MCNET: Multi-Omics Integration for Gene Regulatory Network Inference from scRNA-seq

Abstract

Deep learning has emerged as a powerful approach in var- ious domains, including biological network analysis. This paper investigates the advancements in computational tech- niques for inferring gene regulatory networks (GRNs) and in- troduces MCNET, a state-of-the-art deep learning algorithm. MCNET integrates multi-omics data to infer GRNs and ex- tract biologically significant representations from single-cell RNA sequencing (scRNA-seq) data. By incorporating atten- tion mechanisms and graph convolutional networks, MCNET captures intricate regulatory relationships among genes. Ex- tensive benchmarking on diverse scRNA-seq datasets demon- strates MCNETs superiority over existing methods in GRN inference, scRNA-seq data visualization, clustering, and sim- ulation. Notably, MCNET accurately predicts gene regula- tions on cell-type marker genes in the mouse cortex, validated by epigenetic data. The introduction of MCNET paves the way for advanced analysis of scRNA-seq data and provides a powerful tool for inferring GRNs in a multi-omics con- text. Moreover, this paper addresses the integration of multi- omics data in gene regulatory network inference, proposing MCNET as a method that efficiently analyzes and visualizes homogeneous gene regulatory networks derived from diverse omics data. The inference capability of MCNET is evalu- ated through extensive experiments with simulation data and applied to analyze the biological network of psychiatric dis- orders using human brain data.