanmoview.inm.u-toyama.ac.jp/kampo/), a novel platform for the analysis of natural medicines, which provides various useful scientific resources on Japanese traditional formulas Kampo medicines, constituent herbal drugs, constituent compounds, and target proteins of these constituent compounds. Potential target proteins of these constituent compounds were predicted by docking simulations and machine learning methods based on large-scale omics data (e.g., genome, proteome, metabolome, interactome). The current version of KampoDB contains 42 Kampo medicines, 54 crude drugs, 1230 constituent compounds, 460 known target proteins, and 1369 potential target proteins, and has functional annotations for biological pathways and molecular functions. KampoDB is useful for mode-of-action analysis of natural medicines and prediction of new indications for a wide range of diseases.

    DOI: 10.1038/s41598-018-29516-1

    Web of Science

    Scopus

    PubMed

  56. Predicting inhibitory and activatory drug targets by chemically and genetically perturbed transcriptome signatures Reviewed International journal

    Ryusuke Sawada, Michio Iwata, Yasuo Tabei, Haruka Yamato, Yoshihiro Yamanishi

    Scientific Reports   Vol. 8 ( 1 ) page: 156 - 156   2018.1

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:Nature Publishing Group  

    Genome-wide identification of all target proteins of drug candidate compounds is a challenging issue in drug discovery. Moreover, emerging phenotypic effects, including therapeutic and adverse effects, are heavily dependent on the inhibition or activation of target proteins. Here we propose a novel computational method for predicting inhibitory and activatory targets of drug candidate compounds. Specifically, we integrated chemically-induced and genetically-perturbed gene expression profiles in human cell lines, which avoided dependence on chemical structures of compounds or proteins. Predictive models for individual target proteins were simultaneously constructed by the joint learning algorithm based on transcriptomic changes in global patterns of gene expression profiles following chemical treatments, and following knock-down and over-expression of proteins. This method discriminates between inhibitory and activatory targets and enables accurate identification of therapeutic effects. Herein, we comprehensively predicted drug-target-disease association networks for 1,124 drugs, 829 target proteins, and 365 human diseases, and validated some of these predictions in vitro. The proposed method is expected to facilitate identification of new drug indications and potential adverse effects.

    DOI: 10.1038/s41598-017-18315-9

    Web of Science

    Scopus

    PubMed

  57. Linear and Kernel Model Construction Methods for Predicting Drug–Target Interactions in a Chemogenomic Framework International journal

    Yoshihiro Yamanishi

    Methods in Molecular Biology   Vol. 1825   page: 355 - 368   2018

     More details

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

    © 2018, Springer Science+Business Media, LLC, part of Springer Nature. Identification of drug–target interactions is a crucial process in drug discovery. In this chapter, we present protocols for recent advancements in machine learning methods for predicting drug–target interactions from heterogeneous biological data in a chemogenomic framework, in which prediction is based on the chemical structure data of drug candidate compounds and translated genomic sequence data of target candidate proteins. Most existing methods are based on either linear modeling or kernel modeling. To illustrate linear modeling, we introduce sparsity-induced binary classifiers and sparse canonical correlation analysis. To illustrate kernel modeling, we introduce pairwise kernel-based support vector machines and kernel-based distance learning. Workflows for using these techniques are presented. We also discuss the characteristics of each method and suggest some directions for future research.

    DOI: 10.1007/978-1-4939-8639-2_12

    Web of Science

    Scopus

    PubMed

  58. Scalable Alignment Kernels via Space-Efficient Feature Maps.

    Yasuo Tabei, Yoshihiro Yamanishi, Rasmus Pagh

    CoRR   Vol. abs/1802.06382   2018

     More details

    Publishing type:Research paper (scientific journal)  

    Other Link: https://dblp.uni-trier.de/db/journals/corr/corr1802.html#abs-1802-06382

  59. Sparse Modeling to Analyze Drug-Target Interaction Networks. Reviewed International journal

    Yamanishi Y

    Methods in molecular biology (Clifton, N.J.)   Vol. 1807   page: 181 - 193   2018

     More details

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

    Most drugs produce their phenotypic effects by interacting with target proteins, and understanding the molecular features that underpin drug-target interactions is crucial when designing a novel drug. In this chapter, we introduce the protocols that have driven recent advances in sparse modeling methods for analyzing drug-target interaction networks within a chemogenomic framework. In this approach, the chemical structures of candidate drug compounds are correlated with the genomic sequences of the candidate target proteins. We demonstrate the use of sparse canonical correspondence analysis and sparsity-induced binary classifiers to extract the underlying molecular features that are most strongly involved in drug-target interactions. We focus on drug chemical substructures and protein domains. Workflows for applying these methods are presented, and an application is described in detail. We consider the characteristics of each method and suggest possible directions for future research.

    DOI: 10.1007/978-1-4939-8561-6_13

    Web of Science

    Scopus

    PubMed

  60. Prediction of cancer-associated hotspot mutations that affect GPCR oligomerization

    Nemoto W., Limviphuvadh V., Maurer-Stroh S., Yamanishi Y., Yamanoi M., Toh H.

    EUROPEAN BIOPHYSICS JOURNAL WITH BIOPHYSICS LETTERS   Vol. 46   page: S169 - S169   2017.7

     More details

  61. Prediction of Cancer-Associated Hotspot Mutations that Affect GPCR Oligomerization

    Wataru Nemoto, Vachiranee Limviphuvadh, Sebastian Maurer-Stroh, Shunsuke Fujishiro, Yoshihiro Yamanishi, Yuichi Amemiya, Hiroyuki Toh

    BIOPHYSICAL JOURNAL   Vol. 112 ( 3 ) page: 292A - 292A   2017.2

     More details

    Language:English   Publisher:CELL PRESS  

    DOI: 10.1016/j.bpj.2016.11.1584

    Web of Science

  62. Elucidating the modes of action for bioactive compounds in a cell-specific manner by large-scale chemically-induced transcriptomics Reviewed International journal

    Michio Iwata, Ryusuke Sawada, Hiroaki Iwata, Masaaki Kotera, Yoshihiro Yamanishi

    SCIENTIFIC REPORTS   Vol. 7   page: 40164 - 40164   2017.1

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:NATURE PUBLISHING GROUP  

    The identification of the modes of action of bioactive compounds is a major challenge in chemical systems biology of diseases. Genome-wide expression profiling of transcriptional responses to compound treatment for human cell lines is a promising unbiased approach for the mode-of-action analysis. Here we developed a novel approach to elucidate the modes of action of bioactive compounds in a cell-specific manner using large-scale chemically-induced transcriptome data acquired from the Library of Integrated Network-based Cellular Signatures (LINCS), and analyzed 16,268 compounds and 68 human cell lines. First, we performed pathway enrichment analyses of regulated genes to reveal active pathways among 163 biological pathways. Next, we explored potential target proteins (including primary targets and off-targets) with cell-specific transcriptional similarity using chemical-protein interactome. Finally, we predicted new therapeutic indications for 461 diseases based on the target proteins. We showed the usefulness of the proposed approach in terms of prediction coverage, interpretation, and large-scale applicability, and validated the new prediction results experimentally by an in vitro cellular assay. The approach has a high potential for advancing drug discovery and repositioning.

    DOI: 10.1038/srep40164

    Web of Science

    Scopus

    PubMed

  63. GGIP: Structure and sequence-based GPCR-GPCR interaction pair predictor Reviewed International journal

    Wataru Nemoto, Yoshihiro Yamanishi, Vachiranee Limviphuvadh, Akira Saito, Hiroyuki Toh

    PROTEINS-STRUCTURE FUNCTION AND BIOINFORMATICS   Vol. 84 ( 9 ) page: 1224 - 1233   2016.9

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:WILEY-BLACKWELL  

    G Protein-Coupled Receptors (GPCRs) are important pharmaceutical targets. More than 30% of currently marketed pharmaceutical medicines target GPCRs. Numerous studies have reported that GPCRs function not only as monomers but also as homo- or hetero-dimers or higher-order molecular complexes. Many GPCRs exert a wide variety of molecular functions by forming specific combinations of GPCR subtypes. In addition, some GPCRs are reportedly associated with diseases. GPCR oligomerization is now recognized as an important event in various biological phenomena, and many researchers are investigating this subject. We have developed a support vector machine (SVM)-based method to predict interacting pairs for GPCR oligomerization, by integrating the structure and sequence information of GPCRs. The performance of our method was evaluated by the Receiver Operating Characteristic (ROC) curve. The corresponding area under the curve was 0.938. As far as we know, this is the only prediction method for interacting pairs among GPCRs. Our method could accelerate the analyses of these interactions, and contribute to the elucidation of the global structures of the GPCR networks in membranes. Proteins 2016; 84:1224-1233. (c) 2016 Wiley Periodicals, Inc.

    DOI: 10.1002/prot.25071

    Web of Science

    Scopus

    PubMed

  64. Simultaneous prediction of enzyme orthologs from chemical transformation patterns for de novo metabolic pathway reconstruction Reviewed International journal

    Yasuo Tabei, Yoshihiro Yamanishi, Masaaki Kotera

    BIOINFORMATICS   Vol. 32 ( 12 ) page: 278 - 287   2016.6

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:OXFORD UNIV PRESS  

    Motivation: Metabolic pathways are an important class of molecular networks consisting of compounds, enzymes and their interactions. The understanding of global metabolic pathways is extremely important for various applications in ecology and pharmacology. However, large parts of metabolic pathways remain unknown, and most organism-specific pathways contain many missing enzymes. Results: In this study we propose a novel method to predict the enzyme orthologs that catalyze the putative reactions to facilitate the de novo reconstruction of metabolic pathways from metabolome-scale compound sets. The algorithm detects the chemical transformation patterns of substrate-product pairs using chemical graph alignments, and constructs a set of enzyme-specific classifiers to simultaneously predict all the enzyme orthologs that could catalyze the putative reactions of the substrate-product pairs in the joint learning framework. The originality of the method lies in its ability to make predictions for thousands of enzyme orthologs simultaneously, as well as its extraction of enzyme-specific chemical transformation patterns of substrate-product pairs. We demonstrate the usefulness of the proposed method by applying it to some ten thousands of metabolic compounds, and analyze the extracted chemical transformation patterns that provide insights into the characteristics and specificities of enzymes. The proposed method will open the door to both primary (central) and secondary metabolism in genomics research, increasing research productivity to tackle a wide variety of environmental and public health matters.

    DOI: 10.1093/bioinformatics/btw260

    Web of Science

    Scopus

    PubMed

  65. Scalable partial least squares regression on grammar-compressed data matrices Reviewed

    Yasuo Tabei, Hiroto Saigo, Yoshihiro Yamanishi, Simon J. Puglisi

    Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining   Vol. 13-17-   page: 1875 - 1884   2016

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:Association for Computing Machinery  

    With massive high-dimensional data now commonplace in research and industry, there is a strong and growing demand for more scalable computational techniques for data analysis and knowledge discovery. Key to turning these data into knowledge is the ability to learn statistical models with high interpretability. Current methods for learning statistical models either produce models that are not interpretable or have prohibitive computational costs when applied to massive data. In this paper we address this need by presenting a scalable algorithm for partial least squares regression (PLS), which we call compression-based PLS (cPLS), to learn predictive linear models with a high interpretability from massive high-dimensional data. We propose a novel grammar-compressed representation of data matrices that supports fast row and column access while the data matrix is in a compressed form. The original data matrix is grammarcompressed and then the linear model in PLS is learned on the compressed data matrix, which results in a significant reduction in working space, greatly improving scalability. We experimentally test cPLS on its ability to learn linear models for classification, regression and feature extraction with various massive high-dimensional data, and show that cPLS performs superiorly in terms of prediction accuracy, computational effciency, and interpretability.

    DOI: 10.1145/2939672.2939864

    Web of Science

    Scopus

  66. Predicting target proteins for drug candidate compounds based on drug-induced gene expression data in a chemical structure-independent manner Reviewed International journal

    Yoshiyuki Hizukuri, Ryusuke Sawada, Yoshihiro Yamanishi

    BMC MEDICAL GENOMICS   Vol. 8 ( 1 ) page: 82 - 82   2015.12

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:BIOMED CENTRAL LTD  

    Background: Phenotype-based high-throughput screening is a useful technique for identifying drug candidate compounds that have a desired phenotype. However, the molecular mechanisms of the hit compounds remain unknown, and substantial effort is required to identify the target proteins associated with the phenotype.
    Methods: In this study, we propose a new method to predict target proteins of drug candidate compounds based on drug-induced gene expression data in Connectivity Map and a machine learning classification technique, which we call the "transcriptomic approach."
    Results: Unlike existing methods such as the chemogenomic approach, the transcriptomic approach enabled the prediction of target proteins without dependence on prior knowledge of compound chemical structures. The prediction accuracy of the chemogenomic approach was highly depended on compounds structure similarities in data sets. In contrast, the prediction accuracy of the transcriptomic approach was maintained at a sufficient level, even for benchmark data consisting of structurally diverse compounds.
    Conclusions: The transcriptomic approach reported here is expected to be a useful tool for structure-independent prediction of target proteins for drug candidate compounds.

    DOI: 10.1186/s12920-015-0158-1

    Web of Science

    Scopus

    PubMed

    J-GLOBAL

  67. Large-Scale Prediction of Beneficial Drug Combinations Using Drug Efficacy and Target Profiles Reviewed International journal

    Hiroaki Iwata, Ryusuke Sawada, Sayaka Mizutani, Masaaki Kotera, Yoshihiro Yamanishi

    JOURNAL OF CHEMICAL INFORMATION AND MODELING   Vol. 55 ( 12 ) page: 2705 - 2716   2015.12

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:AMER CHEMICAL SOC  

    The identification of beneficial drug combinations is a challenging issue in pharmaceutical and clinical research toward combinatorial drug therapy. In the present study, we developed a novel computational method for large-scale prediction of beneficial drug combinations using drug efficacy and target profiles. We designed an informative descriptor for each drug drug pair based on multiple drug profiles representing drug-targeted proteins and Anatomical Therapeutic Chemical Classification System codes. Then, we constructed a predictive model by learning a sparsity-induced classifier based on known drug combinations from the Orange Book and KEGG DRUG databases. Our results show that the proposed method outperforms the previous methods in terms of the accuracy of high-confidence predictions, and the extracted features are biologically meaningful. Finally, we performed a comprehensive prediction of novel drug combinations for 2,639 approved drugs, which predicted 142,988 new potentially beneficial drug drug pairs. We showed several examples of successfully predicted drug combinations for a variety of diseases.

    DOI: 10.1021/acs.jcim.5b00444

    Web of Science

    Scopus

    PubMed

    J-GLOBAL

  68. Mining Discriminative Patterns from Graph Data with Multiple Labels and Its Application to Quantitative Structure-Activity Relationship (QSAR) Models Reviewed International journal

    Zheng Shao, Yuya Hirayama, Yoshihiro Yamanishi, Hiroto Saigo

    JOURNAL OF CHEMICAL INFORMATION AND MODELING   Vol. 55 ( 12 ) page: 2519 - 2527   2015.12

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:AMER CHEMICAL SOC  

    Graph data are becoming increasingly common in machine learning and data mining, and its application field pervades to bioinformatics and cheminformatics. Accordingly, as a method to extract patterns from graph data, graph mining recently has been studied and developed rapidly. Since the number of patterns in graph data is huge, a central issue is how to efficiently collect informative patterns suitable for subsequent tasks such as classification or regression. In this paper, we consider mining discriminative subgraphs from graph data with multiple labels. The resulting task has important applications in cheminformatics, such as finding common functional groups that trigger multiple drug side effects, or identifying ligand functional groups that hit multiple targets. In computational experiments, we first verify the effectiveness of the proposed approach in synthetic data, then we apply it to drug adverse effect prediction problem. In the latter dataset, we compared the proposed method with L1-norm logistic regression in combination with the PubChem/Open Babel fingerprint, in that the proposed method showed superior performance with a much smaller number of subgraph patterns. Software is available from https://github.com/axot/GLP.

    DOI: 10.1021/acs.jcim.5b00376

    Web of Science

    Scopus

    PubMed

    J-GLOBAL

  69. Target-Based Drug Repositioning Using Large-Scale Chemical-Protein Interactome Data Reviewed International journal

    Ryusuke Sawada, Hiroaki Iwata, Sayaka Mizutani, Yoshihiro Yamanishi

    JOURNAL OF CHEMICAL INFORMATION AND MODELING   Vol. 55 ( 12 ) page: 2717 - 2730   2015.12

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:AMER CHEMICAL SOC  

    Drug repositioning, or the identification of new indications for known drugs, is a useful strategy for drug discovery. In this study, we developed novel computational methods to predict potential drug targets and new drug indications for systematic drug repositioning using large-scale chemical-protein interactome data. We explored the target space of drugs (including primary targets and off-targets) based on chemical structure similarity and phenotypic effect similarity by making optimal use of millions of compound-protein interactions. On the basis of the target profiles of drugs, we constructed statistical models to predict new drug indications for a wide range of diseases with various molecular features. The proposed method outperformed previous methods in terms of interpretability, applicability, and accuracy. Finally, we conducted a comprehensive prediction of the drug-target-disease association network for 8270 drugs and 1401 diseases and showed biologically meaningful examples of newly predicted drug targets and drug indications. The predictive model is useful to understand the mechanisms of the predicted drug indications.

    DOI: 10.1021/acs.jcim.5b00330

    Web of Science

    Scopus

    PubMed

    J-GLOBAL

  70. Metabolome-scale de novo pathway reconstruction using regioisomer-sensitive graph alignments Reviewed International journal

    Yoshihiro Yamanishi, Yasuo Tabei, Masaaki Kotera

    BIOINFORMATICS   Vol. 31 ( 12 ) page: 161 - 170   2015.6

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:OXFORD UNIV PRESS  

    Motivation: Recent advances in mass spectrometry and related metabolomics technologies have enabled the rapid and comprehensive analysis of numerous metabolites. However, biosynthetic and biodegradation pathways are only known for a small portion of metabolites, with most metabolic pathways remaining uncharacterized.
    Results: In this study, we developed a novel method for supervised de novo metabolic pathway reconstruction with an improved graph alignment-based approach in the reaction-filling framework. We proposed a novel chemical graph alignment algorithm, which we called PACHA (Pairwise Chemical Aligner), to detect the regioisomer-sensitive connectivities between the aligned substructures of two compounds. Unlike other existing graph alignment methods, PACHA can efficiently detect only one common subgraph between two compounds. Our results show that the proposed method outperforms previous descriptor-based methods or existing graph alignment-based methods in the enzymatic reaction-likeness prediction for isomer-enriched reactions. It is also useful for reaction annotation that assigns potential reaction characteristics such as EC (Enzyme Commission) numbers and PIERO (Enzymatic Reaction Ontology for Partial Information) terms to substrate-product pairs. Finally, we conducted a comprehensive enzymatic reaction-likeness prediction for all possible uncharacterized compound pairs, suggesting potential metabolic pathways for newly predicted substrate-product pairs.

    DOI: 10.1093/bioinformatics/btv224

    Web of Science

    Scopus

    PubMed

    J-GLOBAL

  71. Systematic Drug Repositioning for a Wide Range of Diseases with Integrative Analyses of Phenotypic and Molecular Data Reviewed International journal

    Hiroaki Iwata, Ryusuke Sawada, Sayaka Mizutani, Yoshihiro Yamanishi

    JOURNAL OF CHEMICAL INFORMATION AND MODELING   Vol. 55 ( 2 ) page: 446 - 459   2015.2

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:AMER CHEMICAL SOC  

    Drug repositioning, or the appslication of known drugs to new indications, is a challenging issue in pharmaceutical science. In this study, we developed a new computational method to predict unknown drug indications for systematic drug repositioning in a framework of supervised network inference. We defined a descriptor for each drug-disease pair based on the phenotypic features of drugs (e.g., medicinal effects and side effects) and various molecular features of diseases (e.g., disease-causing genes, diagnostic markers, disease-related pathways, and environmental factors) and constructed a statistical model to predict new drug-disease associations for a wide range of diseases in the International Classification of Diseases. Our results show that the proposed method outperforms previous methods in terms of accuracy and applicability, and its performance does not depend on drug chemical structure similarity. Finally, we performed a comprehensive prediction of a drug-disease association network consisting of 2349 drugs and 858 diseases and described biologically meaningful examples of newly predicted drug indications for several types of cancers and nonhereditary diseases.

    DOI: 10.1021/ci500670q

    Web of Science

    Scopus

    PubMed

    J-GLOBAL

  72. Statistical Methods to Predict Drug Side-Effects

    Yamanishi Yoshihiro

    POST-GENOMIC APPROACHES IN DRUG AND VACCINE DEVELOPMENT   Vol. 5   page: 391 - 405   2015

     More details

  73. Benchmarking a Wide Range of Chemical Descriptors for Drug-Target Interaction Prediction Using a Chemogenomic Approach Reviewed International journal

    Ryusuke Sawada, Masaaki Kotera, Yoshihiro Yamanishi

    MOLECULAR INFORMATICS   Vol. 33 ( 11-12 ) page: 719 - 731   2014.12

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:WILEY-V C H VERLAG GMBH  

    The identification of drug-target interactions, or interactions between drug candidate compounds and target candidate proteins, is a crucial process in genomic drug discovery. In silico chemogenomic methods are recently recognized as a promising approach for genome-wide scale prediction of drug-target interactions, but the prediction performance depends heavily on the descriptors and similarity measures of drugs and proteins. In this paper, we investigated the performance of various descriptors and similarity measures of drugs and proteins for the drug-target interaction prediction using a chemogenomic approach. We compared the prediction accuracy of 18 chemical descriptors of drugs (e.g., ECFP, FCFP, E-state, CDK, Klekota-Roth, MACCS, PubChem, Dragon, KCF-S, and graph kernels) and 4 descriptors of proteins (e.g., amino acid composition, domain profile, local sequence similarity, and string kernel) on about one hundred thousand drug-target interactions. We examined the combinatorial effects of drug descriptors and protein descriptors using the same benchmark data under several experimental conditions. Large-scale experiments showed that our proposed KCF-S descriptor worked the best in terms of prediction accuracy. The comparative results are expected to be useful for selecting chemical descriptors in various pharmaceutical applications.

    DOI: 10.1002/minf.201400066

    Web of Science

    Scopus

    PubMed

  74. DINIES: drug-target interaction network inference engine based on supervised analysis Reviewed International journal

    Yoshihiro Yamanishi, Masaaki Kotera, Yuki Moriya, Ryusuke Sawada, Minoru Kanehisa, Susumu Goto

    NUCLEIC ACIDS RESEARCH   Vol. 42 ( W1 ) page: W39 - W45   2014.7

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:OXFORD UNIV PRESS  

    DINIES (drug-target interaction network inference engine based on supervised analysis) is a web server for predicting unknown drug-target interaction networks from various types of biological data (e.g. chemical structures, drug side effects, amino acid sequences and protein domains) in the framework of supervised network inference. The originality of DINIES lies in prediction with state-of-the-art machine learning methods, in the integration of heterogeneous biological data and in compatibility with the KEGG database. The DINIES server accepts any 'profiles' or precalculated similarity matrices (or 'kernels') of drugs and target proteins in tab-delimited file format. When a training data set is submitted to learn a predictive model, users can select either known interaction information in the KEGG DRUG database or their own interaction data. The user can also select an algorithm for supervised network inference, select various parameters in the method and specify weights for heterogeneous data integration. The server can provide integrative analyses with useful components in KEGG, such as biological pathways, functional hierarchy and human diseases.

    DOI: 10.1093/nar/gku337

    Web of Science

    Scopus

    PubMed

    J-GLOBAL

  75. Metabolome-scale prediction of intermediate compounds in multistep metabolic pathways with a recursive supervised approach Reviewed International journal

    Masaaki Kotera, Yasuo Tabei, Yoshihiro Yamanishi, Ai Muto, Yuki Moriya, Toshiaki Tokimatsu, Susumu Goto

    BIOINFORMATICS   Vol. 30 ( 12 ) page: 165 - 174   2014.6

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:OXFORD UNIV PRESS  

    Motivation: Metabolic pathway analysis is crucial not only in metabolic engineering but also in rational drug design. However, the biosynthetic/ biodegradation pathways are known only for a small portion of metabolites, and a vast amount of pathways remain uncharacterized. Therefore, an important challenge in metabolomics is the de novo reconstruction of potential reaction networks on a metabolome-scale.
    Results: In this article, we develop a novel method to predict the multistep reaction sequences for de novo reconstruction of metabolic pathways in the reaction-filling framework. We propose a supervised approach to learn what we refer to as 'multistep reaction sequence likeness', i.e. whether a compound-compound pair is possibly converted to each other by a sequence of enzymatic reactions. In the algorithm, we propose a recursive procedure of using step-specific classifiers to predict the intermediate compounds in the multistep reaction sequences, based on chemical substructure fingerprints/ descriptors of compounds. We further demonstrate the usefulness of our proposed method on the prediction of enzymatic reaction networks from a metabolome-scale compound set and discuss characteristic features of the extracted chemical substructure transformation patterns in multistep reaction sequences. Our comprehensively predicted reaction networks help to fill the metabolic gap and to infer new reaction sequences in metabolic pathways.

    DOI: 10.1093/bioinformatics/btu265

    Web of Science

    Scopus

    PubMed

    J-GLOBAL

  76. 2P270 GGIP : GPCR-GPCR Interaction Pair Predictor(22A. Bioinformatics:Structural genomics,Poster)

    Nemoto Wataru, Yamanishi Yoshihiro, Vachiranee Limviphuvadh, Toh Hiroyuki

    Seibutsu Butsuri   Vol. 54 ( 1 ) page: S239   2014

     More details

    Language:English   Publisher:The Biophysical Society of Japan General Incorporated Association  

    DOI: 10.2142/biophys.54.S239_6

  77. Inferring protein domains associated with drug side effects based on drug-target interaction network Reviewed International journal

    Hiroaki Iwata, Sayaka Mizutani, Yasuo Tabei, Masaaki Kotera, Susumu Goto, Yoshihiro Yamanishi

    BMC SYSTEMS BIOLOGY   Vol. 7 ( S-6 ) page: 18 - 18   2013.12

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:BIOMED CENTRAL LTD  

    Background: Most phenotypic effects of drugs are involved in the interactions between drugs and their target proteins, however, our knowledge about the molecular mechanism of the drug-target interactions is very limited. One of challenging issues in recent pharmaceutical science is to identify the underlying molecular features which govern drug-target interactions.
    Results: In this paper, we make a systematic analysis of the correlation between drug side effects and protein domains, which we call "pharmacogenomic features," based on the drug-target interaction network. We detect drug side effects and protein domains that appear jointly in known drug-target interactions, which is made possible by using classifiers with sparse models. It is shown that the inferred pharmacogenomic features can be used for predicting potential drug-target interactions. We also discuss advantages and limitations of the pharmacogenomic features, compared with the chemogenomic features that are the associations between drug chemical substructures and protein domains.
    Conclusion: The inferred side effect-domain association network is expected to be useful for estimating common drug side effects for different protein families and characteristic drug side effects for specific protein domains.

