Report
Deep learning extracts MoA-specific signatures from high-throughput images of chemically and genetically perturbed Corynebacteria
| Τίτλος: | Deep learning extracts MoA-specific signatures from high-throughput images of chemically and genetically perturbed Corynebacteria |
|---|---|
| Συγγραφείς: | Krentzel, Daniel, Petit, Julienne, Boudehen, Yves-Marie, Mahtal, Nassim, Sadowski, Elodie, Zettor, Agnès, Aubry, Alexandra, Chiaravalli, Jeanne, Aulner, Nathalie, Petrella, Stéphanie, Alzari, Pedro, M, Zimmer, Christophe, Wehenkel, Anne Marie |
| Συνεισφορές: | Imagerie et Modélisation - Imaging and Modeling, Institut Pasteur Paris (IP)-Centre National de la Recherche Scientifique (CNRS)-Université Paris Cité (UPCité), Mécanismes du Cycle Cellulaire Bactérien / Bacterial Cell Cycle Mechanisms, Microbiologie structurale - Structural Microbiology (Microb. Struc. (UMR_3528 / U-Pasteur_5)), BioImagerie Photonique – Photonic BioImaging (UTechS PBI), Institut Pasteur Paris (IP)-Université Paris Cité (UPCité), CHU Pitié-Salpêtrière AP-HP, Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Sorbonne Université (SU), Criblage chémogénomique et biologique (Plateforme) - Chemogenomic and Biological Screening Platform (PF-CCB), Institut Pasteur Paris (IP)-Institut de Chimie - CNRS Chimie (INC-CNRS)-Centre National de la Recherche Scientifique (CNRS)-Université Paris Cité (UPCité), Centre d'Immunologie et des Maladies Infectieuses (CIMI Paris), Institut National de la Santé et de la Recherche Médicale (INSERM)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS), Julius-Maximilians-Universität Würzburg = University of Würzburg Würsburg, Germany (JMU), The UTechS Photonic BioImaging, C2RT, Institut Pasteur, is supported by the French National Research Agency (France BioImaging, ANR-24-INBS-0005 FBI (BIOGEN), Investments for the Future) and acknowledges Institut Pasteur and the Région Île-de-France (DIM1Health program) funding for the use of the Opera Phenix system. This work was supported in part by grants from the Agence Nationale de la Recherche (ANR, France), contracts ANR-21-CE11-0003 (A.M.W.), ANR-24-CE11-4058 (A.M.W), Fondation pour la Recherche Médicale, FRM, EQU202303016284 (P.M.A.), Institut Pasteur PTR_726_BactImMorph (A.M.W.) and by institutional grants from the Institut Pasteur, the CNRS, and Université Paris Cité. J.P. was partially funded through the AMX program from the École Polytechnique. D.K. was funded by the Pasteur-Paris University International doctoral program, the INCEPTION program (Investissement d’Avenir grant ANR-16-CONV-0005) and a Fondation pour la Recherche Médicale Fin de Thèse grant (FDT202404018132). We also acknowledge the INCEPTION program for funding a GPU farm used in this work., ANR-24-INBS-0005,FBI (BIOGEN) (JVCE),France-BioImaging (Biological Imaging Next-Generation Instrument)(2024), ANR-21-CE11-0003,MecaDiv,Caractérisation mécanistique de sous-complexes du divisome bactérien reconstitués in vitro(2021), ANR-24-CE11-4058,Divinet,Comprendre les réseaux de protéines médiés par DivIVA, au cœur du cycle cellulaire chez les bactéries à Gram positif.(2024), ANR-16-CONV-0005,INCEPTION,Institut Convergences pour l'étude de l'Emergence des Pathologies au Travers des Individus et des populatiONs(2016) |
| Πηγή: | https://pasteur.hal.science/pasteur-05549423 ; 2026. |
| Στοιχεία εκδότη: | CCSD |
| Έτος έκδοσης: | 2026 |
| Συλλογή: | Inserm: HAL (Institut national de la santé et de la recherche médicale) |
| Θεματικοί όροι: | [SDV]Life Sciences [q-bio], [INFO]Computer Science [cs] |
| Περιγραφή: | International audience ; 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. |
| Τύπος εγγράφου: | report |
| Γλώσσα: | English |
| Relation: | BIORXIV: 2026.02.23.707449 |
| DOI: | 10.64898/2026.02.23.707449 |
| Διαθεσιμότητα: | https://pasteur.hal.science/pasteur-05549423 https://pasteur.hal.science/pasteur-05549423v1/document https://pasteur.hal.science/pasteur-05549423v1/file/2026.02.23.707449v1.full.pdf https://doi.org/10.64898/2026.02.23.707449 |
| Rights: | https://creativecommons.org/licenses/by-nc-nd/4.0/ ; info:eu-repo/semantics/OpenAccess |
| Αριθμός Καταχώρησης: | edsbas.37CF7FDB |
| Βάση Δεδομένων: | BASE |
| DOI: | 10.64898/2026.02.23.707449 |
|---|