Search

AbstractAntibiotic tolerance, or the ability of bacteria to survive antibiotic treatment in the absence of genetic resistance, has been linked to chronic and recurrent infections. Tolerant cells are often characterized by a low metabolic state, against which most clinically used antibiotics are ineffective. Here, we show that tolerance readily evolves against antibiotics that are strongly dependent on bacterial metabolism, but does not arise against antibiotics whose efficacy is only minimally affected by metabolic state. We identify a mechanism of tolerance evolution in E. coli involving deletion of the sodium-proton antiporter gene nhaA, which results in downregulated metabolism and upregulated stress responses. Additionally, we find that cycling of antibiotics with different metabolic dependencies interrupts evolution of tolerance in vitro, increasing the lifetime of treatment efficacy. Our work highlights the potential for limiting the occurrence and extent of tolerance by accounting for antibiotic dependencies on bacterial metabolism.

Efficient identification of drug mechanisms of action remains a challenge. Computational docking approaches have been widely used to predict drug binding targets; yet, such approaches depend on existing protein structures, and accurate structural predictions have only recently become available from AlphaFold2. Here, we combine AlphaFold2 with molecular docking simulations to predict protein-ligand interactions between 296 proteins spanning Escherichia coli's essential proteome, and 218 active antibacterial compounds and 100 inactive compounds, respectively, pointing to widespread compound and protein promiscuity. We benchmark model performance by measuring enzymatic activity for 12 essential proteins treated with each antibacterial compound. We confirm extensive promiscuity, but find that the average area under the receiver operating characteristic curve (auROC) is 0.48, indicating weak model performance. We demonstrate that rescoring of docking poses using machine learning-based approaches improves model performance, resulting in average auROCs as large as 0.63, and that ensembles of rescoring functions improve prediction accuracy and the ratio of true-positive rate to false-positive rate. This work indicates that advances in modeling protein-ligand interactions, particularly using machine learning-based approaches, are needed to better harness AlphaFold2 for drug discovery.

The discovery of novel structural classes of antibiotics is urgently needed to address the ongoing antibiotic resistance crisis. Deep learning approaches have aided in exploring chemical spaces; these typically use black box models and do not provide chemical insights. Here we reasoned that the chemical substructures associated with antibiotic activity learned by neural network models can be identified and used to predict structural classes of antibiotics. We tested this hypothesis by developing an explainable, substructure-based approach for the efficient, deep learning-guided exploration of chemical spaces. We determined the antibiotic activities and human cell cytotoxicity profiles of 39,312 compounds and applied ensembles of graph neural networks to predict antibiotic activity and cytotoxicity for 12,076,365 compounds. Using explainable graph algorithms, we identified substructure-based rationales for compounds with high predicted antibiotic activity and low predicted cytotoxicity. We empirically tested 283 compounds and found that compounds exhibiting antibiotic activity against Staphylococcus aureus were enriched in putative structural classes arising from rationales. Of these structural classes of compounds, one is selective against methicillin-resistant S. aureus (MRSA) and vancomycin-resistant enterococci, evades substantial resistance, and reduces bacterial titres in mouse models of MRSA skin and systemic thigh infection. Our approach enables the deep learning-guided discovery of structural classes of antibiotics and demonstrates that machine learning models in drug discovery can be explainable, providing insights into the chemical substructures that underlie selective antibiotic activity.

© 2020 The Authors Zheng et al. rationally combine antibiotics using insights on bacterial metabolism to identify drug-drug combinations that sterilize bacterial cultures of both metabolically active and persister cells, while dose-sparing toxic antibiotics.

© 2019, The Author(s), under exclusive licence to Springer Nature Limited. Growth rate and metabolic state of bacteria have been separately shown to affect antibiotic efficacy1–3. However, the two are interrelated as bacterial growth inherently imposes a metabolic burden4; thus, determining individual contributions from each is challenging5,6. Indeed, faster growth is often correlated with increased antibiotic efficacy7,8; however, the concurrent role of metabolism in that relationship has not been well characterized. As a result, a clear understanding of the interdependence between growth and metabolism, and their implications for antibiotic efficacy, are lacking9. Here, we measured growth and metabolism in parallel across a broad range of coupled and uncoupled conditions to determine their relative contribution to antibiotic lethality. We show that when growth and metabolism are uncoupled, antibiotic lethality uniformly depends on the bacterial metabolic state at the time of treatment, rather than growth rate. We further reveal a critical metabolic threshold below which antibiotic lethality is negligible. These findings were general for a wide range of conditions, including nine representative bactericidal drugs and a diverse range of Gram-positive and Gram-negative species (Escherichia coli, Acinetobacter baumannii and Staphylococcus aureus). This study provides a cohesive metabolic-dependent basis for antibiotic-mediated cell death, with implications for current treatment strategies and future drug development.