A deep learning strategy to identify cell types across species from high-density extracellular recordings.

Journal: Cell
PMID: 40023155

Abstract

High-density probes allow electrophysiological recordings from many neurons simultaneously across entire brain circuits but fail to reveal cell type. Here, we develop a strategy to identify cell types from extracellular recordings in awake animals and reveal the computational roles of neurons with distinct functional, molecular, and anatomical properties. We combine optogenetics and pharmacology using the cerebellum as a testbed to generate a curated ground-truth library of electrophysiological properties for Purkinje cells, molecular layer interneurons, Golgi cells, and mossy fibers. We train a semi-supervised deep learning classifier that predicts cell types with greater than 95% accuracy based on the waveform, discharge statistics, and layer of the recorded neuron. The classifier's predictions agree with expert classification on recordings using different probes, in different laboratories, from functionally distinct cerebellar regions, and across species. Our classifier extends the power of modern dynamical systems analyses by revealing the unique contributions of simultaneously recorded cell types during behavior.

Authors

  • Maxime Beau
    Wolfson Institute for Biomedical Research, University College London, London, UK.
  • David J Herzfeld
    Department of Neurobiology, Duke University School of Medicine, Durham, NC, USA.
  • Francisco Naveros
  • Marie E Hemelt
    Department of Neurobiology, Duke University School of Medicine, Durham, NC, USA.
  • Federico D'Agostino
    Wolfson Institute for Biomedical Research, University College London, London, UK.
  • Marlies Oostland
    Wolfson Institute for Biomedical Research, University College London, London, UK; Swammerdam Institute for Life Sciences, University of Amsterdam, Amsterdam, the Netherlands.
  • Alvaro Sánchez-López
    Department of Neuroscience, Baylor College of Medicine, Houston, TX, USA.
  • Young Yoon Chung
    Wolfson Institute for Biomedical Research, University College London, London, UK.
  • Michael Maibach
    Wolfson Institute for Biomedical Research, University College London, London, UK.
  • Stephen Kyranakis
    Department of Biomedical Engineering, Johns Hopkins University, Baltimore, MD, USA.
  • Hannah N Stabb
    Wolfson Institute for Biomedical Research, University College London, London, UK.
  • M Gabriela Martínez Lopera
    Wolfson Institute for Biomedical Research, University College London, London, UK.
  • Agoston Lajko
    Wolfson Institute for Biomedical Research, University College London, London, UK.
  • Marie Zedler
    Wolfson Institute for Biomedical Research, University College London, London, UK.
  • Shogo Ohmae
    Department of Neuroscience, Baylor College of Medicine, Houston, TX, USA.
  • Nathan J Hall
    Department of Neurobiology, Duke University School of Medicine, Durham, NC, USA.
  • Beverley A Clark
    Wolfson Institute for Biomedical Research, University College London, London, UK.
  • Dana Cohen
    The Leslie and Susan Gonda Multidisciplinary Brain Research Center, Bar-Ilan University, Ramat-Gan, Israel.
  • Stephen G Lisberger
    Department of Neurobiology, Duke University School of Medicine, Durham, NC, USA.
  • Dimitar Kostadinov
    Wolfson Institute for Biomedical Research, University College London, London, UK; Centre for Developmental Neurobiology, King's College London, London, UK.
  • Court Hull
    Department of Neurobiology, Duke University School of Medicine, Durham, NC, USA.
  • Michael Häusser
    Wolfson Institute for Biomedical Research, University College London, London, UK; School of Biomedical Sciences, The University of Hong Kong, Hong Kong, China.
  • Javier F Medina
    Department of Neuroscience, Baylor College of Medicine, Houston, Texas 77030, USA; email: jfmedina@bcm.edu.

Keywords

External Resources

Popular Topics
Recent Journals