Multi-target drug development has become an attractive strategy in the discovery of drugs to treat of Alzheimer’s disease (AzD). In this study, for the first time, a rule-based machine learning (ML) approach with classification trees (CT) was applied for the rational design of novel dual-target acetylcholinesterase (AChE) and β-site amyloid-protein precursor cleaving enzyme 1 (BACE1) inhibitors. Updated data from 3524 compounds with AChE and BACE1 measurements were curated from the ChEMBL database. The best global accuracies of training/external validation for AChE and BACE1 were 0.85/0.80 and 0.83/0.81, respectively. The rules were then applied to screen dual inhibitors from the original databases. Based on the best rules obtained from each classification tree, a set of potential AChE and BACE1 inhibitors were identified, and active fragments were extracted using Murcko-type decomposition analysis. More than 250 novel inhibitors were designed in silico based on active fragments and predicted AChE and BACE1 inhibitory activity using consensus QSAR models and docking validations. The rule-based and ML approach applied in this study may be useful for the in silico design and screening of new AChE and BACE1 dual inhibitors against AzD.

Citrulline malate (CM) is a widely sought-after ingredient in the dietary supplement industry due to its ability to enhance exercise performance and promote muscle recovery. With the rising demand for CM, stringent quality control measures are essential, particularly in monitoring residual impurities in raw materials. An HPLC method was developed for the determination of fumaric acid (FA) and maleic acid (MA) impurities in CM raw material using a Shim-pack GIST C18 column (250 × 4.6 mm, 5 µm), detection at 210 nm, injection volume of 10 µL, and flow rate of 0.8 mL/min with a mobile phase consisting of acetonitrile and 3.3 mM potassium dihydrogen phosphate buffer (pH 2.0) (gradient). Another HPLC method was developed for the determination of N-acetylornithine (AO) impurity using the same C18 column, but with a detection wavelength of 200 nm, injection volume of 20 µL, flow rate of 1.0 mL/min, and a mobile phase consisting of 10 mM octane sulfonic acid sodium salt (pH 2.5) and acetonitrile under gradient condition. The methods were validated following AOAC International, confirming their accuracy and reliability (recovery not over than 100.0 ± 5.0% for all; RSD ≤ 1.1, 2.6, 3.0 % for FA, MA, AO respectively) in the range of concentration from 0.1 to 70 µg/mL (FA); 0.1 to 3.5 µg/mL (MA); 0.7 to 5.0 µg/mL (AO) with the coefficients very close of 1 (0.9999 for FA and MA, 0.9994 for AO). LOD, LOQ were established at 0.03, 0.1 for both FA, MA, and 0.5, 0.7 for AO.