An integrated machine learning-to- free energy perturbation (FEP) pipeline is reported, combining XGBoost-based screening, molecular docking, replicate explicit-solvent molecular dynamics (MD), and absolute FEP calculations, as a multi-stage alternative to single-scoring approaches for tetrapeptide lead discovery against BACE-1.
The comprehensive in silico methodology in this work illuminated the inhibitory mechanism of LY3202626 and top hit compounds against BACE1 activity for the first time, which will be highly valuable in further optimization and structural refinement using various functional group modifications to yield more potent next-g...
Computational findings suggest that ligand 4 represents a promising alkynyl-3-carboxamide-based lead scaffold for further development as a potential legumain-targeted therapeutic candidate for AD.
Afifa Noor, H. N. Suha, Istiak Hossain et al.· Physical Chemistry, Chemical...· 0 citations
Alzheimer’s disease (AD) is a chronic, progressive neurodegenerative disorder predominantly affecting 47 million people worldwide. Dysregulation of BACE-1, the initiating enzyme in the amyloidogenic cascade, plays a pivotal role in AD pathogenesis. Conventional anticholinesterase inhibitors can only provide symptomat...
Pitam Ghosh, Ryena Dhir, Dinki Sharma et al.· Journal of Computational Bio...· 0 citations
This research provides new technology and potential lead compound for the development of future anti-Alzheimer’s disease drug as well as demonstrates that integrating machine learning-assisted virtual screening with natural product libraries is an effective strategy for discovering novel BACE1 inhibitors.
Yi-Ming Bai, Jun Zhao, Shu-Rong Zhang et al.· ACS Omega· 0 citations
These findings identify Olaparib as a novel high-affinity repurposing lead, while Paliperidone and Risperidone are reported as chemically informative secondary NAC–groove binders rather than proposed antiparkinsonian therapeutics, given that their dopamine D2-antagonist pharmacology is clinically associated with drug-i...
M. Abdelsayed, Y. Boulaamane· International Journal of Mol...· 0 citations
GSK3BMTPred, a multitask deep neural network model, was developed for simultaneous prediction of inhibitor classification and inhibitory potency and identified compounds showing stable interactions with key Adenosine Triphosphate (ATP) residues and favorable predicted absorption, distribution, metabolism, excretion, an...
