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

2018 年度 実績報告書

膜タンパク質の天然変性領域の予測と解析

研究課題

研究課題/領域番号 17F17050
研究機関東京大学

研究代表者

清水 謙多郎  東京大学, 大学院農学生命科学研究科(農学部), 教授 (80178970)

研究分担者 FANG CHUN  東京大学, 農学生命科学研究科, 外国人特別研究員
研究期間 (年度) 2017-10-13 – 2020-03-31
キーワード天然変性 / タンパク質 / 深層学習
研究実績の概要

In the second year, our research focused on detail of "adopting feature fusion and feature compression method for identifying IDRs and motifs in IDPs"; the main works were as follows: (1) Applied effective feature-encoding scheme to combine more predictive features into fewer dimensions for prediction, it includes: (a) Remove the redundant features and strengthen the predictive features to enhance the accuracy of prediction. Using the scaling skills to enhance the predictive features and weaken the noise features; (b) Adopt the image processing technology to preprocess the conserved features included in PSSM; (c) Modify PSSM to combine the detailed local conservation patterns of residues with the distribution of scores in PSSM for prediction. (2) Adopted the feature fusion method, rather than connecting all features in series to design the algorithms, it includes: (a) Firstly, all the physicochemical features were clustered; (b) Secondly, factors were calculated to represent each clustering; (c) Finally, all features (including the revised PSSM and factors calculated from physicochemical features) were fused and compressed by matrix operations to reduce the feature dimensions. (3) For MoRFs in IDPs, detailed analysis was carried out according to their different lengths, and the related algorithms was designed respectively for them. (4) Implemented the related web tools for publication.

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

According to the methods that we developed, the world top prediction accuracy was achieved. We published two papers on the achievement.

今後の研究の推進方策

In the third year, we improve the performance of our MoRFs prediction system by integrating the amino acid sequence features designed in the previous year such as the revised PSSM and factors calculated from physicochemical features. We construct the Web site for MoRFs prediction and publish a paper of our research in the last four months.

  • 研究成果

    (2件)

すべて 2019 2018

すべて 雑誌論文 (2件) (うち査読あり 2件、 オープンアクセス 1件)

  • [雑誌論文] Prediction of MoRFs Based on n-gram Convolutional Neural Network2019

    • 著者名/発表者名
      Chun Fang, Yoshitaka Moriwaki, Caihong Li, and Kentaro Shimizu
    • 雑誌名

      Proceedings of 11th International Conferenceon Bioinformatics and Computational Biology

      巻: 60 ページ: 113-119

    • DOI

      10.29007/5k4z

    • 査読あり
  • [雑誌論文] Identifying MoRFs in Disordered Protein Using Enlarged Conserved Features2018

    • 著者名/発表者名
      Chun Fang, Yoshitaka Moriwaki, Daming Zhu, and K. Shimizu
    • 雑誌名

      2018 6th International Conference on Bioinformatics and Computational Biology

      巻: 12 ページ: 50-54

    • DOI

      10.1145/3194480.3198908

    • 査読あり / オープンアクセス

URL: 

公開日: 2019-12-27  

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