Ribosome phenotypes for rapid classification of antibiotic-susceptible and resistant strains of Escherichia coli
Communications Biology Nature Research 8:1 (2025) 319
Abstract:
Rapid antibiotic susceptibility tests (ASTs) are an increasingly important part of clinical care as antimicrobial resistance (AMR) becomes more common in bacterial infections. Here, we use the spatial distribution of fluorescently labelled ribosomes to detect intracellular changes associated with antibiotic susceptibility in E. coli cells using a convolutional neural network (CNN). By using ribosome-targeting probes, one fluorescence image provides data for cell segmentation and susceptibility phenotyping. Using 60,382 cells from an antibiotic-susceptible laboratory strain of E. coli, we showed that antibiotics with different mechanisms of action result in distinct ribosome phenotypes, which can be identified by a CNN with high accuracy (99%, 98%, 95%, and 99% for ciprofloxacin, gentamicin, chloramphenicol, and carbenicillin). With 6 E. coli strains isolated from bloodstream infections, we used 34,205 images of ribosome phenotypes to train a CNN that could classify susceptible cells with 91% accuracy and resistant cells with 99% accuracy. Such accuracies correspond to the ability to differentiate susceptible and resistant samples with 99% confidence with just 2 cells, meaning that this method could eliminate lengthy culturing steps and could determine susceptibility with 30 min of antibiotic treatment. The ribosome phenotype method should also be able to identify phenotypes in other strains and species.Tunable fluorogenic DNA probes drive fast and high-resolution single-molecule fluorescence imaging
(2025)
Rapid identification of bacterial isolates using microfluidic adaptive channels and multiplexed fluorescence microscopy
Lab on a Chip Royal Society of Chemistry 24:20 (2024) 4843-4858
Abstract:
We demonstrate the rapid capture, enrichment, and identification of bacterial pathogens using Adaptive Channel Bacterial Capture (ACBC) devices. Using controlled tuning of device backpressure in polydimethylsiloxane (PDMS) devices, we enable the controlled formation of capture regions capable of trapping bacteria from low cell density samples with near 100% capture efficiency. The technical demands to prepare such devices are much lower compared to conventional methods for bacterial trapping and can be achieved with simple benchtop fabrication methods. We demonstrate the capture and identification of seven species of bacteria with bacterial concentrations lower than 1000 cells per mL, including common Gram-negative and Gram-positive pathogens such as Escherichia coli and Staphylococcus aureus. We further demonstrate that species identification of the trapped bacteria can be undertaken in the order of one-hour using multiplexed 16S rRNA-FISH with identification accuracies of 70–98% with unsupervised classification methods across 7 species of bacteria. Finally, by using the bacterial capture capabilities of the ACBC chip with an ultra-rapid antimicrobial susceptibility testing method employing fluorescence imaging and convolutional neural network (CNN) classification, we demonstrate that we can use the ACBC chip as an imaging flow cytometer that can predict the antibiotic susceptibility of E. coli cells after identification.Infection inspection: using the power of citizen science for image-based prediction of antibiotic resistance in Escherichia coli treated with ciprofloxacin
Scientific Reports Springer Nature 14:1 (2024) 19543
Abstract:
Antibiotic resistance is an urgent global health challenge, necessitating rapid diagnostic tools to combat its threat. This study uses citizen science and image feature analysis to profile the cellular features associated with antibiotic resistance in Escherichia coli. Between February and April 2023, we conducted the Infection Inspection project, in which 5273 volunteers made 1,045,199 classifications of single-cell images from five E. coli strains, labelling them as antibiotic-sensitive or antibiotic-resistant based on their response to the antibiotic ciprofloxacin. User accuracy in image classification reached 66.8 ± 0.1%, lower than our deep learning model's performance at 75.3 ± 0.4%, but both users and the model were more accurate when classifying cells treated at a concentration greater than the strain's own minimum inhibitory concentration. We used the users' classifications to elucidate which visual features influence classification decisions, most importantly the degree of DNA compaction and heterogeneity. We paired our classification data with an image feature analysis which showed that most of the incorrect classifications happened when cellular features varied from the expected response. This understanding informs ongoing efforts to enhance the robustness of our diagnostic methodology. Infection Inspection is another demonstration of the potential for public participation in research, specifically increasing public awareness of antibiotic resistance.Single-molecule tracking reveals the functional allocation, in vivo interactions, and spatial organization of universal transcription factor NusG.
Molecular cell 84:5 (2024) 926-937.e4