A hybrid of RSM, ANFIS, and machine learning algorithm approach for ultrasound-assisted extraction of bioactive compounds from Semecarpus anacardium Linn

Abstract

ABSTRACT Ultrasound-assisted solvent extraction (UASE) was appslied to extract phytoconstituents from Semecarpus anacardium L. The effective extraction parameters were optimized using the Response Surface Methodology (RSM) with Central Composite Face Centered design (CCFC), and the optimization parameters were validated through Adaptive Neuro-Fuzzy Inference System (ANFIS) and Machine Learning (ML) algorithm models. The four independent parameters, i.e. ethanol concentration (X 1: 62–72% v/v), temperature (X 2: 38–48°C), ultrasonic-exposure time (X 3: 12–24 min), and particle size (X 4: 2–5 mm) were optimized. The maximum yield of phytocompounds was achieved at X 1 = 67%, X 2 = 43°C, X 3 = 18 min, and X 4 = 3.5 mm. The optimized yield of total phenolic, flavonoid, and antioxidant activity was considered when selecting process parameters. In this scenario, the optimized yields of total polyphenolic content (y1 = 619.25 mg gallic acid equivalent (GAE)/g), total flavonoid content (y2 = 151.24 mg Quercetin equivalents (QE)/g), free radical scavenging abilities (%DPPH*sc (y3 = 66.41%), and %ABTS*sc (y4 = 56.94%). The LC-MS peaks identify the presence of semecarpetin, butein, and amentoflavone, whereas GS-MS peaks represent seventeen gaseous components. Furthermore, the bioactive-rich optimized extract was nontoxic and supported the growth of macrophage- and epithelial cells in vitro. Conclusively, optimizing the UASE parameters enhanced the yield of bioactive compounds of S. anacardium L.