Drug discovery guided by maximum drug likeness

TL;DR

This paper introduces the Maximum Drug-Likeness (MDL) concept and a 5-fold MDL strategy that uses deep learning to identify promising drug candidates with high clinical translatability, validated by antibacterial activity experiments.

Contribution

It presents a novel 33-dimensional property spectrum and an ensemble deep learning approach for drug screening, improving the identification of high-potential molecules.

Findings

Successfully prioritized 15 candidate molecules from 16 million compounds.

Experimental validation showed the lead compound's potent antibacterial activity.

The strategy demonstrated superior binding stability compared to existing antibiotics.

Abstract

To overcome the high attrition rate and limited clinical translatability in drug discovery, we introduce the concept of Maximum Drug-Likeness (MDL) and develop an applicable Fivefold MDL strategy (5F-MDL) to reshape the screening paradigm. The 5F-MDL strategy integrates an ensemble of 33 deep learning sub-models to construct a 33-dimensional property spectrum that quantifies the global phenotypic alignment of candidate molecules with clinically approved drugs along five axes: physicochemical properties, pharmacokinetics, efficacy, safety, and stability. Using drug-likeness scores derived from this 33-dimensional profile, we prioritized 15 high-potential molecules from a 16-million-molecule library. Experimental validation demonstrated that the lead compound M2 not only exhibits potent antibacterial activity, with a minimum inhibitory concentration (MIC) of 25.6 ug/mL, but also achieves binding stability superior to cefuroxime, as indicated by Molecular Mechanics Poisson-Boltzmann surface area (MM-PBSA) calculations of -38.54 kcal/mol and a root-mean-square deviation (RMSD) of 2.8 A. This strategy could overcome scaffold constraints and offers an efficient route for discovering lead compounds with favorable prospects against drug-resistant bacteria.