Parameter inference of general nonlinear dynamical models of gene regulatory networks from small and noisy time series

• The methods requires lesser function evaluations than previous approaches.
• The procedure reproduces the behavior of the variables of the actual dynamical system.
• The method is competitive in the dynamic reconstruction from genetic expression time series.

A new inference approach to general dynamic models of gene regulatory networks (GRN) is introduced. The methodology is based on a Maximum a Posteriori (MAP) smoothing of time series data from which mean field variables of the dynamics are estimated. The interactions are modeled by a Continuous Time Recurrent Neural Network (CTRNN). Parameter estimation of the CTRNN is performed without the need to numerically solve the system of nonlinear differential equations. The method is tested on a benchmark of real genetic networks and displays superior performance, in terms of the mean squared error of the expression dynamics, compared to other formalisms.