Development of a machine learning model and glycan profile database for understanding glycan function
| Project/Area Number |
26330333
|
|---|
| 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 | Soka University |
|---|
Principal Investigator |
|
|---|
| Research Collaborator |
HOSODA Masae
TAKAHASHI Yushi
|
|---|
| Project Period (FY) |
2014-04-01 – 2017-03-31
|
| Project Status |
Completed (Fiscal Year 2016)
|
| Budget Amount *help |
¥4,550,000 (Direct Cost: ¥3,500,000、Indirect Cost: ¥1,050,000)
Fiscal Year 2016: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Fiscal Year 2015: ¥1,690,000 (Direct Cost: ¥1,300,000、Indirect Cost: ¥390,000)
Fiscal Year 2014: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
|
|---|
| Keywords | 糖鎖 / アラインメント / ウェブツール / 糖鎖認識タンパク質 / 糖鎖インフォマティクス / マルチプルアラインメント / グライコミクス / 確率モデル / 機械学習 / アルゴリズム |
|---|
| Outline of Final Research Achievements |
In order to develop a machine learning model for understanding glycan function, it was necessary to first determine the topology of the pattern to learn from glycan data. Thus, it became necessary to develop a multiple glycan alignment algorithm, which we called MCAW. From this we realized that it was possible to use MCAW directly to analyze glycan function from technologies such as glycan arrays. Therefore, we proceeded to analyze such experimental data using MCAW. We used the high-affinity glycans of glycan-binding proteins as input to MCAW. As a result, we found that MCAW was able to produce glycan recognition patterns that have been confirmed in the literature, in addition to other patterns that were not necessarily found readily. Thus we show that MCAW was able to produce results based on the experimental data. We are working on developing a glycan profile database based on these analytical results.
|
Report
(4 results)
Research Products
(7 results)
