Integrated Pharmacophore, Docking, Machine Learning, and Molecular Dynamics Approach for the Discovery and Validation of LuxS Quorum-Sensing Inhibitors to Combat Antibiotic Resistance

Abstract

Antibiotic resistance is a major global health problem that reduces the effectiveness of traditional antibiotics. Quorum sensing (QS) refers to a signaling mechanism mediated by small signaling molecules (autoinducers) that regulates the bacterial ability to resist the action of antibiotics. The LuxS enzyme is involved in the QS pathway and cleaves S-ribosylhomocysteine (SRH) into 4,5-dihydroxy-2,3-pentanedione (DPD), which is then converted into its active form, autoinducer-2 (AI-2). This role in the QS pathway makes LuxS an attractive therapeutic target for developing new drugs to inhibit AI-2 formation. Therefore, this study presents an integrated computational framework combining pharmacophore-based virtual screening with machine learning (ML)-guided prioritization to identify potential LuxS inhibitors. Unlike conventional docking approaches, the ML models incorporate residue-level interaction features to refine hit selection. The identified top hits demonstrated stable binding profiles and favorable energetics during molecular dynamics simulations and MM/PBSA analysis. These findings highlight the effectiveness of the proposed workflow in improving hit prioritization and provide a rational strategy for designing QS inhibitors to combat antibiotic resistance.