    DOI: 10.1186/1752-0509-7-S6-S18

    Web of Science

    PubMed

    J-GLOBAL

  78. KCF-S: KEGG Chemical Function and Substructure for improved interpretability and prediction in chemical bioinformatics Reviewed International journal

    Masaaki Kotera, Yasuo Tabei, Yoshihiro Yamanishi, Yuki Moriya, Toshiaki Tokimatsu, Minoru Kanehisa, Susumu Goto

    BMC SYSTEMS BIOLOGY   Vol. 7 ( S-6 ) page: S2 - 2   2013.12

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:BIOMED CENTRAL LTD  

    Background: In order to develop hypothesis on unknown metabolic pathways, biochemists frequently rely on literature that uses a free-text format to describe functional groups or substructures. In computational chemistry or cheminformatics, molecules are typically represented by chemical descriptors, i.e., vectors that summarize information on its various properties. However, it is difficult to interpret these chemical descriptors since they are not directly linked to the terminology of functional groups or substructures that the biochemists use.
    Methods: In this study, we used KEGG Chemical Function (KCF) format to computationally describe biochemical substructures in seven attributes that resemble biochemists' way of dealing with substructures.
    Results: We established KCF-S (KCF-and-Substructures) format as an additional structural information of KCF. Applying KCF-S revealed the specific appearance of substructures from various datasets of molecules that describes the characteristics of the respective datasets. Structure-based clustering of molecules using KCF-S resulted the clusters in which molecular weights and structures were less diverse than those obtained by conventional chemical fingerprints. We further applied KCF-S to find the pairs of molecules that are possibly converted to each other in enzymatic reactions, and KCF-S clearly improved predictive performance than that presented previously.
    Conclusions: KCF-S defines biochemical substructures with keeping interpretability, suggesting the potential to apply more studies on chemical bioinformatics. KCF and KCF-S can be automatically converted from Molfile format, enabling to deal with molecules from any data sources.

    DOI: 10.1186/1752-0509-7-S6-S2

    Web of Science

    Scopus

    PubMed

  79. Scalable prediction of compound-protein interactions using minwise hashing Reviewed International journal

    Yasuo Tabei, Yoshihiro Yamanishi

    BMC Systems Biology   Vol. 7 ( S-6 ) page: S3 - 3   2013.12

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:BioMed Central Ltd.  

    The identification of compound-protein interactions plays key roles in the drug development toward discovery of new drug leads and new therapeutic protein targets. There is therefore a strong incentive to develop new efficient methods for predicting compound-protein interactions on a genome-wide scale. In this paper we develop a novel chemogenomic method to make a scalable prediction of compound-protein interactions from heterogeneous biological data using minwise hashing. The proposed method mainly consists of two steps: 1) construction of new compact fingerprints for compound-protein pairs by an improved minwise hashing algorithm, and 2) application of a sparsity-induced classifier to the compact fingerprints. We test the proposed method on its ability to make a large-scale prediction of compound-protein interactions from compound substructure fingerprints and protein domain fingerprints, and show superior performance of the proposed method compared with the previous chemogenomic methods in terms of prediction accuracy, computational efficiency, and interpretability of the predictive model. All the previously developed methods are not computationally feasible for the full dataset consisting of about 200 millions of compound-protein pairs. The proposed method is expected to be useful for virtual screening of a huge number of compounds against many protein targets.

    DOI: 10.1186/1752-0509-7-S6-S3

    Web of Science

    Scopus

    PubMed

  80. Inferring Chemogenomic Features from Drug-Target Interaction Networks Reviewed International journal

    Yoshihiro Yamanishi

    MOLECULAR INFORMATICS   Vol. 32 ( 11-12 ) page: 991 - 999   2013.12

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:WILEY-V C H VERLAG GMBH  

    Drug effects are mainly caused by the interactions between drug molecules and target proteins including primary targets and off-targets. Understanding of the molecular mechanisms behind overall drugtarget interactions is crucial in the drug design process. In this paper we review recently developed methods to infer chemogenomic features (the underlying associations between drug chemical substructures and protein domains) which are strongly involved in drug-target interaction networks. We show the usefulness of the methods to detect ligand chemical fragments specific for each protein domain and ligand core substructures important for a wide range of protein families. We also discuss how to use the chemogenomic features for predicting unknown drug-target interactions on a large scale.

    DOI: 10.1002/minf.201300079

    Web of Science

    Scopus

    PubMed

  81. Succinct interval-splitting tree for scalable similarity search of compound-protein pairs with property constraints Reviewed

    Yasuo Tabei, Akihiro Kishimoto, Masaaki Kotera, Yoshihiro Yamanishi

    Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining   Vol. 128815   page: 176 - 184   2013.8

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:Association for Computing Machinery  

    Analyzing functional interactions between small compounds and proteins is indispensable in genomic drug discovery. Since rich information on various compound-protein interactions is available in recent molecular databases, strong demands for making best use of such databases require to invent powerful methods to help us find new functional compoundprotein pairs on a large scale. We present the succinct interval-splitting tree algorithm (SITA) that efficiently performs similarity search in databases for compound-protein pairs with respect to both binary fingerprints and real-valued properties. SITA achieves both time and space efficiency by developing the data structure called interval-splitting trees, which enables to efficiently prune the useless portions of search space, and by incorporating the ideas behind wavelet tree, a succinct data structure to compactly represent trees. We experimentally test SITA on the ability to retrieve similar compound-protein pairs/substrate-product pairs for a query from large databases with over 200 million compoundprotein pairs/substrate-product pairs and show that SITA performs better than other possible approaches.

    DOI: 10.1145/2487575.2487637

    Scopus

    Other Link: http://dblp.uni-trier.de/db/conf/kdd/kdd2013.html#conf/kdd/TabeiKKY13

  82. Supervised de novo reconstruction of metabolic pathways from metabolome-scale compound sets Reviewed International journal

    Masaaki Kotera, Yasuo Tabei, Yoshihiro Yamanishi, Toshiaki Tokimatsu, Susumu Goto

    BIOINFORMATICS   Vol. 29 ( 13 ) page: 135 - 144   2013.7

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:OXFORD UNIV PRESS  

    Motivation: The metabolic pathway is an important biochemical reaction network involving enzymatic reactions among chemical compounds. However, it is assumed that a large number of metabolic pathways remain unknown, and many reactions are still missing even in known pathways. Therefore, the most important challenge in metabolomics is the automated de novo reconstruction of metabolic pathways, which includes the elucidation of previously unknown reactions to bridge the metabolic gaps.
    Results: In this article, we develop a novel method to reconstruct metabolic pathways from a large compound set in the reaction-filling framework. We define feature vectors representing the chemical transformation patterns of compound-compound pairs in enzymatic reactions using chemical fingerprints. We apply a sparsity-induced classifier to learn what we refer to as 'enzymatic-reaction likeness', i.e. whether compound pairs are possibly converted to each other by enzymatic reactions. The originality of our method lies in the search for potential reactions among many compounds at a time, in the extraction of reaction-related chemical transformation patterns and in the large-scale applicability owing to the computational efficiency. In the results, we demonstrate the usefulness of our proposed method on the de novo reconstruction of 134 metabolic pathways in Kyoto Encyclopedia of Genes and Genomes (KEGG). Our comprehensively predicted reaction networks of 15 698 compounds enable us to suggest many potential pathways and to increase research productivity in metabolomics.

    DOI: 10.1093/bioinformatics/btt244

    Web of Science

    Scopus

    PubMed

    J-GLOBAL

  83. スパース統計モデルによる薬物-疾患ネットワークの予測(合同企画セッション:バイオデータマイニング)

    岩田 浩明, 山西 芳裕

    電子情報通信学会技術研究報告. NC, ニューロコンピューティング   Vol. 113 ( 111 ) page: 155   2013.6

     More details

    Language:Japanese   Publisher:一般社団法人電子情報通信学会  

    近年の新薬開発の行き詰まりを打開する方法として、既存薬の作用を徹底的に調べあげ新たに薬効を見つけ出し、本来それが開発された疾患とは別の疾患に対する治療薬として再開発する創薬研究が注目を浴びている。本研究では、薬物に関するケミカルなデータと疾患に関するフェノタイプのデータから潜在的な薬物と疾患の関係を網羅的に予測する機械学習の手法を開発した。教師付き学習のアルゴリズムにスパース統計モデルを導入することで特徴抽出を可能にし、予測された関係に関与している薬物の標的タンパク質と疾患のフェノタイプの組み合わせを同定する点が独自の点である。また抽出された標的タンパク質の生物学的妥当性をPathway Enrichment解析を用いて評価した。本発表ではこれらの結果と、既知のデータから学習して生成したモデルを適用することで得られる新規の薬と疾患の関連解析の結果について紹介する。

    CiNii Research

  84. KEGG OC: a large-scale automatic construction of taxonomy-based ortholog clusters Reviewed International journal

    Akihiro Nakaya, Toshiaki Katayama, Masumi Itoh, Kazushi Hiranuka, Shuichi Kawashima, Yuki Moriya, Shujiro Okuda, Michihiro Tanaka, Toshiaki Tokimatsu, Yoshihiro Yamanishi, Akiyasu C. Yoshizawa, Minoru Kanehisa, Susumu Goto

    NUCLEIC ACIDS RESEARCH   Vol. 41 ( D1 ) page: D353 - D357   2013.1

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:OXFORD UNIV PRESS  

    The identification of orthologous genes in an increasing number of fully sequenced genomes is a challenging issue in recent genome science. Here we present KEGG OC (http://www.genome.jp/tools/oc/), a novel database of ortholog clusters (OCs). The current version of KEGG OC contains 1 176 030 OCs, obtained by clustering 8 357 175 genes in 2112 complete genomes (153 eukaryotes, 1830 bacteria and 129 archaea). The OCs were constructed by applying the quasi-clique-based clustering method to all possible protein coding genes in all complete genomes, based on their amino acid sequence similarities. It is computationally efficient to calculate OCs, which enables to regularly update the contents. KEGG OC has the following two features: (i) It consists of all complete genomes of a wide variety of organisms from three domains of life, and the number of organisms is the largest among the existing databases; and (ii) It is compatible with the KEGG database by sharing the same sets of genes and identifiers, which leads to seamless integration of OCs with useful components in KEGG such as biological pathways, pathway modules, functional hierarchy, diseases and drugs. The KEGG OC resources are accessible via OC Viewer that provides an interactive visualization of OCs at different taxonomic levels.

    DOI: 10.1093/nar/gks1239

    Web of Science

    Scopus

    PubMed

    J-GLOBAL

  85. Chemogenomic approaches to infer drug-target interaction networks. Reviewed International journal

    Yamanishi Y

    Methods in molecular biology (Clifton, N.J.)   Vol. 939   page: 97 - 113   2013

     More details

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

    The identification of drug-target interactions from heterogeneous biological data is critical in the drug development. In this chapter, we review recently developed in silico chemogenomic approaches to infer unknown drug-target interactions from chemical information of drugs and genomic information of target proteins. We review several kernel-based statistical methods from two different viewpoints: binary classification and dimension reduction. In the results, we demonstrate the usefulness of the methods on the prediction of drug-target interactions from chemical structure data and genomic sequence data. We also discuss the characteristics of each method, and show some perspectives toward future research direction.

    DOI: 10.1007/978-1-62703-107-3_9

    PubMed

  86. Succinct Interval-Splitting Tree for Scalable Similarity Search of Compound-Protein Pairs with Property Constraints

    Tabei Yasuo, Kishimoto Akihiro, Kotera Masaaki, Yamanishi Yoshihiro

    19TH ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING (KDD'13)     page: 176 - 184   2013

     More details

  87. Drug Side-Effect Prediction Based on the Integration of Chemical and Biological Spaces Reviewed International journal

    Yoshihiro Yamanishi, Edouard Pauwels, Masaaki Kotera

    JOURNAL OF CHEMICAL INFORMATION AND MODELING   Vol. 52 ( 12 ) page: 3284 - 3292   2012.12

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:AMER CHEMICAL SOC  

    Drug side-effects, or adverse drug reactions, have become a major public health concern and remain one of the main causes of drug failure and of drug withdrawal once they have reached the market. Therefore, the identification of potential severe side-effects is a challenging issue. In this paper, we develop a new method to predict potential side-effect profiles of drug candidate molecules based on their chemical structures and target protein information on a large scale. We propose several extensions of kernel regression model for multiple responses to deal with heterogeneous data sources. The originality lies in the integration of the chemical space of drug chemical structures and the biological space of drug target proteins in a unified framework. As a result, we demonstrate the usefulness of the proposed method on the simultaneous prediction of 969 side-effects for approved drugs from their chemical substructure and target protein profiles and show that the prediction accuracy consistently improves owing to the proposed regression model and integration of chemical and biological information. We also conduct a comprehensive side-effect prediction for uncharacterized drug molecules stored in DrugBank and confirm interesting predictions using independent information sources. The proposed method is expected to be useful at many stages of the drug development process.

    DOI: 10.1021/ci2005548

    Web of Science

    Scopus

    PubMed

    J-GLOBAL

  88. Drug target prediction using adverse event report systems: a pharmacogenomic approach Reviewed International journal

    Masataka Takarabe, Masaaki Kotera, Yosuke Nishimura, Susumu Goto, Yoshihiro Yamanishi

    BIOINFORMATICS   Vol. 28 ( 18 ) page: I611 - I618   2012.9

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:OXFORD UNIV PRESS  

    Motivation: Unexpected drug activities derived from off-targets are usually undesired and harmful; however, they can occasionally be beneficial for different therapeutic indications. There are many uncharacterized drugs whose target proteins (including the primary target and off-targets) remain unknown. The identification of all potential drug targets has become an important issue in drug repositioning to reuse known drugs for new therapeutic indications.
    Results: We defined pharmacological similarity for all possible drugs using the US Food and Drug Administration's (FDA's) adverse event reporting system (AERS) and developed a new method to predict unknown drug-target interactions on a large scale from the integration of pharmacological similarity of drugs and genomic sequence similarity of target proteins in the framework of a pharmacogenomic approach. The proposed method was applicable to a large number of drugs and it was useful especially for predicting unknown drug-target interactions that could not be expected from drug chemical structures. We made a comprehensive prediction for potential off-targets of 1874 drugs with known targets and potential target profiles of 2519 drugs without known targets, which suggests many potential drug-target interactions that were not predicted by previous chemogenomic or pharmacogenomic approaches.

    DOI: 10.1093/bioinformatics/bts413

    Web of Science

    Scopus

    PubMed

    J-GLOBAL

  89. Identification of chemogenomic features from drug-target interaction networks using interpretable classifiers Reviewed International journal

    Yasuo Tabei, Edouard Pauwels, Veronique Stoven, Kazuhiro Takemoto, Yoshihiro Yamanishi

    BIOINFORMATICS   Vol. 28 ( 18 ) page: I487 - I494   2012.9

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:OXFORD UNIV PRESS  

    Motivation: Drug effects are mainly caused by the interactions between drug molecules and their target proteins including primary targets and off-targets. Identification of the molecular mechanisms behind overall drug-target interactions is crucial in the drug design
    Results: We develop a classifier-based approach to identify chemogenomic features (the underlying associations between drug chemical substructures and protein domains) that are involved in drug-target interaction networks. We propose a novel algorithm for extracting informative chemogenomic features by using L-1 regularized classifiers over the tensor product space of possible drug-target pairs. It is shown that the proposed method can extract a very limited number of chemogenomic features without loosing the performance of predicting drug-target interactions and the extracted features are biologically meaningful. The extracted substructure-domain association network enables us to suggest ligand chemical fragments specific for each protein domain and ligand core substructures important for a wide range of protein families.

    DOI: 10.1093/bioinformatics/bts412

    Web of Science

    Scopus

    PubMed

    J-GLOBAL

  90. Relating drug-protein interaction network with drug side effects Reviewed International journal

    Sayaka Mizutani, Edouard Pauwels, Veronique Stoven, Susumu Goto, Yoshihiro Yamanishi

    BIOINFORMATICS   Vol. 28 ( 18 ) page: I522 - I528   2012.9

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:OXFORD UNIV PRESS  

    Motivation: Identifying the emergence and underlying mechanisms of drug side effects is a challenging task in the drug development process. This underscores the importance of system-wide approaches for linking different scales of drug actions; namely drug-protein interactions (molecular scale) and side effects (phenotypic scale) toward side effect prediction for uncharacterized drugs.
    Results: We performed a large-scale analysis to extract correlated sets of targeted proteins and side effects, based on the co-occurrence of drugs in protein-binding profiles and side effect profiles, using sparse canonical correlation analysis. The analysis of 658 drugs with the two profiles for 1368 proteins and 1339 side effects led to the extraction of 80 correlated sets. Enrichment analyses using KEGG and Gene Ontology showed that most of the correlated sets were significantly enriched with proteins that are involved in the same biological pathways, even if their molecular functions are different. This allowed for a biologically relevant interpretation regarding the relationship between drug-targeted proteins and side effects. The extracted side effects can be regarded as possible phenotypic outcomes by drugs targeting the proteins that appear in the same correlated set. The proposed method is expected to be useful for predicting potential side effects of new drug candidate compounds based on their protein-binding profiles.

    DOI: 10.1093/bioinformatics/bts383

    Web of Science

    Scopus

    PubMed

    J-GLOBAL

  91. GENIES: gene network inference engine based on supervised analysis Reviewed International journal

    Masaaki Kotera, Yoshihiro Yamanishi, Yuki Moriya, Minoru Kanehisa, Susumu Goto

    NUCLEIC ACIDS RESEARCH   Vol. 40 ( W1 ) page: W162 - W167   2012.7

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:OXFORD UNIV PRESS  

    Gene network inference engine based on supervised analysis (GENIES) is a web server to predict unknown part of gene network from various types of genome-wide data in the framework of supervised network inference. The originality of GENIES lies in the construction of a predictive model using partially known network information and in the integration of heterogeneous data with kernel methods. The GENIES server accepts any 'profiles' of genes or proteins (e.g. gene expression profiles, protein subcellular localization profiles and phylogenetic profiles) or pre-calculated gene-gene similarity matrices (or 'kernels') in the tab-delimited file format. As a training data set to learn a predictive model, the users can choose either known molecular network information in the KEGG PATHWAY database or their own gene network data. The user can also select an algorithm of supervised network inference, choose various parameters in the method, and control the weights of heterogeneous data integration. The server provides the list of newly predicted gene pairs, maps the predicted gene pairs onto the associated pathway diagrams in KEGG PATHWAY and indicates candidate genes for missing enzymes in organism-specific metabolic pathways. GENIES (http://www.genome.jp/tools/genies/) is publicly available as one of the genome analysis tools in GenomeNet.

    DOI: 10.1093/nar/gks459

    Web of Science

    Scopus

    PubMed

    J-GLOBAL

  92. Network Completion Using Dynamic Programming and Least-Squares Fitting Reviewed International journal

    Natsu Nakajima, Takeyuki Tamura, Yoshihiro Yamanishi, Katsuhisa Horimoto, Tatsuya Akutsu

    SCIENTIFIC WORLD JOURNAL   Vol. 2012   page: 957620 - 957620   2012

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:HINDAWI LTD  

    We consider the problem of network completion, which is to make the minimum amount of modifications to a given network so that the resulting network is most consistent with the observed data. We employ here a certain type of differential equations as gene regulation rules in a genetic network, gene expression time series data as observed data, and deletions and additions of edges as basic modification operations. In addition, we assume that the numbers of deleted and added edges are specified. For this problem, we present a novel method using dynamic programming and least-squares fitting and show that it outputs a network with the minimum sum squared error in polynomial time if the maximum indegree of the network is bounded by a constant. We also perform computational experiments using both artificially generated and real gene expression time series data.

    DOI: 10.1100/2012/957620

    Web of Science

    Scopus

    PubMed

    J-GLOBAL

  93. Predicting drug side-effect profiles: a chemical fragment-based approach Reviewed International journal

    Edouard Pauwels, Veronique Stoven, Yoshihiro Yamanishi

    BMC BIOINFORMATICS   Vol. 12   page: 169 - 169   2011.5

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:BIOMED CENTRAL LTD  

    Background: Drug side-effects, or adverse drug reactions, have become a major public health concern. It is one of the main causes of failure in the process of drug development, and of drug withdrawal once they have reached the market. Therefore, in silico prediction of potential side-effects early in the drug discovery process, before reaching the clinical stages, is of great interest to improve this long and expensive process and to provide new efficient and safe therapies for patients.
    Results: In the present work, we propose a new method to predict potential side-effects of drug candidate molecules based on their chemical structures, applicable on large molecular databanks. A unique feature of the proposed method is its ability to extract correlated sets of chemical substructures (or chemical fragments) and side-effects. This is made possible using sparse canonical correlation analysis (SCCA). In the results, we show the usefulness of the proposed method by predicting 1385 side-effects in the SIDER database from the chemical structures of 888 approved drugs. These predictions are performed with simultaneous extraction of correlated ensembles formed by a set of chemical substructures shared by drugs that are likely to have a set of side-effects. We also conduct a comprehensive side-effect prediction for many uncharacterized drug molecules stored in DrugBank, and were able to confirm interesting predictions using independent source of information.
    Conclusions: The proposed method is expected to be useful in various stages of the drug development process.

    DOI: 10.1186/1471-2105-12-169

    Web of Science

    Scopus

    PubMed

    J-GLOBAL

  94. Extracting Sets of Chemical Substructures and Protein Domains Governing Drug-Target Interactions Reviewed International journal

    Yoshihiro Yamanishi, Edouard Pauwels, Hiroto Saigo, Veronique Stovent

    JOURNAL OF CHEMICAL INFORMATION AND MODELING   Vol. 51 ( 5 ) page: 1183 - 1194   2011.5

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:AMER CHEMICAL SOC  

    The identification of rules governing molecular recognition between drug chemical substructures and protein functional sites is a challenging issue at many stages of the drug development process. In this paper we develop a novel method to extract sets of drug chemical substructures and protein domains that govern drug-target interactions on a genome-wide scale. This is made possible using sparse canonical correspondence analysis (SCCA) for analyzing drug substructure profiles and protein domain profiles simultaneously. The method does not depend on the availability of protein 3D structures. From a data set of known drug-target interactions including enzymes, ion channels, G protein-coupled receptors, and nuclear receptors, we extract a set of chemical substructures shared by drugs able to bind to a set of protein domains. These two sets of extracted chemical substructures and protein domains form components that can be further exploited in a drug discovery process. This approach successfully clusters protein domains that may be evolutionary unrelated but that bind a common set of chemical substructures. As shown in several examples, it can also be very helpful for predicting new protein-ligand interactions and addressing the problem of ligand specificity. The proposed method constitutes a contribution to the recent field of chemogenomics that aims to connect the chemical space with the biological space.

    DOI: 10.1021/ci100476q

    Web of Science

    Scopus

    PubMed

    J-GLOBAL

  95. Prediction of compound-protein interactions with machine learning methods Reviewed

    Yoshihiro Yamanishi, Hisashi Kashima

    Chemoinformatics and Advanced Machine Learning Perspectives: Complex Computational Methods and Collaborative Techniques     page: 304 - 317   2011

     More details

    Language:English   Publishing type:Part of collection (book)   Publisher:IGI Global  

    In silico prediction of compound-protein interactions from heterogeneous biological data is critical in the process of drug development. In this chapter the authors review several supervised machine learning methods to predict unknown compound-protein interactions from chemical structure and genomic sequence information simultaneously. The authors review several kernel-based algorithms from two different viewpoints: binary classification and dimension reduction. In the results, they demonstrate the usefulness of the methods on the prediction of drug-target interactions and ligand-protein interactions from chemical structure data and genomic sequence data. © 2011, IGI Global.

    DOI: 10.4018/978-1-61520-911-8.ch016

    Web of Science

    Scopus

  96. Chemoinformatics and Advanced Machine Learning Perspectives: Complex Computational Methods and Collaborative Techniques Preface

    Lodhi Huma, Yamanishi Yoshihiro

    CHEMOINFORMATICS AND ADVANCED MACHINE LEARNING PERSPECTIVES: COMPLEX COMPUTATIONAL METHODS AND COLLABORATIVE TECHNIQUES     page: XV - XVI   2011

     More details

  97. Preface

    Lodhi H., Yamanishi Y.

    Chemoinformatics and Advanced Machine Learning Perspectives: Complex Computational Methods and Collaborative Techniques     2010.12

     More details

    Publisher:Chemoinformatics and Advanced Machine Learning Perspectives: Complex Computational Methods and Collaborative Techniques  

    DOI: 10.4018/978-1-61520-911-8

    Scopus

  98. Cartesian Kernel: An Efficient Alternative to the Pairwise Kernel Reviewed

    Hisashi Kashima, Satoshi Oyama, Yoshihiro Yamanishi, Koji Tsuda

    IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS   Vol. E93D ( 10 ) page: 2672 - 2679   2010.10

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:IEICE-INST ELECTRONICS INFORMATION COMMUNICATIONS ENG  

    Pairwise classification has many applications including network prediction, entity resolution, and collaborative filtering. The pairwise kernel has been proposed for those purposes by several research groups independently, and has been used successfully in several fields. In this paper, we propose an efficient alternative which we call a Cartesian kernel. While the existing pairwise kernel (which we refer to as the Kronecker kernel) can be interpreted as the weighted adjacency matrix of the Kronecker product graph of two graphs, the Cartesian kernel can be interpreted as that of the Cartesian graph, which is more sparse than the Kronecker product graph. We discuss the generalization bounds of the two pairwise kernels by using eigenvalue analysis of the kernel matrices. Also, we consider the N-wise extensions of the two pairwise kernels. Experimental results show the Cartesian kernel is much faster than the Kronecker kernel, and at the same time, competitive with the Kronecker kernel in predictive performance.

