The Inverse Aspect of Metaheuristics for the Parameter Identification of S-systems

摘要: The genetic regulatory network, which is constructed from the time‐courses data sets, always described as highly nonlinear differential equations. Mathematical and computational modeling technologies focus on efficiently identifying parameters of dynamic biological system. Various derivative‐free derivative‐ based optimization have been proposed recently to infer S‐type networks (S‐systems). S‐system coupled power‐law functions. As involved genes and/or proteins increase, identification becomes increasingly difficult; multiple attractors exist in How develop an algorithm reduce computation time while keeping accuracy necessary. In this study, a gradient‐based metaheuristics proposed. method starts with hill‐climbing optimization, solves stagnation phenomenon by using climbing operation migration synchronous evolution. This was tested four systems. To show performance solution quality time, we let learning be implemented wide search space ([0, 100] for rate constants [‐100, kinetic orders) initialized all at bad point (the neighbourhood 80).