2. Academic Validation
  3. Variability vs. phenotype: Multimodal analysis of Dravet syndrome brain organoids powered by deep learning

Variability vs. phenotype: Multimodal analysis of Dravet syndrome brain organoids powered by deep learning

  • iScience. 2025 Oct 23;28(11):113831. doi: 10.1016/j.isci.2025.113831.
Isabel Turpin-Moreno 1 2 3,  Adriana Modrego 1 2,  Andrea Martí-Sarrias 1 2 3,  Laura García-González 1 2 3,  Alba Ortega-Gasco 2 4 5,  Anna-Christina Haeb 2 4 5 6 7,  Ruth Pareja 1 2 3,  Jordi Soriano 6 7,  Núria Ruiz 1 8,  Irene Peñuelas-Haro 1 9,  Elisa Espinet 1 9,  Arcadi Navarro 3 10 11 12,  Daniel Tornero 2 4 5 13,  Oscar Lao 14,  Sandra Acosta 1 2 3 15
Affiliations

Affiliations

  • 1 Department of Pathology and Experimental Therapeutics, Medical School, Universitat de Barcelona, Barcelona, Spain.
  • 2 Institut of Neuroscience (INUB), Universitat de Barcelona, Barcelona, Spain.
  • 3 Barcelona Brain Research Centre (BBRC), Barcelona, Spain.
  • 4 Department of Biomedicine, Universitat de Barcelona, Barcelona, Spain.
  • 5 August Pi i Sunyer Biomedical Research Institute (IDIBAPS), 08036 Barcelona, Spain.
  • 6 Departament de Física de la Matèria Condensada, Universitat de Barcelona, Barcelona, Spain.
  • 7 Universitat de Barcelona Institute of Complex Systems (UBICS), Barcelona, Spain.
  • 8 Department of Pathology, Hospital Universitari de Bellvitge, L'Hospitalet de Llobregat, Barcelona, Spain.
  • 9 Oncology Program, Institut d'Investigació Biomèdica de Bellvitge, L'Hospitalet de Llobregat, Barcelona, Spain.
  • 10 Institució Catalana de Recerca i Estudis Avançats (ICREA) and Universitat Pompeu Fabra, Barcelona, Spain.
  • 11 IBE, Institute of Evolutionary Biology (UPF-CSIC), Department of Medicine and Life Sciences, Universitat Pompeu Fabra, L'Hospitalet de Llobregat, Barcelona, Spain.
  • 12 Centre for Genomic Regulation (CRG), The Barcelona Institute for Science and Technology, Barcelona, Spain.
  • 13 Centro de Investigación Biomédica en Red Sobre Enfermedades Neurodegenerativas (CIBERNED), Madrid, Spain.
  • 14 Group of Algorithms for Population Genomics, Department of Genetics, Institut de Biologia Evolutiva, IBE, (CSIC-Universitat Pompeu Fabra), Barcelona, Spain.
  • 15 Neurocience Program, Institut de Recerca Sant Joan de Déu (IRSJD), Esplugues de Llobregat, Spain.
PMID: 41323276 DOI: 10.1016/j.isci.2025.113831
Abstract

Dravet syndrome (DS) is a developmental epileptic encephalopathy (DEE) driven by pathogenic variants in the SCN1A gene. Brain organoids (BOs) have emerged as reliable models for neurodevelopmental genetic disorders, reproducing human brain developmental milestones and rising as a promising drug testing tool. Here, we determined the underlying molecular DS pathophysiology affecting neuronal connectivity, revealing an early onset excitatory-inhibitory imbalance in maturing DS Organoid circuitry. However, neuronal circuitry modeling in BOs remains hampered by the notorious inter- and intra-organoid variability. Thus, leveraging deep learning (DL), we developed ImPheNet, a predictive tool grounded in BO live imaging datasets, to overcome the limitations of the intrinsic BOs variability. ImPheNet accurately classified healthy and DS phenotypes at early onset stages, revealing differences between genotypes and upon antiseizure drug exposure. Altogether, our DL-predictive live imaging strategy, ImPheNet, emerges as a powerful tool to accelerate DEEs research and advance toward treatment discovery in a time- and cost-efficient manner.

Keywords

artificial intelligence; biological sciences; neuroscience; optical imaging; techniques in neuroscience.

Figures
Products