In-silicoDrug Repurposing pipeline for Epilepsy: Integrating Deep Learning and Structure-based Approaches

Abstract

AbstractEpilepsy is a severe neurological disorder characterized by its chronic predisposition to recurrent epileptic seizures. Due to its considerable global prevalence and healthcare burden, the pursuit of effective new medication for epilepsy treatment remains an urgent and significant challenge in medical practice. Drug repurposing emerges as a cost-effective and efficient strategy to combat this disorder. This study leverages the transformer-based deep learning methods coupled with molecular binding affinity calculation to develop a novelin-silicodrug repurposing pipeline for epilepsy. The number of candidate inhibitors approved for chronic conditions against 24 gain-of-function (GOF) encoding targets implicated in epileptogenesis ranged from zero to several hundred. Nearly half of candidate medications for each target were used for psychiatric diseases and most of anti-epileptic drugs (AEDs) in market were screened, highlighting the effectiveness of our pipeline. Furthermore, Lomitapide, a cholesterol-lowering drug, emerged as particularly noteworthy, exhibiting high binding affinity for ten targets and verified by molecular dynamics (MD) simulation. These findings demonstrated the practical potential of ourin-silicodrug repurposing pipeline in epilepsy treatment, providing a novel perspective on therapeutic strategies for other central nervous system (CNS) disease.