Detecting spatially co-expressed gene clusters with functional coherence by graph-regularized convolutional neural network

Abstract

Motivation Clustering spatial-resolved gene expressions is an essential analysis to reveal gene activities in the underlying morphological context by their functional roles. However, conventional clustering analysis does not consider gene expression co-localizations in tissue for detecting spatial expression patterns or functional relationships among the genes for biological interpretation in the spatial context. In this paper, we present a Convolutional Neural Network (CNN) regularized by the graph of Protein-Protein Interaction (PPI) network to cluster spatially-resolved gene expressions. This method improves the coherence of spatial patterns and provides biological interpretation of the gene clusters in the spatial context by exploiting the spatial localization by convolution and gene functional relationships by graph-Laplacian regularization. Results In the experiments, we tested clustering the spatially variable genes or all expressed genes in the transcriptome in 22 Visium spatial transcriptomics datasets of different tissue sections publicly available from 10x Genomics and spatialLIBD. The results demonstrate that the PPI-regularized CNN constantly detects gene clusters with coherent spatial patterns and significantly enriched by gene functions with the-state-of-the-art performance. Additional case studies on mouse kidney tissue and human breast cancer tissue suggest that the PPI-regularized CNN also detects spatially co-expressed genes to define the corresponding morphological context in the tissue with valuable insights. Availability Source code is available at https://github.com/kuanglab/CNN-PReg.

Learning context-aware, distributed gene representations in spatial transcriptomics with SpaCEX

“…To systematically evaluate this ability, we utilize twelve human dorsolateral prefrontal cortex (DLPFC) 10x Visium datasets (10x-hDLPFC) (16) and a mouse hippocampus Slide-seqV2 dataset (ssq-mHippo) (17), as listed in SI Appendix , Table S1. We benchmark SpaCEX against four state-of-the-art competing methods: CNN-PReg (18), Giotto (19), Spark (20) and STUtility (21) ( SI Appendix , Table S2). Our initial assessment involves visualizing spatial expression maps of four randomly selected genes from each of two SpaCEX-identified clusters, chosen to represent high and medium quality clusters, respectively (see “Identifying groups of spatially co-expressed genes” in Methods).…”

“…S1. We benchmark SpaCEX against four state-of-the-art competing methods: CNN-PReg (18), Giotto (19), Spark (20) and STUtility (21) (SI Appendix, Table S2). Our initial assessment involves visualizing spatial expression maps of four randomly selected genes from each of two SpaCEX-identified clusters, chosen to represent high and medium quality clusters, respectively (see "Identifying groups of spatially co-expressed genes" in Methods).…”

Recent Advances in Deep Learning for Protein-Protein Interaction Analysis: A Comprehensive Review

“…This model outperformed existing models on a benchmark dataset and accurately predicted PPIs for unknown viruses. Song et al [ 60 ] proposed a method for clustering spatially resolved gene expression data using a graph-regularized convolutional neural network. This method leverages the graph of a PPI network, improving the coherence of spatial patterns and providing biological interpretation of the gene clusters in the spatial context.…”