DeepBacs for multi-task bacterial image analysis using open-source deep learning approaches

Spahn, Christoph; Gómez-de-Mariscal, Estibaliz; Laine, Romain F.; Pereira, Pedro M.; Chamier, Lucas von; Conduit, Mia; Pinho, Mariana G.; Jacquemet, Guillaume; Holden, Séamus; Heilemann, Mike; Henriques, Ricardo

doi:10.1038/s42003-022-03634-z

Cited by 39 publications

(49 citation statements)

References 86 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A powerful emerging technique based on cytological profiling has been successfully used to identify the cellular pathways targeted by the inhibitors (Nonejuie et al 2013; Martin et al 2020), including cell division inhibition by FtsZ (Araújo-Bazán et al 2016). The recent advances in computational image analysis and deep learning approaches (von Chamier et al 2021; Spahn et al 2022) could further advance image-based screening for FtsZ inhibitors (Andreu et al 2022). Thus, our results here suggest that the fission yeast expression system can be used to identify small molecules that directly target FtsZ, probe the molecular determinants of resistance and establish a proof-of-concept of an in vivo cell-based assay to discover antimicrobials that specifically target the bacterial cytoskeleton.…”

Section: Discussionmentioning

confidence: 99%

A salt bridge-mediated resistance mechanism to FtsZ inhibitor PC190723 revealed by a cell-based screen

Sharma

Poddar

Chakraborty

et al. 2022

Preprint

View full text Add to dashboard Cite

Bacterial cell division proteins, especially the tubulin homolog FtsZ, have emerged as strong targets for developing new antibiotics. Several assays have been designed to screen for small molecules targeting FtsZ but rely upon a multitude of steps to validate the target and to ensure minimum toxicity to the eukaryotic cells. Here, we have utilized the fission yeast heterologous expression system to develop a single step cell-based assay to screen for small molecules that directly and specifically target the bacterial cell division protein FtsZ and are non-toxic to eukaryotic cells. As a proof-of-concept of the utility of this assay, we demonstrate the effect of the inhibitors sanguinarine, berberine and PC190723 on FtsZ. Though sanguinarine and berberine affect FtsZ polymerization, they exert a toxic effect on the cells. Further, using this assay system, we show that PC190723 affects Helicobacter pylori FtsZ function and gain new insights into the molecular determinants of resistance to PC190723. Based on sequence and structural analysis and site-specific mutations, we demonstrate that the presence of salt-bridge interactions between the central H7 helix and beta-sheet S10 and S7 mediate resistance to PC190723 in FtsZ. The single step in vivo cell-based assay using fission yeast enabled us to dissect the contribution of sequence-specific features of FtsZ and cell permeability effects associated with bacterial cell envelopes. Thus, our assay functions as a powerful tool to rapidly identify new molecules that specifically target the bacterial cell division protein FtsZ, or other polymeric bacterial cytoskeletal proteins, understand how they affect polymerization dynamics and study resistance determinants in targets.

show abstract

Section: Discussionmentioning

confidence: 99%

A salt bridge-mediated resistance mechanism to FtsZ inhibitor PC190723 revealed by a cell-based screen

Sharma

Poddar

Chakraborty

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…a bacterium with a lateral and a polar focus was assigned “lateral”). The overall number of bacteria in a field of view was determined by using the deep learning based network, DeepBacs [74], that was previously trained with differential interferometry contrast (DIC) micrographs of Y. enterocolitica . The overall percentage of cells with foci is displayed in the figure.…”

Section: Methodsmentioning

confidence: 99%

Pilotins are mobile T3SS components involved in assembly and substrate specificity of the bacterial type III secretion system

Wimmi

Fleck

Helbig

et al. 2022

Preprint

View full text Add to dashboard Cite

In animal pathogens, assembly of the type III secretion system injectisome requires the presence of so-called pilotins, small lipoproteins that assist the formation of the secretin ring in the outer membrane. Using a combination of functional assays, interaction studies, proteomics and live-cell microscopy, we determined the contribution of the pilotin to assembly, function and substrate selectivity of the T3SS and identified potential new downstream roles of pilotin proteins. In the absence of its pilotin SctG, Yersinia enterocolitica forms few, largely polar injectisome sorting platforms and needles. In line, the majority of export apparatus subcomplexes is mobile in these strains, suggesting the absence of fully assembled injectisomes. Remarkably, the export of late T3SS substrates including the virulence effectors is hardly affected in these bacteria, whereas early T3SS substrates, such as the needle subunits, are only exported to a very low degree. We found that pilotins transiently interact with the secretin and the large export apparatus component SctV, but mostly localize throughout the bacterial membrane, where they form transient mobile clusters, which do not colocalize with assembled injectisomes. In addition, pilotins interact with non-T3SS components, including sugar transporters. Pilotins therefore have additional functions downstream injectisome assembly, which include the regulation of type III secretion and a potential new link to the cellular energy metabolism.

show abstract

“…The S. aureus dataset from Spahn et al [44] is available at https://zenodo.org/ record/5550933%23.Y6IhFNLMJH4 and https://zenodo.org/record/5551141#.Y6IjBdLMJH5. All other datasets are available at https://s3.valeria.science/ flclab-tagan/index.html.…”

Section: Declarationsmentioning

confidence: 99%

Resolution Enhancement with a Task-Assisted GAN to Guide Optical Nanoscopy Image Analysis and Acquisition

Bouchard

Wiesner

Deschênes

et al. 2021

Preprint

View full text Add to dashboard Cite

We introduce a deep learning model for resolution enhancement and prediction of super-resolved biological structures, which is based on a Generative Adversarial Network (GAN) assisted by a complementary segmentation task. It is applied to predict biological nanostructures from diffraction-limited images and to guide microscopists for quantitative fixed- and live-cell STimulated Emission Depletion (STED) microscopy. More specifically, we show that the use of a complementary segmentation task improves the accuracy of the predicted nanostructures over state-of-the art resolution enhancement generative approaches, allowing quantitative analysis of the sub-diffraction structures in the resulting generated images.

show abstract

DeepBacs for multi-task bacterial image analysis using open-source deep learning approaches

Cited by 39 publications

References 86 publications

A salt bridge-mediated resistance mechanism to FtsZ inhibitor PC190723 revealed by a cell-based screen

A salt bridge-mediated resistance mechanism to FtsZ inhibitor PC190723 revealed by a cell-based screen

Pilotins are mobile T3SS components involved in assembly and substrate specificity of the bacterial type III secretion system

Resolution Enhancement with a Task-Assisted GAN to Guide Optical Nanoscopy Image Analysis and Acquisition

Contact Info

Product

Resources

About