Comprehensive Characterization of Human Lung Large Cell Carcinoma Identifies Transcriptomic Signatures with Potential Implications in Response to Immunotherapy

Abstract

Lung cancer is the leading cause of cancer mortality worldwide, with non-small cell lung cancer (NSCLC) being the most prevalent histology. While immunotherapy with checkpoint inhibitors has shown outstanding results in NSCLC, the precise identification of responders remains a major challenge. Most studies attempting to overcome this handicap have focused on adenocarcinomas or squamous cell carcinomas. Among NSCLC subtypes, the molecular and immune characteristics of lung large cell carcinoma (LCC), which represents 10% of NSCLC cases, are not well defined. We hypothesized that specific molecular aberrations may impact the immune microenvironment in LCC and, consequently, the response to immunotherapy. To that end, it is particularly relevant to thoroughly describe the molecular genotype-immunophenotype association in LCC-to identify robust predictive biomarkers and improve potential benefits from immunotherapy. We established a cohort of 18 early-stage, clinically annotated, LCC cases. Their molecular and immune features were comprehensively characterized by genomic and immune-targeted sequencing panels along with immunohistochemistry of immune cell populations. Unbiased clustering defined two novel subgroups of LCC. Pro-immunogenic tumors accumulated certain molecular alterations, showed higher immune infiltration and upregulated genes involved in potentiating immune responses when compared to pro-tumorigenic samples, which favored tumoral progression. This classification identified a set of biomarkers that could potentially predict response to immunotherapy. These results could improve patient selection and expand potential benefits from immunotherapy.

Keywords: checkpoint inhibitors; immunotherapy; lung large cell carcinoma; multiparametric analysis; non-small cell lung cancer; predictive biomarkers.

Figure 1

Experimental design of the study. Samples from resected early-stage large cell carcinoma (LCC) of a clinically annotated cohort of 18 patients were subjected to molecular and immune profiling and integrative bioinformatics to find associations permitting patient subgroup classification according to potential responses to immunotherapy.

Figure 2

Characterization of tumor immune infiltrate and PD-L1 expression. (A) Representative images of the expression of immune markers for CD20, CD4, CD68 and CD8 by immunohistochemistry in LCC tumors. Score 0: <1%, negative; Score 1: 1–10%, low expression; Score 2: >10%, high expression. Scale bar = 2 µm. No sample had a Score of 0 for CD68; (B) Representative images of the expression of PD-L1 by immunohistochemistry in LCC tumors. Staining ≥1% was considered to represent positivity. Scale bar = 2 µm.

Figure 3

Definition of novel subgroups of Large Cell Carcinoma (LCC) tumors based on molecular and immune profiles. Large Cell Carcinomas (N = 18). (A) Heatmap of expression of genes involved in tumor–immune system communication. Groups of tumors are shown in the horizontal axis and clusters of genes in the vertical axis as defined by consensus clustering. Molecular, immune and clinical annotations are shown above the heatmap (see legend). For gene annotations, molecular alterations are represented as colored sections. The heatmap scale is expressed in percentiles; (B) Over-Representation Analysis (ORA) bringing together onco-immune functions. Each colored sector represents a functional category whose size illustrates over- or under-representation of genes in that cluster within a specific function. Over-represented functions allow patient groups to be classified as pro-tumorigenic or pro-immunogenic according to their tumor immunogenicity. The over or under-representation of each functional category was statistically evaluated with a Fisher’s exact test. * (p < 0.05), ** (p < 0.01), *** (p < 0.001); (C) Immune cell population distribution in the pro-immunogenic and pro-tumorigenic LCC subgroups.

Figure 4

Analysis of differential gene expression. Pro-immunogenic vs. Pro-tumorigenic subgroups. (A) Volcano plot of differentially expressed genes between the pro-immunogenic group and the pro-tumorigenic group of LCC tumors. A false discovery rate (FDR) ≤ 0.05 and log₂ Fold Change ≥ |1| were required to reach statistical significance; (B) Selection of the most upregulated genes in the pro-immunogenic tumors; (C) Selection of the most upregulated genes in the pro-tumorigenic tumors; (D) Selection of the most statistically significant upregulated genes in the pro-immunogenic tumors; (E) Selection of the most statistically significant upregulated genes in the pro-tumorigenic tumors.

Figure 5

Survival analysis of the defined LCC subgroups and selection of candidate predictive biomarkers for response to immunotherapy. Kaplan–Meier analysis of progression free survival (PFS) (A); and overall survival (OS) (B) between pro-immunogenic (red) and pro-tumorigenic (blue) tumors. OS and PFS data could not be retrieved from all 18 LCC patients. Statistical analyses were performed with a log-rank (Mantel–Cox) test for which a p-value below 0.05 was considered significant; (C) Selected candidate predictive biomarkers of response to immunotherapy characteristic of pro-immunogenic LCC tumors. FDR = False Discovery Rate; (D) Selected candidate predictive biomarkers of response to immunotherapy characteristic of pro-tumorigenic LCC tumors; (E) Heatmap of expression of the selected biomarkers, grouped by clusters, in pro-tumorigenic tumors (left) and pro-immunogenic tumors (right).