The increasing availability of patient-derived multimodal biological data for various diseases has opened up avenues for finding the optimal methods for jointly leveraging the information extracted in a customizable and scalable manner. Here, we propose the Proximogram, a graph-based representation that provides a joint construct for embedding independently obtained omics and spatial data. To evaluate the representation, we generated proximograms from 2 distinct biological sources, namely, multiplexed immunofluorescence images and single-cell RNA-seq data obtained from patients across two pancreatic diseases that include normal and chronic Pancreatitis (CP) and pancreatic ductal adenocarcinoma (PDAC). The generated proximograms were used as inputs to 2 distinct graph deep-learning models. The improved classification results over simpler spatial-data-based input graphs point to the increased discriminatory power obtained by integrating structural information from single-cell ligand-receptor signaling data and the spatial architecture of cells in each disease class, which can help point to markers of high diagnostic significance.
Keywords: Graph convolutional networks: GCN; Graph theory; Omics; Pancreatic cancer; Spatial analysis.
Copyright © 2024 The Authors. Published by Elsevier Ltd.. All rights reserved.