Evolutionary modeling and inference of genetic network

We have modeled relations of genetic regulatory network in a form of ordinary differential equations using the Evolutionary Modeling method. The model was derived by hybrid algorithm of Genetic Programming with statistical analysis. It models the gene expression profile as a general polynomial function of other gene's expression. The method of genetic programming and Least Mean Square method were combined to identify the regulatory pathways and its degree of influence from the given time series in a concise form. The results of multiple runs were statistically analyzed to indicate the term with robust and significant influence. Our approach was applied and evaluated to artificial data. The method has also been applied to a publicly available gene expression profile.