scTenifoldNet: A Machine Learning Workflow for Constructing and Comparing Transcriptome-wide Gene Regulatory Networks from Single-Cell Data

Daniel Osorio; Yan Zhong; Guanxun Li; Jianhua Z Huang; James J Cai

doi:10.1016/j.patter.2020.100139

scTenifoldNet: A Machine Learning Workflow for Constructing and Comparing Transcriptome-wide Gene Regulatory Networks from Single-Cell Data

Patterns (N Y). 2020 Nov 5;1(9):100139. doi: 10.1016/j.patter.2020.100139. eCollection 2020 Dec 11.

Authors

Daniel Osorio¹, Yan Zhong², Guanxun Li², Jianhua Z Huang², James J Cai^{1

3

4}

Affiliations

¹ Department of Veterinary Integrative Biosciences, Texas A&M University, College Station, TX 77843, USA.
² Department of Statistics, Texas A&M University, College Station, TX 77843, USA.
³ Department of Electrical and Computer Engineering, Texas A&M University, College Station, TX 77843, USA.
⁴ Interdisciplinary Program of Genetics, Texas A&M University, College Station, TX 77843, USA.

Abstract

We present scTenifoldNet-a machine learning workflow built upon principal-component regression, low-rank tensor approximation, and manifold alignment-for constructing and comparing single-cell gene regulatory networks (scGRNs) using data from single-cell RNA sequencing. scTenifoldNet reveals regulatory changes in gene expression between samples by comparing the constructed scGRNs. With real data, scTenifoldNet identifies specific gene expression programs associated with different biological processes, providing critical insights into the underlying mechanism of regulatory networks governing cellular transcriptional activities.

Keywords: gene regulatory network; machine learning; manifold alignment; principal-component regression; scRNA-seq; scTenifoldNet; single-cell RNA sequencing; tensor decomposition.