2013 Fiscal Year Final Research Report
Massive Parallel Evolutionary Computation Theory based on a Molecular Realization of WetGA
| Project/Area Number |
23300084
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (B)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 一般 |
|---|
| Research Field |
Sensitivity informatics/Soft computing
|
|---|
| Research Institution | Tokyo Institute of Technology |
|---|
Principal Investigator |
YAMAMURA Masayuki 東京工業大学, 総合理工学研究科(研究院), 教授 (00220442)
|
|---|
| Co-Investigator(Renkei-kenkyūsha) |
SAKAMOTO Kensaku 独立行政法人理化学研究所, チームリーダー (50240685)
SOMEYA Hiroshi 東海大学, 情報理工学部, 講師 (00333518)
KOMIYA Ken 東京工業大学, 大学院・総合理工学研究科, 助教 (20396790)
|
|---|
| Project Period (FY) |
2011-04-01 – 2014-03-31
|
| Keywords | ウェットGA / 進化計算 / タンパク質工学 / 最適化 / 高度並列GA |
|---|
| Research Abstract |
We proposed WetGA implemented on biomoleculer experiments based on the knowledge obtained in the applications of evolutionary computation inspired from real life. We achieved the ideal population distribution transition through twelve generations in the application testbed which engineers tyrRS protein to recognize new substrate. We modeled the difficulty of the fitness landscape then actually evolved a new protein by new generation alternation model which can start with one local minima. We analyzed the mutation accumulation distribution in each generation by reading the sequences of all samples. We also proposed a new evolutionary computation scheme assuming massive parallel computer architectures.
|
Research Products
(7 results)