    DOI: 10.1587/transinf.E93.D.2672

    Web of Science

    Scopus

    Other Link: http://dblp.uni-trier.de/db/journals/ieicet/ieicet93d.html#journals/ieicet/KashimaOYT10

  99. Simultaneous Prediction of Biological Networks of Multiple Species from Genome-wide Data and Evolutionary Information: A Semi-supervised Approach Reviewed

    Hisashi Kashima, Tsuyoshi Kato, Yoshihiro Yamanishi, Masashi Sugiyama, Koji Tsuda

    IEEE Transactions on Knowledge and Data Enginieering   Vol. 22 ( 7 ) page: 957 - 968   2010.7

  100. Drug-target interaction prediction from chemical, genomic and pharmacological data in an integrated framework Reviewed International journal

    Yoshihiro Yamanishi, Masaaki Kotera, Minoru Kanehisa, Susumu Goto

    BIOINFORMATICS   Vol. 26 ( 12 ) page: i246 - i254   2010.6

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:OXFORD UNIV PRESS  

    Motivation: In silico prediction of drug-target interactions from heterogeneous biological data is critical in the search for drugs and therapeutic targets for known diseases such as cancers. There is therefore a strong incentive to develop new methods capable of detecting these potential drug-target interactions efficiently.
    Results: In this article, we investigate the relationship between the chemical space, the pharmacological space and the topology of drug-target interaction networks, and show that drug-target interactions are more correlated with pharmacological effect similarity than with chemical structure similarity. We then develop a new method to predict unknown drug-target interactions from chemical, genomic and pharmacological data on a large scale. The proposed method consists of two steps: (i) prediction of pharmacological effects from chemical structures of given compounds and (ii) inference of unknown drug-target interactions based on the pharmacological effect similarity in the framework of supervised bipartite graph inference. The originality of the proposed method lies in the prediction of potential pharmacological similarity for any drug candidate compounds and in the integration of chemical, genomic and pharmacological data in a unified framework. In the results, we make predictions for four classes of important drug-target interactions involving enzymes, ion channels, GPCRs and nuclear receptors. Our comprehensively predicted drug-target interaction networks enable us to suggest many potential drug-target interactions and to increase research productivity toward genomic drug discovery.
    Supplementary information: Datasets and all prediction results are available at http://cbio.ensmp.fr/(similar to)yyamanishi/pharmaco/.
    Availability: Softwares are available upon request.
    Contact: yoshihiro.yamanishi@ensmp.fr

    DOI: 10.1093/bioinformatics/btq176

    Web of Science

    Scopus

    PubMed

    J-GLOBAL

  101. Integer programming-based method for completing signaling pathways and its application to analysis of colorectal cancer.

    Tamura T., Yamanishi Y., Tanabe M., Goto S., Kanehisa M., Horimoto K., Akutsu T.

    Genome informatics. International Conference on Genome Informatics   Vol. 24   page: 193 - 203   2010

     More details

    Publisher:Genome informatics. International Conference on Genome Informatics  

    Signaling pathways are often represented by networks where each node corresponds to a protein and each edge corresponds to a relationship between nodes such as activation, inhibition and binding. However, such signaling pathways in a cell may be affected by genetic and epigenetic alteration. Some edges may be deleted and some edges may be newly added. The current knowledge about known signaling pathways is available on some public databases, but most of the signaling pathways including changes upon the cell state alterations remain largely unknown. In this paper, we develop an integer programming-based method for inferring such changes by using gene expression data. We test our method on its ability to reconstruct the pathway of colorectal cancer in the KEGG database.

    DOI: 10.1142/9781848166585_0016

    Scopus

  102. Integer programming-based method for completing signaling pathways and its application to analysis of colorectal cancer. Reviewed

    Tamura T, Yamanishi Y, Tanabe M, Goto S, Kanehisa M, Horimoto K, Akutsu T

    Genome informatics. International Conference on Genome Informatics   Vol. 24   page: 193 - 203   2010

     More details

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

    Signaling pathways are often represented by networks where each node corresponds to a protein and each edge corresponds to a relationship between nodes such as activation, inhibition and binding. However, such signaling pathways in a cell may be affected by genetic and epigenetic alteration. Some edges may be deleted and some edges may be newly added. The current knowledge about known signaling pathways is available on some public databases, but most of the signaling pathways including changes upon the cell state alterations remain largely unknown. In this paper, we develop an integer programming-based method for inferring such changes by using gene expression data. We test our method on its ability to reconstruct the pathway of colorectal cancer in the KEGG database.

    PubMed

  103. Simultaneous inference of biological networks of multiple species from genome-wide data and evolutionary information: a semi-supervised approach Reviewed International journal

    Hisashi Kashima, Yoshihiro Yamanishi, Tsuyoshi Kato, Masashi Sugiyama, Koji Tsuda

    BIOINFORMATICS   Vol. 25 ( 22 ) page: 2962 - 2968   2009.11

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:OXFORD UNIV PRESS  

    Motivation: The existing supervised methods for biological network inference work on each of the networks individually based only on intra-species information such as gene expression data. We believe that it will be more effective to use genomic data and cross-species evolutionary information from different species simultaneously, rather than to use the genomic data alone.Results: We created a new semi-supervised learning method called Link Propagation for inferring biological networks of multiple species based on genome-wide data and evolutionary information. The new method was applied to simultaneous reconstruction of three metabolic networks of Caenorhabditis elegans, Helicobacter pylori and Saccharomyces cerevisiae, based on gene expression similarities and amino acid sequence similarities. The experimental results proved that the new simultaneous network inference method consistently improves the predictive performance over the individual network inferences, and it also outperforms in accuracy and speed other established methods such as the pairwise support vector machine.

    DOI: 10.1093/bioinformatics/btp494

    Web of Science

    Scopus

    PubMed

  104. Supervised prediction of drug-target interactions using bipartite local models Reviewed International journal

    Kevin Bleakley, Yoshihiro Yamanishi

    BIOINFORMATICS   Vol. 25 ( 18 ) page: 2397 - 2403   2009.9

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:OXFORD UNIV PRESS  

    Motivation: In silico prediction of drug-target interactions from heterogeneous biological data is critical in the search for drugs for known diseases. This problem is currently being attacked from many different points of view, a strong indication of its current importance. Precisely, being able to predict new drug-target interactions with both high precision and accuracy is the holy grail, a fundamental requirement for in silico methods to be useful in a biological setting. This, however, remains extremely challenging due to, amongst other things, the rarity of known drug-target interactions.
    Results: We propose a novel supervised inference method to predict unknown drug-target interactions, represented as a bipartite graph. We use this method, known as bipartite local models to first predict target proteins of a given drug, then to predict drugs targeting a given protein. This gives two independent predictions for each putative drug-target interaction, which we show can be combined to give a definitive prediction for each interaction. We demonstrate the excellent performance of the proposed method in the prediction of four classes of drug-target interaction networks involving enzymes, ion channels, G protein-coupled receptors (GPCRs) and nuclear receptors in human. This enables us to suggest a number of new potential drug-target interactions.

    DOI: 10.1093/bioinformatics/btp433

    Web of Science

    Scopus

    PubMed

    J-GLOBAL

  105. E-zyme: predicting potential EC numbers from the chemical transformation pattern of substrate-product pairs Reviewed International journal

    Yoshihiro Yamanishi, Masahiro Hattori, Masaaki Kotera, Susumu Goto, Minoru Kanehisa

    BIOINFORMATICS   Vol. 25 ( 12 ) page: I179 - I186   2009.6

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:OXFORD UNIV PRESS  

    Motivation: The IUBMB's Enzyme Nomenclature system, commonly known as the Enzyme Commission (EC) numbers, plays key roles in classifying enzymatic reactions and in linking the enzyme genes or proteins to reactions in metabolic pathways. There are numerous reactions known to be present in various pathways but without any official EC numbers, most of which have no hope to be given ones because of the lack of the published articles on enzyme assays.
    Results: In this article we propose a new method to predict the potential EC numbers to given reactant pairs (substrates and products) or uncharacterized reactions, and a web-server named E-zyme as an application. This technology is based on our original biochemical transformation pattern which we call an 'RDM pattern', and consists of three steps: (i) graph alignment of a query reactant pair (substrates and products) for computing the query RDM pattern, (ii) multi-layered partial template matching by comparing the query RDM pattern with template patterns related with known EC numbers and (iii) weighted major voting scheme for selecting appropriate EC numbers. As the result, cross-validation experiments show that the proposed method achieves both high coverage and high prediction accuracy at a practical level, and consistently outperforms the previous method.

    DOI: 10.1093/bioinformatics/btp223

    Web of Science

    Scopus

    PubMed

    J-GLOBAL

  106. Supervised bipartite graph inference

    Yamanishi Y.

    Advances in Neural Information Processing Systems 21 - Proceedings of the 2008 Conference     page: 1841 - 1848   2009

     More details

    Publisher:Advances in Neural Information Processing Systems 21 - Proceedings of the 2008 Conference  

    We formulate the problem of bipartite graph inference as a supervised learning problem, and propose a new method to solve it from the viewpoint of distance metric learning. The method involves the learning of two mappings of the heterogeneous objects to a unified Euclidean space representing the network topology of the bipartite graph, where the graph is easy to infer. The algorithm can be formulated as an optimization problem in a reproducing kernel Hilbert space. We report encouraging results on the problem of compound-protein interaction network reconstruction from chemical structure data and genomic sequence data.

    Scopus

  107. Link propagation: A fast semi-supervised learning algorithm for link prediction Reviewed

    Hisashi Kashima, Tsuyoshi Kato, Yoshihiro Yamanishi, Masashi Sugiyama, Koji Tsuda

    Society for Industrial and Applied Mathematics - 9th SIAM International Conference on Data Mining 2009, Proceedings in Applied Mathematics   Vol. 3   page: 1093 - 1104   2009

     More details

    Publishing type:Research paper (international conference proceedings)   Publisher:SIAM  

    We propose Link Propagation as a new semi-supervised learning method for link prediction problems, where the task is to predict unknown parts of the network structure by using auxiliary information such as node similarities. Since the proposed method can fill in missing parts of tensors, it is applicable to multi-relational domains, allowing us to handle multiple types of links simultaneously. We also give a novel efficient algorithm for Link Propagation based on an accelerated conjugate gradient method.

    DOI: 10.1137/1.9781611972795.94

    Scopus

  108. On Pairwise Kernels: An Efficient Alternative and Generalization Analysis Reviewed

    Hisashi Kashima, Satoshi Oyama, Yoshihiro Yamanishi, Koji Tsuda

    ADVANCES IN KNOWLEDGE DISCOVERY AND DATA MINING, PROCEEDINGS   Vol. 5476   page: 1030 - +   2009

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:SPRINGER-VERLAG BERLIN  

    Pairwise classification has many applications including network prediction, entity resolution, and collaborative filtering. The pairwise kernel has been proposed for those purposes by several research groups independently, and become successful in various fields. In this paper, we propose an efficient alternative which we call Cartesian kennel. While the existing pairwise kernel (which we refer to as Kronecker kernel) can be interpreted as the weighted adjacency matrix of the Kronecker product graph of two graphs, the Cartesian kernel can be interpreted as that of the Cartesian graph which is more sparse than the Kronecker product graph. Experimental results show the Cartesian kernel is much faster than the existing pairwise kernel, and at the same time, competitive with the existing pairwise kernel in predictive performance. We discuss the generalization bounds by the two pairwise kernels by using eigenvalue analysis of the kernel matrices.

    DOI: 10.1007/978-3-642-01307-2_110

    Web of Science

    Scopus

  109. Prediction of drug-target interaction networks from the integration of chemical and genomic spaces Reviewed International journal

    Yoshihiro Yamanishi, Michihiro Araki, Alex Gutteridge, Wataru Honda, Minoru Kanehisa

    BIOINFORMATICS   Vol. 24 ( 13 ) page: I232 - I240   2008.7

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:OXFORD UNIV PRESS  

    Motivation: The identification of interactions between drugs and target proteins is a key area in genomic drug discovery. Therefore, there is a strong incentive to develop new methods capable of detecting these potential drug-target interactions efficiently.
    Results: In this article, we characterize four classes of drug-target interaction networks in humans involving enzymes, ion channels, G-protein-coupled receptors (GPCRs) and nuclear receptors, and reveal significant correlations between drug structure similarity, target sequence similarity and the drug-target interaction network topology. We then develop new statistical methods to predict unknown drug-target interaction networks from chemical structure and genomic sequence information simultaneously on a large scale. The originality of the proposed method lies in the formalization of the drug-target interaction inference as a supervised learning problem for a bipartite graph, the lack of need for 3D structure information of the target proteins, and in the integration of chemical and genomic spaces into a unified space that we call &apos;pharmacological space&apos;. In the results, we demonstrate the usefulness of our proposed method for the prediction of the four classes of drug-target interaction networks. Our comprehensively predicted drug-target interaction networks enable us to suggest many potential drug-target interactions and to increase research productivity toward genomic drug discovery.

    DOI: 10.1093/bioinformatics/btn162

    Web of Science

    Scopus

    PubMed

    J-GLOBAL

  110. KEGG for linking genomes to life and the environment Reviewed International journal

    Minoru Kanehisa, Michihiro Araki, Susumu Goto, Masahiro Hattori, Mika Hirakawa, Masumi Itoh, Toshiaki Katayama, Shuichi Kawashima, Shujiro Okuda, Toshiaki Tokimatsu, Yoshihiro Yamanishi

    NUCLEIC ACIDS RESEARCH   Vol. 36 ( Database issue ) page: D480 - D484   2008.1

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:OXFORD UNIV PRESS  

    KEGG (http://www.genome.jp/kegg/) is a database of biological systems that integrates genomic, chemical and systemic functional information. KEGG provides a reference knowledge base for linking genomes to life through the process of PATHWAY mapping, which is to map, for example, a genomic or transcriptomic content of genes to KEGG reference pathways to infer systemic behaviors of the cell or the organism. In addition, KEGG provides a reference knowledge base for linking genomes to the environment, such as for the analysis of drug-target relationships, through the process of BRITE mapping. KEGG BRITE is an ontology database representing functional hierarchies of various biological objects, including molecules, cells, organisms, diseases and drugs, as well as relationships among them. KEGG PATHWAY is now supplemented with a new global map of metabolic pathways, which is essentially a combined map of about 120 existing pathway maps. In addition, smaller pathway modules are defined and stored in KEGG MODULE that also contains other functional units and complexes. The KEGG resource is being expanded to suit the needs for practical applications. KEGG DRUG contains all approved drugs in the US and Japan, and KEGG DISEASE is a new database linking disease genes, pathways, drugs and diagnostic markers.

    DOI: 10.1093/nar/gkm882

    Web of Science

    Scopus

    PubMed

    J-GLOBAL

  111. Supervised Bipartite Graph Inference. Reviewed

    Yoshihiro Yamanishi

    Advances in Neural Information Processing Systems 21, Proceedings of the Twenty-Second Annual Conference on Neural Information Processing Systems, Vancouver, British Columbia, Canada, December 8-11, 2008   Vol. 21   page: 1841 - 1848   2008

     More details

    Publishing type:Research paper (international conference proceedings)   Publisher:Curran Associates, Inc.  

    Other Link: http://dblp.uni-trier.de/db/conf/nips/nips2008.html#conf/nips/Yamanishi08

  112. Glycan classification with tree kernels Reviewed International journal

    Yoshihiro Yamanishi, Francis Bach, Jean-Philippe Vert

    BIOINFORMATICS   Vol. 23 ( 10 ) page: 1211 - 1216   2007.5

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:OXFORD UNIV PRESS  

    Motivation: Glycans are covalent assemblies of sugar that play crucial roles in many cellular processes. Recently, comprehensive data about the structure and function of glycans have been accumulated, therefore the need for methods and algorithms to analyze these data is growing fast.
    Results: This article presents novel methods for classifying glycans and detecting discriminative glycan motifs with support vector machines (SVM). We propose a new class of tree kernels to measure the similarity between glycans. These kernels are based on the comparison of tree substructures, and take into account several glycan features such as the sugar type, the sugar bound type or layer depth. The proposed methods are tested on their ability to classify human glycans into four blood components: leukemia cells, erythrocytes, plasma and serum. They are shown to outperform a previously published method. We also applied a feature selection approach to extract glycan motifs which are characteristic of each blood component. We confirmed that some leukemia-specific glycan motifs detected by our method corresponded to several results in the literature.

    DOI: 10.1093/bioinformatics/btm090

    Web of Science

    Scopus

    PubMed

    J-GLOBAL

  113. Prediction of missing enzyme genes in a bacterial metabolic network - Reconstruction of the lysine-degradation pathway of Pseudomonas aeruginosa Reviewed International journal

    Yoshihiro Yamanishi, Hisaaki Mihara, Motoharu Osaki, Hisashi Muramatsu, Nobuyoshi Esaki, Tetsuya Sato, Yoshiyuki Hizukuri, Susumu Goto, Minoru Kanehisa

    FEBS JOURNAL   Vol. 274 ( 9 ) page: 2262 - 2273   2007.5

     More details

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

    The metabolic network is an important biological network which consists of enzymes and chemical compounds. However, a large number of metabolic pathways remains unknown, and most organism-specific metabolic pathways contain many missing enzymes. We present a novel method to identify the genes coding for missing enzymes using available genomic and chemical information from bacterial genomes. The proposed method consists of two steps: (a) estimation of the functional association between the genes with respect to chromosomal proximity and evolutionary association, using supervised network inference; and (b) selection of gene candidates for missing enzymes based on the original candidate score and the chemical reaction information encoded in the EC number. We applied the proposed methods to infer the metabolic network for the bacteria Pseudomonas aeruginosa from two genomic datasets: gene position and phylogenetic profiles. Next, we predicted several missing enzyme genes to reconstruct the lysine-degradation pathway in P. aeruginosa using EC number information. As a result, we identified PA0266 as a putative 5-aminovalerate aminotransferase (EC 2.6.1.48) and PA0265 as a putative glutarate semialdehyde dehydrogenase (EC 1.2.1.20). To verify our prediction, we conducted biochemical assays and examined the activity of the products of the predicted genes, PA0265 and PA0266, in a coupled reaction. We observed that the predicted gene products catalyzed the expected reactions; no activity was seen when both gene products were omitted from the reaction.

    DOI: 10.1111/j.1742-4658.2007.05763.x

    Web of Science

    Scopus

    PubMed

    J-GLOBAL

  114. Prediction of nitrogen metabolism-related genes in Anabaena by kernel-based network analysis Reviewed International journal

    Shinobu Okamoto, Yoshihiro Yamanishi, Shigeki Ehira, Shuichi Kawashima, Koichiro Tonomura, Minoru Kanehisa

    PROTEOMICS   Vol. 7 ( 6 ) page: 900 - 909   2007.3

     More details

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

    Prediction of molecular interaction networks from large-scale datasets in genomics and other ornics experiments is an important task in terms of both developing bioinformatics methods and solving biological problems. We have applied a kernel-based network inference method for extracting functionally related genes to the response of nitrogen deprivation in cyanobacteria Anabaena sp. PCC 7120 integrating three heterogeneous datasets: microarray data, phylogenetic profiles, and gene orders on the chromosome. We obtained 1348 predicted genes that are somehow related to known genes in the Kyoto Encyclopedia of Genes and Genomes (KEGG) pathways. While this dataset contained previously known genes related to the nitrogen deprivation condition, it also contained additional genes. Thus, we attempted to select any relevant genes using the constraints of Pfam. domains and NtcA-binding sites. We found candidates of nitrogen metabolism-related genes, which are depicted as extensions of existing KEGG pathways. The prediction of functional relationships between proteins rather than functions of individual proteins will thus assist the discovery from the large-scale datasets.

    DOI: 10.1002/pmic.200600862

    Web of Science

    Scopus

    PubMed

    J-GLOBAL

  115. The prediction of function for uncharacterized genes using kernel-based network inference and domain profile analysis

    Okamoto Shinobu, Yamanishi Yoshihiro, Ehira Shigeki, Kanehisa Minoru, Nakamura Yasukazu

    PLANT AND CELL PHYSIOLOGY   Vol. 48   page: S156 - S156   2007

     More details

  116. Inference of protein-protein interactions by using co-evolutionary information Reviewed

    Tetsuya Sato, Yoshihiro Yamanishi, Katsuhisa Horimoto, Minoru Kanehisa, Hiroyuki Toh

    ALGEBRAIC BIOLOGY, PROCEEDINGS   Vol. 4545   page: 322 - +   2007

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:SPRINGER-VERLAG BERLIN  

    The mirror tree is a method to predict protein-protein interaction by evaluating the similarity between distance matrices of proteins. It is known, however, that predictions by the mirror tree method include many false positives. We suspected that the information about the evolutionary relationship of source organisms may be the cause of the false positives, because the information is shared by the distance matrices. Therefore, we excluded the information from the distance matrices and evaluated the similarity of the residuals as the intensity of co-evolution. We developed two different methods with a projection operation and partial correlation coefficient. The number of false positives were drastically reduced by our methods.

    DOI: 10.1007/978-3-540-73433-8_23

    Web of Science

    Scopus

  117. An improved scoring scheme for predicting glycan structures from gene expression data.

    Suga A., Yamanishi Y., Hashimoto K., Goto S., Kanehisa M.

    Genome informatics. International Conference on Genome Informatics   Vol. 18   page: 237 - 246   2007

     More details

    Publisher:Genome informatics. International Conference on Genome Informatics  

    The prediction of glycan structures from gene expression of glycosyltransferases (GTs) is a challenging new area in computational biology because the biosynthesis of glycan chains is under the control of GT expression. In this paper we developed a new method for predicting glycan structures from gene expression data. There are two main original aspects of the proposed method. First, we proposed to increase the number of predictable glycan structure candidates by estimating missing glycans from a global glycan structure map, which enables us to predict new glycan structures that are not stored in the database. Second, we proposed a more general scoring scheme based on real-valued gene expression intensity rather than converting it into binary information. In the result we applied the proposed method to predicting cancer-specific glycan structures from gene expression profiles for patients of acute lymphocytic leukemia (ALL) and acute myelocytic leukemia (AML). We confirmed that several of the predicted glycan structures successfully correspond to known cancer-specific glycan structures according to the literature, and our method outperforms the previous methods at a statistically significant level.

    DOI: 10.1142/9781860949920_0023

    Scopus

  118. An improved scoring scheme for predicting glycan structures from gene expression data Reviewed

    Akitsugu Suga, Yoshihiro Yamanishi, Kosuke Hashimoto, Susumu Goto, Minoru Kanehisa

    GENOME INFORMATICS 2007, VOL 18   Vol. 18   page: 237 - 246   2007

     More details

    Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:IMPERIAL COLLEGE PRESS  

    The prediction of glycan structures from gene expression of glycosyltransferases (GTs) is a challenging new area in computational biology because the biosynthesis of glycan chains is under the control of GT expression. In this paper we developed a new method for predicting glycan structures from gene expression data. There are two main original aspects of the proposed method. First, we proposed to increase the number of predictable glycan structure candidates by estimating missing glycans from a global glycan structure map, which enables us to predict new glycan structures that are not stored in the database. Second, we proposed a more general scoring scheme based on real-valued gene expression intensity rather than converting it into binary information. In the result we applied the proposed method to predicting cancer-specific glycan structures from gene expression profiles for patients of acute lymphocytic leukemia (ALL) and acute myelocytic leukemia (AML). We confirmed that several of the predicted glycan structures successfully correspond to known cancer-specific glycan structures according to the literature, and our method outperforms the previous methods at a statistically significant level.

    DOI: 10.11234/gi1990.18.237

    Web of Science

    PubMed

    J-GLOBAL

  119. Partial correlation coefficient between distance matrices as a new indicator of protein-protein interactions Reviewed International journal

    Tetsuya Sato, Yoshihiro Yamanishi, Katsuhisa Horimoto, Minoru Kanehisa, Hiroyuki Toh

    BIOINFORMATICS   Vol. 22 ( 20 ) page: 2488 - 2492   2006.10

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:OXFORD UNIV PRESS  

    Motivation: The computational prediction of protein-protein interactions is currently a major issue in bioinformatics. Recently, a variety of co-evolution-based methods have been investigated toward this goal. In this study, we introduced a partial correlation coefficient as a new measure for the degree of co-evolution between proteins, and proposed its use to predict protein-protein interactions.
    Results: The accuracy of the prediction by the proposed method was compared with those of the original mirror tree method and the projection method previously developed by our group. We found that the partial correlation coefficient effectively reduces the number of false positives, as compared with other methods, although the number of false negatives increased in the prediction by the partial correlation coefficient.

    DOI: 10.1093/bioinformatics/btl419

    Web of Science

    Scopus

    PubMed

    J-GLOBAL

  120. Alteration of gene expression by hepatitis B virus DNA integration in human hepatocellular carcinoma

    Tamori Akihiro, Yamanishi Yoshihisa, Kawashima Shuichi, Kanehisa Minoru, Enomoto Masaru, Habu Daiki, Tanaka Hiromu, Kubo Shoji, Shiomi Susumu, Nishiguchi Shuhei

    CANCER RESEARCH   Vol. 66 ( 8 )   2006.4

     More details

  121. Extraction of leukemia specific glycan motifs in humans by computational glycomics Reviewed International journal

    Y Hizukuri, Y Yamanishi, O Nakamura, F Yagi, S Goto, M Kanehisa

    CARBOHYDRATE RESEARCH   Vol. 340 ( 14 ) page: 2270 - 2278   2005.10

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:ELSEVIER SCI LTD  

    There have been almost no standard methods for conducting computational analyses on glycan structures in comparison to DNA and proteins. In this paper, we present a novel method for extracting functional motifs from glycan structures using the KEGG/GLYCAN database. First, we developed a new similarity measure for comparing glycan structures taking into account the characteristic mechanisms of glycan biosynthesis, and we tested its ability to classify glycans of different blood components in the framework of support vector machines (SVMs), The results show that our method can successfully classify glycans from four types of human blood components: leukemic cells, erythrocyte, serum, and plasma. Next we extracted characteristic functional motifs of glycans considered to be specific to each blood component. We predicted the substruct the alpha-D-Neup5AC-(2--&gt;3)-beta-D-Galp-(1--&gt;4)-D-GlcpNAc as a leukemia specific glycan motif. Based on the fact that the Agrocybe cylindracea galectin (ACG) specifically binds to the same substructure, we conducted an experiment using Cell agglutination assay and confirmed that this fungal lectin specifically recognized human leukemic cells. (C) 2005 Elsevier Ltd. All rights reserved.

