bioRxiv (Cold Spring Harbor Laboratory) · 2024 · 19 citations · 21 references
Life SciencesBioinformaticsCell BiologyComputer VisionProteomicsSingle-cell Systems BiologyDeep LearningFluorescence MicroscopyFunctional ProteomicsProtein Complex AnalysisProteomics Data IntegrationSingle-cell ProteomicsMultimodal Self-supervised LearningProtein FluorescenceProtein Localization ProfilingSelf-supervised Protein Representation LearningSubcellular Organization ModelingSubcellular Protein DistributionSubcellular Protein LocalizationSubcellular Proteome Mapping
Cell morphology and subcellular protein organization provide important insights into cellular function and behavior. These features of cells can be studied using large-scale protein fluorescence microscopy, and machine learning has become a powerful tool to interpret the resulting images for biological insights. Here, we introduce SubCell, a suite of self-supervised deep learning models for fluorescence microscopy designed to accurately capture cellular morphology, protein localization, cellular organization, and biological function beyond what humans can readily perceive. These models were trained on the proteome-wide image collection from the Human Protein Atlas with a novel proteome-aware learning objective. SubCell outperforms state-of-the-art methods across a variety of tasks relevant to single-cell biology and generalizes to other fluorescence microscopy datasets without any fine-tuning. Additionally, we construct the first proteome-wide hierarchical map of proteome organization that is directly learned from image data. This vision-based multiscale cell map defines cellular subsystems with high resolution of protein complexes, reveals proteins with similar functions, and distinguishes dynamic and stable behaviors within cellular compartments. Finally, Subcell enables a rich multimodal protein representation when integrated with a protein sequence model, allowing for a more comprehensive capture of gene function than either vision-only or sequence-only models alone. In conclusion, SubCell creates deep, image-driven representations of cellular architecture that are applicable across diverse biological contexts and datasets.
21
A Simple Framework for Contrastive Learning of Visual Representations
Ting Chen, Simon Kornblith, Mohammad Norouzi et al. · arXiv (Cornell University) · 2020 · 7.3K citations · Full text
A subcellular map of the human proteome
Peter Thul, Lovisa Åkesson, Mikaela Wiking et al. · Science · 2017 · 3K citations
A new multipoint method for genome-wide association studies by imputation of genotypes
Jonathan Marchini, Bryan Howie, Simon Myers et al. · Nature Genetics · 2007 · 2.7K citations
CellProfiler 3.0: Next-generation image processing for biology
Claire McQuin, Allen Goodman, Vasiliy S. Chernyshev et al. · PLoS Biology · 2018 · 2.1K citations · Full text