Related Experiment Video
Updated: Jul 6, 2025
Rapid and Robust Analysis of Cellular and Molecular Polarization Induced by Chemokine Signaling
Published on: December 12, 2014
PEPSI: Polarity measurements from spatial proteomics imaging suggest immune cell engagement
Eric Wu1, Zhenqin Wu, Aaron T Mayer
1Department of Electrical Engineering, Stanford University, Stanford, CA, USA2Enable Medicine, Inc., Menlo Park, CA, USA, wue@stanford.edu.
Insights
We developed a new metric to analyze cell protein patterns from imaging data, identifying distinct immune cell states in tumors. This approach enhances the prediction of patient survival outcomes using deep learning models.
Area of Science:
- Cell biology
- Immunology
- Computational pathology
Background:
- Subcellular protein localization is crucial for cell function but challenging to quantify.
- High-resolution microscopy is typically required for such measurements.
Purpose of the Study:
- To develop a novel metric for quantifying surface protein polarity from immunofluorescence imaging data.
- To identify distinct immune cell states within tumor microenvironments based on protein polarity.
- To assess the impact of polarity-defined cell subtypes on deep learning model performance for survival prediction.
Main Methods:
- Development of a quantitative metric for surface protein polarity using immunofluorescence (IF) imaging.
- Application of the metric to analyze over two million cells from 600 patient samples.
- Integration of polarity-defined cell subtypes into deep learning models for survival outcome prediction.
Main Results:
- Identification of distinct immune cell states characterized by polar protein expression within tumor microenvironments.
- Demonstration that polar expression correlates with tumor-immune cell engagement.
- Significant improvement in the performance of deep learning models for predicting patient survival when incorporating polarity-defined cell subtypes.
Conclusions:
- Subcellular protein expression patterns, specifically polarity, can effectively phenotype immune cell functional states.
- This method offers a novel approach for analyzing complex cellular phenotypes in cancer research.
- The findings have potential applications in precision medicine and improving prognostic models.
Abstract:
Subcellular protein localization is important for understanding functional states of cells, but measuring and quantifying this information can be difficult and typically requires high-resolution microscopy. In this work, we develop a metric to define surface protein polarity from immunofluorescence (IF) imaging data and use it to identify distinct immune cell states within tumor microenvironments. We apply this metric to characterize over two million cells across 600 patient samples and find that cells identified as having polar expression exhibit characteristics relating to tumor-immune cell engagement. Additionally, we show that incorporating these polarity-defined cell subtypes improves the performance of deep learning models trained to predict patient survival outcomes. This method provides a first look at using subcellular protein expression patterns to phenotype immune cell functional states with applications to precision medicine.
