Comparison of artificial neural network, genetic programming, and mechanistic modeling of complex biological processes

摘要

Artificial neural network (ANN), genetic programming (GP), and mechanistic modeling approaches were compared to model cometabolic enzyme kinetics of simulated degradation of ammonia and trichlorethyl- ene (TCE) in a quasi-steady-state bioreactor. ANN and GP approaches effectively modeled complex pro- cesses involving decreases and increases in metabolic activity, and made subsequent predictions of sys- tem behavior and responses to perturbation. The mechanistic model used fundamentally derived rate equations governing the cometabolic processes and applied them for modeling.