Development of fully automated NMR data analysis assisted by AI

• Project/Area Number: 18K06152
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Multi-year Fund
• Section: 一般
• Review Section: Basic Section 43040:Biophysics-related
• Research Institution: Institute of Physical and Chemical Research (2019-2020); Osaka University (2018)
• Principal Investigator: Kobayashi Naohiro 国立研究開発法人理化学研究所, 放射光科学研究センター, 上級研究員 (80272160)
• Co-Investigator(Kenkyū-buntansha): 児嶋 長次郎 大阪大学, 蛋白質研究所, 特任研究員 (50333563)
• Project Period (FY): 2018-04-01 – 2021-03-31
• Project Status: Completed (Fiscal Year 2020)
• Budget Amount: ¥4,420,000 (Direct Cost: ¥3,400,000、Indirect Cost: ¥1,020,000); Fiscal Year 2020: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000); Fiscal Year 2019: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000); Fiscal Year 2018: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
• Keywords: NMR / 自動解析 / 人工知能 / 構造解析 / 自動化 / 高度化 / 深層学習 / 核磁気共鳴 / データベース

Outline of Final Research Achievements

Compared to other methods such as X-ray crystallography and cryo-electron microscopy, the NMR method relies heavily on experience and manual analysis. We have succeeded in the world's first attempt to incorporate AI technology for further advancement, and has released a system that enables highly quick and accurate analysis even by beginners of NMR study. We published our result to a inter national journal as the first analysis tool equipped with a function that can perform noise removal with high accuracy using AI. In addition, by using a non-linear sampling method of multidimensional NMR spectra, the measurement time was reduced to 25%, and a total of 18 new NMR structure were determined by automated analysis, 12 of which took only a few days from measurement to completion of structural analysis and data verification, and two of which were fully automated. We are planning to publish all these strategy and automated system.

Academic Significance and Societal Importance of the Research Achievements

令和２年度までの成果として人工知能により高度化、高速化された解析システムが完成し、公開論文化された。公共データベースであるPDBへの述べ新規登録件数は18件以上にのぼり、そのうち13件は小型のタンパク質ながら新規フォールドであり測定、信号帰属解析、検証、登録には通常半年から１年を要することはごく普通である。今回の開発研究により大規模な測定期間短縮、解析やデータ検証の自動化が高度化されシステムとして統合され、その性能は世界最高レベルに達したと言っても過言ではない。この創薬研究などへの社会的インパクトは極めて大きいと考え、令和３年度内での国際学会発表、国際誌への投稿準備中である。

