Shengxian Cao, Yu Wang and Zhenhao Tang* Pages 1 - 11 ( 11 )
Time series expression data contain relations among different genes, which are difficult to model precisely. We propose an adaptive Elman neural network (AENN) to reveal these relationships, with parameters optimized adaptively by a genetic algorithm (GA) to improve the accuracy of the model. In addition, we use a Pearson correlation analysis to discover the relationships among genes. To evaluate our proposed method, we compared several alternative data-driven approaches, including a neural fuzzy recurrent network (NFRN), a basic Elman neural network (ENN), and an ensemble network. The experimental results from simulated and real datasets demonstrate that the proposed approach has a promising performance for modeling gene regulation networks (GRNs). We also obtained gene expression data for slime-forming bacteria by transcriptome gene sequencing and used our method to establish a GRN for 6 genes.
Gene regulation network, Elman neural network, Gene algorithm, Pearson correlation analysis, Yeast gene data, Machine learning, Myxomycete
School of Automation Engineering, Northeast Electric Power University, Jilin, School of Automation Engineering, Northeast Electric Power University, Jilin, School of Automation Engineering, Northeast Electric Power University, Jilin