Machine learning prediction of dual and dose-response effects of flavone carbon and oxygen glycosides on acrylamide formation.

Introduction: The extensive occurrence of acrylamide in heat processing foods has continuously raised a potential health risk for the public in the recent 20 years. Machine learning emerging as a robust computational tool has been highlighted for predicting the generation and control of processing contaminants. Methods: We used the least squares support vector regression (LS-SVR) as a machine learning approach to investigate the effects of flavone carbon and oxygen glycosides on acrylamide formation under a low moisture condition. Acrylamide was prepared through oven heating via a potato-based model with equimolar doses of asparagine and reducing sugars. Results: Both inhibition and promotion effects were observed when the addition levels of flavonoids ranged 1-10,000 µmol/L. The formation of acrylamide could be effectively mitigated (37.6%-55.7%) when each kind of flavone carbon or oxygen glycoside (100 µmol/L) was added. The correlations between acrylamide content and trolox-equivalent antioxidant capacity (TEAC) within inhibitory range (R 2 = 0.85) had an advantage over that within promotion range (R 2 = 0.87) through multiple linear regression. Discussion: Taking ΔTEAC as a variable, a LS-SVR model was optimized as a predictive tool to estimate acrylamide content (R 2 inhibition = 0.87 and R 2 promotion = 0.91), which is pertinent for predicting the formation and elimination of acrylamide in the presence of exogenous antioxidants including flavonoids.

Catechins protect against acrylamide- and glycidamide-induced cellular toxicity via rescuing cellular apoptosis and DNA damage.

Acrylamide (AA) occurs in both various environmental and dietary sources and has raised widespread concern as a probable carcinogen. Glycidamide (GA) is the main genotoxic metabolite through P450 2E1 (CYP2E1). In the present study, we investigated the protective effect of (-)-epigallocatechin gallate (EGCG) and (-)-epicatechin (EC) against AA- and GA-induced hepatotoxicity in HepG2 cells. The results demonstrated that EC and EGCG inhibited AA- and GA-induced cytotoxicity and mitochondria-mediated cellular apoptosis. Moreover, exposure to AA (100 µg/mL) and GA (50 µg/mL) caused cell cycle arrest and DNA damage, while EC and EGCG ranging from 12.5 to 50 µg/mL rescued cell cycle arrest and inhibited DNA damage. Furthermore, EC and EGCG down-regulated pro-apoptotic protein Bax and Caspase 3 after a 24-h treatment in HepG2 cells exposed to AA (100 µg/mL) or GA (50 µg/mL). Also, the intervention with EC or EGCG up-regulated the expression of DNA repair related protein PARP and down-regulated the expression of Cleaved-PARP. Besides, EC exerted better protective effect than EGCG against AA- and GA-induced cytotoxicity in HepG2 cells. Altogether, EC and EGCG were effective in protecting AA- and GA-induced hepatotoxicity via rescuing cellular apoptosis and DNA damage, as well as promoting cell cycle progression in HepG2 cells.