    DOI: 10.1016/j.carres.2005.07.012

    Web of Science

    Scopus

    PubMed

    J-GLOBAL

  122. The inference of protein-protein interactions by co-evolutionary analysis is improved by excluding the information about the phylogenetic relationships Reviewed International journal

    T Sato, Y Yamanishi, M Kanehisa, H Toh

    BIOINFORMATICS   Vol. 21 ( 17 ) page: 3482 - 3489   2005.9

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:OXFORD UNIV PRESS  

    Motivation: The prediction of protein-protein interactions is currently an important issue in bioinformatics. The mirror tree method uses evolutionary information to predict protein-protein interactions. However, it has been recognized that predictions by the mirror tree method lead to many false positives. The incentive of our study was to solve this problem by improving the method of extracting the co-evolutionary information regarding the protein pairs.
    Results: We developed a novel method to predict protein-protein interactions from co-evolutionary information in the framework of the mirror tree method. The originality is the use of the projection operator to exclude the information about the phylogenetic relationships among the source organisms from the distance matrix. Each distance matrix was transformed into a vector for the operation. The vector is referred to as a 'phylogenetic vector'. We have proposed three ways to extract the phylogenetic information: (1) using the 16S rRNA from the same source organisms as the proteins under consideration, (2) averaging the phylogenetic vectors and (3) analyzing the principal components of the phylogenetic vectors. We examined the performance of the proposed methods to predict interacting protein pairs from Escherichia coli, using experimentally verified data. Our method was successful, and it drastically reduced the number of false positives in the prediction.

    DOI: 10.1093/bioinformatics/bti564

    Web of Science

    Scopus

    PubMed

    J-GLOBAL

  123. Alteration of gene expression in human hepatocellular carcinoma with integrated hepatitis B virus DNA Reviewed International journal

    A Tamori, Y Yamanishi, S Kawashima, M Kanehisa, M Enomoto, H Tanaka, S Kubo, S Shiomi, S Nishiguchi

    CLINICAL CANCER RESEARCH   Vol. 11 ( 16 ) page: 5821 - 5826   2005.8

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:AMER ASSOC CANCER RESEARCH  

    Purpose: Integration of hepatitis B virus (HBV) DNA into the human genome is one of the most important steps in HBV-related carcinogenesis. This study attempted to find the link between HBV DNA, the adjoining cellular sequence, and altered gene expression in hepatocellular carcinoma (HCC) with integrated HBV DNA.
    Experimental Design: We examined 15 cases of HCC infected with HBV by cassette ligation mediated PCR. The human DNA adjacent to the integrated HBV DNA was sequenced. Protein coding sequences were searched for in the human sequence. In five cases with HBV DNA integration, from which good quality RNA was extracted, gene expression was examined by cDNA microarray analysis.
    Results: The human DNA sequence successive to integrated HBV DNA was determined in the 15 HCCs. Eight protein-coding regions were involved: ras-responsive element binding protein 1, calmodulin 1, mixed lineage leukemia 2 (MLL-2), FLJ333655, LOC220272, LOC255345, LOC220220, and LOC168991. The MLL2 gene was expressed in three cases with HBV DNA integrated into exon 3 of MLL2 and in one case with HBV DNA integrated into intron 3 of MLL2. Gene expression analysis suggested that two HCCs with HBV integrated into MLL2 had similar patterns of gene expression compared with three HCCs with HBV integrated into other loci of human chromosomes.
    Conclusions: HBV DNA was integrated at random sites of human DNA, and the MLL2 gene was one of the targets for integration. Our results suggest that HBV DNA might modulate human genes near integration sites, followed by integration site-specific expression of such genes during hepatocarcinogenesis.

    DOI: 10.1158/1078-0432.CCR-04-2055

    Web of Science

    Scopus

    PubMed

    J-GLOBAL

  124. Supervised enzyme network inference from the integration of genomic data and chemical information Reviewed International journal

    Y Yamanishi, JP Vert, M Kanehisa

    BIOINFORMATICS   Vol. 21 ( SUPPL. 1 ) page: I468 - I477   2005.6

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:OXFORD UNIV PRESS  

    Motivation: The metabolic network is an important biological network which relates enzyme proteins and chemical compounds. A large number of metabolic pathways remain unknown nowadays, and many enzymes are missing even in known metabolic pathways. There is, therefore, an incentive to develop methods to reconstruct the unknown parts of the metabolic network and to identify genes coding for missing enzymes.
    Results: This paper presents new methods to infer enzyme networks from the integration of multiple genomic data and chemical information, in the framework of supervised graph inference. The originality of the methods is the introduction of chemical compatibility as a constraint for refining the network predicted by the network inference engine. The chemical compatibility between two enzymes is obtained automatically from the information encoded by their Enzyme Commission (EC) numbers. The proposed methods are tested and compared on their ability to infer the enzyme network of the yeast Saccharomyces cerevisiae from four datasets for enzymes with assigned EC numbers: gene expression data, protein localization data, phylogenetic profiles and chemical compatibility information. It is shown that the prediction accuracy of the network reconstruction consistently improves owing to the introduction of chemical constraints, the use of a supervised approach and the weighted integration of multiple datasets. Finally, we conduct a comprehensive prediction of a global enzyme network consisting of all enzyme candidate proteins of the yeast to obtain new biological findings.

    DOI: 10.1093/bioinformatics/bti1012

    Web of Science

    Scopus

    PubMed

    J-GLOBAL

  125. Supervised graph inference

    Vert J.P., Yamanishi Y.

    Advances in Neural Information Processing Systems     2005

     More details

    Publisher:Advances in Neural Information Processing Systems  

    We formulate the problem of graph inference where part of the graph is known as a supervised learning problem, and propose an algorithm to solve it. The method involves the learning of a mapping of the vertices to a Euclidean space where the graph is easy to infer, and can be formulated as an optimization problem in a reproducing kernel Hilbert space. We report encouraging results on the problem of metabolic network reconstruction from genomic data.

    Scopus

  126. Sensitivity analysis in functional principal component analysis.

    Yoshihiro Yamanishi, Yutaka Tanaka

    Computational Statistics   Vol. 20 ( 2 ) page: 311 - 326   2005

     More details

    Publishing type:Research paper (scientific journal)  

    DOI: 10.1007/BF02789706

    Web of Science

    Scopus

  127. Protein network inference from multiple genomic data: a supervised approach Reviewed

    Y. Yamanishi, J. -P. Vert, M. Kanehisa

    BIOINFORMATICS   Vol. 20 ( SUPPL. 1 ) page: 363 - 370   2004.8

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:OXFORD UNIV PRESS  

    Motivation: An increasing number of observations support the hypothesis that most biological functions involve the interactions between many proteins, and that the complexity of living systems arises as a result of such interactions. In this context, the problem of inferring a global protein network for a given organism, using all available genomic data about the organism, is quickly becoming one of the main challenges in current computational biology.
    Results: This paper presents a new method to infer protein networks from multiple types of genomic data. Based on a variant of kernel canonical correlation analysis, its originality is in the formalization of the protein network inference problem as a supervised learning problem, and in the integration of heterogeneous genomic data within this framework. We present promising results on the prediction of the protein network for the yeast Saccharomyces cerevisiae from four types of widely available data: gene expressions, protein interactions measured by yeast two-hybrid systems, protein localizations in the cell and protein phylogenetic profiles. The method is shown to outperform other unsupervised protein network inference methods. We finally conduct a comprehensive prediction of the protein network for all proteins of the yeast, which enables us to propose protein candidates for missing enzymes in a biosynthesis pathway.

    DOI: 10.1093/bioinformatics/bth910

    Web of Science

    Scopus

    PubMed

  128. Supervised Graph Inference. Reviewed

    Jean-Philippe Vert, Yoshihiro Yamanishi

    Advances in Neural Information Processing Systems 17 [Neural Information Processing Systems, NIPS 2004, December 13-18, 2004, Vancouver, British Columbia, Canada]   Vol. 17   page: 1433 - 1440   2004

     More details

    Publishing type:Research paper (international conference proceedings)  

    Other Link: http://dblp.uni-trier.de/db/conf/nips/nips2004.html#conf/nips/VertY04

  129. Extraction of species-specific glycan substructures.

    Hizukuri Y., Yamanishi Y., Hashimoto K., Kanehisa M.

    Genome informatics. International Conference on Genome Informatics   Vol. 15 ( 1 ) page: 69 - 81   2004

     More details

    Publisher:Genome informatics. International Conference on Genome Informatics  

    Glycans, which are carbohydrate sugar chains attached to some lipids or proteins, have a huge variety of structures and play a key role in cell communication, protein interaction and immunity. The availability of a number of glycan structures stored in the KEGG/GLYCAN database makes it possible for us to conduct a large-scale comparative research of glycans. In this paper, we present a novel approach to compare glycan structures and extract characteristic glycan substructures of certain organisms. In the algorithm we developed a new similarity measure of glycan structures taking into account of several biological aspects of glycan synthesis and glycosyltransferases, and we confirmed the validity of our similarity measure by conducting experiments on its ability to classify glycans between organisms in the framework of a support vector machine. Finally, our method successfully extracted a set of candidates of substructrues which are characteristic to human, rat, mouse, bovine, pig, chicken, yeast, wheat and sycamore, respectively. We confirmed that the characteristic substructures extracted by our method correspond to the substructures which are known as the species-specific sugar chain of gamma-glutamyltranspeptidases in the kidney.

    Scopus

  130. Extraction of species-specific glycan substructures. Reviewed

    Hizukuri Y, Yamanishi Y, Hashimoto K, Kanehisa M

    Genome informatics. International Conference on Genome Informatics   Vol. 15 ( 1 ) page: 69 - 81   2004

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:Japanese Society for Bioinformatics  

    Glycans, which are carbohydrate sugar chains attached to some lipids or proteins, have a huge variety of structures and play a key role in cell communication, protein interaction and immunity. The availability of a number of glycan structures stored in the KEGG/GLYCAN database makes it possible for us to conduct a large-scale comparative research of glycans. In this paper, we present a novel approach to compare glycan structures and extract characteristic glycan substructures of certain organisms. In the algorithm we developed a new similarity measure of glycan structures taking into account of several biological aspects of glycan synthesis and glycosyltransferases, and we confirmed the validity of our similarity measure by conducting experiments on its ability to classify glycans between organisms in the framework of a support vector machine. Finally, our method successfully extracted a set of candidates of substructrues which are characteristic to human, rat, mouse, bovine, pig, chicken, yeast, wheat and sycamore, respectively. We confirmed that the characteristic substructures extracted by our method correspond to the substructures which are known as the species-specific sugar chain of γ-glutamyltranspeptidases in the kidney.

    DOI: 10.11234/gi1990.15.69

    PubMed

    J-GLOBAL

  131. Extraction of correlated gene clusters from multiple genomic data by generalized kernel canonical correlation analysis Reviewed

    Y. Yamanishi, J. -P. Vert, A. Nakaya, M. Kanehisa

    BIOINFORMATICS   Vol. 19   page: i323 - i330   2003.7

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:OXFORD UNIV PRESS  

    Motivation: A major issue in computational biology is the reconstruction of pathways from several genomic datasets, such as expression data, protein interaction data and phylogenetic profiles. As a first step toward this goal, it is important to investigate the amount of correlation which exists between these data.
    Method: We present new methods to measure the correlation between several heterogeneous datasets, and to extract sets of genes which share similarities with respect to multiple biological attributes. The originality of our approach is the extension of the concept of correlation for non-vectorial data, which is made possible by the use of generalized kernel canonical correlation analysis (KCCA), and the method we propose to extract groups of genes responsible for the detected correlations. Moreover, two variants of KCCA are proposed when more than two datasets are available.
    Result: These methods are successfully tested on their ability to recognize operons in the Escherichia coli genome, from the comparison of three datasets corresponding to functional relationships between genes in metabolic pathways, geometrical relationships along the chromosome, and co-expression relationships as observed by gene expression data.

    DOI: 10.1093/bioinformatics/btg1045

    Web of Science

    Scopus

    PubMed

    Other Link: http://dblp.uni-trier.de/db/conf/ismb/ismb2003.html#conf/ismb/YamanishiVNK03

  132. Extraction of organism groups from phylogenetic profiles using independent component analysis. Reviewed

    Yamanishi Y, Itoh M, Kanehisa M

    Genome informatics. International Conference on Genome Informatics   Vol. 13   page: 61 - 70   2002

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:Japanese Society for Bioinformatics  

    In recent years, the analysis of orthologous genes based on phylogenetic profiles has received popularity in bioinfomatics. We propose a new method to extract organism groups and their hierarchy from phylogenetic profiles using the independent component analysis (ICA). The method involves first finding independent axes in the projected space from the multivariate data matrix representing phylogenetic profiles for a number of orthologous genes. Then the extracted axes are correlated with major organism groups, according to the extent of affiliaion of axes scores for all the genes to specific organisms. The ICA was applied to the phylogenetic profiles created for 2875 orthologs in 77 organisms by using the KEGG/GENES database. The 9 extracted components out of 18 predefined components well represented the organism groups as categorized in KEGG. Furthermore, we performed the cluster analysis and obtained the hierarchy of organism groups.

    DOI: 10.11234/gi1990.13.61

    PubMed

  133. Extraction of organism groups from phylogenetic profiles using independent component analysis.

    Yamanishi Y., Itoh M., Kanehisa M.

    Genome informatics. International Conference on Genome Informatics   Vol. 13   page: 61 - 70   2002

     More details

    Publisher:Genome informatics. International Conference on Genome Informatics  

    In recent years, the analysis of orthologous genes based on phylogenetic profiles has received popularity in bioinfomatics. We propose a new method to extract organism groups and their hierarchy from phylogenetic profiles using the independent component analysis (ICA). The method involves first finding independent axes in the projected space from the multivariate data matrix representing phylogenetic profiles for a number of orthologous genes. Then the extracted axes are correlated with major organism groups, according to the extent of affiliation of axes scores for all the genes to specific organisms. The ICA was applied to the phylogenetic profiles created for 2,875 orthologs in 77 organisms by using the KEGG/GENES database. The 9 extracted components out of 18 predefined components well represented the organism groups as categorized in KEGG. Furthermore, we performed the cluster analysis and obtained the hierarchy of organism groups.

    Scopus

▼display all

Books 4

  1. 革新的AI創薬  ~医療ビッグデータ、人工知能がもたらす創薬研究の未来像~

    飯田緑, 山西芳裕( Role: Contributor ,  分子ネットワークを有効活用したAI創薬手法)

    (株)エヌ・ティー・エス  2022.7  ( ISBN:978-4860437886

     More details

    Total pages:390   Responsible for pages:113-124   Language:Japanese Book type:Textbook, survey, introduction

  2. Chemoinformatics and advanced machine learning perspectives: Complex computational methods and collaborative techniques

    Lodhi H., Yamanishi Y.

    Chemoinformatics and Advanced Machine Learning Perspectives: Complex Computational Methods and Collaborative Techniques  2010.12  ( ISBN:9781615209118

     More details

    Chemoinformatics is a scientific area that endeavours to study and solve complex chemical problems using computational techniques and methods. Chemoinformatics and Advanced Machine Learning Perspectives: Complex Computational Methods and Collaborative Techniques provides an overview of current research in machine learning and applications to chemoinformatics tasks. As a timely compendium of research, this book offers perspectives on key elements that are crucial for complex study and investigation. © 2011 by IGI Global. All rights reserved.

    DOI: 10.4018/978-1-61520-911-8

    Scopus

  3. Chemoinformatics and Advanced Machine Learning Perspectives

    Huma Lodhi, Yoshihiro Yamanishi( Role: Edit)

    IGI Global  2010.7 

  4. Supervised Inference of Metabolic Networks from the Integration of Genomic Data and Chemical Information

    Yamanishi Y.

    Elements of Computational Systems Biology  2010.4  ( ISBN:9780470180938

MISC 156

  1. Prediction of therapeutic target molecules using genetically perturbed omics data Invited

    難波里子, 岩田通夫, 山西芳裕

    実験医学   Vol. 41 ( 7 ) page: 1193 - 1199   2023.5

     More details

    Authorship:Last author, Corresponding author   Language:Japanese   Publishing type:Article, review, commentary, editorial, etc. (trade magazine, newspaper, online media)  

    J-GLOBAL

  2. ダイレクトリプログラミングを誘導する低分子化合物組み合わせのin silico予測

    濱野桃子, 中村透, 岩田通夫, 江口凌平, 竹下潤一, 山西芳裕

    日本再生医療学会総会(Web)   Vol. 22nd   2023.3

     More details

    Authorship:Last author, Corresponding author   Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    J-GLOBAL

  3. 肺癌 効果予測因子 血清エクソソームの最新プロテオミクスによる小細胞肺癌の新規バイオマーカーの探索

    山本 真, 菅 泰彦, 武田 吉人, 中坪 大亮, 榎本 貴俊, 吉村 華子, 網屋 沙織, 原 伶奈, 川崎 貴裕, 白山 敬之, 三宅 浩太郎, 伊藤 眞里, 足立 淳, 上條 陽平, 澤田 隆介, 山西 芳裕, 熊ノ郷 淳

    日本呼吸器学会誌   Vol. 12 ( 増刊 ) page: 194 - 194   2023.3

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)   Publisher:(一社)日本呼吸器学会  

  4. 心筋組織におけるDNA損傷は原疾患によらず左室駆出率の低下した心不全の治療反応及び予後を予測する

    戴 哲皓, 候 聡志, 野村 征太郎, 藤田 寛奈, 濱野 桃子, 山西 芳裕, 尾上 健児, 小室 一成

    日本内科学会雑誌   Vol. 112 ( 臨増 ) page: 144 - 144   2023.2

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)   Publisher:(一社)日本内科学会  

    J-GLOBAL

  5. 最先端の研究技術を基盤とした心脈管作動物質研究の未来 AIが拓く創薬と医療 循環器疾患への応用に向けて Invited

    山西 芳裕

    血管   Vol. 46 ( 1 ) page: 36 - 36   2023.1

     More details

    Authorship:Lead author, Last author, Corresponding author   Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)   Publisher:日本心脈管作動物質学会  

  6. Single-cell-specific drug activities are revealed by a tensor imputation algorithm Invited

    Michio Iwata, Yoshihiro Yamanishi

    NATURE COMPUTATIONAL SCIENCE   Vol. 2 ( 11 ) page: 707 - 708   2022.11

     More details

    Authorship:Last author, Corresponding author   Language:English   Publishing type:Article, review, commentary, editorial, etc. (scientific journal)   Publisher:SPRINGERNATURE  

    We developed a computational method to reveal the drug-induced single-cell transcriptomic landscape. This algorithm enabled us to impute unknown drug-induced single-cell gene expression profiles using tensor imputation, predict cell type-specific drug efficacy, detect cell-type-specific marker genes, and identify the trajectories of regulated biological pathways while considering intercellular heterogeneity.

    DOI: 10.1038/s43588-022-00353-7

    Web of Science

  7. PRISM成果利用システム「峰」の構築 新薬創出を加速する人工知能の開発

    樋口 千洋, 黒田 正孝, 伊藤 眞里, 長尾 知生子, 浜本 隆二, 黒橋 禎夫, 高村 大也, 奥野 恭史, 山西 芳裕, 水口 賢司, 夏目 やよい

    医療情報学連合大会論文集   Vol. 42回   page: 1064 - 1066   2022.11

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)   Publisher:(一社)日本医療情報学会  

  8. エクソソームのプロテオミクスを用いた小細胞肺癌における新規バイオマーカー探索

    菅 泰彦, 山本 真, 吉村 華子, 白山 敬之, 三宅 浩太郎, 上條 陽平, 澤田 隆介, 山西 芳裕, 伊藤 眞里, 足立 淳, 武田 吉人, 熊ノ郷 淳

    肺癌   Vol. 62 ( 6 ) page: 678 - 678   2022.11

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)   Publisher:(NPO)日本肺癌学会  

    J-GLOBAL

  9. AIサイエンスによるがん研究の臨床応用と創薬にむけて AIによるデータ駆動型創薬と医療(Data-driven drug discovery and healthcare by AI) Invited

    山西 芳裕

    日本癌学会総会記事   Vol. 81回   page: S1 - 3   2022.9

     More details

    Language:English   Publishing type:Research paper, summary (national, other academic conference)   Publisher:(一社)日本癌学会  

  10. エクソソームを用いた小細胞肺癌における新規バイオマーカー探索(Discovery of novel biomarkers of small cell lung cancer by proteomics of exosomes.)

    菅 泰彦, 山本 真, 吉村 華子, 白山 敬之, 三宅 浩太郎, 武田 吉人, 伊藤 眞里, 足立 淳, 上條 陽平, 澤田 隆介, 山西 芳裕, 熊ノ郷 淳

    日本癌学会総会記事   Vol. 81回   page: P - 3298   2022.9

     More details

    Language:English   Publishing type:Research paper, summary (national, other academic conference)   Publisher:(一社)日本癌学会  

    J-GLOBAL

  11. 生薬比率を考慮した漢方薬の作用機序や効能のin silico予測

    島田 祐樹, 江副 晃洋, 澤田 隆介, 柴田 友和, 門脇 真, 山西 芳裕

    和漢医薬学会学術大会要旨集   Vol. 39回   page: 73 - 73   2022.8

     More details

    Authorship:Last author, Corresponding author   Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)   Publisher:(一社)和漢医薬学会  

    J-GLOBAL

  12. Analysis of drug-induced transcriptome responses by machine learning toward drug discovery Invited

    岩田通夫, 山西芳裕

    医学のあゆみ   Vol. 281 ( 11 ) page: 1103 - 1108   2022.6

     More details

    Authorship:Last author, Corresponding author   Language:Japanese   Publishing type:Article, review, commentary, editorial, etc. (trade magazine, newspaper, online media)  

    CiNii Books

    J-GLOBAL

  13. AIによるデータ駆動型研究が拓く生命医科学と創薬 Invited

    山西 芳裕

    日本内分泌学会雑誌   Vol. 98 ( 1 ) page: 247 - 247   2022.4

     More details

    Authorship:Lead author, Last author, Corresponding author   Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)   Publisher:(一社)日本内分泌学会  

    J-GLOBAL

  14. Network medicine for drug discovery Invited

    飯田緑, 岩田通夫, 山西芳裕

    Diabetes Journal   Vol. 49 ( 2 ) page: 71 - 74   2022.4

     More details

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

    J-GLOBAL

  15. Drug repositioning based on the docking affinity for all human protein structures obtained by AlphaFold2

    坂尻由子, 柴田友和, 澤田隆介, 山西芳裕

    日本薬学会年会要旨集(Web)   Vol. 142年会   page: 26L - pm10   2022.3

     More details

    Authorship:Last author, Corresponding author   Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    J-GLOBAL

  16. Large-scale prediction of food functions and elucidation of the mode-of-action by machine learning

    柴田友和, 田中由祐, 田口大夢, 澤田隆介, 青柳守紘, 平尾宜司, 山西芳裕

    日本薬学会年会要旨集(Web)   Vol. 142年会   page: 27L - pm08   2022.3

     More details

    Authorship:Last author, Corresponding author   Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    J-GLOBAL

  17. A structure generator to exhaustively create molecules with novel chemical substructures

    海東和麻, 山西芳裕

    日本薬学会年会要旨集(Web)   Vol. 142年会   page: 26T - pm02   2022.3

     More details

    Authorship:Last author, Corresponding author   Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    J-GLOBAL

  18. Data-driven drug discovery and molecular design by AI

    山西芳裕

    日本薬学会年会要旨集(Web)   Vol. 142年会   page: S41 - 1   2022.3

     More details

    Authorship:Last author, Corresponding author   Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    J-GLOBAL

  19. Drug side-effect prediction based on the binding affinity with all human protein structures obtained by AlphaFold2

    澤田隆介, 柴田友和, 坂尻由子, 山西芳裕

    日本薬学会年会要旨集(Web)   Vol. 142年会   page: 26J - am11   2022.3

     More details

    Authorship:Last author, Corresponding author   Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    J-GLOBAL

  20. AIが拓くデータ駆動型創薬とヘルスケア : 医薬品や食品のビッグデータ解析の最前線—Data-driven drug discovery and healthcare by artificial intelligence : recent advances in computational analysis of drugs and foods—特集 デジタル革命や数理科学を駆使したDisease-Free Societyの実現に向けての取り組み Invited

    山西 芳裕

    糖尿病・内分泌代謝科 = Diabetology, endocrinology & metabolology / 糖尿病・内分泌代謝科編集委員会 編   Vol. 54 ( 1 ) page: 26 - 34   2022.1

     More details

    Authorship:Lead author, Last author, Corresponding author   Language:Japanese   Publishing type:Article, review, commentary, editorial, etc. (scientific journal)   Publisher:科学評論社  

    CiNii Books

  21. Data-driven drug discovery and healthcare by machine learning: computational analysis of drugs and foods Invited

    山西芳裕

    Pharm Tech Japan   Vol. 38 ( 1 ) page: 69 - 74   2022.1

     More details

    Authorship:Lead author, Last author, Corresponding author   Language:Japanese   Publishing type:Article, review, commentary, editorial, etc. (scientific journal)  

    J-GLOBAL

  22. ヒト全タンパク質に対する結合親和性を考慮した医薬品化合物の薬理作用予測 Invited

    山西 芳裕

    日本臨床薬理学会学術総会抄録集   Vol. 43   page: 3-C-S41-2 - 2   2022

     More details

    Authorship:Lead author, Last author, Corresponding author   Language:Japanese   Publisher:一般社団法人 日本臨床薬理学会  

    医薬品開発において、化合物とタンパク質の結合親和性を定量的に評価することは非常に重要であり、ドッキングシミュレーションと機械学習は重要な役割を果たす。ドッキングシミュレーションには実験的に決定されたタンパク質の立体構造情報が必要であるが、現在立体構造データが利用可能なタンパク質はヒトゲノムにコードされている全タンパク質の一部に過ぎない。近年、AI技術の進歩とともにタンパク質立体構造の予測技術が大幅に向上してきている。なかでもニューラルネットワーク技術を取り入れたAlphaFold v2.0(以下AlphaFold2)は、X線結晶構造解析など実験的に決定したタンパク質立体構造と遜色ない精度を持つ。本研究では、AlphaFold2を活用してヒトゲノムにコードされている全タンパク質の立体構造情報に基づき、医薬品化合物の薬効や副作用予測を行う手法を提案する。まずAlphaFold2で予測したヒト全タンパク質(約20,000タンパク質配列)の立体構造データをAlphaFold Protein Structure Databaseより取得した。医薬品化合物に対してヒト全タンパク質立体構造とのドッキングシミュレーションを行い、それらの結合親和性プロファイルを作成し、様々な疾患に対する薬効や副作用を予測する機械学習モデルを構築した。提案手法は高性能の予測だけではなく、薬効や副作用の作用機序の考察を可能にした。提案手法は、医薬品開発に有用であることが期待できる。

