Geometric deep learning and multiple-instance learning for 3D cell-shape profiling.

Journal: Cell systems
PMID:

Abstract

The three-dimensional (3D) morphology of cells emerges from complex cellular and environmental interactions, serving as an indicator of cell state and function. In this study, we used deep learning to discover morphology representations and understand cell states. This study introduced MorphoMIL, a computational pipeline combining geometric deep learning and attention-based multiple-instance learning to profile 3D cell and nuclear shapes. We used 3D point-cloud input and captured morphological signatures at single-cell and population levels, accounting for phenotypic heterogeneity. We applied these methods to over 95,000 melanoma cells treated with clinically relevant and cytoskeleton-modulating chemical and genetic perturbations. The pipeline accurately predicted drug perturbations and cell states. Our framework revealed subtle morphological changes associated with perturbations, key shapes correlating with signaling activity, and interpretable insights into cell-state heterogeneity. MorphoMIL demonstrated superior performance and generalized across diverse datasets, paving the way for scalable, high-throughput morphological profiling in drug discovery. A record of this paper's transparent peer review process is included in the supplemental information.

Authors

  • Matt De Vries
    The Institute of Cancer Research, London, United Kingdom.
  • Lucas G Dent
    Department of Cancer Biology, Institute of Cancer Research, London, UK.
  • Nathan Curry
    Department of Physics, Imperial College London, London, UK.
  • Leo Rowe-Brown
    Department of Physics, Imperial College London, London, UK.
  • Vicky Bousgouni
    Institute of Cancer Research, Chester Beatty Laboratories, London, UK.
  • Olga Fourkioti
    The Institute of Cancer Research, London, United Kingdom. olga.fourkioti@icr.ac.uk.
  • Reed Naidoo
    The Institute of Cancer Research, London, United Kingdom.
  • Hugh Sparks
    Photonics Group, Department of Physics, Imperial College London, London, United Kingdom.
  • Adam Tyson
    Gatsby Computational Neuroscience Unit, University College London, London, UK.
  • Chris Dunsby
    Department of Physics, Imperial College, London, UK.
  • Chris Bakal
    Institute of Cancer Research, Chester Beatty Laboratories, London, UK.