Ultrasound-aided extraction of bioactive ingredients from Vitis vinifera seeds using optimized conditions of Central Composite Design of RSM, ANFIS modeling, and Machine Learning algorithm

Abstract

Abstract Grape seeds are a cost-effective source of antioxidant and potential therapeutic compounds in the form of polyphenols. Therapeutic important polyphenols were completely extracted from grape seeds using an ultrasound-aided extraction technique and examined the antioxidant properties. The present study aimed to determine the optimized condition and green process for maximum extraction of polyphenols from grape seeds through RSM (response surface methodology), ANFIS (adaptive neuro-fuzzy inference system), and machine learning (ML) algorithm models. Effect of five independent variables and their ranges, particle size (X1: 0.5-1 mm), methanol concentration (X2: 60-70% in distilled water), ultrasound exposure time (X3:18-28 min), temperature (X4: 35-45 °C), and ultrasound intensity (X5: 65-75 W cm-2) at five levels (-2, -1, 0, +1, and +2) concerning dependent variables, total phenolic contents (y1), total flavonoid contents (y2), %DPPH*sc (y3), %ABTS*sc (y4) and FRAP (y5) were selected. The optimized condition was observed at X1= 0.155 mm, X2= 65% methanol in water, X3= 23 min ultrasound exposure time, X4= 40 °C, and X5=70 W cm-2 ultrasound intensity. Under this situation, the optimal yields of TPC, TFC, and antioxidant scavenging potential were achieved to be 670.32 mg GAE/g, 451.45 mg RE/g, 81.23% DPPH*sc, 77.39% ABTS*sc and 71.55 μg mol (Fe(II))/g FRAP. This optimal condition yielded equal experimental and expected values. A well-fitted quadratic model was recommended. Furthermore, the validated extraction parameters were optimized and compared using the ANFIS and random forest regressor-ML algorithm. Additionally, GC-MS and LC-MS analyses were performed to find the existence of the bioactive compounds in the optimized extract.