Related Experiment Video
Updated: Jul 5, 2025
Highly Resolved Intravital Striped-illumination Microscopy of Germinal Centers
Published on: April 9, 2014
Spatial Morphoproteomic Features Predict Uniqueness of Immune Microarchitectures and Responses in Lymphoid Follicles
Thomas Hu1,2, Mayar Allam1, Vikram Kaushik1
1Wallace H. Coulter Department of Biomedical Engineering, Georgia Institute of Technology and Emory University, Atlanta, GA, USA.
Insights
SNOWFLAKE, a graph neural network pipeline, accurately predicts disease status from multiplex imaging data. It identifies disease-relevant cellular interactions in human B-cell follicles, outperforming other methods.
Area of Science:
- Computational biology
- Bioinformatics
- Machine learning in healthcare
Background:
- Multiplex imaging enables single-cell characterization within microenvironments.
- Understanding cellular organization and biomarkers is crucial for analyzing multiplex datasets.
Approach:
- Introduced SNOWFLAKE, a graph neural network framework for disease status prediction using multiplex cell expression and morphology.
- Applied SNOWFLAKE to COVID-19 human B-cell follicle data.
Key Points:
- SNOWFLAKE demonstrated superior predictive power compared to existing machine learning and deep learning methods.
- Morphological features were integrated into graph edge features for motif extraction.
- Attribution methods identified disease-relevant subgraphs and unique cellular interactions.
Conclusions:
- SNOWFLAKE effectively extracts low-dimensional embeddings from subgraphs, separating disease statuses.
- The pipeline generalizes for multiplex imaging data analysis by extracting disease-relevant subgraphs.
Abstract:
Multiplex imaging technologies allow the characterization of single cells in their cellular environments. Understanding the organization of single cells within their microenvironment and quantifying disease-status related biomarkers is essential for multiplex datasets. Here we proposed SNOWFLAKE, a graph neural network framework pipeline for the prediction of disease-status from combined multiplex cell expression and morphology in human B-cell follicles. We applied SNOWFLAKE to a multiplex dataset related to COVID-19 infection in humans and showed better predictive power of the SNOWFLAKE pipeline compared to other machine learning and deep learning methods. Moreover, we combined morphological features inside graph edge features to utilize attribution methods for extracting disease-relevant motifs from single-cell spatial graphs. The underlying subgraphs were further analyzed and associated with disease status across the dataset. We showed that SNOWFLAKE successfully extracted significant low dimensional embedding from subgraphs with a clear separation between disease status and helped characterize unique cellular interactions in the subgraphs. SNOWFLAKE is a generalizable pipeline for the analysis of multiplex imaging data modality by extracting disease-relevant subgraphs guided by graph-level prediction.
