2016 Fiscal Year Final Research Report
Three-dimensional data mining from protein molecular surfaces for discovery of knowledge about protein functions
Project/Area Number |
24300056
|
Research Category |
Grant-in-Aid for Scientific Research (B)
|
Allocation Type | Partial Multi-year Fund |
Section | 一般 |
Research Field |
Intelligent informatics
|
Research Institution | Kobe University |
Principal Investigator |
OHKAWA Takenao 神戸大学, 大学院システム情報学研究科, 教授 (30223738)
|
Project Period (FY) |
2012-04-01 – 2017-03-31
|
Keywords | 知識発見 / データマイニング / バイオインフォマティクス / 三次元データ / バイオデータ処理 / バイクラスタリング |
Outline of Final Research Achievements |
In this research, we aimed to develop several methods of three-dimensional data mining from protein molecular surfaces for discovery of knowledge about protein functions. Molecular surfaces are regarded as three-dimensional images that are expressed by point clouds or graphs. The functional sites of proteins are extracted by biclustering of matched points in the point clouds or by an optimal graph discovery. In addition, we proposed an effective method to search for related articles on protein structure analysis by considering a user's intention and developed a new method for the automatic extraction of protein-protein interaction information from scientific articles by predicting dominant keywords.
|
Free Research Field |
情報工学
|