No Evidence for Distinct Transcriptomic Subgroups of Devil Facial Tumor Disease (DFTD)

Abstract

Contagious cancers represent one of the least understood types of infections in wildlife. Devil Facial Tumor Disease (comprised of two different contagious cancers, DFT1 and DFT2) has led to an 80% decline in the Tasmanian devil (Sarcophilus harrisii ) population at the regional level since it was first observed in 1996. There are currently no treatment options for the disease, and research efforts are focused on vaccine development. Although DFT1 is clonal, phylogenomic studies have identified different genetic variants of the pathogen. We postulated that different genetic strains may have different gene expression profiles and would therefore require different vaccine components. Here, we aimed to test this hypothesis by applying two types of unsupervised clustering (hierarchical and k-means) to 35 DFT1 transcriptomes selected from the disease's four major phylogenetic clades. The two algorithms produced conflicting results, and there was low support for either method individually. Validation metrics, such as the Gap statistic method, the Elbow method, and the Silhouette method, were ambiguous, contradictory, or indicated that our dataset only consisted of a single cluster. Collectively, our results show that the different phylogenetic clades of DFT1 all have similar gene expression profiles. Previous studies have suggested that transcriptomic differences exist between tumours from different locations. However, our study differs in that it considers both tumor purity and genotypic clade when analysing differences between DFTD biopsies. These results have important implications for therapeutic development, as they indicate that a single vaccine or treatment approach has the potential to be effective for a large cross-section of DFT1 tumors. As one of the largest studies to use transcriptomics to investigate phenotypic variation within a single contagious cancer, it also provides novel insight into this unique group of diseases.

Keywords: contagious cancer; unsupervised clustering; wildlife disease.

FIGURE 1

(A) MDS plot and (B) t‐SNE plot of distances between TMM normalized gene counts for each DFT1 sample. Neither method of dimension reduction indicated strong separation between the clusters. Clade A2 exhibited the tightest clustering of all groups, but this did not include all samples in A2. Samples are colored by genotypic clade.

FIGURE 2

Heatmaps displaying (A) 1000 most variable genes (B) 500 most variable genes (C) 250 most variable genes (D) 100 most variable genes. None showed a clear mosaic pattern that would be expected if distinct clusters were present in the dataset. Yellow represents a higher value (indicating genes are upregulated in that sample) and dark blue represents a lower value (indicating that genes are downregulated in that sample). The name of the clade is in square brackets after the sample name.

FIGURE 3

Clustering validation indices. The Gap statistic method indicated the optimum number of clusters was one for both (A) hierarchical clustering and (B) k‐means clustering; the Elbow method was ambiguous for both (C) hierarchical clustering and (D) k‐means clustering; and the Silhouette method indicated the optimum number of clusters was 10 (the maximum) for (E) hierarchical clustering and 4 for (F) k‐means clustering. The dotted line represents the highest value, that is, what the test deems to be the optimum number of clusters in the dataset.

FIGURE 4

K means clustering results with k = 4. Each cluster contained samples from at least two different genotypic clades.