    DOI: 10.50993/jsptsuppl.43.0_3-c-s41-2

    J-GLOBAL

  23. Link Prediction in Chemical Compound Network Under Observation Bias

    乾拓海, 原田将之介, LIU Yang, 竹内孝, 瀧川一学, 山西芳裕, 鹿島久嗣

    人工知能学会全国大会(Web)   Vol. 36th   2022

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    J-GLOBAL

  24. Recent advances in drug design by structure generator

    海東和麻, 山西芳裕

    Medchem News (Web)   Vol. 32 ( 1 )   2022

     More details

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

    J-GLOBAL

  25. トランスオミクス解析によるダイレクトリプログラミング誘導転写因子の予測

    濱野桃子, 江口凌平, 岩田通夫, 中村透, 山西芳裕

    日本再生医療学会総会(Web)   Vol. 21st   2022

     More details

    Authorship:Last author, Corresponding author   Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    J-GLOBAL

  26. Data-driven drug discovery and healthcare by artificial intelligence: recent advances in computational analysis of drugs and foods. Invited

    山西芳裕

    月刊糖尿病・内分泌代謝科   Vol. 54 ( 1 )   2022

     More details

    Authorship:Lead author, Last author, Corresponding author   Language:Japanese   Publishing type:Article, review, commentary, editorial, etc. (scientific journal)  

    J-GLOBAL

  27. Open platform “Mine′′: Development of Artificial Intelligence (AI) to accelerate new drug discovery

    樋口千洋, 黒田正孝, 黒田正孝, 伊藤眞里, 長尾知生子, 長尾知生子, 浜本隆二, 黒橋禎夫, 高村大也, 奥野恭史, 山西芳裕, 水口賢司, 水口賢司, 夏目やよい, 夏目やよい

    医療情報学連合大会論文集(CD-ROM)   Vol. 42nd   2022

     More details

    Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)  

    J-GLOBAL

  28. Data-driven drug discovery and healthcare by AI Invited

    山西芳裕

    日本癌学会学術総会抄録集(Web)   Vol. 81st   2022

     More details

    Authorship:Lead author, Last author, Corresponding author   Language:English   Publishing type:Research paper, summary (national, other academic conference)  

    J-GLOBAL

  29. Generation of novel drugs from chemical big data: an introduction of structure generators

    海東和麻, 山西芳裕

    実験医学   Vol. 39 ( 19 ) page: 3024 - 3027   2021.12

     More details

    Language:Japanese  

    J-GLOBAL

  30. AIによる創薬・診断の強化 AIによるデータ駆動型研究が拓く創薬

    山西 芳裕

    日本癌学会総会記事   Vol. 80回   page: [S20 - 1]   2021.9

     More details

    Language:English   Publisher:(一社)日本癌学会  

  31. 本態性振戦患者の血漿アミノ酸プロファイル

    三浦 史郎, 鎌田 崇嗣, 藤岡 竜太, 山西 芳裕

    臨床神経学   Vol. 61 ( Suppl. ) page: S298 - S298   2021.9

     More details

    Language:Japanese   Publisher:(一社)日本神経学会  

    J-GLOBAL

  32. Unraveling the relationships between chemical and organisms through network biology

    飯田緑, 山西芳裕

    環境ホルモン学会研究発表会プログラム・要旨集   Vol. 23回   page: 22 - 22   2021.9

     More details

    Language:Japanese  

    J-GLOBAL

  33. AIによるデータ駆動型研究が拓く創薬や医療

    山西 芳裕

    糖尿病   Vol. 64 ( 7 ) page: 404 - 404   2021.7

     More details

    Language:Japanese   Publisher:(一社)日本糖尿病学会  

  34. 創薬・創剤における人工知能の活用 機械学習によるデータ駆動型創薬

    山西 芳裕

    日本薬学会年会要旨集   Vol. 141年会   page: S12 - 2   2021.3

     More details

    Language:Japanese   Publisher:(公社)日本薬学会  

  35. Elucidating the modes of action by identification of transcription factors organizing chemically perturbed genes through large-scale ChIP-seq data.

    ZOU Zhaonan, 岩田通夫, 山西芳裕, 沖真弥

    日本薬学会年会要旨集(Web)   Vol. 141年会   page: 29V09 - am02S   2021.3

     More details

    Language:Japanese  

    J-GLOBAL

  36. 薬剤群のシナジー効果の機序を解明する

    山西 芳裕

    実験医学   Vol. 39(8)   page: 1257 - 1257   2021

  37. Construction of biologically-interpretable chemical–disease association focused on transcription factors organizing chemically-perturbed genes

    Zhaonan Zou, Iwata Michio, Yamanishi Yoshihiro, Oki Shinya

    Proceedings for Annual Meeting of The Japanese Pharmacological Society   Vol. 94   page: 1-Y-E3-4   2021

     More details

    Language:Japanese   Publisher:Japanese Pharmacological Society  

    Modification of disease-elicited gene expression is one of the core aspects in numerous drugs’ modes of action. To predict drug–disease associations, transcriptomics-based approaches with pathway analysis, graph theory and supervised machine learning-based calculation were developed. However, the pharmacological mechanism employed by drugs remain largely unknown.

    In this study, we focused on transcription factors (TFs) that integratively regulate differentially expressed genes (DEGs) in response to drug treatment. In particular, TF enrichment analysis (TFEA) was performed for each chemical to identify TFs with enriched binding for DEGs by combining the chemically perturbed transcriptome data (CTD) and TF-binding database ChIP-Atlas. Performance evaluation with area under the ROC curve (AUC) suggests the reliability of TFEA in drug target discovery (global AUC = 0.66). Furthermore, we successfully identified the key factors that link drugs to diseases or side effects by utilizing protein-disease database DisGeNET (global AUC = 0.68). This approach is with high confidence because it is fully based on actual experiments of given transcriptome data and public ChIP-seq data. In the pharmaceutical field, TFEA is useful to shed light on compounds failed to be approved by identifying TFs primarily involved in the modes of action, together with the factors associated with potential side effects. Approved drugs including agents composed of unidentified ingredients such as traditional herbal medicines can also be re-examined for novel targets and actions, thus beneficial to drug repositioning research.

    DOI: 10.1254/jpssuppl.94.0_1-y-e3-4

  38. 機械学習によるデータ駆動型研究が拓く創薬と医療

    山西芳裕

    俯瞰セミナーシリーズ報告書 機械学習と科学 令和2年     2021

     More details

  39. Construction of deep generative models for drug candidate chemical structures design using a new chemical representation

    海東和麻, 山西芳裕

    日本薬学会年会要旨集(Web)   Vol. 141st   2021

     More details

  40. Computational prediction of small molecules for direct reprogramming

    濱野桃子, 中村透, 岩田通夫, 江口凌平, 山西芳裕

    日本分子生物学会年会プログラム・要旨集(Web)   Vol. 44th   2021

     More details

  41. トランスオミクスアプローチによる一細胞レベルの心不全分子メカニズムの解明

    濱野桃子, 野村征太郎, 小室一成, 山西芳裕

    日本薬学会関東支部大会講演要旨集   Vol. 65th (CD-ROM)   2021

     More details

  42. Interaction network analysis of GPCRs

    檜垣優介, 根本航, 山西芳裕, 藤博幸

    日本分子生物学会年会プログラム・要旨集(Web)   Vol. 44th   2021

     More details

  43. AIによるデータ駆動型研究が拓く創薬や医療

    山西芳裕

    糖尿病(Web)   Vol. 64 ( 7 )   2021

     More details

  44. Data-driven drug discovery and healthcare by artificial intelligence

    山西芳裕

    CBI学会大会   Vol. 2021 (CD-ROM)   2021

     More details

  45. Data-driven drug discovery by artificial intelligence

    山西芳裕

    日本がん分子標的治療学会学術集会プログラム・抄録集   Vol. 25th   2021

     More details

  46. AIによるデータ駆動型研究が拓く創薬

    山西芳裕

    日本癌学会学術総会抄録集(Web)   Vol. 80th   2021

     More details

  47. 遺伝子発現プロファイルから医薬候補化合物を設計する構造生成器

    海東和麻, 山西芳裕

    構造活性相関シンポジウム講演要旨集   Vol. 49th (CD-ROM)   2021

     More details

  48. Prediction of drug-induced transcriptome responses by tensor factorization toward drug discovery

    岩田通夫, YUAN Longhao, ZHAO Qibin, 田部井靖生, 山西芳裕

    実験医学   Vol. 38 ( 20 ) page: 3401 - 3407   2020.12

     More details

    Language:Japanese  

    J-GLOBAL

  49. 【神経症候学と神経診断学-AIは味方か敵か?】特異的症状の症候学・診断学とAI 認知機能障害

    三浦 史郎, 山西 芳裕, 大八木 保政

    Clinical Neuroscience   Vol. 38 ( 11 ) page: 1389 - 1390   2020.11

     More details

    Language:Japanese   Publisher:(株)中外医学社  

    J-GLOBAL

  50. 遺伝性脊髄小脳変性症にトピラマートは有効か?

    三浦 史郎, 澤田 隆介, 貴田 浩志, 頼田 章子, 鎌田 崇嗣, 山西 芳裕

    臨床神経学   Vol. 60 ( Suppl. ) page: S433 - S433   2020.11

     More details

    Language:Japanese   Publisher:(一社)日本神経学会  

  51. 薬物治療標的となりうる膵がん新規ドライバー遺伝子ASAP2の同定

    増田 隆明, 藤井 昌志, 岩田 通夫, 松本 佳大, 大津 甫, 武石 一樹, 米村 祐輔, 山西 芳裕, 三森 功士

    日本癌学会総会記事   Vol. 79回   page: OJ4 - 2   2020.10

     More details

    Language:English   Publisher:(一社)日本癌学会  

  52. Recent advances in drug discovery and healthcare using artificial intelligence

    海東和麻, 山西芳裕

    実験医学   Vol. 38 ( 15 ) page: 2623 - 2628   2020.9

     More details

    Language:Japanese  

    J-GLOBAL

  53. Data-driven drug discovery and repositioning by artificial intelligence

    山西芳裕

    医学のあゆみ   Vol. 274 ( 9 ) page: 843 - 847   2020.8

     More details

  54. 人工知能を活用した医薬品化合物の効能および副作用の予測

    山西 芳裕

    Pharm stage / 技術情報協会 編   Vol. 20 ( 4 ) page: 48 - 60   2020.7

     More details

    Language:Japanese   Publisher:技術情報協会  

    CiNii Books

    J-GLOBAL

  55. cutting-edge medicine 人工知能(AI)技術のヘルスケア利活用 深層学習によるデータ駆動型創薬—Data-driven drug discovery by deep learning

    海東 和麻, 山西 芳裕

    Precision medicine = プレシジョンメディシン / 「Precision medicine」編集委員会 編   Vol. 3 ( 5 ) page: 401 - 404   2020.5

     More details

    Language:Japanese   Publisher:北隆館  

    CiNii Books

    Other Link: https://search.jamas.or.jp/link/ui/2020231859

  56. Identification of novel CFTR correctors by in silico screening

    谷口正伍, 福田亮介, BERENGER Francois, 澤田隆介, 山口美穂, 井上敬太郎, 青木俊介, 山西芳裕, 沖米田司

    日本薬学会年会要旨集(Web)   Vol. 140年会   page: 26Q - am089S   2020.3

     More details

    Language:Japanese  

    J-GLOBAL

  57. Data-driven drug discovery and healthcare by artificial intelligence

    山西芳裕

    日本薬学会年会要旨集(Web)   Vol. 140年会   page: S43 - 5   2020.3

     More details

    Language:Japanese  

    J-GLOBAL

  58. パイオニア転写因子を考慮したデータ駆動型ダイレクトリプログラミング

    江口凌平, 濱野桃子, 岩田通夫, 中村透, 沖真弥, 山西芳裕

    日本分子生物学会年会プログラム・要旨集(Web)   Vol. 43rd   2020

     More details

  59. 多層オミクス解析による遺伝子発現機構のディジーゾーム解析と治療薬探索

    岩田通夫, 沖真弥, 山西芳裕

    日本分子生物学会年会プログラム・要旨集(Web)   Vol. 43rd   2020

     More details

  60. 低分子化合物のオミクス解析によるデータ駆動型ダイレクトリプログラミング

    中村透, 岩田通夫, 濱野桃子, 江口凌平, 山西芳裕

    日本分子生物学会年会プログラム・要旨集(Web)   Vol. 43rd   2020

     More details

  61. Novel drug molecular structure generation system using deep learning

    海東和麻, 山西芳裕

    日本薬学会年会要旨集(Web)   Vol. 140th   2020

     More details

  62. 遺伝子発現制御に着目した薬剤摂動トランスクリプトームと大規模ChIP-seqデータの統合解析による薬剤作用ターゲット探索

    鄒兆南, 岩田通夫, 山西芳裕, 沖真弥

    日本分子生物学会年会プログラム・要旨集(Web)   Vol. 43rd   2020

     More details

  63. がん予防~大腸がん予防の今後を考える~ AIを用いた抗がん作用薬の同定(Cancer Prevention - Contemplation on Future Colorectal Cancer Prevention AI-based identification of anticancer drugs)

    山西 芳裕

    日本癌学会総会記事   Vol. 78回   page: SP6 - 3   2019.9

     More details

    Language:English   Publisher:(一社)日本癌学会  

  64. 数理科学・情報科学と生命科学の融合-和漢医薬学研究の新地平へ向けて AI技術による和漢薬の作用機序解析と効能予測

    山西 芳裕

    和漢医薬学会学術大会要旨集   Vol. 36回   page: 56 - 56   2019.8

     More details

    Language:Japanese   Publisher:(一社)和漢医薬学会  

    J-GLOBAL

  65. 機械学習によるデータ駆動型ドラッグリポジショニング—Data-driven drug repositioning by machine learning—特集 創薬インフォマティクス

    山西 芳裕

    医学のあゆみ   Vol. 268 ( 12 ) page: 973 - 977   2019.3

     More details

    Language:Japanese   Publisher:医歯薬出版  

    医薬品開発の低迷を打開する戦略として、既存薬の新しい効能を発見し、本来とは別の疾患に対する治療薬として新薬開発を行うドラッグリポジショニング(DR)が注目されている。近年の生命医科学や創薬科学では疾患、薬物、低分子化合物、遺伝子、蛋白質、代謝産物などに関する大量のオミックスデータが得られるようになり、このようなビッグデータのDRへの有効活用が期待されている。本稿では、さまざまな医薬ビッグデータと機械学習(AI基盤技術)を用いてDRを行うインシリコ(in silico)手法を解説する。とくに、分子プロファイルの比較、疾患の分子機序類似性、ポリファーマコロジー、パスウェイ制御の観点から、疾患に対する治療薬候補を網羅的かつ体系的に予測する手法とその応用例を紹介する。(著者抄録)

    CiNii Books

    J-GLOBAL

    Other Link: https://search.jamas.or.jp/link/ui/2019144389

  66. 漢方薬の効能を予測するアルゴリズム/データベースの開発

    山西 芳裕, 門脇 真

    バイオサイエンスとインダストリー   Vol. 77 ( 2 ) page: 126 - 127   2019.3

     More details

    Language:Japanese   Publisher:(一財)バイオインダストリー協会  

    J-GLOBAL

  67. 内科治療と創薬のための機械学習によるオミクスデータ解析(Omics Data Analysis by Machine Learning for Medical Treatment and Drug Discovery)

    山西 芳裕

    日本循環器学会学術集会抄録集   Vol. 83回   page: SS13 - 5   2019.3

     More details

    Language:English   Publisher:(一社)日本循環器学会  

    J-GLOBAL

  68. 生命医科学や創薬における機械学習の最前線

    山西 芳裕

    化学と教育   Vol. 67 ( 2 ) page: 66 - 69   2019.2

     More details

    Language:Japanese   Publisher:公益社団法人 日本化学会  

    近年の生命医科学では,遺伝子,タンパク質,化合物,薬物,疾患に関するビッグデータが得られるようになってきた。ビッグデータ解析から新しい医学的発見や新薬開発につなげる研究が期待されている。本稿では,様々な医薬データを機械学習(人工知能の基盤技術)で有効活用した疾患研究や創薬応用を紹介する。特に,既存薬物から新規効能を発見するドラッグリポジショニングに基づく創薬への応用を解説する。

    DOI: 10.20665/kakyoshi.67.2_66

    CiNii Books

    J-GLOBAL

  69. 化合物の薬効や副作用をビッグデータから予測する機械学習—Machine Learning to Predict Pharmaceutical Effects and Side Effects of Compounds from Big Data

    山西 芳裕

    化學工業   Vol. 70 ( 2 ) page: 152 - 156   2019.2

     More details

    Language:Japanese   Publisher:小峰工業出版  

    CiNii Books

  70. AI-based identification of anticancer drugs

    山西芳裕

    日本癌学会学術総会抄録集(Web)   Vol. 78th   2019

     More details

  71. 深層学習を利用した分子設計システムの構築

    海東和麻, 山西芳裕

    メディシナルケミストリーシンポジウム講演要旨集   Vol. 37th   2019

     More details

  72. 深層学習を利用した分子設計システムの構築

    海東和麻, 山西芳裕

    メディシナルケミストリーシンポジウム講演要旨集   Vol. 37th   2019

     More details

  73. 医薬品設計を志向した深層学習モデルの開発

    海東和麻, 山西芳裕

    日本薬学会九州支部大会講演要旨集   Vol. 36th   2019

     More details

  74. 化合物の薬効や副作用をビッグデータから予測する機械学習

    山西芳裕

    化学工業   Vol. 70 ( 2 )   2019

     More details

  75. 一細胞解析による心不全の分子病態メカニズムの解明

    濱野桃子, 野村征太郎, 野村征太郎, 油谷浩幸, 小室一成, 山西芳裕

    日本分子生物学会年会プログラム・要旨集(Web)   Vol. 42nd   2019

     More details

  76. GPCR間相互作用ペアの予測手法の改良

    島村幸稀英, LIMVIPHUVADH Vachiranee, 山西芳裕, 藤博幸, 根本航

    日本細胞生物学会大会(Web)   Vol. 71st   2019

     More details

  77. GPCR間相互作用ペアの予測手法

    島村幸稀英, LIMVIPHUVADH Vachiranee, 山西芳裕, 藤博幸, 根本航

    GPCR研究会プログラム・抄録集   Vol. 15th   2019

     More details

  78. AI創薬:薬効や副作用を予測するデータ駆動型アプローチ

    山西芳裕

    日本リウマチ学会総会・学術集会プログラム・抄録集   Vol. 63rd   2019

     More details

  79. AI創薬:薬効や副作用を予測するデータ駆動型アプローチ

    山西芳裕

    日本実験動物学会総会講演要旨集(Web)   Vol. 66th   2019

     More details

  80. データ駆動型ドラッグリポジショニング—Data-driven drug repositioning—特集 プレシジョンメディシンと創薬

    山西 芳裕

    Precision medicine = プレシジョンメディシン / 「Precision medicine」編集委員会 編   Vol. 1 ( 1 ) page: 36 - 39   2018.10

     More details

    Language:Japanese   Publisher:北隆館  

    効率的な創薬戦略として、既存薬の新しい効能を発見し、本来とは別の疾患に対する治療薬として開発するドラッグリポジショニングが注目されている。近年の生命医科学では、疾患、薬物、遺伝子、タンパク質、代謝産物に関する大量のオミックスデータが得られるようになり、このようなビッグデータのドラッグリポジショニングへの有効活用が期待されている。本稿では、様々な医薬ビッグデータと機械学習(AI基盤技術)を用いてドラッグリポジショニングを行うインシリコ手法を紹介する。(著者抄録)

    CiNii Books

    J-GLOBAL

    Other Link: https://search.jamas.or.jp/link/ui/2019124444

  81. AI創薬:薬効や副作用を予測するデータ駆動型アプローチ

    山西芳裕, 山西芳裕

    構造活性フォーラム講演要旨集   Vol. 2018   page: 1(1)‐1(2),1‐11 - 227   2018.6

     More details

    Language:Japanese  

    J-GLOBAL

  82. Tensor‐train分解アルゴリズムによる高次テンソルデータ解析:薬物応答遺伝子発現データへの応用

    岩田通夫, YUAN Longhao, ZHAO Qibin, 田部井靖生, BERENGER Francois, 澤田隆介, 秋好紗弥香, 山西芳裕, 山西芳裕

    日本計算機統計学会大会論文集   Vol. 32nd ( 0 ) page: 76‐77 - 77   2018.5

     More details

    Language:Japanese   Publisher:日本計算機統計学会  

    DOI: 10.20551/jscstaikai.32.0_76

    J-GLOBAL

  83. Drug Discovery Using <i>In Silico</i> Methods and Drug Repositioning

    Yamanishi Yoshihiro

    Journal of Pharmaceutical Science and Technology, Japan   Vol. 78 ( 2 ) page: 77 - 81   2018

     More details

    Language:Japanese   Publisher:公益社団法人 日本薬剤学会  

    DOI: 10.14843/jpstj.78.77

  84. 標的分子を考慮した医薬品化合物の副作用プロファイルの予測

    水谷紗弥佳, EDOUARD Pauwels, EDOUARD Pauwels, VERONIQUE Stoven, VERONIQUE Stoven, 五斗進, 山西芳裕, 山西芳裕

    ケモインフォマティクス討論会予稿集(Web)   Vol. 41st   2018

     More details

  85. 医薬ビックデータとフェノタイプスクリーニングによる変形性関節症治療薬の探索

    味八木 茂, 山西 芳裕

    研究結果報告書集 : 交通安全等・高齢者福祉   Vol. 24   page: 123 - 125   2018

     More details

    Language:Japanese   Publisher:三井住友海上福祉財団  

    CiNii Books

    J-GLOBAL

  86. 一般化合物の毒性予測

    山西 芳裕

    日本化学会情報化学部会誌   Vol. 36 ( 3 ) page: 42   2018

     More details

    Language:Japanese   Publisher:公益社団法人 日本化学会・情報化学部会  

    DOI: 10.11546/cicsj.36.42

  87. ドラッグリポジショニングによるCFTRコレクターの開発

    藤原健, 山西芳裕, 田中健一郎, 沖米田司

    日本薬学会年会要旨集(CD-ROM)   Vol. 138th ( 3 ) page: ROMBUNNO.26PA‐pm190 - 190   2018

     More details

    Language:Japanese  

    J-GLOBAL

  88. Drug Discovery Using In Silico Methods and Drug Repositioning

    山西芳裕, 山西芳裕

    薬剤学(Web)   Vol. 78 ( 2 )   2018

     More details

  89. Tensor-train分解アルゴリズムによる高次テンソル解析:薬物応答遺伝子発現データからの創薬

    岩田通夫, YUAN Longhao, ZHAO Qibin, 田部井靖生, 山西芳裕

    統計関連学会連合大会講演報告集   Vol. 2018   2018

     More details

  90. Tensor-train分解アルゴリズムによる薬物応答遺伝子発現データからの創薬

    岩田通夫, YUAN Longhao, ZHAO Qibin, 田部井靖生, 山西芳裕, 山西芳裕

    ケモインフォマティクス討論会予稿集(Web)   Vol. 41st   2018

     More details

  91. 漢方薬リポジショニング:ビッグデータと機械学習による漢方薬の効能予測

    澤田隆介, 岩田通夫, 梅崎雅人, 臼井義比古, 小林敏一, 窪野孝貴, 林周作, 門脇真, 山西芳裕, 山西芳裕

    ケモインフォマティクス討論会予稿集(Web)   Vol. 41st   2018

     More details

  92. 遺伝子発現機構のディジーゾーム解析による疾患間の関連性解析と治療薬探索

    岩田通夫, 沖真弥, 田部井靖生, 山西芳裕, 山西芳裕

    日本分子生物学会年会プログラム・要旨集(Web)   Vol. 41st   2018

     More details

  93. 『AI,インシリコ』による創薬研究,化合物評価の最前線 インシリコによるドラッグリポジショニング研究

    山西芳裕, 山西芳裕

    月刊PHARM STAGE   Vol. 17 ( 8 ) page: 15‐19 - 10   2017.11

     More details

    Language:Japanese  

    CiNii Books

    J-GLOBAL

  94. トクシュウ 『 AI,インシリコ 』 ニ ヨル ソウヤク ケンキュウ,カゴウブツ ヒョウカ ノ サイゼンセン

      Vol. 17 ( 8 ) page: 15 - 19   2017.11

     More details

    Language:Japanese  

    CiNii Books

  95. 機械学習とデータ駆動型ドラッグリポジショニングによる創薬

    山西芳裕, 山西芳裕

    CBI学会大会   Vol. 2017   page: 36   2017.10

     More details

    Language:Japanese  

    J-GLOBAL

  96. 異種オミックスデータに基づく医薬品候補化合物の標的分子や効能の予測

    澤田隆介, 山西芳裕

    CBI学会大会   Vol. 2017   page: 68   2017.10

     More details

    Language:Japanese  

    J-GLOBAL

  97. データ駆動型ドラッグリポジショニングによるシステム創薬

    山西芳裕, 山西芳裕

    HAB研究機構学術年会プログラム・要旨集   Vol. 24th   page: 10‐11   2017.6

     More details

    Language:Japanese  

    J-GLOBAL

  98. 生命科学・医学研究における事例に学ぶ 18.データ駆動型の創薬―統計的手法を用いて

    山西芳裕, 山西芳裕, 山西芳裕

    実験医学   Vol. 35 ( 5 ) page: 891‐894 - 894   2017.3

     More details

    Language:Japanese  

    J-GLOBAL

  99. ドラッグリポジショニングによるCFTRコレクターの開発

    藤原健, 山西芳裕, 田中健一郎, 沖米田司

    日本生化学会大会(Web)   Vol. 90th   page: ROMBUNNO.1P‐1244 (WEB ONLY) - 1244]   2017

     More details

    Language:Japanese  

    J-GLOBAL

  100. GGIP:GPCR間相互作用ペア予測手法

    根本航, 山西芳裕, LIMVIPHUVADH Vachiranee, 藤博幸

    日本蛋白質科学会年会プログラム・要旨集   Vol. 16th   page: 29 - 06]   2016.5

     More details

    Language:Japanese  

    J-GLOBAL

  101. GPCR間相互作用状態を変化させることで疾患を引き起こす変異の予測

    藤代俊輔, VACHIRANEE Limviphuvadh, SEBASTIAN Maurer‐Stroh, 山西芳裕, 藤博幸, 根本航

    日本生化学会大会(Web)   Vol. 89th   page: ROMBUNNO.2T11‐05(2P‐126) (WEB ONLY) - 126)]   2016

