Development of protein interaction prediction methods by modeling protein substructures

2015 Fiscal Year Final Research Report

• Project/Area Number: 24500361
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Multi-year Fund
• Section: 一般
• Research Field: Bioinformatics/Life informatics
• Research Institution: Kyoto University
• Principal Investigator: Hayashida Morihiro 京都大学, 化学研究所, 助教 (40402929)
• Project Period (FY): 2012-04-01 – 2016-03-31
• Keywords: 条件付き確率場 / タンパク質RNA複合体 / タンパク質複合体 / SIFT特徴量

Outline of Final Research Achievements

We developed a similarity measure between protein tertiary structures using SIFT local feature descriptor, which is often used in the field of image recognition. The proposed measure outperforms previously developed measures based on image compression. Furthermore, we proposed conditional random field models for predicting residue-base contacts in protein-RNA complexes. In addition, we developed methods for predicting protein heterodimers and heterotrimers in higher accuracy than existing methods.

Free Research Field

バイオインフォマティクス