Discovery of antibiotics that selectively kill metabolically dormant bacteria.

There is a need to discover and develop non-toxic antibiotics that are effective against metabolically dormant bacteria, which underlie chronic infections and promote antibiotic resistance. Traditional antibiotic discovery has historically favored compounds effective against actively metabolizing cells, a property that is not predictive of efficacy in metabolically inactive contexts. Here, we combine a stationary-phase screening method with deep learning-powered virtual screens and toxicity filtering to discover compounds with lethality against metabolically dormant bacteria and favorable toxicity profiles. The most potent and structurally distinct compound without any obvious mechanistic liability was semapimod, an anti-inflammatory drug effective against stationary-phase E. coli and A. baumannii. Integrating microbiological assays, biochemical measurements, and single-cell microscopy, we show that semapimod selectively disrupts and permeabilizes the bacterial outer membrane by binding lipopolysaccharide. This work illustrates the value of harnessing non-traditional screening methods and deep learning models to identify non-toxic antibacterial compounds that are effective in infection-relevant contexts.

Discovery of a structural class of antibiotics with explainable deep learning.

The discovery of novel structural classes of antibiotics is urgently needed to address the ongoing antibiotic resistance crisis1-9. Deep learning approaches have aided in exploring chemical spaces1,10-15; 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.

BioAutoMATED: An end-to-end automated machine learning tool for explanation and design of biological sequences.

The design choices underlying machine-learning (ML) models present important barriers to entry for many biologists who aim to incorporate ML in their research. Automated machine-learning (AutoML) algorithms can address many challenges that come with applying ML to the life sciences. However, these algorithms are rarely used in systems and synthetic biology studies because they typically do not explicitly handle biological sequences (e.g., nucleotide, amino acid, or glycan sequences) and cannot be easily compared with other AutoML algorithms. Here, we present BioAutoMATED, an AutoML platform for biological sequence analysis that integrates multiple AutoML methods into a unified framework. Users are automatically provided with relevant techniques for analyzing, interpreting, and designing biological sequences. BioAutoMATED predicts gene regulation, peptide-drug interactions, and glycan annotation, and designs optimized synthetic biology components, revealing salient sequence characteristics. By automating sequence modeling, BioAutoMATED allows life scientists to incorporate ML more readily into their work.

Sequence-to-function deep learning frameworks for engineered riboregulators.

While synthetic biology has revolutionized our approaches to medicine, agriculture, and energy, the design of completely novel biological circuit components beyond naturally-derived templates remains challenging due to poorly understood design rules. Toehold switches, which are programmable nucleic acid sensors, face an analogous design bottleneck; our limited understanding of how sequence impacts functionality often necessitates expensive, time-consuming screens to identify effective switches. Here, we introduce Sequence-based Toehold Optimization and Redesign Model (STORM) and Nucleic-Acid Speech (NuSpeak), two orthogonal and synergistic deep learning architectures to characterize and optimize toeholds. Applying techniques from computer vision and natural language processing, we 'un-box' our models using convolutional filters, attention maps, and in silico mutagenesis. Through transfer-learning, we redesign sub-optimal toehold sensors, even with sparse training data, experimentally validating their improved performance. This work provides sequence-to-function deep learning frameworks for toehold selection and design, augmenting our ability to construct potent biological circuit components and precision diagnostics.

A CRISPR-based assay for the detection of opportunistic infections post-transplantation and for the monitoring of transplant rejection.

In organ transplantation, infection and rejection are major causes of graft loss. They are linked by the net state of immunosuppression. To diagnose and treat these conditions earlier, and to improve long-term patient outcomes, refined strategies for the monitoring of patients after graft transplantation are needed. Here, we show that a fast and inexpensive assay based on CRISPR-Cas13 accurately detects BK polyomavirus DNA and cytomegalovirus DNA from patient-derived blood and urine samples, as well as CXCL9 messenger RNA (a marker of graft rejection) at elevated levels in urine samples from patients experiencing acute kidney transplant rejection. The assay, which we adapted for lateral-flow readout, enables-via simple visualization-the post-transplantation monitoring of common opportunistic viral infections and of graft rejection, and should facilitate point-of-care post-transplantation monitoring.

LADL: light-activated dynamic looping for endogenous gene expression control.

Mammalian genomes are folded into tens of thousands of long-range looping interactions. The cause-and-effect relationship between looping and genome function is poorly understood, and the extent to which loops are dynamic on short time scales remains an unanswered question. Here, we engineer a new class of synthetic architectural proteins for directed rearrangement of the three-dimensional genome using blue light. We target our light-activated-dynamic-looping (LADL) system to two genomic anchors with CRISPR guide RNAs and induce their spatial colocalization via light-induced heterodimerization of cryptochrome 2 and a dCas9-CIBN fusion protein. We apply LADL to redirect a stretch enhancer (SE) away from its endogenous Klf4 target gene and to the Zfp462 promoter. Using single-molecule RNA-FISH, we demonstrate that de novo formation of the Zfp462-SE loop correlates with a modest increase in Zfp462 expression. LADL facilitates colocalization of genomic loci without exogenous chemical cofactors and will enable future efforts to engineer reversible and oscillatory loops on short time scales.