¹Research Group of Computer-Aided Drug Design and Discovery of Bioactive Natural Products, Faculty of Pharmacy, Sanata Dharma University, Campus 3 Paingan Maguwoharjo Depok Sleman, Yogyakarta 55282, Indonesia DOI : 10.29228/jrp.792 Acetylcholinesterase (AChE) inhibitors have been used to delay the dementia progression in Alzheimer’s Disease (AD). In 2017, a structure-based virtual screening (SBVS) protocol was made publicly available and successfully employed to discover chalcone derivatives and short peptides as AChE inhibitors. During the upgrading process of the SBVS protocol, an optimized version of the enhanced directory of useful decoys (DUDE) was released. This optimized DUDE was named DUDE-Z. In this article, the re-optimization of the upgraded SBVS protocol is presented. The optimization process made use of a machine learning package and library called recursive partitioning and regression tree (RPART) in R statistical computing software environment. The optimized SBVS protocol has the F-measure value of 0.322 against the DUDE-Z. The protocol was subsequently analyzed to efficiently screen on a newly released openaccessed natural products database LOTUS (https://lotus.naturalproducts.net/) to discover bioactive natural products as AChE inhibitors. The SBVS campaigns on 276,518 natural products identified 867 compounds as virtual hits, thirtyseven of which were identified as compounds found in the species from Kingdom Plantae. Keywords : Structure-based virtual screening; machine learning; acetylcholinesterase; natural products