A comprehensive analysis of breast cancer microbiota and host gene expression

Abstract

The inflammatory tumoral-immune response alters the physiology of the tumor microenvironment, which may attenuate genomic instability. In addition to inducing inflammatory immune responses, several pathogenic bacteria produce genotoxins. However the extent of microbial contribution to the tumor microenvironment biology remains unknown. We utilized The Cancer Genome Atlas, (TCGA) breast cancer data to perform a novel experiment utilizing unmapped and mapped RNA sequencing read evidence to minimize laboratory costs and effort. Our objective was to characterize the microbiota and associate the microbiota with the tumor expression profiles, for 668 breast tumor tissues and 72 non-cancerous adjacent tissues. The prominent presence of Proteobacteria was increased in the tumor tissues and conversely Actinobacteria abundance increase in non-cancerous adjacent tissues. Further, geneset enrichment suggests Listeria spp to be associated with the expression profiles of genes involved with epithelial to mesenchymal transitions. Moreover, evidence suggests H. influenza may reside in the surrounding stromal material and was significantly associated with the proliferative pathways: G2M checkpoint, E2F transcription factors, and mitotic spindle assembly. In summary, further unraveling this complicated interplay should enable us to better diagnose and treat breast cancer patients.

Fig 1. Two distinct microbiota are present in breast tissue samples, both tumor (n = 668) and NCA (n = 72).

(A) Optimal k-cluster selection analysis demonstrating a majority decision among the 26 metrics for 2 clusters was concordant for both tissue cohorts identifying a systemic handling bias. (B) The t-SNE projections for the 668 tumors samples, demonstrating tissues demonstrating separation and cohesion among the batches. (C) Filtering was re-applied among the tissue samples and per processing differences. Venn diagram demonstrates a core 327 bacterial OTU’s was observed among all samples. (D) Abundance differences were observed for 48 OTU’s. A PCA plot of these significant OTU’s is presented demonstrating that the batch differences had been accounted for, NCA tissues indicated with an ‘N’ and tumor samples indicated with a ‘T’.

Fig 2. Phylum compositions of the tumor and NCA tissues.

The most prevalent phylum in the breast microbiota is Proteobacteria, followed by Actinobacteria and Firmicutes. These observations were consistent among each of the tissue types (tumor shaded in purple NCA shaded in green). These distributions are consistent with the observations by Urbaniak, et al, see insert.

Fig 3. OTU’s significantly different among the breast cancer populations.

(A) Twenty-four species were observed to have average abundance between 0.5% - 19.3% among the NCA samples. These species are presented as a barplot summary averaged among each subtype. (B) A cladogram of the 48 differentially abundant species, 12 of the 24 prevelent species (average relative abundance greater than 0.5%) were observed to be signicant after Benjamini and Hochberg correction for mutiple testing error. (C) The average relative abundance and standard deviation of the 12 species differing in abundance depicted in the barplots, with the NCA tissue cohort’s averages in green and tumor cohort averages in purple.

Fig 4. Microbial association with breast cancer.

A) Fourteen hallmark pathways which were observed to significantly enriched with differentially expressed genes (in green), versus the universe set of 16,363 genes. Three organisms (H. influenza, N. Subflava, and L. fleischmanni) demonstrated correlation to a sufficient set of genes for geneset enrichment analysis: 229, 30, and 58, genes respectively. H. influenze shared enrichment in three of those pathways. Those three pathways (G2M checkpoint, E2F targets, and mitotic spindle), remain enriched, after applying Bonferroni correction (the vertical purple dashed line). L, Fleischmannii was also enriched in gene correlations among the epithelial mesenchymal transition pathway, after Bonferroni correction for multiple testing. B) To reduce any bias from differential expression selection the genes in the 50 hallmark pathways were additionally analyzed for mutual information content with the microbial compositional data. A hive plot depicting the network of the 50 pathways and their genes (green), known gene-gene (protein-protein) interactions (yellow), and OTU’s-gene associations (purple) is presented. The connectivity of the pathway and OTU’s nodes are presented with the text on the right. We again observe the same 3 networks demonstrated the most connectivity and that H. influenza as the predominant microbial association.