     More details

    Language:Japanese  

    J-GLOBAL

  102. 医薬ビッグデータと機械学習によるインシリコ創薬

    山西芳裕, 山西芳裕, 山西芳裕

    日本計算機統計学会シンポジウム論文集   Vol. 29th   page: 151 - 152   2015.11

     More details

    Language:Japanese  

    J-GLOBAL

  103. ドラッグリポジショニング 既存薬が新薬に生まれ変わる温故知新のサイエンス!第11回 ビッグデータに基づくインシリコDRスクリーニング

    山西芳裕

    実験医学   Vol. 33 ( 11 ) page: 1824 - 1828   2015.7

     More details

    Language:Japanese  

    J-GLOBAL

  104. 「データ中心科学」バイオインフォマティクスやケモインフォマティクスにおける機械学習

    山西芳裕

    人工知能   Vol. 30 ( 2 ) page: 224 - 229   2015.3

     More details

    Language:Japanese  

    CiNii Books

    J-GLOBAL

  105. Machine Learning in Bioinformatics and Chemoinformatics

    Yamanishi Yoshihiro

    journal of the Japanese Society for Artificial Intelligence   Vol. 30 ( 2 ) page: 224 - 229   2015.3

     More details

    Language:Japanese   Publisher:社団法人人工知能学会  

    DOI: 10.11517/jjsai.30.2_224

    CiNii Books

  106. 化合物応答遺伝子発現プロファイルの大規模解析による生理活性化合物の作用機序推定と創薬への応用

    岩田通夫, 澤田隆介, 岩田浩明, 山西芳裕, 山西芳裕

    日本生化学会大会(Web)   Vol. 88th   page: 4T26L-03(3P0880) (WEB ONLY) - 03(3P0880)]   2015

     More details

    Language:Japanese  

    J-GLOBAL

  107. 薬物の標的タンパク質プロファイルとオミックス情報に基づくドラッグリポジショニング

    澤田隆介, 岩田浩明, 山西芳裕, 山西芳裕

    日本生化学会大会(Web)   Vol. 88th   page: 2P0922 (WEB ONLY) - [2P0922]   2015

     More details

    Language:Japanese  

    J-GLOBAL

  108. 和漢薬・生薬由来化合物のターゲットタンパク質探索データベースの構築

    梅嵜雅人, 山西芳裕, 山西芳裕

    和漢医薬学会学術大会要旨集   Vol. 32nd   page: 99 - 99   2015

     More details

    Language:Japanese  

    J-GLOBAL

  109. GGIP: GPCR間相互作用ペア予測手法

    根本航, 山西芳裕, VACHIRANEE Limviphuvadh, 藤博幸

    日本生化学会大会(Web)   Vol. 87th   page: 2T09P-06(2P-272) (WEB ONLY)   2014

     More details

    Language:Japanese  

    J-GLOBAL

  110. ネットワーク解析によるドラッグリポジショニング

    山西芳裕

    日本薬剤学会年会講演要旨集(Web)   Vol. 29th   page: GAKUJUTSUSHIMPOJIUMU5,YAMANISHI (WEB ONLY) - 44   2014

     More details

    Language:Japanese  

    J-GLOBAL

  111. 異種オミックスデータの融合に基づく分子間相互作用ネットワークの予測

    山西芳裕

    Proc Annu Conf Jpn Soc Bioinform   Vol. 2013   page: 55   2013.10

     More details

    Language:Japanese  

    J-GLOBAL

  112. ドラッグリポジショニングのためのイン・シリコ法の開発

    岩田浩明, 吉原美奈子, 山西芳裕

    構造活性相関シンポジウム講演要旨集   Vol. 41st   page: 19 - 20   2013.10

     More details

    Language:Japanese  

    J-GLOBAL

  113. 機械学習による薬物の標的分子や副作用の網羅的予測

    山西芳裕

    構造活性相関シンポジウム講演要旨集   Vol. 41st   page: 5 - 6   2013.10

     More details

    Language:Japanese  

    J-GLOBAL

  114. ゲノム情報,ケミカル情報,薬理情報から薬物標的分子を予測する統計手法

    山西芳裕

    統計関連学会連合大会講演報告集   Vol. 2013   page: 140   2013.9

     More details

    Language:Japanese  

    J-GLOBAL

  115. スパース統計モデルによる薬物-疾患ネットワークの予測(合同企画セッション:バイオデータマイニング)

    岩田 浩明, 山西 芳裕

    電子情報通信学会技術研究報告. NC, ニューロコンピューティング   Vol. 113 ( 111 ) page: 155 - 155   2013.6

     More details

    Language:Japanese   Publisher:一般社団法人電子情報通信学会  

    近年の新薬開発の行き詰まりを打開する方法として、既存薬の作用を徹底的に調べあげ新たに薬効を見つけ出し、本来それが開発された疾患とは別の疾患に対する治療薬として再開発する創薬研究が注目を浴びている。本研究では、薬物に関するケミカルなデータと疾患に関するフェノタイプのデータから潜在的な薬物と疾患の関係を網羅的に予測する機械学習の手法を開発した。教師付き学習のアルゴリズムにスパース統計モデルを導入することで特徴抽出を可能にし、予測された関係に関与している薬物の標的タンパク質と疾患のフェノタイプの組み合わせを同定する点が独自の点である。また抽出された標的タンパク質の生物学的妥当性をPathway Enrichment解析を用いて評価した。本発表ではこれらの結果と、既知のデータから学習して生成したモデルを適用することで得られる新規の薬と疾患の関連解析の結果について紹介する。

    CiNii Books

  116. スパース統計モデルによる薬物‐疾患ネットワークの予測

    岩田浩明, 山西芳裕

    電子情報通信学会技術研究報告   Vol. 113 ( 111(NC2013 1-14) ) page: 155 - 1   2013.6

     More details

    Language:Japanese  

    CiNii Books

    J-GLOBAL

  117. ドラッグリポジショニングへの応用に向けた薬物‐疾患ネットワーク予測

    岩田浩明, 吉原美奈子, 山西芳裕

    日本分子生物学会年会プログラム・要旨集(Web)   Vol. 36th   page: 3P-1055 (WEB ONLY)   2013

     More details

    Language:Japanese  

    J-GLOBAL

  118. 薬物・標的タンパク質間相互作用ネットワークの予測

    山西芳裕, 山西芳裕

    CICSJ Bull (Web)   Vol. 31 ( 2 ) page: 26 - 26   2013

     More details

    Language:Japanese   Publisher:Division of Chemical Information and Computer Sciences The Chemical Society of Japan  

    DOI: 10.11546/cicsj.31.26

    J-GLOBAL

  119. 創薬科学におけるバイオインフォマティクス

    山西 芳裕

    日本化学会情報化学部会誌   Vol. 31 ( 2 ) page: 25 - 25   2013

     More details

    Language:Japanese   Publisher:Division of Chemical Information and Computer Sciences The Chemical Society of Japan  

    DOI: 10.11546/cicsj.31.25

  120. GPCRヘテロダイマー形成ペアの組織レベルでの優先的な共発現

    根本航, 山西芳裕, 藤博幸

    日本生化学会大会(Web)   Vol. 85th   page: 2T09-06 (WEB ONLY) - 06   2012

     More details

    Language:Japanese  

    J-GLOBAL

  121. 薬剤標的タンパク質と副作用の関連分析のための統計手法

    水谷紗弥佳, PAUWELS Edouard, STOVEN Veronique, 五斗進, 山西芳裕

    日本分子生物学会年会プログラム・要旨集(Web)   Vol. 35th   page: 4P-0052 (WEB ONLY) - 53   2012

     More details

    Language:Japanese  

    J-GLOBAL

  122. Computational Method to Predict Interacting Pairs of Druggable GPCRs

    Nemoto Wataru, Yamanishi Yoshihiro, Toh Hiroyuki

    Abstracts for Annual Meeting of Japanese Proteomics Society   Vol. 2012 ( 0 ) page: 86 - 86   2012

     More details

    Language:Japanese   Publisher:日本プロテオーム学会(日本ヒトプロテオーム機構)  

    DOI: 10.14889/jhupo.2012.0.86.0

    J-GLOBAL

  123. KEGG OC:系統関係に基づいた大規模オーソログクラスタの自動生成

    守屋勇樹, 中谷明弘, 片山俊明, 伊藤真純, 平糠和志, 川島秀一, 奥田修二郎, 田中道廣, 時松敏明, 山西芳裕, 吉沢明康, 金久實, 五斗進

    日本分子生物学会年会プログラム・要旨集(Web)   Vol. 35th   page: 3P-0075 (WEB ONLY)   2012

     More details

    Language:Japanese  

    J-GLOBAL

  124. Gタンパク質共役型受容体オリゴマー相互作用ペア予測

    根本航, 山西芳裕, 藤博幸

    生化学   Vol. 84回   page: ROMBUNNO.2P-0389 - 0389   2011

     More details

    Language:Japanese  

    J-GLOBAL

  125. 複数生物種ネットワークの同時予測 : 半教師つき学習によるアプローチ—Simultaneous Inference of Multiple Biological Networks—バイオ情報学(BIO) Vol.2010-BIO-21

    鹿島 久嗣, 山西 芳裕, 加藤 毅

    情報処理学会研究報告   Vol. 2010年度 ( 2 ) page: 1 - 8   2010.8

     More details

    Language:Japanese   Publisher:情報処理学会  

    CiNii Books

  126. Simultaneous inference of multiple biological networks

    鹿島 久嗣, 山西 芳裕, 加藤 毅

    IEICE technical report   Vol. 110 ( 82 ) page: 111 - 118   2010.6

     More details

    Language:Japanese   Publisher:電子情報通信学会  

  127. Simultaneous inference of multiple biological networks

    鹿島 久嗣, 山西 芳裕, 加藤 毅

    IEICE technical report   Vol. 110 ( 83 ) page: 111 - 118   2010.6

     More details

    Language:Japanese   Publisher:電子情報通信学会  

  128. Simultaneous Inference of Multiple Biological Networks

    Hisashi Kashima, Yoshihiro Yamanishi, Tsuyoshi Kato, Masashi Sugiyama, Koji Tsuda

    IPSJ SIG technical reports   Vol. 2010 ( 19 ) page: 1 - 8   2010.6

     More details

    Language:Japanese   Publisher:Information Processing Society of Japan (IPSJ)  

    The existing supervised methods for biological network inference work on each of the networks individually based only on intra-species information such as gene expression data. We believe that it will be more effective to use genomic data and cross-species evolutionary information from different species simultaneously, rather than to use the genomic data alone. We created a new semi-supervised learning method called Link Propagation for inferring biological networks of multiple species based on genome-wide data and evolutionary information. The new method was applied to simultaneous reconst...

  129. Simultaneous Inference of Multiple Biological Networks

    鹿島久嗣, 山西芳裕, 加藤毅, 杉山将, 津田宏治

    電子情報通信学会技術研究報告   Vol. 110 ( 83(NC2010 1-28) ) page: 111 - 118   2010.6

     More details

    Language:Japanese   Publisher:情報処理学会  

    従来、生体ネットワークの予測は、遺伝子発現などの個々の生物種のもつ情報をもとに、種別に行われてきた。これに対し、本研究では 「リンク伝搬法」 と名付けた半教師つき学習法によって、複数の生物種のネットワークを同時に予測する方法を提案する。各生物種のもつ情報として遺伝子発現の類似度を、生物種間をまたぐ情報としてアミノ酸配列の類似度を用いて、C. elegans、H. pylori および S. cerevisiae のネットワークの同時予測を行い、ペアワイズ SVM などの既存手法を精度と速度の両面において上回ることを示す。The existing supervised methods for biological network inference work on each of the networks individually based only on intra-species information such as gene expression data. We believe that it will be more effective to use genomic data and cross-species evolutionary information from different species simultaneously, rather than to use the genomic data alone. We created a new semi-supervised learning method called Link Propagation for inferring biological networks of multiple species based on genome-wide data and evolutionary information. The new method was applied to simultaneous reconstruction of three metabolic networks of C. elegans, H. pylori, and S. cerevisiae, based on gene expression similarities and amino acid sequence similarities. The experimental results proved that the new simultaneous network inference method consistently improves the predictive performance over the individual network inferences, and it also outperforms in accuracy and speed other established methods such as the pairwise support vector machine.

    CiNii Books

    J-GLOBAL

  130. Link Propagation: a semi-supervised approach to link prediction

    鹿島 久嗣, 加藤 毅, 山西 芳裕

    人工知能基本問題研究会   Vol. 73   page: 19 - 24   2009.3

     More details

    Language:Japanese   Publisher:人工知能学会  

    CiNii Books

  131. Link Propagation: A Semi-supervised Approach to Link Prediction

    鹿島久嗣, 加藤毅, 山西芳裕, 杉山将, 津田宏治

    人工知能学会人工知能基本問題研究会資料   Vol. 73rd   page: 19 - 24   2009.3

     More details

    Language:Japanese  

    J-GLOBAL

  132. KEGG OC:網羅的なオーソログクラスターの自動生成

    中谷明弘, 伊藤真純, 奥田修二郎, 川島秀一, 田中道廣, 時松敏明, 片山俊明, 平糠和志, 守屋勇樹, 山西芳裕, 吉沢明康, 金久實

    生化学     page: 4P-0986   2008

     More details

    Language:Japanese  

    J-GLOBAL

  133. KEGG OC:オーソログクラスターのマニュアルアノテーション

    川島秀一, 伊藤真純, 奥田修二郎, 片山俊明, 田中道廣, 時松敏明, 中谷明弘, 平糠和志, 守屋勇樹, 山西芳裕, 吉沢明康, 金久實

    生化学     page: 4P-0987   2008

     More details

    Language:Japanese  

    J-GLOBAL

  134. KEGG OC:全生物種ゲノムにおけるオーソログ遺伝子のバリエーションと高速検索技術

    片山俊明, 伊藤真純, 奥田修二郎, 川島秀一, 田中道廣, 時松敏明, 中谷明弘, 平糠和志, 守屋勇樹, 山西芳裕, 吉沢明康, 金久實

    生化学   Vol. 81回・31回   page: 4T9-4 - 4   2008

     More details

    Language:Japanese  

    J-GLOBAL

  135. ネットワーク推定とドメインプロファイル解析による機能未知遺伝子の探索

    岡本忍, 山西芳裕, 得平茂樹, 金久實, 中村保一

    日本植物生理学会年会要旨集   Vol. 48th ( 0 ) page: 233 - 558   2007.3

     More details

    Language:Japanese   Publisher:日本植物生理学会  

    Prediction of molecular interaction networks from large-scale datasets in genomics and other omics experiments is an important task in terms of both developing bioinformatics methods and solving biological problems. We have applied a kernel-based network inference method for extracting functionally related genes to the response of nitrogen deprivation in cyanobacteria &lt;i&gt;Anabaena&lt;/i&gt; PCC7120 integrating three heterogeneous datasets: microarray, phylogenetic profiles, and gene orders on the chromosome. We obtained 1348 predicted genes that are somehow related to known genes in KEGG PATHWAY. While this dataset contained previously known genes related to the nitrogen deprivation response, it also contained unknown genes. Moreover, we attempted to select any relevant genes using the constraints of Pfam domains and NtcA binding sites. We found candidates of nitrogen metabolism-related genes, which are depicted as extensions of existing KEGG PATHWAYs. We showed promising results suggesting that our approach will be helpful in designing experiments in the post-genome era.

    DOI: 10.14841/jspp.2007.0.558.0

    J-GLOBAL

  136. Prediction of Protein-Protein Interactions by Using Co-Evolutionary Information

    SATO Tetsuya, YAMANISHI Yoshihiro, KANEHISA Minoru, TOH Hiroyuki

    Biophysics   Vol. 47 ( 1 ) page: 4 - 11   2007.1

     More details

    Language:Japanese   Publisher:一般社団法人日本生物物理学会  

    A distance matrix is a set of genetic distances between all possible pairs of proteins under consideration, and is used to construct a phylogenetic tree by the distance matrix method. Pazos and Valencia (2001) have developed a method to predict protein-protein interaction by evaluating the similarity of the distance matrices, under the assumption that the phylogenetic trees of interacting proteins resemble each other through co-evolution. It is known, however, that the prediction includes many false positives. We postulated that the cause of the false positives is the background similarity of the phylogenetic relationship of the source organisms. We have developed a method to exclude such information from the distance matrices with a projection operator. The number of false positives was drastically reduced from the prediction by evaluating the similarity between the residuals after the projection operation.

    DOI: 10.2142/biophys.47.004

    CiNii Books

    J-GLOBAL

  137. 共進化の強度とインターフェースの構造的特徴との関連

    佐藤哲也, 山西芳裕, 金久實, 藤博幸

    生化学     page: 4P-0267   2007

     More details

    Language:Japanese  

    J-GLOBAL

  138. 予測と発見 カーネル法による複数のゲノムデータからのタンパク質間機能ネットワークの推定

    山西芳裕, VERT Jean‐Philippe

    統計数理   Vol. 54 ( 2 ) page: 357 - 373   2006.12

     More details

    Language:Japanese  

    CiNii Books

    J-GLOBAL

  139. Estimating Protein Network from Multiple Genomic Data by Kernel Methods

    Vert Jean-Philipp

    統計数理 = Proceedings of the Institute of Statistical Mathematics   Vol. 54 ( 2 ) page: 357 - 373   2006.12

     More details

    Language:Japanese   Publisher:統計数理研究所  

    要旨あり予測と発見研究詳解

    CiNii Books

  140. シュードモナスのリジン分解経路におけるミッシング酵素の同定と解析

    三原久明, 大崎元晴, 桧作好之, 山西芳裕, 五斗進, 金久実, 栗原達夫, 江崎信芳

    ビタミン   Vol. 80 ( 4 ) page: 254 - 254   2006.4

     More details

  141. 系統関係を利用したタンパク質相互作用予測

    藤博幸, 佐藤哲也, 山西芳裕, 金久實

    日本蛋白質科学会年会プログラム・要旨集   Vol. 6th   page: 20   2006.3

     More details

    Language:Japanese  

    J-GLOBAL

  142. カーネル法による複数のゲノムデータからのタンパク質間機能ネットワークの推定 (特集 予測と発見)

    山西 芳裕, Vert Jean-Philippe

    統計数理   Vol. 54 ( 2 ) page: 357 - 373   2006

     More details

    Language:Japanese   Publisher:統計数理研究所  

  143. 共進化情報を利用したタンパク質間相互作用の予測

    佐藤哲也, 山西芳裕, 金久実, 藤博幸

    日本分子生物学会年会講演要旨集   Vol. 28th   page: 566   2005.11

     More details

    Language:Japanese  

    J-GLOBAL

  144. ゲノム情報に基づいたリジン分解系タンパク質ネットワークの再構築

    大崎元晴, 村松久司, 山西芳裕, 桧作好之, 三原久明, 五斗進, 金久実, 栗原達夫, 江崎信芳

    日本農芸化学会大会講演要旨集   Vol. 2005   page: 62   2005.3

     More details

    Language:Japanese  

    J-GLOBAL

  145. Statistical analysis for predicting gene functions

    山西芳裕

    スーパーコンピューターラボラトリー 平成16年度 研究成果報告書     page: 85 - 86   2005

     More details

    Language:Japanese  

    J-GLOBAL

  146. 生物種及び組織間における比較グライコーム解析

    桧作好之, 山西芳裕, 河野信, 五斗進, 金久実

    日本分子生物学会年会プログラム・講演要旨集   Vol. 27th   page: 848   2004.11

     More details

    Language:Japanese  

    J-GLOBAL

  147. カーネル法を用いた複数の異質なゲノムデータからのタンパク質ネットワークの推定

    山西芳裕, 佐藤哲也, VERT J‐P, 大崎元晴, 村松久司, 三原久明, 江崎信芳, 桧作好之, 五斗進

    日本分子生物学会年会プログラム・講演要旨集   Vol. 27th   page: 358   2004.11

     More details

    Language:Japanese  

    J-GLOBAL

  148. G7-6 関数主成分分析における影響分析(一般セッション(G7) : 多変量解析)(第30回日本行動計量学会大会発表一覧)

    大井手 寛浩, 山西 芳裕, 田中 豊

    行動計量学   Vol. 30 ( 2 ) page: 233 - 234   2004.1

     More details

    Language:Japanese   Publisher:日本行動計量学会  

    CiNii Books

  149. Statistical analysis for predicting gene functions

    山西芳裕

    スーパーコンピューターラボラトリー 平成15年度 研究成果報告書     page: 93 - 94   2004

     More details

    Language:Japanese  

    J-GLOBAL

  150. バイオインフォマティクスにおける基本アルゴリズム

    Akutsu, Tatsuya, Yamanishi, Yoshihiro

      Vol. 81 ( 1 ) page: 120 - 129   2003.10

     More details

    Language:Japanese  

    CiNii Books

  151. 関数データのペナルティ付き正準判別分析(セッション3)(日本計算機統計学会第15回シンポジウム報告)

    山西 芳裕, 田中 豊

    計算機統計学   Vol. 15 ( 1 ) page: 93 - 93   2003

     More details

    Language:Japanese   Publisher:日本計算機統計学会  

    DOI: 10.20551/jscswabun.15.1_93_1

    CiNii Books

  152. ゲノムからの生命システム解明への貢献

    山西 芳裕

    計算機統計学   Vol. 15 ( 2 ) page: 325 - 325   2003

     More details

    Language:Japanese   Publisher:日本計算機統計学会  

    DOI: 10.20551/jscswabun.15.2_325

    CiNii Books

  153. スカラー応答の関数重回帰における空間的非定常性のモデリング(セッション6)(日本計算機統計学会第16回大会報告)

    山西 芳裕, 大井手 寛浩, 田中 豊

    計算機統計学   Vol. 15 ( 1 ) page: 102 - 102   2003

     More details

    Language:Japanese   Publisher:日本計算機統計学会  

    DOI: 10.20551/jscswabun.15.1_102_1

    CiNii Books

  154. Statistical analysis for predicting genetic functions

    山西芳裕

    スーパーコンピューターラボラトリー 平成14年度 研究成果報告書     page: 88 - 89   2003

     More details

    Language:Japanese  

    J-GLOBAL

  155. 関数主成分分析における影響分析(多変量解析)

    大井手 寛浩, 山西 芳裕, 田中 豊

    日本行動計量学会大会発表論文抄録集   Vol. 30   page: 180 - 183   2002.8

     More details

    Language:Japanese   Publisher:日本行動計量学会  

    CiNii Books

  156. スカラー応答の関数重回帰における空間的非定常性のモデリング

    山西芳裕, 大井手寛浩, 田中豊

    日本計算機統計学会大会論文集   Vol. 16th   page: 122 - 125   2002.5

     More details

▼display all

Presentations 111

  1. 機械学習による新薬候補の探索と構造設計 Invited

    山西芳裕

    日本薬学会 第144年会, シンポジウム「AIで切り拓く未来の創薬・医療」  2024.3.31 

     More details

    Event date: 2024.3

    Language:Japanese   Presentation type:Oral presentation (invited, special)  

    Venue:横浜   Country:Japan  

  2. 遺伝子発現プロファイルの細胞特異性を考慮した疾患治療薬の探索と設計

    山中知茂, 岩田通夫, 海東和麻, 山西芳裕

    日本薬学会 第144年会  2024.3.30 

     More details

    Event date: 2024.3

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:横浜   Country:Japan  

  3. 大規模な臨床ビッグデータの解析による疾患予防薬とメカニズムの推定

    一ノ瀬音葉, 関谷拓海, 澤田隆介, 大谷則子, 山西芳裕

    日本薬学会 第144年会  2024.3.30 

     More details

    Event date: 2024.3

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:横浜   Country:Japan  

  4. 機械学習による薬剤標的分子予測と薬剤組み合わせの効果の検討

    亀淵由乃, 難波里子, 関谷拓海, 大谷則子, 岩田通夫, 山西芳裕

    日本薬学会第144年会  2024.3.31 

     More details

    Event date: 2024.3

    Language:Japanese   Presentation type:Poster presentation  

    Venue:横浜   Country:Japan  

  5. 細胞形態画像から医薬品候補化合物の標的分子を予測する機械学習手法の開発

    石原慎也, 岩田通夫, 林広夢, 濱野桃子, 霜古田一優, 木谷晃広, 吹田直政, 山西芳裕

    日本薬学会 第144年会  2024.3.31 

     More details

    Event date: 2024.3

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:横浜   Country:Japan  

  6. 多層オミクスデータを活用したAI創薬 Invited

    山西芳裕

    第113回日本病理学会総会, シンポジウム「仮説駆動型、データ駆動型病理学研究」  2024.3.29 

     More details

    Event date: 2024.3

    Language:Japanese   Presentation type:Oral presentation (invited, special)  

    Venue:名古屋   Country:Japan  

  7. 機械学習とビッグデータを用いた食品の機能性および微生物を介した作用メカニズムの推定

    三枝奈々子, 柴田友和, 澤田隆介, 関谷拓海, 山西芳裕

    日本農芸化学会 2024年度大会(創立100周年記念大会)  2024.3.27 

     More details

    Event date: 2024.3

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:新潟   Country:Japan  

  8. PPAR-γに結合するチアゾリジン系リガンドのMD/FMO連携による相互作用解析 Invited

    Daiki Arai, Shun Kitahara, Hideo Doi, Koji Okuwaki, Yoshinori Hirano, Eiji Yamamoto, Kenji Yasuoka, Kazuma Kaitoh, Yoshihiro Yamanishi, and Yuji Mochizuki

    第71回応用物理学会春季学術講演会  2024.3.23 

     More details

    Event date: 2024.3

    Language:Japanese   Presentation type:Oral presentation (invited, special)  

    Venue:東京   Country:Japan  

  9. シングルセルマルチオミクスデータを用いた生体内リプログラミング誘導転写因子の予測

    濱野桃子, 川崎瞭太、廣瀨昌樹, 山西芳裕

    第23回日本再生医療学会  2024.3.23 

     More details

    Event date: 2024.3

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:新潟   Country:Japan  

  10. AI・ビッグデータ駆動型研究が拓く医療と創薬 Invited

    山西芳裕

    第18回バイオメディカル研究所インタラクティブセミナー  2024.3.5 

     More details

    Event date: 2024.3

    Language:Japanese   Presentation type:Oral presentation (invited, special)  

    Country:Japan  

  11. 人工知能が拓く創薬と医療 Invited

    山西芳裕

    第17回健康医療開発機構シンポジウム「デジタルメディシン-その現状と未来-」  2024.3.2 

     More details

    Event date: 2024.3

    Language:Japanese   Presentation type:Oral presentation (invited, special)  

    Venue:東京   Country:Japan  

  12. AI・ビッグデータ時代の創薬や医療の可能性 Invited

    山西芳裕

    第10回CBI学会個別化医療研究会  2024.2.27 

     More details

    Event date: 2024.2

    Language:Japanese   Presentation type:Oral presentation (invited, special)  

    Venue:岐阜   Country:Japan  

  13. 機械学習による治療標的分子の予測と希少疾患への応用 Invited

    難波里子, 李晨, 大谷則子, 山西芳裕

    第10回CBI学会個別化医療研究会  2024.2.27 

     More details

    Event date: 2024.2

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:岐阜   Country:Japan  

  14. GxVAEs: Two Joint VAEs Generate Hit Molecules from Gene Expression Profiles International conference

    Li, C., Yamanishi, Y.

