Single-cell Subcellular Protein Localisation Using Novel Ensembles of Diverse Deep Architectures
This work addresses the challenge of understanding protein distributions in cells for biomedical research and treatment development, representing a strong specific gain in a domain-specific context.
The paper tackles the problem of single-cell subcellular protein localization by introducing the Hybrid subCellular Protein Localiser (HCPL), which uses novel deep neural network architectures and an 'AI-trains-AI' approach to achieve state-of-the-art performance in classifying protein patterns within individual cells.
Unravelling protein distributions within individual cells is key to understanding their function and state and indispensable to developing new treatments. Here we present the Hybrid subCellular Protein Localiser (HCPL), which learns from weakly labelled data to robustly localise single-cell subcellular protein patterns. It comprises innovative DNN architectures exploiting wavelet filters and learnt parametric activations that successfully tackle drastic cell variability. HCPL features correlation-based ensembling of novel architectures that boosts performance and aids generalisation. Large-scale data annotation is made feasible by our "AI-trains-AI" approach, which determines the visual integrity of cells and emphasises reliable labels for efficient training. In the Human Protein Atlas context, we demonstrate that HCPL defines state-of-the-art in the single-cell classification of protein localisation patterns. To better understand the inner workings of HCPL and assess its biological relevance, we analyse the contributions of each system component and dissect the emergent features from which the localisation predictions are derived.