Optimization of fungal secondary metabolites production via response surface methodology coupled with multi-parameter optimized artificial neural network model.

Filamentous fungi's secondary metabolites (SMs) possess significant application owing to their distinct structure and diverse bioactivities, yet their restricted yield levels often hinder further research and application. The study developed a response surface methodology-artificial neural network (RSM-ANN) strategy with multi-parameter optimizations of the ANN model to optimize medium for the production of two high-value fungal SMs, echinocandin E and paraherquamide A. Multi-parameter optimization of the ANN model was achieved through stratifying experimental data, fully adjusting neural network internals, and evaluating metaheuristic algorithms for optimal initial weights and biases. Experimental validation of models revealed that ANN-genetic algorithm models outperformed traditional RSM models in terms of determination coefficients, accuracy, and mean squared errors. ANN models showed outstanding robustness across a variety of fungal species, mediums, and experimental designs (Central Composite Design or Box-Behnken Design). This work refines the RSM-ANN optimization technique to increase fungal SM production efficiency, enabling industrial-scale production and applications.