Evaluation of phenolic profile and multi-biological activities of Lepista glaucocana extracts optimized by ANN-GA and RSM models.

In this study, extraction parameters were optimized using Response Surface Methodology (RSM) and Artificial Neural Network-Genetic Algorithm (ANN-GA) approaches to determine the highest levels of biological activities of Lepista glaucocana (Bres.) Singer. Optimization parameters included temperature, time, and ethanol/water ratio. Subsequently, antioxidant, anticholinesterase, and antiproliferative activities, as well as phenolic contents, of the extracts produced under optimum conditions were determined. The results showed that the ANN-GA optimized extract exhibited significantly higher total antioxidant status (TAS), ferric reducing antioxidant power (FRAP), and DPPH radical scavenging activity compared to the RSM extract. Consequently, total oxidant status (TOS) and oxidative stress index (OSI) values ​​were lower in the ANN-GA extract. ANN-GA extract showed stronger inhibitory effects against acetylcholinesterase (AChE) and butyrylcholinesterase (BChE) enzymes with lower IC50 values ​​compared to RSM extracts. In antiproliferative assays, ANN-GA extract exhibited dose-dependent cytotoxicity against A549 (lung), MCF-7 (breast), and DU-145 (prostate) cancer cell lines. LC-MS/MS analyses revealed higher levels of phenolic compounds such as gallic acid, protocatechuic acid, syringic acid, and 2-hydroxycinnamic acid in the ANN-GA optimized extract. Consequently, the ANN-GA model was found to be a more efficient optimization tool than RSM. It was also determined that L. glaucocana may be a promising natural source of multifunctional bioactive compounds with antioxidant, anticholinesterase-related, and in vitro antiproliferative potential.