Artificial Intelligence-Assisted Optimization of Extraction Enhances the Biological Activity of Phylloporia Ribis

Abstract

This research focuses on enhancing the extraction efficiency of Phylloporia ribis and assessing its biological functions. Key parameters including extraction temperature, duration, and ethanol-to-water ratio were optimized through both Response Surface Methodology (RSM) and an integrated Artificial Neural Network-Genetic Algorithm (ANN-GA) approach. The extracts obtained via ANN-GA exhibited greater antioxidant activity and higher concentrations of phenolic constituents such as gallic acid, quercetin, and vanillic acid. Compared to RSM-optimized samples, ANN-GA extracts demonstrated superior free radical scavenging, stronger ferric reducing power, and a more potent dose-dependent inhibition of cell proliferation. In addition, P. ribis extracts showed enzyme-inhibitory properties against acetylcholinesterase and butyrylcholinesterase, suggesting their potential utility in pharmaceutical and biotechnological applications. The ANN-GA method appears to be a promising tool for maximizing both the yield of phenolic compounds and the biological efficacy of extracts. Further advanced biotechnological optimization studies are advised to unlock the full therapeutic potential of P. ribis.