• 研究課題をさがす
  • 研究者をさがす
  • KAKENの使い方
  1. 前のページに戻る

Fully automated protein NMR assignments and structures from raw time-domain data by deep learning

研究課題

研究課題/領域番号 23K05660
研究種目

基盤研究(C)

配分区分基金
応募区分一般
審査区分 小区分43020:構造生物化学関連
研究機関東京都立大学

研究代表者

PETER GUENTERT  東京都立大学, 理学研究科, 客員教授 (20392110)

研究分担者 池谷 鉄兵  東京都立大学, 理学研究科, 准教授 (30457840)
伊藤 隆  東京都立大学, 理学研究科, 教授 (80261147)
研究期間 (年度) 2023-04-01 – 2026-03-31
研究課題ステータス 交付 (2023年度)
配分額 *注記
4,810千円 (直接経費: 3,700千円、間接経費: 1,110千円)
2025年度: 1,430千円 (直接経費: 1,100千円、間接経費: 330千円)
2024年度: 1,820千円 (直接経費: 1,400千円、間接経費: 420千円)
2023年度: 1,560千円 (直接経費: 1,200千円、間接経費: 360千円)
キーワードNMR / machine learning / automated assignment / protein structure / protein / spectra analysis / ARTINA
研究開始時の研究の概要

Using generated training data, we will apply deep learning for (i) a better treatment of time-domain data acquired with non-uniform sampling (NUS) than conventional approaches, (ii) resolution enhancement by virtual decoupling, and (iii) deconvolution of highly overlapped signals. In this way, time-consuming or costly experimental methods for obtaining better NMR spectra can be replaced by computational alternatives, thereby increasing the efficiency, completeness, and quality of NMR spectra analysis.

研究実績の概要

The ARTINA workflow for machine learning-based automated NMR spectra analysis was combined with AlphaFold structure prediction and UCBShift chemical shift prediction in order to drastically reduce the amount of NMR spectra that are required for obtaining the chemical shift assignment of a protein. Extensive studies have been performed to identify the optimal sets of NMR spectra for the assignment of the backbone or all chemical shifts in a protein. This was published in Klukowski et al., Science Advances 9, eadi9323 (2023).

In addition, ARTINA was generalized to additional biomacromolecular systems. Originally, ARTINA was designed exclusively for monomeric proteins composed of standard amino acid residues. This restriction has been lifted to enable automated NMR spectra analysis also for protein-protein, protein-small molecule ligand, RNA and DNA systems. This significantly extends the applicability of the method to biologically important systems.

A large scale data set comprising more than 1300 multidimensional NMR spectra, from which the chemical shift assignments and three-dimensional structures of 100 proteins can be obtained, has been published as open research data for general use by the NMR research community. Published in Klukowski et al., Nature Scientific Data 11, 30 (2024).

現在までの達成度 (区分)
現在までの達成度 (区分)

2: おおむね順調に進展している

理由

Research progressed as planned. In particular, we started to develop new machine learning models specifically for analyzing two-dimensional homonuclear NMR spectra of proteins (see below).

今後の研究の推進方策

As a new direction of research, we have started to implement new machine learning models specifically for the purpose of analyzing two-dimensional 1H-1H NMR spectra of proteins up to ~20 kDa. If successful, this will enable efficient NMR studies of proteins without isotope labeling and requiring much less NMR measurement time.

Training and testing data is crucial for machine learning applications, which constitutes a limiting factor for its use in biological NMR spectroscopy. In order to collect and make available a larger and more diverse set of multi-dimensional NMR spectra, we are developing a new public website and data repository for the upload, storage, and access of primary biomolecular NMR data, i.e. spectra or time-domain data. This should become available for general use by the NMR research community in the near future.

報告書

(1件)
  • 2023 実施状況報告書
  • 研究成果

    (12件)

すべて 2024 2023 その他

すべて 雑誌論文 (6件) (うち国際共著 6件、 査読あり 6件、 オープンアクセス 6件) 学会発表 (3件) (うち国際学会 2件、 招待講演 3件) 備考 (3件)

  • [雑誌論文] The 100-protein NMR spectra dataset: A resource for biomolecular NMR data analysis2024

    • 著者名/発表者名
      Klukowski Piotr、Damberger Fred F.、Allain Frederic H.-T.、Iwai Hideo、Kadavath Harindranath、Ramelot Theresa A.、Montelione Gaetano T.、Riek Roland、Guentert Peter
    • 雑誌名

      Scientific Data

      巻: 11 号: 1 ページ: 30-30

    • DOI

      10.1038/s41597-023-02879-5

    • 関連する報告書
      2023 実施状況報告書
    • 査読あり / オープンアクセス / 国際共著
  • [雑誌論文] 1H, 13C, and 15N resonance assignments and solution structure of the N-terminal divergent calponin homology (NN-CH) domain of human intraflagellar transport protein 542024

