Single-cell Subcellular Protein Localisation Using Novel Ensembles of Diverse Deep Architectures

TL;DR

This paper introduces HCPL, a novel deep learning ensemble method that accurately localizes subcellular proteins in single cells, leveraging weakly labeled data and innovative architectures for improved performance and biological insight.

Contribution

The paper presents HCPL, a new ensemble deep learning framework with wavelet-based architectures and an AI-trains-AI approach for large-scale, weakly labeled data annotation in protein localization.

Findings

HCPL achieves state-of-the-art accuracy in protein localization classification.

Ensembling and wavelet architectures improve robustness and generalization.

Analysis reveals biologically relevant features learned by HCPL.

Abstract

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.