Multitask learning of a biophysically-detailed neuron model.

Item request has been placed! ×
Item request cannot be made. ×
loading   Processing Request
  • Additional Information
    • Source:
      Publisher: Public Library of Science Country of Publication: United States NLM ID: 101238922 Publication Model: eCollection Cited Medium: Internet ISSN: 1553-7358 (Electronic) Linking ISSN: 1553734X NLM ISO Abbreviation: PLoS Comput Biol Subsets: MEDLINE
    • Publication Information:
      Original Publication: San Francisco, CA : Public Library of Science, [2005]-
    • Subject Terms:
    • Abstract:
      The human brain operates at multiple levels, from molecules to circuits, and understanding these complex processes requires integrated research efforts. Simulating biophysically-detailed neuron models is a computationally expensive but effective method for studying local neural circuits. Recent innovations have shown that artificial neural networks (ANNs) can accurately predict the behavior of these detailed models in terms of spikes, electrical potentials, and optical readouts. While these methods have the potential to accelerate large network simulations by several orders of magnitude compared to conventional differential equation based modelling, they currently only predict voltage outputs for the soma or a select few neuron compartments. Our novel approach, based on enhanced state-of-the-art architectures for multitask learning (MTL), allows for the simultaneous prediction of membrane potentials in each compartment of a neuron model, at a speed of up to two orders of magnitude faster than classical simulation methods. By predicting all membrane potentials together, our approach not only allows for comparison of model output with a wider range of experimental recordings (patch-electrode, voltage-sensitive dye imaging), it also provides the first stepping stone towards predicting local field potentials (LFPs), electroencephalogram (EEG) signals, and magnetoencephalography (MEG) signals from ANN-based simulations. While LFP and EEG are an important downstream application, the main focus of this paper lies in predicting dendritic voltages within each compartment to capture the entire electrophysiology of a biophysically-detailed neuron model. It further presents a challenging benchmark for MTL architectures due to the large amount of data involved, the presence of correlations between neighbouring compartments, and the non-Gaussian distribution of membrane potentials.
      Competing Interests: The authors have declared that no competing interests exist.
      (Copyright: © 2024 Verhellen et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.)
    • References:
      J Physiol. 1952 Apr;116(4):449-72. (PMID: 14946713)
      Nature. 1999 Mar 25;398(6725):338-41. (PMID: 10192334)
      Elife. 2023 Jul 24;12:. (PMID: 37486105)
      J Physiol. 2022 Jan;600(2):173-174. (PMID: 34904231)
      J Physiol. 1962 Jan;160:106-54. (PMID: 14449617)
      J Physiol. 1968 Mar;195(1):215-43. (PMID: 4966457)
      J Neurophysiol. 2005 Apr;93(4):2194-232. (PMID: 15525801)
      J Comput Neurosci. 2008 Jun;24(3):291-313. (PMID: 17926125)
      J Physiol. 1959 Oct;148:574-91. (PMID: 14403679)
      PLoS Comput Biol. 2011 Jul;7(7):e1002107. (PMID: 21829333)
      PLoS Comput Biol. 2022 Aug 12;18(8):e1010353. (PMID: 35960767)
      J Physiol. 2001 Jun 1;533(Pt 2):447-66. (PMID: 11389204)
      Neuron. 2021 Sep 1;109(17):2727-2739.e3. (PMID: 34380016)
      Neuron. 2020 May 6;106(3):388-403.e18. (PMID: 32142648)
      PLoS Biol. 2018 Oct 26;16(10):e2006422. (PMID: 30365484)
      Brain Struct Funct. 2018 Apr;223(3):1409-1435. (PMID: 29143946)
      J Neurosci. 2012 Aug 22;32(34):11798-811. (PMID: 22915121)
      PLoS Comput Biol. 2013;9(7):e1003137. (PMID: 23874180)
      Neuron. 2011 Dec 8;72(5):859-72. (PMID: 22153380)
      Neuron. 2019 May 22;102(4):735-744. (PMID: 31121126)
      J Physiol. 2016 Jul 1;594(13):3809-25. (PMID: 27079755)
      Elife. 2022 Nov 07;11:. (PMID: 36341568)
      Nat Neurosci. 2000 Nov;3 Suppl:1165. (PMID: 11127828)
      Front Neuroinform. 2018 Dec 18;12:92. (PMID: 30618697)
      J Physiol. 1952 Apr;116(4):424-48. (PMID: 14946712)
      Neural Comput. 1997 Nov 15;9(8):1735-80. (PMID: 9377276)
      J Comput Neurosci. 2010 Dec;29(3):423-44. (PMID: 20502952)
      PLoS Comput Biol. 2015 Dec 14;11(12):e1004584. (PMID: 26657024)
      Cell. 2015 Oct 08;163(2):456-92. (PMID: 26451489)
      J Physiol. 1952 Apr;116(4):497-506. (PMID: 14946715)
      Cereb Cortex. 2016 Dec;26(12):4461-4496. (PMID: 27797828)
      IEEE/ACM Trans Comput Biol Bioinform. 2022 Nov-Dec;19(6):3093-3102. (PMID: 35576418)
      J Neurosci. 2018 Jun 27;38(26):6011-6024. (PMID: 29875266)
      Cereb Cortex. 2007 Sep;17(9):2204-13. (PMID: 17124287)
      PLoS Comput Biol. 2020 Mar 10;16(3):e1007725. (PMID: 32155141)
      Front Neuroinform. 2022 Jun 27;16:884046. (PMID: 35832575)
      Neural Comput. 1997 Aug 15;9(6):1179-209. (PMID: 9248061)
      J Physiol. 1952 Apr;116(4):473-96. (PMID: 14946714)
      Biophys J. 2008 Feb 1;94(3):784-802. (PMID: 17921225)
      J Physiol. 1952 Aug;117(4):500-44. (PMID: 12991237)
      Cereb Cortex. 2014 Mar;24(3):785-806. (PMID: 23203991)
      J Neurosci. 2017 May 17;37(20):5123-5143. (PMID: 28432143)
      Proc R Soc Lond B Biol Sci. 1977 Jul 28;198(1130):1-59. (PMID: 20635)
      Neuroimage. 2021 Jan 15;225:117467. (PMID: 33075556)
      PLoS Comput Biol. 2021 Apr 2;17(4):e1008893. (PMID: 33798190)
    • Publication Date:
      Date Created: 20240731 Date Completed: 20240812 Latest Revision: 20240814
    • Publication Date:
      20240814
    • Accession Number:
      PMC11318869
    • Accession Number:
      10.1371/journal.pcbi.1011728
    • Accession Number:
      39083546