Artificial Intelligence-Assisted Optimization of Amanita caesarea Extracts for Bioactive Compounds and Functional Food Applications

This study evaluated the effects of different extraction optimization approaches on the biological activities and phenolic compositions of the edible mushroom Amanita caesarea (Scop.) Pers. Extraction time, extraction temperature and solvent ratio were optimized using Artificial Neural Network–Genetic Algorithm (ANN-GA) and Response Surface Methodology (RSM), while the best experimental extract (BEE) was also included for comparison. The extracts were analyzed for antioxidant parameters (TAS, TOS, OSI, FRAP, and DPPH), antiproliferative and anticholinesterase activities, and phenolic compound profiles by LC-MS/MS. The results showed that the optimization strategy markedly influenced both chemical composition and biological activity. Among the evaluated extracts, the ANN-GA-optimized sample showed the most pronounced biological performance. This extract was characterized by stronger antioxidant activity, a more balanced redox status, enhanced antiproliferative and anticholinesterase effects, and higher amounts of several phenolic constituents, especially gallic acid. Overall, the findings indicate that A. caesarea is a promising natural source of bioactive compounds and that AI-assisted optimization can improve its potential use in functional food and nutraceutical applications.