Research Products

• [Journal Article] Mechanism of hERG inhibition by gating-modifier toxin, APETx1, deduced by functional characterization (2021)
  • Author(s): Matsumura Kazuki、Shimomura Takushi、Kubo Yoshihiro、Oka Takayuki、Kobayashi Naohiro、Imai Shunsuke、Yanase Naomi、Akimoto Madoka、Fukuda Masahiro、Yokogawa Mariko、Ikeda Kazuyoshi、Kurita Jun-ichi、Nishimura Yoshifumi、Shimada Ichio、Osawa Masanori
  • Journal Title: BMC Molecular and Cell Biology Volume: 22 Issue: 1 Pages: 1-16
  • DOI: 10.1186/s12860-020-00337-3
  • Peer Reviewed / Open Access
• [Journal Article] Solution structure of Gaussia Luciferase with five disulfide bonds and identification of a putative coelenterazine binding cavity by heteronuclear NMR. (2020)
  • Author(s): N. Wu, N. Kobayashi, K. Tsuda, S. Unzai, T. Saotome, Y. Kuroda and T. Yamazaki.
  • Journal Title: Sci. Rep. Volume: 10 Issue: 1 Pages: 20069-20069
  • DOI: 10.1038/s41598-020-76486-4
  • Peer Reviewed / Open Access / Int'l Joint Research
• [Journal Article] Nucleus Accumbens-Associated Protein 1 Binds DNA Directly through the BEN Domain in a Sequence-Specific Manner (2020)
  • Author(s): Nakayama Naomi、Sakashita Gyosuke、Nagata Takashi、Kobayashi Naohiro、Yoshida Hisashi、Park Sam-Yong、Nariai Yuko、Kato Hiroaki、Obayashi Eiji、Nakayama Kentaro、Kyo Satoru、Urano Takeshi
  • Journal Title: Biomedicines Volume: 8 Issue: 12 Pages: 608-608
  • DOI: 10.3390/biomedicines8120608
  • Peer Reviewed / Open Access
• [Journal Article] Robust folding of a de novo designed ideal protein even with most of the core mutated to valine. (2020)
  • Author(s): R. Koga, M. Yamamoto, K. Takahiro, N. Kobayashi, T. Sugiki, T. Fujiwara and N. Koga
  • Journal Title: Proc. Natl. Acad. Sci. USA Volume: 117 Issue: 49 Pages: 31149-31156
  • DOI: 10.1073/pnas.2002120117
  • NAID: 120006952207
  • Peer Reviewed / Open Access
• [Journal Article] H, 13C and 15N resonance assignment of the YTH domain of YTHDC2. (2020)
  • Author(s): F. He, R. Endo, K. Kuwasako, M. Takahashi, K. Tsuda, T. Nagata, S. Watanabe, A. Tanaka, N. Kobayashi, T. Kigawa, P. Guentert, M. Shirouzu, S. Yokoyama and Y. Muto.
  • Journal Title: Biomol. NMR Assign. Volume: 15 Issue: 1 Pages: 1-7
  • DOI: 10.1007/s12104-020-09974-3
  • Peer Reviewed / Int'l Joint Research
• [Journal Article] Crystal contact-free conformation of an intrinsically flexible loop in protein crystal: Tim21 as the case study (2020)
  • Author(s): Bala Siqin、Shinya Shoko、Srivastava Arpita、Ishikawa Marie、Shimada Atsushi、Kobayashi Naohiro、Kojima Chojiro、Tama Florence、Miyashita Osamu、Kohda Daisuke
  • Journal Title: Biochimica et Biophysica Acta (BBA) - General Subjects Volume: 1864 Issue: 2 Pages: 129418-129418
  • DOI: 10.1016/j.bbagen.2019.129418
  • Peer Reviewed / Int'l Joint Research
• [Journal Article] BioMagResBank (BMRB) as a Resource for Structural Biology (2020)
  • Author(s): Romero Pedro R.、Kobayashi Naohiro、Wedell Jonathan R.、Baskaran Kumaran、Iwata Takeshi、Yokochi Masashi、Maziuk Dimitri、Yao Hongyang、Fujiwara Toshimichi、Kurusu Genji、Ulrich Eldon L.、Hoch Jeffrey C.、Markley John L.
  • Journal Title: Methods Molelcular Biology Volume: 14 Pages: 187-218
  • DOI: 10.1007/978-1-0716-0270-6_14
  • ISBN: 9781071602690, 9781071602706
  • Peer Reviewed / Int'l Joint Research
