Combined structure-based virtual screening and machine learning approach for the identification of potential dual inhibitors of ACC and DGAT2.

Acetyl-coenzyme A carboxylase (ACC) and diacylglycerol acyltransferase 2 (DGAT2) are recognized as potential therapeutic targets for nonalcoholic fatty liver disease (NAFLD). Inhibitors targeting ACC and DGAT2 have exhibited the capacity to reduce hepatic fat in individuals afflicted with NAFLD. However, there are no reports of dual inhibitors targeting ACC and DGAT2 for the treatment of NAFLD. Here, we aimed to identify potential dual inhibitors of ACC and DGAT2 using an integrated in silico approach. Machine learning-based virtual screening of commercial molecule databases yielded 395,729 hits, which were subsequently subjected to molecular docking aimed at both the ACC and DGAT2 binding sites. Based on the docking scores, nine compounds exhibited robust interactions with critical residues of both ACC and DGAT2, displaying favorable drug-like features. Molecular dynamics simulations (MDs) unveiled the substantial impact of these compounds on the conformational dynamics of the proteins. Furthermore, binding free energy assessments highlighted the notable binding affinities of specific compounds (V003-8107, G340-0503, Y200-1700, E999-1199, V003-6429, V025-4981, V006-1474, V025-0499, and V021-8916) to ACC and DGAT2. The compounds proposed in this study, identified using a multifaceted computational strategy, warrant experimental validation as potential dual inhibitors of ACC and DGAT2, with implications for the future development of novel drugs targeting NAFLD.