    • 著者名/発表者名
      Kuwasako Kanako、Dang Weirong、He Fahu、Takahashi Mari、Tsuda Kengo、Nagata Takashi、Tanaka Akiko、Kobayashi Naohiro、Kigawa Takanori、Guentert Peter、Shirouzu Mikako、Yokoyama Shigeyuki、Muto Yutaka
    • 雑誌名

      Biomolecular NMR Assignments

      巻: 18 号: 1 ページ: 71-78

    • DOI

      10.1007/s12104-024-10170-w

    • 関連する報告書
      2023 実施状況報告書
    • 査読あり / オープンアクセス / 国際共著
  • [雑誌論文] NMRtist: an online platform for automated biomolecular NMR spectra analysis2023

    • 著者名/発表者名
      Klukowski Piotr, Riek Roland, Guentert Peter
    • 雑誌名

      Bioinformatics

      巻: 39 号: 2

    • DOI

      10.1093/bioinformatics/btad066

    • 関連する報告書
      2023 実施状況報告書
    • 査読あり / オープンアクセス / 国際共著
  • [雑誌論文] Facilitating the structural characterisation of non-canonical amino acids in biomolecular NMR2023

    • 著者名/発表者名
      Kuschert Sarah、Stroet Martin、Chin Yanni Ka-Yan、Conibear Anne Claire、Jia Xinying、Lee Thomas、Bartling Christian Reinhard Otto、Stromgaard Kristian、Guentert Peter、Rosengren Karl Johan、Mark Alan Edward、Mobli Mehdi
    • 雑誌名

      Magnetic Resonance

      巻: 4 号: 1 ページ: 57-72

    • DOI

      10.5194/mr-4-57-2023

    • 関連する報告書
      2023 実施状況報告書
    • 査読あり / オープンアクセス / 国際共著
  • [雑誌論文] Chemical shift transfer: an effective strategy for protein NMR assignment with ARTINA2023

    • 著者名/発表者名
      Wetton Henry、Klukowski Piotr、Riek Roland、Guentert Peter
    • 雑誌名

      Frontiers in Molecular Biosciences

      巻: 10 ページ: 1244029-1244029

    • DOI

      10.3389/fmolb.2023.1244029

    • 関連する報告書
      2023 実施状況報告書
    • 査読あり / オープンアクセス / 国際共著
  • [雑誌論文] Time-optimized protein NMR assignment with an integrative deep learning approach using AlphaFold and chemical shift prediction2023

    • 著者名/発表者名
      Klukowski Piotr、Riek Roland、Guentert Peter
    • 雑誌名

      Science Advances

      巻: 9 号: 47

    • DOI

      10.1126/sciadv.adi9323

    • 関連する報告書
      2023 実施状況報告書
    • 査読あり / オープンアクセス / 国際共著
  • [学会発表] Automated biomolecular NMR spectra analysis, assignments, and structures with the deep learning technique ARTINA2024

    • 著者名/発表者名
      Guentert Peter
    • 学会等名
      The ESPERANCE Project Practical Course
    • 関連する報告書
      2023 実施状況報告書
    • 招待講演
  • [学会発表] Accelerating protein chemical shift assignment by deep learning for visual spectra analysis, structure and shift prediction2023

    • 著者名/発表者名
      Guentert Peter
    • 学会等名
      iNEXT-Discovery 2023 Conference
    • 関連する報告書
      2023 実施状況報告書
    • 国際学会 / 招待講演
  • [学会発表] Structure-based protein chemical shift assignment from minimal NMR data with the hybrid deep learning approach ARTINA2023

    • 著者名/発表者名
      Guentert Peter
    • 学会等名
      EUROMAR 2023 Conference
    • 関連する報告書
      2023 実施状況報告書
    • 国際学会 / 招待講演
  • [備考] NMRtist cloud computing service

    • URL

      https://nmrtist.org/

    • 関連する報告書
      2023 実施状況報告書
  • [備考] The 100-protein NMR spectra dataset

    • URL

      https://doi.org/10.3929/ethz-b-000630211

    • 関連する報告書
      2023 実施状況報告書
  • [備考] The 100-protein NMR spectra dataset

    • URL

      https://nmrdb.ethz.ch/

    • 関連する報告書
      2023 実施状況報告書

URL: 

公開日: 2023-04-13   更新日: 2024-12-25  

サービス概要 検索マニュアル よくある質問 お知らせ 利用規程 科研費による研究の帰属

Powered by NII kakenhi