Optimization based evaluation of biological activities and chemical composition of Russula vinosa

This study aimed to optimize the extraction conditions of Russula vinosa, an edible and medicinal mushroom, to enhance its biological activity. The effects of extraction parameters (temperature, time, and ethanol-water ratio) were evaluated using Response Surface Methodology (RSM) and Artificial Neural Network-Genetic Algorithm (ANN-GA) approaches. The results showed that ANN-GA optimization yielded extracts with improved antioxidant properties, reflected by higher FRAP (193.010 mg TE/g), TAS (6.439 mmol/L), and DPPH (159.927 mg TE/g) values, along with lower TOS (11.074 µmol/L) and OSI (0.172) compared to RSM. In addition, ANN-GA extracts exhibited stronger anticholinesterase activity and enhanced antiproliferative effects. Chemical profiling revealed that ANN-GA optimization resulted in higher levels of key phenolic compounds, including gallic acid, quercetin, caffeic acid, and fumaric acid, indicating improved extraction efficiency. Overall, these findings demonstrate that ANN-GA provides a more effective optimization strategy than RSM by enhancing both bioactive compound recovery and biological activity. This study highlights the potential of R. vinosa as a valuable natural resource for functional food and pharmaceutical applications.