Self-supervised classification of subcellular morphometric phenotypes reveals extracellular matrix-specific morphological responses

Machine learning-based approach for automated classification of cell and extracellular matrix using nanomechanical properties

Fibrosis characterized by excess accumulation of extracellular matrix (ECM) due to complex cell-ECM interactions plays a pivotal role in pathogenesis. Herein, we employ the pancreatic ductal adenocarcinoma (PDAC) model to investigate dynamic alterations in nanomechanical attributes arising from the cell-ECM interactions to study the fibrosis paradigm. Several segregated studies performed on cellular and ECM components fail to recapitulate their complex collaboration. We utilized collagen and fibronectin, the two most abundant PDAC ECM components, and studied their nanomechanical attributes. We demonstrate alteration in morphology and nanomechanical attributes of collagen with varying thicknesses of collagen gel. Furthermore, by mixing collagen and fibronectin in various stoichiometry, their nanomechanical attributes were observed to vary. To demonstrate the dynamicity and complexity of cell-ECM, we utilized Panc-1 and AsPC-1 cells with or without collagen. We observed that Panc-1 and AsPC-1 cells interact differently with collagen and vice versa, evident from their alteration in nanomechanical properties. Further, using nanomechanics data, we demonstrate that ML-based techniques were able to classify between ECM as well as cell, and cell subtypes in the presence/absence of collagen with higher accuracy. This work demonstrates a promising avenue to explore other ECM components facilitating deeper insights into tumor microenvironment and fibrosis paradigm.

From pixels to phenotypes: Integrating image-based profiling with cell health data as BioMorph features improves interpretability

Cell Painting assays generate morphological profiles that are versatile descriptors of biological systems and have been used to predict in vitro and in vivo drug effects. However, Cell Painting features extracted from classical software such as CellProfiler are based on statistical calculations and often not readily biologically interpretable. In this study, we propose a new feature space, which we call BioMorph, that maps these Cell Painting features with readouts from comprehensive Cell Health assays. We validated that the resulting BioMorph space effectively connected compounds not only with the morphological features associated with their bioactivity but with deeper insights into phenotypic characteristics and cellular processes associated with the given bioactivity. The BioMorph space revealed the mechanism of action for individual compounds, including dual-acting compounds such as emetine, an inhibitor of both protein synthesis and DNA replication. Overall, BioMorph space offers a biologically relevant way to interpret the cell morphological features derived using software such as CellProfiler and to generate hypotheses for experimental validation.

Self-supervised deep learning for highly efficient spatial immunophenotyping

BACKGROUND

Efficient biomarker discovery and clinical translation depend on the fast and accurate analytical output from crucial technologies such as multiplex imaging. However, reliable cell classification often requires extensive annotations. Label-efficient strategies are urgently needed to reveal diverse cell distribution and spatial interactions in large-scale multiplex datasets.

METHODS

This study proposed Self-supervised Learning for Antigen Detection (SANDI) for accurate cell phenotyping while mitigating the annotation burden. The model first learns intrinsic pairwise similarities in unlabelled cell images, followed by a classification step to map learnt features to cell labels using a small set of annotated references. We acquired four multiplex immunohistochemistry datasets and one imaging mass cytometry dataset, comprising 2825 to 15,258 single-cell images to train and test the model.

FINDINGS

With 1% annotations (18-114 cells), SANDI achieved weighted F1-scores ranging from 0.82 to 0.98 across the five datasets, which was comparable to the fully supervised classifier trained on 1828-11,459 annotated cells (-0.002 to -0.053 of averaged weighted F1-score, Wilcoxon rank-sum test, P = 0.31). Leveraging the immune checkpoint markers stained in ovarian cancer slides, SANDI-based cell identification reveals spatial expulsion between PD1-expressing T helper cells and T regulatory cells, suggesting an interplay between PD1 expression and T regulatory cell-mediated immunosuppression.

INTERPRETATION

By striking a fine balance between minimal expert guidance and the power of deep learning to learn similarity within abundant data, SANDI presents new opportunities for efficient, large-scale learning for histology multiplex imaging data.

FUNDING

This study was funded by the Royal Marsden/ICR National Institute of Health Research Biomedical Research Centre.