Development of fully automated NMR data analysis assisted by AI

2020 Fiscal Year Final Research Report

• 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
• Keywords: NMR / 自動解析 / 人工知能

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.

Free Research Field

NMR分光学

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。