Arfeen_2024_Molecules_29_

Alzheimer's disease (AD) is a neurodegenerative disorder associated with the dysregulation of several key enzymes, including acetylcholinesterase (AChE), cyclooxygenase-2 (COX-2), glycogen synthase kinase 3beta (GSK-3beta), beta-site amyloid precursor protein cleaving enzyme 1 (BACE-1), and caspase-3. In this study, machine learning algorithms such as Random Forest (RF), Gradient Boost (GB), and Extreme Gradient Boost (XGB) were employed to screen US-FDA approved drugs from the ZINC15 database to identify potential dual inhibitors of COX-2 and AChE. The models were trained using molecules obtained from the ChEMBL database, with 5039 molecules for AChE and 3689 molecules for COX-2. Specifically, 1248 and 3791 molecules were classified as active and inactive for AChE, respectively, while 858 and 2831 molecules were classified as active and inactive for COX-2. The three machine learning models achieved prediction accuracies ranging from 92% to 95% for both AChE and COX-2. Virtual screening of US-FDA drugs from the ZINC15 database identified sertraline (SETL) as a potential dual inhibitor of AChE and COX-2. Further docking studies of SETL in the active sites of AChE and COX-2, as well as BACE-1, GSK-3beta, and caspase-3, revealed strong binding affinities for all five proteins. In vivo validation was conducted using a lipopolysaccharide (LPS)-induced rat model pretreated with SETL for 30 days. The results demonstrated a significant decrease in the levels of AChE (p < 0.001), BACE-1 (p < 0.01), GSK-3beta (p < 0.05), and COX-2 (p < 0.05). Additionally, the downstream effects were evaluated, showing significant decreases in the apoptosis marker caspase-3 (p < 0.05) and the oxidative stress marker malondialdehyde (MDA) (p < 0.001), indicating that SETL is clinically localized in its effectiveness, mitigating both enzymatic activity and the associated pathological changes of cognitive impairment and AD.