A Cancer-Specific Qualitative Method for Estimating the Proportion of Tumor-Infiltrating Immune Cells

Abstract

Tumor-infiltrating immune cells are important components in the tumor microenvironment (TME) and different types of these cells exert different effects on tumor development and progression; these effects depend upon the type of cancer involved. Several methods have been developed for estimating the proportion of immune cells using bulk transcriptome data. However, there is a distinct lack of methods that are capable of predicting the immune contexture in specific types of cancer. Furthermore, the existing methods are based on absolute gene expression and are susceptible to experimental batch effects, thus resulting in incomparability across different datasets. In this study, we considered two common neoplasms as examples (colorectal cancer [CRC] and melanoma) and introduced the Tumor-infiltrating Immune Cell Proportion Estimator (TICPE), a cancer-specific qualitative method for estimating the proportion of tumor-infiltrating immune cells. The TICPE was based on the relative expression orderings (REOs) of gene pairs within a sample and is notably insensitive to batch effects. Performance evaluation using public expression data with mRNA mixtures, single-cell RNA-Seq (scRNA-Seq) data, immunohistochemistry data, and simulated bulk RNA-seq samples, indicated that the TICPE can estimate the proportion of immune cells with levels of accuracy that are clearly superior to other methods. Furthermore, we showed that the TICPE could effectively detect prognostic signals in patients with tumors and changes in the fractions of immune cells during immunotherapy in melanoma. In conclusion, our work presented a unique novel method, TICPE, to estimate the proportion of immune cells in specific cancer types and explore the effect of the infiltration of immune cells on the efficacy of immunotherapy and the prognosis of cancer. The source code for TICPE is available at https://github.com/huitingxiao/TICPE.

Keywords: immunotherapy; prognosis; relative expression orderings; signature genes; tumor microenvironment.

Figure 1

The pipeline of the TICPE algorithm. (A) Summary of the data sources used in the study to develop the TICPE. (B) The pipeline of the TICPE algorithm. RankComp algorithm was used to identify robust signature genes compared with cancer cells for each type of immune cell from the known marker genes. The upregulated score was the reversal significance of all signature genes corresponding to the cell type. Using the simulated model for each cell type, we derived a transformation pipeline for the scores. For each queried sample, calculated upregulated scores and transformed them to estimated cell proportions using learned parameters.

Figure 2

Performance assessment of the TICPE in solid tumors. (A) Correlation of the TICPE predictions with the cell proportions for the populations introduced in the mixtures. (B) Comparison with single-cell RNA-Seq data from colon samples. (C) Correlation of the TICPE predictions with corresponding cell densities measured by immunohistochemistry from colon cancer primary tumors. (D) Correlation of the TICPE predictions versus known cell type fractions on 100 simulated bulk samples generated from scRNA-seq from colon samples. Correlations were based on Pearson correlation. Proportions of cells observed experimentally were given in Supplementary Table 2 .

Figure 3

Performance comparison with other methods. (A) Scatter plot organized by cell type showing the performance of different marker gene sets identified from four sources. Methods performance was quantified using Pearson’s correlation (R). Different colors represented marker genes collated from different methods and different datasets had corresponding shapes. (B, C) Performance of TICPE and other methods on CRC and melanoma validation cohorts, respectively. Here rows corresponded to methods and columns showed the Pearson correlation coefficient for the corresponding cell type in each dataset. (D) Correlation deviation of each method in both CRC and melanoma validation datasets.

Figure 4

The application of TICPE on prognostic analysis for melanoma. Survival high CD4+ T/CD8+ T/NK cells and low CD4+ T/CD8+ T/NK cells groups in melanoma patients, respectively. P values comparing two groups were calculated with the log-rank test.

Figure 5

The application of TICPE on immunotherapy for melanoma. (A) The significant proportion differences of CD8+ T cells (left)/NK cells (right) in different response groups at pre- and on-treatment (anti-PD1) time point. (B) Change of the estimated immune cell proportions between pre-treatment and on-treatment time point in paired responders.