ImmuCellAI: A Unique Method for Comprehensive T-Cell Subsets Abundance Prediction and its Application in Cancer Immunotherapy.

Ya‐Ru Miao,An‐Yuan Guo,Qian Lei,Qiong Zhang,Gui‐Yan Xie,Hongxiang Wang,Mei Luo

doi:10.1002/advs.201902880

Abstract

The distribution and abundance of immune cells, particularly T‐cell subsets, play pivotal roles in cancer immunology and therapy. T cells have many subsets with specific function and current methods are limited in estimating them, thus, a method for predicting comprehensive T‐cell subsets is urgently needed in cancer immunology research. Here, Immune Cell Abundance Identifier (ImmuCellAI), a gene set signature‐based method, is introduced for precisely estimating the abundance of 24 immune cell types including 18 T‐cell subsets, from gene expression data. Performance evaluation on both the sequencing data with flow cytometry results and public expression data indicate that ImmuCellAI can estimate the abundance of immune cells with superior accuracy to other methods especially on many T‐cell subsets. Application of ImmuCellAI to immunotherapy datasets reveals that the abundance of dendritic cells, cytotoxic T, and gamma delta T cells is significantly higher both in comparisons of on‐treatment versus pre‐treatment and responders versus non‐responders. Meanwhile, an ImmuCellAI result‐based model is built for predicting the immunotherapy response with high accuracy (area under curve 0.80–0.91). These results demonstrate the powerful and unique function of ImmuCellAI in tumor immune infiltration estimation and immunotherapy response prediction.

Highlights

The immune system, comprising various proteins, immune cells, and tissues, is complex and important for host defense[1]
Algorithmic overview of the ImmuCellAI method ImmuCellAI was designed to estimate the abundance of 18 T-cell subsets [CD4+, CD8+, CD4+ naïve, CD8+ naïve, central memory T (Tcm), effector memory T (Tem), Tr1, iTreg, nTreg, Th1, Th2, Th17, Tfh, T cells (Tc), mucosal-associated invariant T cells (MAIT), Tex, gamma delta T, and natural killer T (NKT) cells] and six other important immune cells [B cells, macrophages, monocytes, neutrophils, dendritic cells (DC), and NK cells] (Figure 1A)
A brief illustration of the core algorithm of ImmuCellAI is represented in Figure 1B, and its detailed algorithm is described in the Online Methods section

Summary

Introduction

The immune system, comprising various proteins, immune cells, and tissues, is complex and important for host defense[1]. Dysfunctions of immune cells such as abnormal distributions with respect to abundance and type as well as abnormal development and functions are always associated with diseases, including cancers[2,3]. Investigating immune cell distribution in individuals could provide important insights into immune status, disease progression and prognosis, and therapy ( in cancer immunotherapy)[4]. Several methods, including xCell[11], CIBERSORT[12], EPIC[13], TIMER[14], and MCP-counter[15], have been developed for enumerating immune cells from bulk transcriptome data of tumor samples, whereas rare method has been designed for estimating the abundance of numerous T-cell subsets, such as iTreg, Tc, and exhausted T cells (Tex). We developed Immune Cell Abundance Identifier (ImmuCellAI), a method to robustly and precisely estimate the abundance of 24 immune cell types (including 18 T-cell subsets) from transcriptome data. Pan-cancer data to explore the influence of immune cells on the efficacy of immunotherapy and clinical progression of patients with cancer

Results

Performance of ImmuCellAI in RNA-Seq and microarray datasets

Materials and Methods

Compensation matrix correction

Other public datasets

Case study of immune therapy and prediction model building