The Tumor Microbiome as a Predictor of Outcomes in Patients with Metastatic Melanoma Treated with Immune Checkpoint Inhibitors

Abstract

Emerging evidence supports the important role of the tumor microbiome in oncogenesis, cancer immune phenotype, cancer progression, and treatment outcomes in many malignancies. In this study, we investigated the metastatic melanoma tumor microbiome and its potential roles in association with clinical outcomes, such as survival, in patients with metastatic disease treated with immune checkpoint inhibitors (ICI). Baseline tumor samples were collected from 71 patients with metastatic melanoma before treatment with ICIs. Bulk RNA sequencing (RNA-seq) was conducted on the formalin-fixed, paraffin-embedded and fresh frozen tumor samples. Durable clinical benefit (primary clinical endpoint) following ICIs was defined as overall survival >24 months and no change to the primary drug regimen (responders). We processed RNA-seq reads to carefully identify exogenous sequences using the {exotic} tool. The age of the 71 patients with metastatic melanoma ranged from 24 to 83 years, 59% were male, and 55% survived >24 months following the initiation of ICI treatment. Exogenous taxa were identified in the tumor RNA-seq, including bacteria, fungi, and viruses. We found differences in gene expression and microbe abundances in immunotherapy-responsive versus nonresponsive tumors. Responders showed significant enrichment of bacteriophages in the phylum Uroviricota, and nonresponders showed enrichment of several bacteria, including Campylobacter jejuni. These microbes correlated with immune-related gene expression signatures. Finally, we found that models for predicting prolonged survival with immunotherapy using both microbe abundances and gene expression outperformed models using either dataset alone. Our findings warrant further investigation and potentially support therapeutic strategies to modify the tumor microbiome in order to improve treatment outcomes with ICIs.

Significance: We analyzed the tumor microbiome and interactions with genes and pathways in metastatic melanoma treated with immunotherapy and identified several microbes associated with immunotherapy response and immune-related gene expression signatures. Machine learning models that combined microbe abundances and gene expression outperformed models using either dataset alone in predicting immunotherapy responses.

Figure 1

Graphical summary. RNA-seq data from tumor specimens are processed to microbe abundances and human gene expression. Each is associated with ICI response, and then integrative analyses combine them into a model to predict outcomes.

Figure 2

Immune-related gene expression associates with the response to ICIs. A, Gene expression differences between the tumors responsive (right) and nonresponsive (left) to ICI treatment. Significantly different genes after FDR correction are colored and labeled. B and C, GSEA comparing responders vs. the nonresponders using the Hallmark gene set and TIMEx cell types. FDR < 0.1 was used as the cutoff. D, Mann–Whitney comparison of responders and nonresponders for signatures reaching the 0.05 FDR threshold.

Figure 3

Melanoma tumors that respond to ICIs have a distinct tumor microbiome. A, The relative abundances of the tumor microbiome at the phylum level showed wide intersample variation in the abundances of Proteobacteria (blue) and viruses [Uroviricota (maroon)], without gross differences between nonresponders (NR) and responders (R). B, Differential abundance analysis of taxa found within tumor RNA-seq data. Colored points represent significantly (P value <0.05) enriched taxa with a high (>1.00) fold difference in abundance between responders and nonresponders to ICIs. C, The diversity of the tumor microbiome between responders and nonresponders shows no significant differences. D, The diversity of the microbiome is a poor predictor of outcomes.

Figure 4

Association of microbes and gene signatures. Effect size plot showing the top nine most significantly enriched species. Spearman correlation coefficients between the significantly enriched species, the most significantly correlated signatures, and other gene sets shown in a heatmap.

Figure 5

Prediction of response using gene expression and microbes. Mann–Whitney comparisons of the mean AUROC values from random forest model comparisons.

Figure 6

Prediction of random forest model combining microbe abundance and gene signatures. Balanced accuracies achieved by the microbe abundance, gene expression, and combined models for each of the three datasets.