• [Journal Article] How Does the Recently Discovered Peptide MIP Exhibit Much Higher Binding Affinity than an Anticancer Protein p53 for an Oncoprotein MDM2 (2019)
  • Author(s): Yamada Tatsuya、Hayashi Tomohiko、Hikiri Simon、Kobayashi Naohiro、Yanagawa Hiroshi、Ikeguchi Mitsunori、Katahira Masato、Nagata Takashi、Kinoshita Masahiro
  • Journal Title: Journal of Chemical Information and Modeling Volume: 59 Issue: 8 Pages: 3533-3544
  • DOI: 10.1021/acs.jcim.9b00226
  • Peer Reviewed / Open Access / Int'l Joint Research
• [Journal Article] Noise peak filtering in multi-dimensional NMR spectra using convolutional neural networks (2018)
  • Author(s): Kobayashi, N., Hattori, Y., Nagata, T., Shinya, S., Guentert, P., Kojima, C., Fujiwara, T.
  • Journal Title: Bioinformatics Volume: 34 Issue: 24 Pages: 4300-4301
  • DOI: 10.1093/bioinformatics/bty581
  • Peer Reviewed / Open Access / Int'l Joint Research
• [Presentation] 高速・高精度な MagRO による NMR 構造解析の完全自動化 (2020)
  • Author(s): 小林直宏，杉木俊彦，南慎太朗，佐久間航也，長島敏雄，児嶋長次郎，藤原敏道，小杉貴洋，古賀理恵，古賀信康，山崎俊夫
  • Organizer: 第59回NMR討論会
• [Presentation] ヒト脂質輸送蛋白質CERがクラミジア封入体の膜蛋白Incにハイジャックされる分子機序の溶NMR解析 (2020)
  • Author(s): 杉木俊彦，熊谷圭悟，新家粧子，小林直宏，藤原敏道，花田賢太郎，児嶋長次郎
  • Organizer: 第59回NMR討論会
• [Presentation] 多次元固体 MAS-NMR を用いたヘリオロドプシンの立体構造解析 (2020)
  • Author(s): 鈴木しぶき，長島敏雄, 金子莉奈, 沖津貴志, 和田昭盛, 小林直宏, 山崎俊夫, 井上圭一, 神取秀樹, 川村出
  • Organizer: 第59回NMR討論会
• [Presentation] Structural differences and Novel Polymorphs of Synthetic and brain-derived Aβ42 Fibrils by1H-detected SSNMR (2020)
  • Author(s): A. Wickramasinghe, Y. Xiao, N. Kobayashi, T. Yamazaki and Y. Ishii
  • Organizer: 第59回NMR討論会
• [Presentation] 生体系NMRの最前線 基礎から学ぶー構造解析自動化 (2020)
  • Author(s): 小林直宏
  • Organizer: 令和２年蛋白研セミナー
  • Invited
• [Presentation] Design of Globin-like Complicated Folds (2020)
  • Author(s): 佐久間航也、小林直宏、杉木俊彦、鈴木かの、小林直也、小杉貴洋、村田武士、古賀理恵、古賀信康
  • Organizer: 64th BioPhysical Society Annual Meeting, SanDiego
  • Int'l Joint Research
• [Presentation] Exploration of novel αβ protein folds by de novo design (2020)
  • Author(s): 南慎太郎、小林直宏、杉木俊彦、鈴木かの、千見寺浄慈、古賀理恵、古賀信康
  • Organizer: 64th BioPhysical Society Annual Meeting, SanDiego
  • Int'l Joint Research
• [Presentation] Nearly complete assignments for 23kDa membrane protein by solid-state NMR using MagRO system assisted by Graph_Robot based on finite automaton theory. (2019)
  • Author(s): 小林直宏、長嶋敏夫、山崎俊夫
  • Organizer: 第58回NMR討論会
• [Presentation] Structural characterization of Aβ(1-42) fi brils in nano-mole scale by 1H-detected SSNMR under UFMASStructural characterization of Aβ(1-42) fi brils in nano-mole scale by 1H-detected SSNMR under UFMAS (2019)
  • Author(s): Ayesha Wickramasinghe, Yiling Xiao、小林直宏、石井佳誉
  • Organizer: 第58回NMR討論会
• [Presentation] Deep-MagRO: 深層学習を応用した高速かつ高精度な統合的NMR解析システム (2018)
  • Author(s): 小林直宏、杉木俊彦、永田崇、Peter Guentert, 児嶋長次郎、藤原敏道
  • Organizer: 第57回NMR討論会
• [Presentation] Application of Deep Neural Networks for Highly Accurate NMR Structure Analysis by Deep-MagRO (2018)
  • Author(s): Naohiro Kobayashi, Toshihiko Sugiki, Yoshikazu Hattori, Takashi Nagata, Shoko Shinya, Julia M. Wuerz, Rie Koga, Nobuyasu Koga, Peter Guentert, Chojiro Kojima and Toshimichi Fujiwara
  • Organizer: ICMRBS2018
  • Int'l Joint Research
• [Remarks] NMR Tool Box
  • URL: https://bmrbdep.pdbj.org/en/nmr_tool_box.html