    The 38th Annual AAAI Conference on Artificial Intelligence (AAAI2024)  2024.2.20 

     More details

    Event date: 2024.2

    Language:English   Presentation type:Oral presentation (general)  

    Venue:Vancouver   Country:Canada  

  15. GxVAEs: Two Joint VAEs Generate Hit Molecules from Gene Expression Profiles International conference

    Li, C., Yamanisi, Y.

    The 38th Annual AAAI Conference on Artificial Intelligence (AAAI2024)  2024.2.20 

     More details

    Event date: 2024.2

    Language:English   Presentation type:Poster presentation  

    Venue:Vancouver   Country:Canada  

  16. AI・ビッグデータ時代の創薬の可能性 Invited

    山西芳裕

    医療産業イノベーションフォーラム「製薬業界でのAI活用の現在地」  2024.2.14 

     More details

    Event date: 2024.2

    Language:Japanese   Presentation type:Oral presentation (invited, special)  

    Venue:東京   Country:Japan  

  17. Data-driven drug discovery and healthcare by machine learning Invited International conference

    Yamanishi, Y.

    The 14th International Conference on Bioscience, Biochemistry and Bioinformatics (ICBBB2024)  2024.1.14 

     More details

    Event date: 2024.1

    Language:English   Presentation type:Oral presentation (keynote)  

    Venue:Kyoto   Country:Japan  

  18. AIによるデータ駆動型創薬と医療 Invited

    山西芳裕

    日本学術会議薬学委員会生物系薬学分科会 公開シンポジウム「AIが拓く創薬と医療の未来」  2024.1.12 

     More details

    Event date: 2024.1

    Language:Japanese   Presentation type:Oral presentation (invited, special)  

    Venue:東京   Country:Japan  

  19. 機械学習によるデータ駆動型細胞リプログラミング Invited

    山西芳裕

    第14回 がんゲノム・エピゲノム、数理統計解析についての研究会  2023.12.16 

     More details

    Event date: 2023.12

    Language:Japanese   Presentation type:Oral presentation (invited, special)  

    Venue:別府   Country:Japan  

  20. Data-driven drug discovery and healthcare by machine learning Invited International conference

    Yamanishi, Y.

    International Workshop on Data-driven Science for Graphs: Algorithms, Architectures, and Applications (IEEE BigData)  2023.12.17 

     More details

    Event date: 2023.12

    Language:English   Presentation type:Oral presentation (keynote)  

    Venue:Sorrento   Country:Italy  

  21. シナジー効果を高める薬物の組み合わせを予測する情報技術の開発

    亀淵由乃, 難波里子, 関谷拓海, 大谷則子, 岩田通夫, 山西芳裕

    第97回日本薬理学会年会・第44回日本臨床薬理学会学術総会  2023.12.14 

     More details

    Event date: 2023.12

    Language:Japanese   Presentation type:Poster presentation  

    Venue:神戸   Country:Japan  

  22. 臨床ビッグデータ解析による疾患予防メカニズムの推定

    一ノ瀬音葉, 関谷拓海, 澤田隆介, 大谷則子, 山西芳裕

    第97回日本薬理学会年会・第44回日本臨床薬理学会学術総会  2023.12.14 

     More details

    Event date: 2023.12

    Language:Japanese   Presentation type:Poster presentation  

    Venue:神戸   Country:Japan  

  23. シングルセルマルチオミクスデータを用いたダイレクトリプログラミング誘導転写因子の予測

    濱野桃子, 廣瀨昌樹, 江口凌平, 岩田通夫, 沖真弥, 山西芳裕

    第46回日本分子生物学会年会, シンポジウム「細胞デジタル社会が織りなす高次生命現象の理解」  2023.12.6 

     More details

    Event date: 2023.12

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:神戸   Country:Japan  

  24. 一細胞オミックスデータに基づくダイレクトリプログラミング誘導転写因子の予測

    廣瀬昌樹, 濱野桃子, 岩田通夫, 沖真弥, 山西芳裕

    第46回日本分子生物学会  2023.12.6 

     More details

    Event date: 2023.12

    Language:Japanese   Presentation type:Poster presentation  

    Venue:神戸   Country:Japan  

  25. 細胞特異性を考慮した遺伝子発現プロファイルによる疾患治療薬の探索

    山中知茂, 岩田通夫, 海東和麻, 山西芳裕

    第46回日本分子生物学会  2023.12.6 

     More details

    Event date: 2023.12

    Language:Japanese   Presentation type:Poster presentation  

    Venue:神戸   Country:Japan  

  26. Data-driven drug discovery and healthcare by machine learning Invited International conference

    Yamanishi, Y.

    The 13th International Workshop on Biomedical and Health Informatics (BHI2023)  2023.12.7 

     More details

    Event date: 2023.12

    Language:English   Presentation type:Oral presentation (keynote)  

    Venue:Istanbul   Country:Turkey  

  27. Data-driven drug discovery and healthcare by machine learning Invited International conference

    Yamanishi, Y.

    The 8th Autumn School of Chemoinformatics in Nara 2023  2023.11.29 

     More details

    Event date: 2023.11

    Language:English   Presentation type:Oral presentation (invited, special)  

    Venue:Nara   Country:Japan  

  28. Chemical Space Visualization Toward Data-Driven DNA-Encoded Library Design International conference

    Kaitoh, K., Yamanishi, Y.

    The 8th Autumn School of Chemoinformatics in Nara 2023  2023.11.28 

     More details

    Event date: 2023.11

    Language:English   Presentation type:Poster presentation  

    Venue:Nara   Country:Japan  

  29. Gene Expression Data-Driven Scaffold-Constrained Molecular Structure Generation by Deep Neural Network International conference

    Matsukiyo, Y., Yamanaka, C., Li, C., Yamanishi, Y.

    The 8th Autumn School of Chemoinformatics in Nara 2023  2023.11.29 

     More details

    Event date: 2023.11

    Language:English   Presentation type:Oral presentation (general)  

    Venue:Nara   Country:Japan  

  30. 深層学習モデルによる所望の特性を持つ合成可能な化学構造の生成

    髙田慎之助, 海東和麻, 津田宏治, 山西芳裕

    第46回ケモインフォマティクス討論会  2023.11.22 

     More details

    Event date: 2023.11

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:東京   Country:Japan  

  31. 深層学習による遺伝子発現プロファイルからの医薬品の構造設計

    松清優樹、山中知茂, 山西芳裕

    第46回ケモインフォマティクス討論会  2023.11.21 

     More details

    Event date: 2023.11

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:東京   Country:Japan  

  32. 複数の治療標的分子にデュアルで作用する医薬品化合物を構造生成するAI開発

    安田花純、李晨、海東和麻, 山西芳裕

    第46回ケモインフォマティクス討論会  2023.11.21 

     More details

    Event date: 2023.11

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:東京   Country:Japan  

  33. AI・ビッグデータ時代の創薬の可能性 Invited

    山西芳裕

    第51回構造活性相関シンポジウム  2023.11.20 

     More details

    Event date: 2023.11

    Language:Japanese   Presentation type:Oral presentation (invited, special)  

    Venue:東京   Country:Japan  

  34. DNA-encoded library 設計を指向したケミカルスペースの可視化

    海東和麻, 山西芳裕

    第40回メディシナルケミストリーシンポジウム  2023.11.13 

     More details

    Event date: 2023.11

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:名古屋   Country:Japan  

  35. 未病に焦点を当てた劇薬:チアジアゾール骨格を有する新規GLS1阻害剤の創製

    山辺果歩, 金山大介, 岡田卓哉, 条美智子, 小泉桂一, 坂尻由子, 柴田友和, 澤田隆介, 山西芳裕, 豊岡尚樹

    第40回メディシナルケミストリーシンポジウム  2023.11.13 

     More details

    Event date: 2023.11

    Language:Japanese   Presentation type:Poster presentation  

    Venue:名古屋   Country:Japan  

  36. Automatic biomarker discovery for idiopathic pulmonary fibrosis by correlation analysis of serum extracellular vesicles proteomic data and clinical data

    Yohey Kamijo, Mari N Itoh, Yoshito Takeda, Masataka Kuroda, Jun Adachi, Yayoi Natsume-Kitatani, Kenji Mizuguchi, Atsushi Kumanogoh, and Yoshihiro Yamanishi

    2023.10.24 

     More details

    Event date: 2023.10

    Language:Japanese   Presentation type:Poster presentation  

  37. Chemical Space Analysis for Cytochrome P450–Induced Orphan Nuclear Receptors Ligands

    Kazuma Kaitoh and Yoshihiro Yamanishi

    2023.10.24 

     More details

    Event date: 2023.10

    Language:Japanese   Presentation type:Poster presentation  

  38. Computational prediction of target molecules of drug candidate compounds from cell morphology images

    Shinya Ishihara, Michio Iwata, Hiromu Hayashi, Momoko Hamano, Kazumasa Shimofuruta, Akihiro Kitani, Naomasa Suita, and Yoshihiro Yamanishi

    情報計算化学生物学会(CBI学会)2023年大会  2023.10.24 

     More details

    Event date: 2023.10

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:東京   Country:Japan  

  39. Scaffold-Retained Transformer GAN for Molecular Generation with Chemical Property Optimization

    Chen Li and Yoshihiro Yamanishi

    情報計算化学生物学会(CBI学会)2023年大会  2023.10.24 

     More details

    Event date: 2023.10

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:東京   Country:Japan  

  40. De novo inhibitor and activator design from gene expression profiles via deep learning and Bayesian optimization

    松清優樹、山中知茂, 山西芳裕

    情報計算化学生物学会(CBI学会)2023年大会  2023.10.24 

     More details

    Event date: 2023.10

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:東京   Country:Japan  

  41. Transformer Encoder-based Generative Adversarial Network for Design of Polypharmacological Drugs

    安田花純、李晨、海東和麻, 山西芳裕

    情報計算化学生物学会(CBI学会)2023年大会  2023.10.24 

     More details

    Event date: 2023.10

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:東京   Country:Japan  

  42. Generating Synthesizable Compound Structures with Desired Properties via Deep Learning Models

    髙田慎之助, 海東和麻, 津田宏治, 山西芳裕

    情報計算化学生物学会(CBI学会)2023年大会  2023.10.24 

     More details

    Event date: 2023.10

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:東京   Country:Japan  

  43. AIによるデータ駆動型が拓く生命医科学と創薬 Invited

    山西芳裕

    トーゴーの日シンポジウム2023  2023.10.5 

     More details

    Event date: 2023.10

    Language:Japanese   Presentation type:Oral presentation (invited, special)  

    Venue:東京   Country:Japan  

  44. SpotGAN: A Reverse-Transformer GAN Generates Scaffold-Constrained Molecules with Property Optimization International conference

    Li, C., Yamanishi, Y.

    European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD 2023)  2023.9.18 

     More details

    Event date: 2023.9

    Language:English   Presentation type:Oral presentation (general)  

    Venue:Torino   Country:Italy  

  45. SpotGAN: A Reverse-Transformer GAN Generates Scaffold-Constrained Molecules with Property Optimization International conference

    Li, C., Yamanisi, Y.

    Proceedings of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD 2023)  2023.9.18 

     More details

    Event date: 2023.9

    Language:English   Presentation type:Poster presentation  

    Venue:Torino   Country:Italy  

  46. ダイレクトリプログラミングを誘導するパスウェイ制御機構の同定と最適な低分子化合物の組み合わせ予測

    濱野桃子, 中村透, 岩田通夫, 江口凌平, 竹下潤一, 山西芳裕

    第12回生命医薬情報学連合大会  2023.9.8 

     More details

    Event date: 2023.9

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:柏   Country:Japan  

  47. 腸内細菌代謝物質と疾患の相関解析と食品による制御手法の開発

    三枝奈々子, 柴田友和, 澤田隆介, 関谷拓海, 山西芳裕

    第12回生命医薬情報学連合大会  2023.9.7 

     More details

    Event date: 2023.9

    Language:Japanese   Presentation type:Poster presentation  

    Venue:柏   Country:Japan  

  48. シングルセルレベルの細胞変換過程を考慮したダイレクトリプログラミング誘導化合物の予測

    伊藤緑, 濱野桃子, 山西芳裕

    第12回生命医薬情報学連合大会  2023.9.7 

     More details

    Event date: 2023.9

    Language:Japanese   Presentation type:Poster presentation  

    Venue:柏   Country:Japan  

  49. GWASとTWASの融合による希少疾患に対する治療標的分子の予測

    難波里子, 岩田通夫, 山西芳裕

    第12回生命医薬情報学連合大会  2023.9.8 

     More details

    Event date: 2023.9

    Language:Japanese   Presentation type:Poster presentation  

    Venue:柏   Country:Japan  

  50. GWASとTWASの融合による希少疾患に対する治療標的分子の予測

    難波里子、岩田通夫、山西芳裕

    第12回生命医薬情報学連合大会  2023.9.8 

     More details

    Event date: 2023.9

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:柏   Country:Japan  

  51. AIによるデータ駆動型創薬 Invited

    山西芳裕

    第33回 新薬創製談話会「新薬創製に向けて―創発的学際融合・産学連携―」  2023.9.4 

     More details

    Event date: 2023.9

    Language:Japanese   Presentation type:Oral presentation (invited, special)  

    Venue:京都   Country:Japan  

  52. Data-driven drug discovery and healthcare by machine learning Invited International conference

    Yamanishi, Y.

    The 3rd International Conference on Image, Vision and Intelligent Systems (ICIVIS2023)  2023.8.17 

     More details

    Event date: 2023.8

    Language:English   Presentation type:Oral presentation (invited, special)  

    Venue:Baoding   Country:China  

  53. バイオインフォマティクスが拓く医療と創薬 Invited

    山西芳裕

    令和5年度健康・医療データサイエンス人材育成事業シンポジウム「沖縄ならではのSociety5.0実現に向けて」  2023.8.9 

     More details

    Event date: 2023.8

    Language:Japanese   Presentation type:Oral presentation (invited, special)  

    Venue:東京   Country:Japan  

  54. Target repositioning to predict therapeutic target proteins using genetically perturbed transcriptome data International conference

    Namba, S., Iwata, M., Yamanishi, Y.

    The 31st Annual Intelligent Systems For Molecular Biology and the 22nd Annual European Conference on Computational Biology (ISMB/ECCB2023)  2023.7.23 

     More details

    Event date: 2023.7

    Language:English   Presentation type:Poster presentation  

    Venue:Lyon   Country:France  

  55. Drug-induced single-cell transcriptomic landscape is revealed by pathway trajectory analysis with tensor imputation International conference

    Iwata, M., Mutsumine, H., Nakayama, Y., Suita, N.,Yamanishi, Y.

    The 31st Annual Intelligent Systems For Molecular Biology and the 22nd Annual European Conference on Computational Biology (ISMB/ECCB2023)  2023.7.23 

     More details

    Event date: 2023.7

    Language:English   Presentation type:Poster presentation  

    Venue:Lyon   Country:France  

  56. 機械学習モデルによるデータ駆動型創薬と医療 Invited

    山西芳裕

    第5回日本メディカルAI学会学術集会, シンポジウム「先進的モデル化技術による生体情報の予測と発見」  2023.6.18 

     More details

    Event date: 2023.6

    Language:Japanese   Presentation type:Oral presentation (invited, special)  

    Venue:東京   Country:Japan  

  57. 機械学習を活用した化合物の大規模解析と創薬応用 Invited

    山西芳裕

    AMED AIMGAINキックオフシンポジウム「革新的スクリーニング技術 DNA-encoded Libraryの産官学共創」  2023.6.2 

     More details

    Event date: 2023.6

    Language:Japanese   Presentation type:Oral presentation (invited, special)  

    Venue:東京   Country:Japan  

  58. 多階層データを活用したAI創薬 Invited

    山西芳裕

    理研DMP創薬セミナー  2023.5.18 

     More details

    Event date: 2023.5

    Language:Japanese   Presentation type:Oral presentation (invited, special)  

    Venue:東京   Country:Japan  

  59. 特異構造を有する化合物の生物応答理解を指向したトランスクリプトーム解析

    海東 和麻、岩田通夫、平野圭一、内山真伸、山西芳裕

    日本薬学会 第143年会  2023.3.27 

     More details

    Event date: 2023.3

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:札幌   Country:Japan  

  60. ダイレクトリプログラミングを誘導する低分子化合物組み合わせのin silico予測

    濱野桃子, 中村透, 岩田通夫, 江口凌平, 竹下潤一, 山西芳裕

    第22回日本再生医療学会  2023.3.25 

     More details

    Event date: 2023.3

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:京都   Country:Japan  

  61. AIが拓く創薬と医療:循環器疾患への応用に向けて Invited

    山西芳裕

    第52回日本心脈管作動物質学会  2023.2.10 

     More details

    Event date: 2023.2

    Language:Japanese   Presentation type:Oral presentation (invited, special)  

    Venue:北九州   Country:Japan  

  62. バイオインフォマティクスが拓く生命科学と医療・創薬 Invited

    山西芳裕

    GEAR5.0 ライフサイエンス・カンファレンス  2022.12.26 

     More details

    Event date: 2022.12

    Language:Japanese   Presentation type:Oral presentation (invited, special)  

    Venue:恩納村   Country:Japan  

  63. Data-driven drug discovery and molecular design by machine learning Invited International conference

    Yamanishi, Y.

    Inserm/JSPS joint seminar on artificial intelligence and big data approaches in precision medicine and health science   2022.12.4 

     More details

    Event date: 2022.12

    Language:English   Presentation type:Oral presentation (invited, special)  

    Venue:Yamaguchi   Country:Japan  

  64. ヒト全タンパク質に対する結合親和性を考慮した医薬品化合物の薬理作用予測 Invited

    山西芳裕

    第43回日本臨床薬理学会学術総会(JPW2022)  2022.12.2 

     More details

    Event date: 2022.11 - 2022.12

    Language:Japanese   Presentation type:Oral presentation (invited, special)  

    Venue:横浜   Country:Japan  

  65. パイオニア転写因子を考慮したトランスオミクスアプローチによるデータ駆動型ダイレクトリプログラミング

    濱野桃子、江口凌平、岩田通夫、中村透、沖真弥、山西芳裕

    第45回日本分子生物学会年会  2022.11.30 

     More details

    Event date: 2022.11 - 2022.12

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:幕張メッセ   Country:Japan  

  66. AIによるデータ駆動型研究が拓く創薬と医療 Invited

    山西芳裕

    第96回日本薬理学会年会サテライト企画 新薬理学セミナー Digital Pharmacology Conference  2022.11.30 

     More details

    Event date: 2022.11

    Language:Japanese   Presentation type:Oral presentation (invited, special)  

    Venue:横浜   Country:Japan  

  67. Data-driven drug discovery and molecular design by machine learning Invited International conference

    Yamanishi, Y.

    The 7th Autumn School of Chemoinformatics in Nara 2022  2022.11.29 

     More details

    Event date: 2022.11

    Language:English   Presentation type:Oral presentation (invited, special)  

    Venue:Nara   Country:Japan  

  68. AIによるデータ駆動型創薬の可能性 Invited

    山西芳裕

    第23回 協和キリン腎臓シンポジウム  2022.11.26 

     More details

    Event date: 2022.11

    Language:Japanese   Presentation type:Oral presentation (invited, special)  

  69. AIによるデータ駆動型創薬の可能性 Invited

    山西芳裕

    東京大学創薬機構イノベーション人材育成セミナー  2022.11.22 

     More details

    Event date: 2022.11

    Language:Japanese   Presentation type:Oral presentation (invited, special)  

    Venue:東京   Country:Japan  

  70. AIによるデータ駆動型研究が拓く創薬と医療

    山西芳裕

    日本動物実験代替法学会第35 回大会  2022.11.20 

     More details

    Event date: 2022.11

    Language:Japanese   Presentation type:Oral presentation (invited, special)  

    Venue:静岡   Country:Japan  

  71. ケミカル情報とパスウェイ情報による食品の機能性の大規模予測

    三枝奈々子, 柴田友和, 田中由祐, 田口大夢, 澤田隆介, 青柳守紘, 平尾宜司, 山西芳裕

    第45回ケモインフォマティクス討論会  2022.11.19 

     More details

    Event date: 2022.11

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:福岡   Country:Japan  

  72. オミックスデータに基づく薬物の標的分子予測とケミカル空間との相関解析

    関谷拓海, 岩田通夫, 亀淵由乃, 石原慎也, 山西芳裕

    第45回ケモインフォマティクス討論会  2022.11.19 

     More details

    Event date: 2022.11

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:福岡   Country:Japan  

  73. AIによるデータ駆動型研究が拓く創薬と医療 Invited

    山西芳裕

    日本薬物動態学会 第37回年会  2022.11.9 

     More details

    Event date: 2022.11

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:横浜   Country:Japan  

  74. AIによるデータ駆動型研究が拓く創薬と医療 Invited

    山西芳裕

    日本薬物動態学会 第37回年会  2022.11.9 

     More details

    Event date: 2022.11

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:横浜   Country:Japan  

  75. AIによるデータ駆動型研究が拓く創薬と医療 Invited

    山西芳裕

    日本薬物動態学会 第37回年会  2022.11.9 

     More details

    Event date: 2022.11

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:横浜   Country:Japan  

  76. De novo generation of drug candidate compounds from disease-specific transcriptome data using deep learning

    Chikashige Yamanaka, Shunya Uki, Kazuma Kaitoh, 山西芳裕

    情報計算化学生物学会(CBI学会)2022年大会  2022.10.26 

     More details

    Event date: 2022.10

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:東京   Country:Japan  

  77. Molecular Generation using Sequence-based Transformer Generative Adversarial Network

    Chen Li, 山西芳裕

    情報計算化学生物学会(CBI学会)2022年大会  2022.10.25 

     More details

    Event date: 2022.10

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:東京   Country:Japan  

  78. Developing a network-based combination therapy approach for complex diseases

    Midori Iida, Yurika Kuniki, Kenta Yagi, Mitsuhiro Goda, Satoko Namba, Jun-ichi Takeshita, Ryusuke Sawada, Michio Iwata, Yoshito Zamami, Keisuke Ishizawa, and 山西芳裕

    情報計算化学生物学会(CBI学会)2022年大会  2022.10.25 

     More details

    Event date: 2022.10

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:東京   Country:Japan  

  79. AIによるデータ駆動型創薬と医療 Invited

    山西芳裕

    第81回日本癌学会学術総会  2022.9.29 

     More details

    Event date: 2022.9 - 2022.10

    Language:Japanese   Presentation type:Oral presentation (invited, special)  

    Venue:横浜   Country:Japan  

  80. Small compound-based direct cell conversion with combinatorial optimization of pathway regulations International conference

    Nakamura, T., Iwata, M., Hamano, M., Eguchi, R., Takeshita, J., and Yamanishi, Y.

    The 21st European Conference on Computational Biology  2022.9.18 

     More details

    Event date: 2022.9

    Language:English   Presentation type:Oral presentation (general)  

    Venue: Barcelona   Country:Spain  

  81. AIによるデータ駆動型研究が拓く創薬と医療 Invited

    山西芳裕

    ⽇本化学会関東⽀部 2022 年度講演会  2022.9.16 

     More details

    Event date: 2022.9

    Language:Japanese   Presentation type:Oral presentation (invited, special)  

    Country:Japan  

  82. TRANSDIRE:パイオニア転写因子を考慮したトランスオミクス手法によるデータ駆動型ダイレクトリプログラミング

    濱野桃子, 江口凌平, 岩田通夫, 中村透, 沖真弥, 山西芳裕

    第11回生命医薬情報学連合大会  2022.9.14 

     More details

    Event date: 2022.9

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:大阪   Country:Japan  

  83. ターゲットリポジショニング:遺伝子摂動応答トランスクリプトームを用いた治療標的予測

    難波里子、岩田通夫、山西芳裕

    第11回生命医薬情報学連合大会  2022.9.14 

     More details

    Event date: 2022.9

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:大阪   Country:Japan  

  84. 心筋細胞核およびDNA損傷マーカーの染色画像を用いたVision Transformerによる心不全の治療予後予測

    林広夢,候聡志,戴哲皓, 藤田寛奈, 野村征太郎, 清島拓樹, 濱野桃子, 小室一成, 山西芳裕

    第11回生命医薬情報学連合大会  2022.9.14 

     More details

    Event date: 2022.9

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:大阪   Country:Japan  

  85. AIによるデータ駆動型研究が拓く創薬と医療 Invited

    山西芳裕

    日本オミックス医学会シンポジウム  2022.9.6 

     More details

    Event date: 2022.9

    Language:Japanese   Presentation type:Oral presentation (invited, special)  

    Country:Japan  

  86. 生薬比率を考慮した漢方薬の作用機序や効能のin silico予測

    島田祐樹, 江副晃洋, 澤田隆介, 柴田友和, 門脇真, 山西芳裕

    第39回和漢医薬学会学術大会  2022.8.27 

     More details

    Event date: 2022.8

    Language:Japanese   Presentation type:Oral presentation (general)  

    Country:Japan  

  87. Data-driven drug discovery and healthcare by machine learning Invited International conference

    Yamanishi, Y.

