발간년도 : [2015]
| 논문정보 |
|
| 논문명(한글) |
[Vol.10, No.5] Time Series Expression E.coli Prediction for Gene Regulatory Network Reconstruction |
|
| 논문투고자 |
Hee-Jin Yoon |
|
| 논문내용 |
Presenting the relationship of gene and gene is Gene Regulatory Networks(GRN). In the relationship of gene and gene, one of the target gene is affected by regulate genes. Gene regulatory network is divided into two ways by regulate gene activate expression of target gene and repress it. This paper predicted time series expression E.coli data to reconstruction Gene Regulatory Networks. E.coli used in test data is composed of eight genes and has 50 time point. To predict a one target gene, the rest is used for regulator genes. To predict E.coli data, it used Neural Network with Weighted Fuzzy Membership Function(NEWFM). E.coli Data which has time series is used Wavelet for feature extraction. Feature is used for prediction of a Gene Regulatory Networks. By the NEWFM, features were trained and selected minimum feature by Weighted Fuzzy Membership Function Bounded Sum. Data value of selected features is defuzzificated by Takagi-Sugeno value, and by using previous time expression value of regulator genes predicted current time expression value of target gene. Predicted value indicated mean square error(MSE). As comparing, it shows that predicted result is improved by each MSE result; NFRN algorithm is 0.12%, EK algorithm is 0.12%, and NEWFM is 0.003%. |
|
| 첨부논문 |
|
|
|
|
|
자료실 > 논문지 
