Single Cell RNA-Seq and Machine Learning Reveal Novel Subpopulations in Low-Grade Inflammatory Monocytes With Unique Regulatory Circuits.

Jiyoung Lee,Song Li,Shuo Geng,Liwu Li

doi:10.3389/fimmu.2021.627036

Abstract

Subclinical doses of LPS (SD-LPS) are known to cause low-grade inflammatory activation of monocytes, which could lead to inflammatory diseases including atherosclerosis and metabolic syndrome. Sodium 4-phenylbutyrate is a potential therapeutic compound which can reduce the inflammation caused by SD-LPS. To understand the gene regulatory networks of these processes, we have generated scRNA-seq data from mouse monocytes treated with these compounds and identified 11 novel cell clusters. We have developed a machine learning method to integrate scRNA-seq, ATAC-seq, and binding motifs to characterize gene regulatory networks underlying these cell clusters. Using guided regularized random forest and feature selection, our method achieved high performance and outperformed a traditional enrichment-based method in selecting candidate regulatory genes. Our method is particularly efficient in selecting a few candidate genes to explain observed expression pattern. In particular, among 531 candidate TFs, our method achieves an auROC of 0.961 with only 10 motifs. Finally, we found two novel subpopulations of monocyte cells in response to SD-LPS and we confirmed our analysis using independent flow cytometry experiments. Our results suggest that our new machine learning method can select candidate regulatory genes as potential targets for developing new therapeutics against low grade inflammation.

Highlights

The innate immune system acts as the first and immediate line of defense targeting broad pathogens through leukocytes such as neutrophils and monocytes
Our single cell analysis revealed two distinct populations of activated monocytes (C4 and C5) when persistently challenged with subclinical super-low dose LPS, which we named as ML1 and ML2
Consistent with the previous studies with the conventional approaches, we confirmed that the persistent challenge with SLD-LPS preferentially induced the low-grade activation of monocytes as reflected in the increased transcription factor signatures of IRF1, 5, and 7 [6, 32, 60, 61] in the LPS responsive clusters of C4 and C5

Summary

Introduction

The innate immune system acts as the first and immediate line of defense targeting broad pathogens through leukocytes such as neutrophils and monocytes. Lipopolysaccharide (LPS), known as bacterial endotoxin, is a key danger-signal causing various inflammatory responses from the host [1, 2]. A higher dose LPS often accompanying with acute bacterial infection can trigger a robust yet transient inflammatory response, coordinating pathogen removal, and tissue homeostasis [3]. Subclinical doses of LPS commonly associated with chronic inflammation and mucosal leakage can cause low-grade and chronic inflammation [1,2,3,4]. The mechanism of innate immune responses under chronic and low-grade inflammation is poorly understood

Objectives

Methods

Results

Conclusion