Time Series Expression E.coli Prediction for Gene Regulatory Network Reconstruction
1
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
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%.
Abstract
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%.
참고문헌 (15)
- G. D. Hong, "Cognitive load while learning to use a computer program", Applied cognitive psychology, 2(9), pp.151~170 (1999)
- T.Akutsu, "Identification of genetic networks from a small number of gene expression patterns under the Boolean network model", Pacific Symposium on Biocomputing, pp.17~28 (1999)
- M. Chaves, "Methods of robustness analysis for Boolean models of gene control networks", IEEE Proceeding, 153(4), pp.154~167 (2006)
- S. Y. Kim, "Inferring gene networks from time series microarray data using dynamic Bayesian network", Briefings in Bioinformatics, 4(3), pp.228~235 (2003)
- I. A. Maraziotis, "Gene networks reconstruction and time-series prediction from microarray data using recurrent neural fuzzy networks", IET Syst. Biol, pp.41~50 (2007)
- 임준식, "퍼지신경망과 비중복면적 분산 측정법을 이용한 최소의 특징입력 및 퍼지규칙의 추출", 한국지능시스템학회 논문지, 15(5), pp.599~604 (2005), 한국지능시스템학회
- Sang-Hong Lee, "Forcasting KOSPI based on a neural network with weighted fuzzy membership function", Expert System with Application, 38(Issue 4,), pp.4259~4263 (2011)
- Abdulhamit Subasi, "EEG signal classification using wavelet feature extraction and a mixture of expert model", Expert Systems with Application, 32(Issue 4), pp.1084~1093 (2007)
- Hee Jin Yoon, "Algorithm for prediction of gene-gene interaction and reconstruction network using fuzzy neural network", pp.2015
- Husmeire, D, "Sensitivity and specificity of inferring genetic regulatory interactions from microarray experiments with dynamic Bayesian networks", Bioinformatics, 19, pp.2271~2282 (2003)
- Friedman, N., "Using bayesian networks to analysis expression data", J.Comp. Biol, 7, pp.601~620 (2000)
- Lian En Chai, "Inferring E.cloi SOS response pathway from gene expression data using IST-DBN with time lag estimation", Biomedical Infrastructure SCI, 477, pp.5~14 (2013)
- Takagi T, "Fuzzy identification of systems and its applications to modeling and control", IEEE Trans Syst Man Cybem, 15, pp.116~132 (1985)
- Roozbeh Manshaei, "Hybrid-controlled neurofuzzy networks analysis resulting in genetic regulatory networks reconstruction", ISRN Bioinformatics, 2012 (2012)
- I. A. Marziotis, "Gene networks reconstruction and time-series prediction from microarray data using recurrent neural fuzzy networks", IET Syst Biol, 1(1), pp.41~50 (2007)