Report
Προβολή σε EDS

Deep learning extracts MoA-specific signatures from high-throughput images of chemically and genetically perturbed Corynebacteria

Λεπτομέρειες βιβλιογραφικής εγγραφής
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
FullText Text:
  Availability: 0
CustomLinks:
  – Url: https://pasteur.hal.science/pasteur-05549423#
    Name: EDS - BASE (ns324271)
    Category: fullText
    Text: View record from BASE
Header DbId: edsbas
DbLabel: BASE
An: edsbas.37CF7FDB
RelevancyScore: 1010
AccessLevel: 3
PubType: Report
PubTypeId: report
PreciseRelevancyScore: 1009.80889892578
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Deep learning extracts MoA-specific signatures from high-throughput images of chemically and genetically perturbed Corynebacteria
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Krentzel%2C+Daniel%22">Krentzel, Daniel</searchLink><br /><searchLink fieldCode="AR" term="%22Petit%2C+Julienne%22">Petit, Julienne</searchLink><br /><searchLink fieldCode="AR" term="%22Boudehen%2C+Yves-Marie%22">Boudehen, Yves-Marie</searchLink><br /><searchLink fieldCode="AR" term="%22Mahtal%2C+Nassim%22">Mahtal, Nassim</searchLink><br /><searchLink fieldCode="AR" term="%22Sadowski%2C+Elodie%22">Sadowski, Elodie</searchLink><br /><searchLink fieldCode="AR" term="%22Zettor%2C+Agnès%22">Zettor, Agnès</searchLink><br /><searchLink fieldCode="AR" term="%22Aubry%2C+Alexandra%22">Aubry, Alexandra</searchLink><br /><searchLink fieldCode="AR" term="%22Chiaravalli%2C+Jeanne%22">Chiaravalli, Jeanne</searchLink><br /><searchLink fieldCode="AR" term="%22Aulner%2C+Nathalie%22">Aulner, Nathalie</searchLink><br /><searchLink fieldCode="AR" term="%22Petrella%2C+Stéphanie%22">Petrella, Stéphanie</searchLink><br /><searchLink fieldCode="AR" term="%22Alzari%2C+Pedro%2C+M%22">Alzari, Pedro, M</searchLink><br /><searchLink fieldCode="AR" term="%22Zimmer%2C+Christophe%22">Zimmer, Christophe</searchLink><br /><searchLink fieldCode="AR" term="%22Wehenkel%2C+Anne+Marie%22">Wehenkel, Anne Marie</searchLink>
– Name: Author
  Label: Contributors
  Group: Au
  Data: Imagerie et Modélisation - Imaging and Modeling<br />Institut Pasteur Paris (IP)-Centre National de la Recherche Scientifique (CNRS)-Université Paris Cité (UPCité)<br />Mécanismes du Cycle Cellulaire Bactérien / Bacterial Cell Cycle Mechanisms<br />Microbiologie structurale - Structural Microbiology (Microb. Struc. (UMR_3528 / U-Pasteur_5))<br />BioImagerie Photonique – Photonic BioImaging (UTechS PBI)<br />Institut Pasteur Paris (IP)-Université Paris Cité (UPCité)<br />CHU Pitié-Salpêtrière AP-HP<br />Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Sorbonne Université (SU)<br />Criblage chémogénomique et biologique (Plateforme) - Chemogenomic and Biological Screening Platform (PF-CCB)<br />Institut Pasteur Paris (IP)-Institut de Chimie - CNRS Chimie (INC-CNRS)-Centre National de la Recherche Scientifique (CNRS)-Université Paris Cité (UPCité)<br />Centre d'Immunologie et des Maladies Infectieuses (CIMI Paris)<br />Institut National de la Santé et de la Recherche Médicale (INSERM)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS)<br />Julius-Maximilians-Universität Würzburg = University of Würzburg Würsburg, Germany (JMU)<br />The UTechS Photonic BioImaging, C2RT, Institut Pasteur, is supported by the French National Research Agency (France BioImaging, ANR-24-INBS-0005 FBI (BIOGEN)<br />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.<br />ANR-24-INBS-0005,FBI (BIOGEN) (JVCE),France-BioImaging (Biological Imaging Next-Generation Instrument)(2024)<br />ANR-21-CE11-0003,MecaDiv,Caractérisation mécanistique de sous-complexes du divisome bactérien reconstitués in vitro(2021)<br />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)<br />ANR-16-CONV-0005,INCEPTION,Institut Convergences pour l'étude de l'Emergence des Pathologies au Travers des Individus et des populatiONs(2016)
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <i>https://pasteur.hal.science/pasteur-05549423 ; 2026</i>.
– Name: Publisher
  Label: Publisher Information
  Group: PubInfo
  Data: CCSD
– Name: DatePubCY
  Label: Publication Year
  Group: Date
  Data: 2026
– Name: Subset
  Label: Collection
  Group: HoldingsInfo
  Data: Inserm: HAL (Institut national de la santé et de la recherche médicale)
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22[SDV]Life+Sciences+[q-bio]%22">[SDV]Life Sciences [q-bio]</searchLink><br /><searchLink fieldCode="DE" term="%22[INFO]Computer+Science+[cs]%22">[INFO]Computer Science [cs]</searchLink>
– Name: Abstract
  Label: Description
  Group: Ab
  Data: 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.
