Deep learning extracts MoA-specific signatures from high-throughput images of chemically and genetically perturbed Corynebacteria

Abstract

Tuberculosis (TB) is the worldwide leading infectious killer due to a single pathogen and increasing antimicrobial resistance (AMR) makes it imperative to discover and develop new drugs with novel modes of action (MoAs) to treat TB infections. Phenotypic screening of chemical libraries has proven effective at identifying new compounds against bacterial pathogens. However, a major limitation of standard screens is their inability to uncover the MoA of hits thereby preventing targeted selection of compounds with novel MoAs. Linking drug perturbations to mutants from images could potentially enable to predict the targets of compounds that act through novel MoAs. Here, we develop a deep learning (DL)-based method to screen drug-treated Corynebacterium glutamicum (Cglu), a surrogate model for Mycobacterium tuberculosis (Mtb). Our DL model is based on a convolutional neural network architecture that takes high throughput images as input and is trained to distinguish between different MoAs. We show that our approach can robustly differentiate between the MoAs of established antibiotics and correctly recognise the MoA of antibiotics that were not previously seen by the DL model. We also show that inhibitors with the same and previously unseen MoA cluster together and apart from all other reference drugs, allowing for new MoA discovery. Importantly, we show that our model links images of chemical (drugs) and genetic (mutants) perturbations targeting similar pathways, thus paving the way towards mutant-based target prediction of compounds that act through novel MoAs, directly from high-content images. Finally, we explore the phenotypes induced by genetic disruption of pathways and demonstrate that features extracted with our DL model recover known biological relationships from high-throughput images alone using the cell cycle of Cglu as a case study, a finding with promising potential for fundamental mechanistic studies.