Structural analysis of the whole genome data from BioBank Japan
| Project/Area Number |
26860228
|
|---|
| Research Category |
Grant-in-Aid for Young Scientists (B)
|
| Allocation Type | Multi-year Fund |
|---|
| Research Field |
Human genetics
|
|---|
| Research Institution | Institute of Physical and Chemical Research |
|---|
Principal Investigator |
Kamatani Yoichiro 国立研究開発法人理化学研究所, 統合生命医科学研究センター, チームリーダー (00720880)
|
|---|
| Research Collaborator |
SESE Jun 国立研究開発法人産業技術総合研究所, 人工知能研究センター・機械学習研究チーム, チーム長
KOIDO Masaru 国立研究開発法人理化学研究所, 統合生命医科学研究センター, 客員研究員
KANAI Masahiro 国立研究開発法人理化学研究所, 統合生命医科学研究センター, 研修生
|
|---|
| Project Period (FY) |
2014-04-01 – 2017-03-31
|
| Project Status |
Completed (Fiscal Year 2016)
|
| Budget Amount *help |
¥2,340,000 (Direct Cost: ¥1,800,000、Indirect Cost: ¥540,000)
Fiscal Year 2015: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Fiscal Year 2014: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
|
|---|
| Keywords | 機械学習 / ゲノム / 遺伝統計学 / 全ゲノム解析 / エピスタシス / ポリジェニックモデル |
|---|
| Outline of Final Research Achievements |
We used BioBank Japan data and applied machine learning technique to detect genetic factors associated with disease occurrence. By using Random Forest (RF), LASSO, Elastic Net, Support Vector Machine (SVM), Extremely Randomized Trees (ERT), and mixed Random Forest (mixed RF), we identified that LASSO and Elastic Net outperformed other methods. This results indicates the importance of regularization in the genetic association model.
In parallel, we applied LD score regression method or Popcorn method to see the differences of genetic background for the complex disease between Japanese and European populations from the view point of polygenic architecture. We revealed that higher heritability for atopic dermatitis and lower for bipolar disorder in Japanese compared with European population. Further studies would clarify the actual genetic regions responsible for these differences.
|
Report
(4 results)
Research Products
(3 results)
