Infer Gene Regulatory Network Based on the Novel Classifiers Fusion

Abstract

Reconstruction of gene regulatory network (GRN) from gene expression data is still a big challenge. Inference of gene regulatory network is considered as a binary classification problem. In this paper, we develop a new supervised learning approach based on several classifiers fusion (SLCF) for inference of gene regulatory network. According to the characteristics of classified data, SLCF uses three classification methods: direct classification, minimal distance selection and flexible neural tree, respectively. The data from E.coli network is used to test our method and results reveal that SLCF performs better than classical unsupervised and supervised learning methods.