Geometric deep learning and multiple-instance learning for 3D cell-shape profiling.
Loading...
Embargo End Date
ICR Authors
Authors
De Vries, M
Dent, LG
Curry, N
Rowe-Brown, L
Bousgouni, V
Fourkioti, O
Naidoo, R
Sparks, H
Tyson, A
Dunsby, C
Bakal, C
Dent, LG
Curry, N
Rowe-Brown, L
Bousgouni, V
Fourkioti, O
Naidoo, R
Sparks, H
Tyson, A
Dunsby, C
Bakal, C
Document Type
Journal Article
Date
2025-03-19
Date Accepted
2025-02-13
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.
Citation
Cell Systems, 2025, 16 (3), pp. 101229 -
Source Title
Cell Systems
Publisher
CELL PRESS
ISSN
2405-4712
eISSN
2405-4720
Collections
Research Team
Dynamical Cell Systems