    The Eighteenth International Conference on Intelligent Computing  2022.8.9 

     More details

    Event date: 2022.8

    Language:English   Presentation type:Oral presentation (invited, special)  

    Venue:Xi'an   Country:China  

  88. Transformer-Based Objective-Reinforced Generative Adversarial Network to Generate Desired Molecules International conference

    Li, C., Yamanaka, C., Kaitoh, K. and Yamanishi, Y.

    The 31st International Joint Conference on Artificial Intelligence and the 25th European Conference on Artificial Intelligence   2022.7.23 

     More details

    Event date: 2022.7

    Language:English   Presentation type:Oral presentation (general)  

    Venue:Vienna   Country:Austria  

  89. From drug repositioning to target repositioning: prediction of therapeutic targets using genetically perturbed transcriptomic signatures International conference

    Namba, S., Iwata, M., and Yamanishi, Y.

    The 30th International Conference on Intelligent Systems for Molecular Biology  2022.7.10 

     More details

    Event date: 2022.7

    Language:English   Presentation type:Oral presentation (general)  

    Venue:Madison   Country:United States  

  90. ヒト 全タンパク質に対する結合親和性を考慮した化学物質の薬理作用予測 Invited

    山西芳裕

    第49回日本毒性学会学術年会  2022.7.2 

     More details

    Event date: 2022.6 - 2022.7

    Language:Japanese   Presentation type:Oral presentation (invited, special)  

    Venue:札幌   Country:Japan  

  91. 観測バイアスを考慮した化合物ネットワークのリンク予測

    乾拓海, 原田将之介, 劉洋, 竹内孝, 瀧川一学, 山西芳裕, 鹿島久嗣

    2022年度人工知能学会全国大会(第36回)  2022.6.14 

     More details

    Event date: 2022.6

    Language:Japanese   Presentation type:Oral presentation (general)  

    Venue:京都   Country:Japan  

  92. AIによるデータ駆動型研究が拓く生命医科学と創薬 Invited

    山西芳裕

    第95回日本内分泌学会学術総会  2022.6.2 

     More details

    Event date: 2022.6

    Language:Japanese   Presentation type:Oral presentation (invited, special)  

    Venue:別府   Country:Japan  

  93. AIによるデータ駆動型研究が拓く創薬 Invited

    山西芳裕

    第25回ケムステVシンポ  2022.5.20 

     More details

    Event date: 2022.5

    Language:Japanese   Presentation type:Oral presentation (invited, special)  

    Country:Japan  

  94. AIによるデータ駆動型研究が拓く創薬と医療 Invited

    山西芳裕

    第765回新潟医学会例会  2022.5.19 

     More details

    Event date: 2022.5

    Language:Japanese   Presentation type:Oral presentation (invited, special)  

    Country:Japan  

  95. AIによるデータ駆動型創薬と分子設計 Invited

    山西芳裕

    日本薬学会 第142年会  2022.3.28 

     More details

    Event date: 2022.3

    Language:Japanese   Presentation type:Oral presentation (invited, special)  

    Country:Japan  

  96. 機械学習による食品の機能性の網羅的な予測と作用機序の解明

    柴田友和、田中由祐、田口大夢、澤田隆介、青柳守紘、平尾宜司, 山西芳裕

    日本薬学会 第142年会  2022.3.28 

     More details

    Event date: 2022.3

    Language:Japanese   Presentation type:Oral presentation (general)  

    Country:Japan  

  97. AlphaFold2より得られたヒト全タンパク質立体構造との結合親和性に基づく医薬品化合物の副作用予測

    澤田隆介, 坂尻由子, 柴田友和, 山西芳裕

    日本薬学会 第142年会  2022.3.26 

     More details

    Event date: 2022.3

    Language:Japanese   Presentation type:Oral presentation (general)  

    Country:Japan  

  98. AlphaFold2から得られたヒト全タンパク質立体構造への結合親和性を考慮したドラッグリポジショニング

    坂尻由子, 柴田友和, 澤田隆介, 山西芳裕

    日本薬学会 第142年会  2022.3.26 

     More details

    Event date: 2022.3

    Language:Japanese   Presentation type:Oral presentation (general)  

    Country:Japan  

  99. 奇化学構造を重点的に発生させる構造生成器

    海東和麻, 山西芳裕

    日本薬学会 第142年会  2022.3.26 

     More details

    Event date: 2022.3

    Language:Japanese   Presentation type:Oral presentation (general)  

    Country:Japan  

  100. AIによるデータ駆動型創薬と分子設計 Invited

    山西芳裕

    日本薬学会 第142年会  2022.3.28 

     More details

    Event date: 2022.3

    Language:Japanese   Presentation type:Oral presentation (invited, special)  

    Country:Japan  

  101. 奇化学構造を重点的に発生させる構造生成器

    海東和麻, 山西芳裕

    日本薬学会 第142年会  2022.3.26 

     More details

    Event date: 2022.3

    Language:Japanese   Presentation type:Oral presentation (general)  

    Country:Japan  

  102. AlphaFold2から得られたヒト全タンパク質立体構造への結合親和性を考慮したドラッグリポジショニング

    坂尻由子, 柴田友和, 澤田隆介, 山西芳裕

    日本薬学会 第142年会  2022.3.26 

     More details

    Event date: 2022.3

    Language:Japanese   Presentation type:Oral presentation (general)  

    Country:Japan  

  103. AlphaFold2より得られたヒト全タンパク質立体構造との結合親和性に基づく医薬品化合物の副作用予測

    澤田隆介, 坂尻由子, 柴田友和, 山西芳裕

    日本薬学会 第142年会  2022.3.26 

     More details

    Event date: 2022.3

    Language:Japanese   Presentation type:Oral presentation (general)  

    Country:Japan  

  104. 機械学習による食品の機能性の網羅的な予測と作用機序の解明

    柴田友和、田中由祐、田口大夢、澤田隆介、青柳守紘、平尾宜司, 山西芳裕

    日本薬学会 第142年会  2022.3.28 

     More details

    Event date: 2022.3

    Language:Japanese   Presentation type:Oral presentation (general)  

    Country:Japan  

  105. AIによるデータ駆動型創薬と分子設計 Invited

    山西芳裕

    日本薬学会 第142年会  2022.3.28 

     More details

    Event date: 2022.3

    Language:Japanese   Presentation type:Oral presentation (invited, special)  

    Country:Japan  

  106. トランスオミクス解析によるダイレクトリプログラミング誘導転写因子の予測

    濱野桃子, 江口凌平, 岩田通夫, 中村透, 山西芳裕,

    第21回日本再生医療学会  2022.3.19 

     More details

    Event date: 2022.3

    Language:Japanese   Presentation type:Oral presentation (general)  

    Country:Japan  

  107. トランスオミクス解析によるダイレクトリプログラミング誘導転写因子の予測

    濱野桃子, 江口凌平, 岩田通夫, 中村透, 山西芳裕,

    第21回日本再生医療学会  2022.3.19 

     More details

    Event date: 2022.3

    Language:Japanese   Presentation type:Oral presentation (general)  

    Country:Japan  

  108. AIによるデータ駆動型研究が拓く生命医科学と創薬 Invited

    山西芳裕

    第1393回生物科学セミナー  2022.3.14 

     More details

    Event date: 2022.3

    Language:Japanese   Presentation type:Oral presentation (invited, special)  

    Country:Japan  

  109. AIによるデータ駆動型研究が拓く生命医科学と創薬 Invited

    山西芳裕

    第1393回生物科学セミナー  2022.3.14 

     More details

    Event date: 2022.3

    Language:Japanese   Presentation type:Oral presentation (invited, special)  

    Country:Japan  

  110. AIによるデータ駆動型研究が拓く医薬品・食品開発 Invited

    山西芳裕

    生物資源と触媒技術に基づく食・薬・材創生コンソーシアム 第5回シンポジウム  2022.3.2 

     More details

    Event date: 2022.3

    Language:Japanese   Presentation type:Oral presentation (invited, special)  

    Country:Japan  

  111. AIによるデータ駆動型研究が拓く医薬品・食品開発 Invited

    山西芳裕

    生物資源と触媒技術に基づく食・薬・材創生コンソーシアム 第5回シンポジウム  2022.3.2 

     More details

    Event date: 2022.3

    Language:Japanese   Presentation type:Oral presentation (invited, special)  

    Country:Japan  

▼display all

Works 3

  1. DINIES

    Yamanishi, Y., Kotera, M., Moriya, Y., Sawada, R., Kanehisa, M., and Goto, S.

    2014.5

     More details

    Work type:Web Service   Location:Nucleic Acids Research, 42, W39-W45, 2014  

    DOI: 10.1093/nar/gku337

  2. GENIES

    Kotera, M.*, Yamanishi, Y.*, Moriya, Y.*, Kanehisa, M., and Goto, S. (* Joint first author)

    2012.5

     More details

    Work type:Web Service   Location:Nucleic Acids Research, 40, W162-W167, 2012  

    DOI: 10.1093/nar/gks459

  3. E-zyme

    Yamanishi, Y., Hattori, M., Kotera, M., Goto, S., and Kanehisa, M.

    2009.7

     More details

    Work type:Web Service   Location:Bioinformatics, 25, i179-i186, 2009  

    DOI: 10.1093/bioinformatics/btp223

Other research activities 8

  1. 未病に焦点を当てた創薬:GLS1 阻害に基づく新規抗肥満薬の開発研究

    2022.10

  2. パスウェイを考慮した漢方薬の作用機序解析と効能予測

    2022.9

  3. Simulation-guided elucidation of dynamic drug responses of the cellular systems

    2022.9

  4. Transformer-Based Objective-Reinforced Generative Adversarial Network to Generate Desired Molecules

    2022.7

  5. Scaffold-Retained Structure Generator to Extensively Produce Molecules with Unique Chemical Substructures

    2022.6
    -
    2022.7

  6. Simulation-guided elucidation of dynamic drug responses of the cellular systems

    2022.6
    -
    2022.7

  7. 学術変革B「シナジー創薬学」:情報・物質・生命の協奏による化合物相乗効果の統合理解と設計

    2022.6

  8. 生物活性と物性の同時最適化を志向したペプチドの自動設計

    2022.5
    -
    2022.6

▼display all

Research Project for Joint Research, Competitive Funding, etc. 12

  1. マルチオミックス連関による循環器疾患における次世代型精密医療の実現

    2023.4 - 2028.3

    ゲノム医療実現推進プラットフォーム事業 

      More details

    Authorship:Coinvestigator(s)  Grant type:Competitive

  2. 創薬研究を加速する革新的スクリーニング ライブラリープラットフォームの産学連携構築

    2023.4 - 2027.3

    革新的医療技術研究開発推進事業 

      More details

    Authorship:Coinvestigator(s)  Grant type:Competitive

  3. アルカロイド様骨格化合物を用いた肺線維症治療薬の開発

    2023.4 - 2024.3

    健康寿命の延伸を目指した次世代医療橋渡し研究支援拠点シーズA 

      More details

    Authorship:Coinvestigator(s)  Grant type:Competitive

  4. 新薬創出を加速する症例データベースの構築・拡充/創薬ターゲット推定アルゴリズムの開発

    2021.4 - 2023.3

    政策科学総合研究事業(臨床研究等ICT基盤構築・人工知能実装研究事業) 

      More details

    Authorship:Coinvestigator(s)  Grant type:Competitive

  5. 最先端のAI技術を用いたマルチターゲット予測と構造発生を組み合わせた包括的な創薬AIプラットフォームの開発

    2020.8 - 2025.3

    創薬支援推進事業・産学連携による次世代創薬AI開発 

      More details

    Authorship:Coinvestigator(s)  Grant type:Competitive

  6. 創薬標的分子の確かしさを検証するツール物質の探索

    2020.8 - 2021.3

    官民研究開発投資拡大プログラムPRISM創薬分野AIP加速PRISM 

      More details

    Authorship:Principal investigator  Grant type:Competitive

  7. 難治性心血管疾患におけるマルチオミックス解析による病態解明と精密医療

    2020.4 - 2023.3

    難治性疾患実用化研究事業 

      More details

    Authorship:Coinvestigator(s)  Grant type:Competitive

  8. COVID-19に対する治療薬候補化合物の探索

    2020.4 - 2021.3

    戦略的創造研究推進事業AIP加速PRISM追加支援 

      More details

    Authorship:Principal investigator  Grant type:Competitive

  9. 生活習慣病の発症・重症化の予測能向上を目指したバイオマーカーの開発, "DNA 損傷応答・核形態の機械学習による心不全の予後・治療応答予測モデルの構築

    2019.4 - 2022.3

    循環器疾患・糖尿病等生活習慣病対策実用化研究事業 

      More details

    Authorship:Coinvestigator(s)  Grant type:Competitive

  10. マルチオミックス連関による循環器疾患における次世代型精密医療の実現

    2018.6 - 2023.3

    ゲノム医療実現推進プラットフォーム事業 

      More details

    Authorship:Coinvestigator(s)  Grant type:Competitive

  11. ドライ研究とウェット研究の融合による抗がん作用薬の探索

    2016.4 - 2017.3

    新日本先進医療研究財団助成金 

      More details

    Authorship:Principal investigator  Grant type:Competitive

  12. 生命科学における様々な分子に関する網羅的データを解析するための情報技術の開発

    2012.4 - 2016.3

    科学技術人材育成費補助事業「テニュアトラック普及・定着事業(個人選抜型)」 

      More details

    Authorship:Principal investigator 

▼display all

KAKENHI (Grants-in-Aid for Scientific Research) 16

  1. Pure transformer encoder-based generative adversarial networks for molecular generation

    Grant number:23KF0063  2023.4 - 2025.3

    Japan Society for the Promotion of Science  Grants-in-Aid for Scientific Research  Grant-in-Aid for JSPS Fellows

      More details

    Authorship:Principal investigator 

    Grant amount:\2000000 ( Direct Cost: \2000000 )

  2. Creation of data-driven direct reprogramming by AI and avoidance of tumorigenic risk

    Grant number:21K18327  2021.7 - 2024.3

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

      More details

    Authorship:Principal investigator 

    Grant amount:\25870000 ( Direct Cost: \19900000 、 Indirect Cost:\5970000 )

  3. Development of innovative AI methods for predicting therapeutic targets for intractable diseases from medical big data

    Grant number:21H04915  2021.4 - 2026.3

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

      More details

    Authorship:Principal investigator 

    Grant amount:\41470000 ( Direct Cost: \31900000 、 Indirect Cost:\9570000 )

  4. Synergy pharmaceutical science: understanding and design of compound combination effects by integrating information, material, and life sciences

    Grant number:20H05796  2020.10 - 2023.3

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

      More details

    Authorship:Principal investigator 

    Grant amount:\7410000 ( Direct Cost: \5700000 、 Indirect Cost:\1710000 )

  5. Search and design of compounds with synergistic effects by AI

    Grant number:20H05797  2020.10 - 2023.3

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

      More details

    Authorship:Principal investigator 

    Grant amount:\79040000 ( Direct Cost: \60800000 、 Indirect Cost:\18240000 )

  6. The role of chondrocyte/senescent cells-derived exosomal microRNA in pathogenesis of osteoarthritis, and in silico drug discoveryathogenesis of osteoarthritis and in silico drug discovery

    Grant number:19H03785  2019.4 - 2022.3

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

    Miyaki Shigeru

      More details

    Authorship:Coinvestigator(s) 

    Osteoarthritis (OA) is the most prevalent arthritic disease. The present study focused on the role of chondrocyte/senescent cells-derived cellular/exosomal microRNA in OA pathogenesis and in silico drug discovery for OA treatment. Although miR-23 a/b cluster and miR-26a were highly expressed in articular chondrocytes, both cellular and exsomal miRNAs (miR-23a/b and miR-26a) are not essential for OA pathogenesis associated with aging, and mechanical overload and local inflammation by trauma. However, both knock out mice exhibited accelerated aging-phenotype such as bone loss. Thus, we should further examine what function of these miRNAs including exosomal miRNAs is derived from which cells, and their target genes in order to reveal the mechanism of accelerated aging-like phenotype such as osteopenia in knock out mice. These future results might open a new insight in aging mechanisms through miR-23 a/b clusters and miR-26a.

  7. 創薬標的分子の確かしさを検証するツール物質の探索

    Grant number:JPMJCR18Y5  2018.8 - 2023.3

    科学技術振興機構  戦略的創造研究推進事業:AIP加速PRISM 

    山西芳裕

      More details

    Authorship:Principal investigator  Grant type:Competitive

    Grant amount:\211120000 ( Direct Cost: \162400000 、 Indirect Cost:\48720000 )

  8. Development of computational methods for transcription factor regulation and direct cell conversion by small compounds

    Grant number:18K19930  2018.6 - 2020.3

    Grants-in-Aid for Scientific Research  Grant-in-Aid for Challenging Research (Exploratory)

    Yamanishi Yoshihiro

      More details

    Authorship:Principal investigator 

    Grant amount:\6240000 ( Direct Cost: \4800000 、 Indirect Cost:\1440000 )

    Direct reprogramming is a research field on direct conversion of fully differentiated mature cells into a variety of other cell types while bypassing an intermediate pluripotent state (e.g., iPS cell). Direct reprograming is known to have several advantages over the other reprogramming methods in terms of high efficacy and safety, thus, it has been receiving much attentions in regenerative medicine. In this study, we develop novel computational methods to predict TFs and compounds that induce direct reprogramming for a variety of human cells. The prediction is performed by an integrative analysis of genomic data, transcriptome data, and epigenome data. We show the usefulness of the proposed methods on several direct cell conversions.

  9. AI-based drug discovery approach based on biomedical big data and its application to refractory diseases

    Grant number:18H03334  2018.4 - 2021.3

    Grants-in-Aid for Scientific Research  Grant-in-Aid for Scientific Research (B)

    Yamanishi Yoshihiro

      More details

    Authorship:Principal investigator 

    Grant amount:\17290000 ( Direct Cost: \13300000 、 Indirect Cost:\3990000 )

    In this research, we build information infrastructure technologies to realize drug discovery using pharmaceutical big data and machine learning, a fundamental technology of artificial intelligence (AI). Based on information on compounds such as pharmaceuticals, plants, and food ingredients, information on biomolecules such as genes, proteins, and glycans, and information on intractable diseases such as omics data and genomic data including SNPs, we constructed models for predicting the target of compounds in the framework of graph convolutional neural networks and recursive neural networks. We also constructed algorithms that take into account the applicability domains of chemical structures of compounds. Finally, we comprehensively predicted drug candidate compounds for malignant lymphoma and cystic fibrosis, and validated some of the prediction results.

  10. 位置非依存的な新しい分子コーディング法の開発とコンピュータ支援創薬への応用

    Grant number:17F17051  2017.5 - 2019.4

    日本学術振興会  科学研究費補助金(特別研究員奨励費) 

    山西芳裕

      More details

    Authorship:Principal investigator  Grant type:Competitive

    Grant amount:\1800000 ( Direct Cost: \1800000 )

  11. Mode-of-action analysis of Kampo formulae and prediction of their new indications for a wide range of diseases

    Grant number:16H05276  2016.4 - 2019.3

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

    Kadowaki Makoto

      More details

    Authorship:Coinvestigator(s) 

    Natural medicines are useful for treatment of multifactorial and chronic diseases. Here, we present KampoDB, a novel platform for the analysis of natural medicines, which provides various useful scientific resources on Japanese traditional formulas Kampo medicines, constituent herbal drugs, constituent compounds, and target proteins of these constituent compounds. Potential target proteins of these constituent compounds were predicted by docking simulations and machine learning methods based on large-scale omics data (e.g., genome, proteome, metabolome, interactome). The current version of KampoDB contains 42 Kampo medicines, 54 crude drugs, 1230 constituent compounds, 460 known target proteins, and 1369 potential target proteins, and has functional annotations for biological pathways and molecular functions. KampoDB is useful for mode-of-action analysis of natural medicines and prediction of new indications for a wide range of diseases.

  12. エコファーマによる高速かつ省エネ創薬を実現する情報技術の構築

    Grant number:JPMJPR15D8  2015.10 - 2019.3

    科学技術振興機構  戦略的創造研究推進事業(さきがけ) 

    山西芳裕

      More details

    Authorship:Principal investigator  Grant type:Competitive

    Grant amount:\52000000 ( Direct Cost: \40000000 、 Indirect Cost:\12000000 )

    本研究では、新薬候補を人類の資産である既承認薬から見出す創薬戦略「エコ ファーマ」を促進する情報基盤技術を構築します。近年の生命医科学で大量に生み出されてきた遺伝子、タンパク質、化合物、薬物、疾患に関する医薬ビッグ データを融合解析し、様々な疾患に対して効能を持つ既承認薬の候補と治療標的タンパク質を予測する機械学習法を開発します。これによって新薬開発コストを劇的に削減し、高速かつ省エネ創薬の実現を目指します。

  13. Discovery of anti-cancer effects of existing drugs by data-driven drug repositioning

    Grant number:15K14980  2015 - 2016

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

    Yamanishi Yoshihiro

      More details

    Authorship:Principal investigator  Grant type:Competitive

    Grant amount:\3770000 ( Direct Cost: \2900000 、 Indirect Cost:\870000 )

    In this study, we developed a method of drug repositioning for cancer (a drug discovery strategy to identify new effects of existing drugs for treatment of other diseases) based on large-scale data on drugs, genes, proteins and diseases. We performed a computational prediction of anticancer effects of drugs against various cancers, and investigate the prediction result by wet-lab experiment. We were able to confirm the validity of the predicted anticancer effects of some drugs through interaction with cancer therapeutic target molecules.

  14. Development of machine learning methods to comprehensively predict drug targets from omics data

    Grant number:25700029  2013 - 2015

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

    Yamanishi Yoshihiro

      More details

    Authorship:Principal investigator  Grant type:Competitive

    Grant amount:\24050000 ( Direct Cost: \18500000 、 Indirect Cost:\5550000 )

    The identification of interactions between drugs and target proteins is a key area in genomic drug discovery. Various high-throughput experimental projects enable us to analyze the genome, transcriptome, proteome. At the same time, the high-throughput screening of large-scale chemical compound libraries with various biological assays produce chemical and phenotypic data on drugs and bioactive compounds. In this project, we develop machine learning methods to infer unknown drug-target interactions by integrating various large-scale omics data.

  15. ゲノム関連情報から生体分子ネットワークを予測するためのカーネル法の開発

    Grant number:19700274  2007

    文部科学省  科学研究費補助金(若手研究(B))  若手研究(B)

    山西 芳裕

      More details

    Authorship:Principal investigator  Grant type:Competitive

    Grant amount:\2200000 ( Direct Cost: \2200000 )

    私の研究課題は、様々なゲノム関連データを用いて、生体分子(遺伝子やタンパク質、化合物)間の機能的ネットワークの予測法の開発である。主に以下の3点について成果が得られた。遺伝子やタンパク質に関する様々なゲノム関連情報(発現情報、細胞内局在情報、進化情報など)を用いて、遺伝子間の機能ネットワークを予測するシステムGENIESを構築した。複数のデータ統合とカーネル法に基づく教師付き学習のアルゴリズムを実装している点が特長である。現在、オンラインソフトウェアが利用可能となっている(URLは以下の13.備考を参照)。糖鎖という生体分子の構造を、糖鎖転移酵素の遺伝子発現情報から予測する手法を開発した。糖鎖構造を、糖鎖転移酵素とその連続触媒反応から構成されるネットワークの生成物と考え、無向グラフと有向グラフが混在したデータ構造として扱った。連続値の発現データを入力データとして、未知の構造や中間体の予測ができるアルゴリズムが特長である。ガン特異的な糖鎖構造の予測へ応用した成果は、Genome Informatics誌で発表し、現在Webサーバーを構築中である。化合物の構造情報から、その化学反応を予測し、対応する酵素番号(EC番号)を予測する手法を開発した。我々のグループが提唱しているRDMという化学反応分類体系とEC番号の相関をカーネル関数で表現し、それをスコアリングの手順に取り入れることによって、大幅な予測精度の向上を実現した。その手法を実装した化学反応予測システムE-ZYMEを構築し、またNucleic Acids Research誌で発表された最新のKEGGデータベースの論文中にも紹介されている。現在、オンラインソフトウェアが利用可能となっている(URLは以下の13.備考を参照)。

  16. 複数の異なるゲノムデータに基づく生物学的機能予測

    Grant number:04J61620  2004

    日本学術振興会  科学研究費助成事業 特別研究員奨励費  特別研究員奨励費

    山西 芳裕

      More details

    本研究では,様々なゲノム情報から,タンパク質間の機能ネットワークを予測する手法を開発した.カーネル正準相関分析を用いて,ゲノムデータとタンパク質ネットワークの相関モデルを構築し,新規のタンパク質間ネットワークを予測する方法を提案した.この方法の独自性は,教師付き学習の枠組においてネットワーク推定を行なう点にある.まず,第一段階として,ネットワークが既知のタンパク質セットから,ゲノムデータとパスウェイの相関(ネットワーク構築原理)を,数学的に学習させモデルを構築する.第二段階として,そのモデルを,ネットワークの分かっていないタンパク質セットに当てはめ,ネットワークを予測する.実際の適用例として,出芽酵母のタンパク質間の機能ネットワークを,マイクロアレイ遺伝子発現情報,酵母2ハイブリッドシステムによる相互作用情報,タンパク質の細胞内局在情報,系統プロファイルの4種類のデータから予測した.実験によって判明している既知のタンパク質ネットワークを用いて評価した結果,本研究で提案する複数のデータの統合と教師付き学習の効果によって,先行研究の方法(教師なし学習)よりも予測精度が著しく向上することが確認できた.そこで,全てのタンパク質セットに対して提案手法を適用し,出芽酵母の6059個のタンパク質からなる機能的ネットワークを推定した.それを基に,未知のタンパク質の機能や,missing酵素の遺伝子候補を予測し,その妥当性について検討し,この手法が新しい生物学的な発見に繋がる可能性について議論した.

▼display all