15 April 2021 in Nature Communications
Deep Learning (DL) methods are powerful analytical tools for microscopy and can outperform conventional image processing pipelines. Despite the enthusiasm and innovations fuelled by DL technology, the need to access powerful and compatible resources to train DL networks leads to an accessibility barrier that novice users often find difficult to overcome. Here, we present ZeroCostDL4Mic, an entry-level platform simplifying DL access by leveraging the free, cloud-based computational resources of Google Colab. ZeroCostDL4Mic allows researchers with no coding expertise to train and apply key DL networks to perform tasks including segmentation (using U-Net and StarDist), object detection (using YOLOv2), denoising (using CARE and Noise2Void), super-resolution microscopy (using Deep-STORM), and image-to-image translation (using Label-free prediction - fnet, pix2pix and CycleGAN). Importantly, we provide suitable quantitative tools for each network to evaluate model performance, allowing model optimisation. We demonstrate the application of the platform to study multiple biological processes.
7 January 2023 in Trends in Cell Biology
10 September 2025 in Nature Methods
Volume correlative light and electron microscopy (vCLEM) is a powerful imaging technique that enables the visualization of fluorescently labeled proteins within their ultrastructural context. Currently, vCLEM alignment relies on time-consuming and subjective manual methods. This paper presents CLEM-Reg, an algorithm that automates the three-dimensional alignment of vCLEM datasets by leveraging probabilistic point cloud registration techniques. Point clouds are derived from segmentations of common structures in each modality, created by state-of-the-art open-source methods. CLEM-Reg drastically reduces the registration time of vCLEM datasets to a few minutes and achieves correlation of fluorescent signal to submicron target structures in electron microscopy on three newly acquired vCLEM benchmark datasets. CLEM-Reg was then used to automatically obtain vCLEM overlays to unambiguously identify TGN46-positive transport carriers involved in protein trafficking between the trans-Golgi network and plasma membrane. Datasets are available on EMPIAR and BioStudies, and a napari plugin is provided to aid end-user adoption.
23 February 2026 in bioRxiv
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.