Prediction of phosphorylation sites in human protein by machine learning and the functional role of intrinsically disordered regions
| Project/Area Number |
26330336
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Life / Health / Medical informatics
|
|---|
| Research Institution | Ritsumeikan University |
|---|
Principal Investigator |
|
|---|
| Research Collaborator |
NISHIKAWA Ken
FUKUCHI Satoshi
TOHSATO Yukako
|
|---|
| Project Period (FY) |
2014-04-01 – 2017-03-31
|
| Project Status |
Completed (Fiscal Year 2016)
|
| Budget Amount *help |
¥4,680,000 (Direct Cost: ¥3,600,000、Indirect Cost: ¥1,080,000)
Fiscal Year 2016: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2015: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Fiscal Year 2014: ¥2,730,000 (Direct Cost: ¥2,100,000、Indirect Cost: ¥630,000)
|
|---|
| Keywords | 機械学習 / ヒトタンパク質 / 天然変性領域 / リン酸化 / サポートベクターマシン / 進化的保存度 / オーソログ / 予測 / エントロピー / 進化的保存性 / タンパク質 / 独立成分分析 |
|---|
| Outline of Final Research Achievements |
Phosphorylation site in human protein is studied, through the prediction by support vector machine. We focus on the difference in evolutional conservation between intrinsically disordered region (IDR) and the domain, and the functional role of IDR in the post-translational modification.
Sequence conservation is known to be generally low in IDR, while the functionally important modifications are often found in IDR. We proposed a measure of site-specific conservation based on multiple ortholog proteins, as PSSM (Position Specific Scoring Matrix), which is often used as a site-specific conservation measure, assumes sequence conservation which does not work in IDR. Then, the site-specific conservation is found to vary within IDR. The conservation is kept high at a phosphorylation site, especially at the phosphorylation with any clarified function. Prediction accuracy improves to 82.1% using both the conservation and the sequence information in IDR for functional phosphorylation sites.
|
Report
(4 results)
Research Products
(18 results)
