Separable Parameter Estimation Method for Nonlinear Biological Systems

Models for biological systems derived from the generalized mass action law are typically a group of nonlinear ordinary differential equations. However, parameters in such models can be separated into two groups: one group of parameters linear in the model and another group of parameters nonlinear in the model. This paper introduces a separable parameter estimation method to estimate the parameters in such models. The separable parameter estimation method has three steps: in the first step, parameters linear in a model are estimated by optimizing the objective function using linear least squares method, assuming all parameters nonlinear in the model are known. In the second step, substituting the estimated parameters in the first step into the objective function yields a new objective function which is only of parameters nonlinear in the model. Then parameters nonlinear in the model are estimated by proper nonlinear estimation methods. In the last step, the estimates of parameters linear in the model are calculated using the estimates of parameters in the second step. To investigate its performance, the separable estimation method is applied to a biological system and is compared with the conventional parameter estimation methods. Simulation results show the improvement of the separable estimation method.