– Name: TypeDocument
  Label: Document Type
  Group: TypDoc
  Data: report
– Name: Language
  Label: Language
  Group: Lang
  Data: English
– Name: NoteTitleSource
  Label: Relation
  Group: SrcInfo
  Data: BIORXIV: 2026.02.23.707449
– Name: DOI
  Label: DOI
  Group: ID
  Data: 10.64898/2026.02.23.707449
– Name: URL
  Label: Availability
  Group: URL
  Data: https://pasteur.hal.science/pasteur-05549423<br />https://pasteur.hal.science/pasteur-05549423v1/document<br />https://pasteur.hal.science/pasteur-05549423v1/file/2026.02.23.707449v1.full.pdf<br />https://doi.org/10.64898/2026.02.23.707449
– Name: Copyright
  Label: Rights
  Group: Cpyrght
  Data: https://creativecommons.org/licenses/by-nc-nd/4.0/ ; info:eu-repo/semantics/OpenAccess
– Name: AN
  Label: Accession Number
  Group: ID
  Data: edsbas.37CF7FDB
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsbas&AN=edsbas.37CF7FDB
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.64898/2026.02.23.707449
    Languages:
      – Text: English
    Subjects:
      – SubjectFull: [SDV]Life Sciences [q-bio]
        Type: general
      – SubjectFull: [INFO]Computer Science [cs]
        Type: general
    Titles:
      – TitleFull: Deep learning extracts MoA-specific signatures from high-throughput images of chemically and genetically perturbed Corynebacteria
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Krentzel, Daniel
      – PersonEntity:
          Name:
            NameFull: Petit, Julienne
      – PersonEntity:
          Name:
            NameFull: Boudehen, Yves-Marie
      – PersonEntity:
          Name:
            NameFull: Mahtal, Nassim
      – PersonEntity:
          Name:
            NameFull: Sadowski, Elodie
      – PersonEntity:
          Name:
            NameFull: Zettor, Agnès
      – PersonEntity:
          Name:
            NameFull: Aubry, Alexandra
      – PersonEntity:
          Name:
            NameFull: Chiaravalli, Jeanne
      – PersonEntity:
          Name:
            NameFull: Aulner, Nathalie
      – PersonEntity:
          Name:
            NameFull: Petrella, Stéphanie
      – PersonEntity:
          Name:
            NameFull: Alzari, Pedro, M
      – PersonEntity:
          Name:
            NameFull: Zimmer, Christophe
      – PersonEntity:
          Name:
            NameFull: Wehenkel, Anne Marie
      – PersonEntity:
          Name:
            NameFull: Imagerie et Modélisation - Imaging and Modeling
      – PersonEntity:
          Name:
            NameFull: Institut Pasteur Paris (IP)-Centre National de la Recherche Scientifique (CNRS)-Université Paris Cité (UPCité)
      – PersonEntity:
          Name:
            NameFull: Mécanismes du Cycle Cellulaire Bactérien / Bacterial Cell Cycle Mechanisms
      – PersonEntity:
          Name:
            NameFull: Microbiologie structurale - Structural Microbiology (Microb. Struc. (UMR_3528 / U-Pasteur_5))
      – PersonEntity:
          Name:
            NameFull: BioImagerie Photonique – Photonic BioImaging (UTechS PBI)
      – PersonEntity:
          Name:
            NameFull: Institut Pasteur Paris (IP)-Université Paris Cité (UPCité)
      – PersonEntity:
          Name:
            NameFull: CHU Pitié-Salpêtrière AP-HP
      – PersonEntity:
          Name:
            NameFull: Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Sorbonne Université (SU)
      – PersonEntity:
          Name:
            NameFull: Criblage chémogénomique et biologique (Plateforme) - Chemogenomic and Biological Screening Platform (PF-CCB)
      – PersonEntity:
          Name:
            NameFull: Institut Pasteur Paris (IP)-Institut de Chimie - CNRS Chimie (INC-CNRS)-Centre National de la Recherche Scientifique (CNRS)-Université Paris Cité (UPCité)
      – PersonEntity:
          Name:
            NameFull: Centre d'Immunologie et des Maladies Infectieuses (CIMI Paris)
      – PersonEntity:
          Name:
            NameFull: Institut National de la Santé et de la Recherche Médicale (INSERM)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS)
      – PersonEntity:
          Name:
            NameFull: Julius-Maximilians-Universität Würzburg = University of Würzburg Würsburg, Germany (JMU)
      – PersonEntity:
          Name:
            NameFull: The UTechS Photonic BioImaging, C2RT, Institut Pasteur, is supported by the French National Research Agency (France BioImaging, ANR-24-INBS-0005 FBI (BIOGEN)
      – PersonEntity:
          Name:
            NameFull: 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.
      – PersonEntity:
          Name:
            NameFull: ANR-24-INBS-0005,FBI (BIOGEN) (JVCE),France-BioImaging (Biological Imaging Next-Generation Instrument)(2024)
      – PersonEntity:
          Name:
            NameFull: ANR-21-CE11-0003,MecaDiv,Caractérisation mécanistique de sous-complexes du divisome bactérien reconstitués in vitro(2021)
      – PersonEntity:
          Name:
            NameFull: 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)
      – PersonEntity:
          Name:
            NameFull: ANR-16-CONV-0005,INCEPTION,Institut Convergences pour l'étude de l'Emergence des Pathologies au Travers des Individus et des populatiONs(2016)
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 01
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-locals
              Value: edsbas
            – Type: issn-locals
              Value: edsbas.oa
          Titles:
            – TitleFull: https://pasteur.hal.science/pasteur-05549423 ; 2026
              Type: main
ResultId 1