Single-cell analysis reveals new evolutionary complexity in uveal melanoma

Abstract

Uveal melanoma (UM) is a highly metastatic cancer that, in contrast to cutaneous melanoma, is largely unresponsive to checkpoint immunotherapy. Here, we interrogate the tumor microenvironment at single-cell resolution using scRNA-seq of 59,915 tumor and non-neoplastic cells from 8 primary and 3 metastatic samples. Tumor cells reveal novel subclonal genomic complexity and transcriptional states. Tumor-infiltrating immune cells comprise a previously unrecognized diversity of cell types, including CD8⁺ T cells predominantly expressing the checkpoint marker LAG3, rather than PD1 or CTLA4. V(D)J analysis shows clonally expanded T cells, indicating that they are capable of mounting an immune response. An indolent liver metastasis from a class 1B UM is infiltrated with clonally expanded plasma cells, indicative of antibody-mediated immunity. This complex ecosystem of tumor and immune cells provides new insights into UM biology, and LAG3 is identified as a potential candidate for immune checkpoint blockade in patients with high risk UM.

Fig. 1. Aggregate analysis of 59,915 single cells from eight primary and three metastatic uveal melanomas.

a Summary of study design. b t-SNE plot of 59,915 single cells distributed by annotated unsupervised clustering. c t-SNE plot of 59,915 single cells highlighted by gene expression profile (GEP) class. d Pie charts of each of the eight primary and three metastatic tumors showing percentages of annotated cell types.

Fig. 2. Single cell copy-number variation analysis of primary and metastatic uveal melanomas.

a Representative CNV heatmaps with hierarchical clustering from inferCNV analysis from each GEP class. b Summary plot of the CNV profiles from each of the 11 patients inferred from their scRNA-seq data. CNVs were annotated by the chromosome arm in which the CNV event calculated by inferCNV occurred. Canonical CNV events in UM are shown at the top as annotated (red, class 2; blue, class 1; green, class 1 and 2). Source data are provided as a Source Data file. c Clonality trees of each of the 11 patients separated by GEP class. The branches are scaled according to percentage of cells in the calculated subclone containing the corresponding CNVs. *indicates mutations that were found to occur in a subclone by bulk DNA sequencing and thus could not be assigned to a specific branch of the tree.

Fig. 3. Trajectory analysis of uveal melanoma cells.

a Enriched transcription factor motifs determined using SCENIC analysis of 8,598 tumor cells and displayed as a heatmap of z-scored enrichment values. b Monocle 2 trajectory analysis of 7,947 uveal melanoma cells obtained by 5′ gene expression chemistry annotated by calculated states. c Trajectory analysis annotated by sample and overlaid with color by GEP class. d Combined Monocle 2 trajectory analysis displayed by each sample and annotated by calculated state. e Chart depicting pathways found to be significant by MSigDB analysis of each sample cluster determined by BEAM analysis followed by hierarchical clustering.

Fig. 4. Immune microenvironment of uveal melanomas with V(D)J recombination repertoire sequencing of B- and T- lymphocytes.

a t-SNE plot of 9441 single immune cells present in the TME. b Heatmap of averaged RNA expression of immune cell clusters. c Three-dimensional bar chart of immune cell subtypes as a percentage of immune cell population for each tumor. d Single-cell V(D)J recombination repertoire sequencing of T cells from 10 primary and metastatic UMs and B cells from an indolent class 1B metastasis. Red, clonotypes ≥4% T cell frequency; purple, clonotypes <4% and ≥2.5% T cell frequency; blue, clonotypes <2.5% and ≥1.5% T cell frequency; gray, all remaining clonotypes <1.5% T cell frequency. Source data are provided as a Source Data file. e Ridge plot of CD8⁺ T cell subset demonstrating strong expression of LAG3, moderate expression of TIGIT, and minimal expression of PD1, CTLA4, TIM3, and TNFRSF9. f Quantification of multi-color IHC for CD8, LAG3, PD1, CTLA4, and DAPI. 18 total samples were analyzed by IHC including 7 that were analyzed by scRNA-seq and an additional 11 samples. Metastatic samples include BSSR0022 and UMM067L. Other samples represent primary tumors. Quantitation of each sample was performed by whole-slide scanning of a single slide. Source data are provided as a Source Data file. g Representative multi-color IHC images of a primary and a metastatic class 2 UM stained for CD8, LAG3, PD1, CTLA4, and DAPI (scale bar, 50 μm).