2018 Fiscal Year Final Research Report
Relationship between activity and groups of metabolic pathways
| Project/Area Number |
16K07223
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
System genome science
|
|---|
| Research Institution | Nara Institute of Science and Technology |
|---|
Principal Investigator |
Shigehiko Kanaya 奈良先端科学技術大学院大学, 先端科学技術研究科, 教授 (90224584)
|
|---|
| Project Period (FY) |
2016-10-21 – 2019-03-31
|
| Keywords | 代謝マップ / グラフコンボリューションネットワーク / 深層学習 |
|---|
| Outline of Final Research Achievements |
In this study, we constructed a model to predict their precursors based on a novel kind of neural network called the molecular graph convolutional neural network and examined the relationships between activities and metabolites based on metabolic pathways. In order to investigate alkaloid biosynthesis, we trained the network to distinguish the precursors of 566 alkaloids, which are almost all of the alkaloids whose biosynthesis pathways are known, and showed that the model could predict starting substances with an averaged accuracy of 97.5%. The prediction of pathways contributes to understanding of the alkaloids and the application of graph based neural network models to similar problems in bioinformatics would therefore be beneficial. We applied our model to evaluate the precursors of biosynthesis of 18000 alkaloids found in natural organisms and found some rules of relationships between chemical structure and activity.
|
| Free Research Field |
バイオインフォマティクス
|
| Academic Significance and Societal Importance of the Research Achievements |
文献調査をもとに、640種のアルカロイドを中心に３０枚に及ぶ二次代謝経路マップを整理しウエブにより公開した。本代謝経路で、それぞれのアルカロイドの生合成開始物質を明確に確認できる。また、現在までに、12000種のアルカロイド化合物のうち深層学習により、10,051種について、生合成開始物質が予測でき、二次代謝経路予測における基盤となるデータを整備し、生物活性の関係も把握できる公開データベースを構築した。アルカロイド化合物の生合成開始物質の推定が可能になり、二次代謝研究における学術的意義が非常に高いことを示す。また、データを一般公開しており、社会的にも十分な貢献を果たしている。
|
