Profiling Tumor Infiltrating Immune Cells with CIBERSORT

Abstract

Tumor infiltrating leukocytes (TILs) are an integral component of the tumor microenvironment and have been found to correlate with prognosis and response to therapy. Methods to enumerate immune subsets such as immunohistochemistry or flow cytometry suffer from limitations in phenotypic markers and can be challenging to practically implement and standardize. An alternative approach is to acquire aggregative high dimensional data from cellular mixtures and to subsequently infer the cellular components computationally. We recently described CIBERSORT, a versatile computational method for quantifying cell fractions from bulk tissue gene expression profiles (GEPs). Combining support vector regression with prior knowledge of expression profiles from purified leukocyte subsets, CIBERSORT can accurately estimate the immune composition of a tumor biopsy. In this chapter, we provide a primer on the CIBERSORT method and illustrate its use for characterizing TILs in tumor samples profiled by microarray or RNA-Seq.

Keywords: Cancer immunology; Deconvolution; Gene expression; Microarray; RNA-Seq; Support vector regression (SVR); TCGA; Tumor heterogeneity; Tumor infiltrating leukocytes (TILs); Tumor microenvironment.

Figure 1

Overview of CIBERSORT. As input, CIBERSORT requires a “signature matrix” comprised of barcode genes that are enriched in each cell type of interest. Once a suitable knowledgebase is created and validated, CIBERSORT can be applied to characterize cell type proportions in bulk tissue expression profiles. Although originally validated using a signature matrix containing 22 functionally defined human immune subsets (LM22) profiled by microarrays, CIBERSORT is a general framework that can be applied to diverse cell phenotypes and genomic data types, including RNA-Seq. To quantitatively capture deconvolution confidence, CIBERSORT calculates several quality control metrics, including a deconvolution p-value.

Figure 2

CIBERSORT web interface. All files except the LM22 gene signature need to be uploaded to the CIBERSORT website before proceeding to this page. When using LM22, the user will need to select their uploaded mixture file and specify “LM22 (22 immune cell types)” for the signature gene file. When creating custom gene signatures, a reference sample file and a phenotype classes file are required, and need to be uploaded to the webserver. For CIBERSORT to generate a meaningful p-value, we recommend at least 100 permutations, however this parameter can be significantly lower (or even set to 1) for exploratory analyses.

Figure 3

Inferred composition of 22 immune cell subsets in malignant and healthy prostate biopsies (related to section 3.2). The results were generated using CIBERSORT and the built-in LM22 immune cell gene signature, and the stacked bar plot figure was automatically generated by the CIBERSORT webserver.

Figure 4

Estimated proportions of six major leukocyte subsets (B cells, CD8 T cells, CD4 T cells, NK cells, monocytes/macrophages, neutrophils) in skin cutaneous melanoma tumor biopsies profiled by The Cancer Genome Atlas (TCGA). The results were determined using a custom RNA-Seq leukocyte signature matrix (‘LM6’, section 3.3.3), and the heat map figure was generated by the CIBERSORT webserver.

Figure 5

Association between inferred tumor-infiltrating CD8 T cell content and overall survival in patients with skin cutaneous melanoma profiled by TCGA (related to section 4). Estimated CD8 T cell levels were stratified by a median split, and the separation between survival curves was evaluated using a log-rank test. Only patients with available survival data and with a significant CIBERSORT p-value (<0.05) were considered for this analysis (n = 364). HR, hazard ratio. 95% confidence intervals for the hazard ratio are shown in brackets.