Colorectal cancer mutational profiles correlate with defined microbial communities in the tumor microenvironment

Abstract

Variation in the gut microbiome has been linked to colorectal cancer (CRC), as well as to host genetic variation. However, we do not know whether, in addition to baseline host genetics, somatic mutational profiles in CRC tumors interact with the surrounding tumor microbiome, and if so, whether these changes can be used to understand microbe-host interactions with potential functional biological relevance. Here, we characterized the association between CRC microbial communities and tumor mutations using microbiome profiling and whole-exome sequencing in 44 pairs of tumors and matched normal tissues. We found statistically significant associations between loss-of-function mutations in tumor genes and shifts in the abundances of specific sets of bacterial taxa, suggestive of potential functional interaction. This correlation allows us to statistically predict interactions between loss-of-function tumor mutations in cancer-related genes and pathways, including MAPK and Wnt signaling, solely based on the composition of the microbiome. In conclusion, our study shows that CRC microbiomes are correlated with tumor mutational profiles, pointing towards possible mechanisms of molecular interaction.

Fig 1. Correlation between the microbial community at a tumor that differentiates between tumor stage.

(A) Low-stage (stages 1–2) and high-stage (stages 3–4) tumors can be differentiated using a risk index classifier generated from microbial abundance data (y-axis). The central black bar indicates the median, and the thin black bars represent the 25th and 75th percentiles. (B) A receiver operating characteristic (ROC) curve was generated using a 10-fold cross-validation (blue dotted lines). The average of the 10-fold cross-validation curves is represented as a thick black line. (C) Differences in the mean abundances of a subset of the taxa predicted to interact differentially with high-stage and low-stage tumors. This subset represents those taxa that had a mean difference in abundance of greater than 0.1%, proportionally.

Fig 2. Commonly mutated genes show a predicted interaction with changes in the abundances of several microbial taxa.

(A) A heatmap of the scaled abundances values (cells) for a subset of taxa chosen as they were identified as discriminatory in each leave-one-out iteration (columns) that were found significantly associated with prevalent LoF mutations (rows). Scaled abundances are from the patients with the indicated mutations. (B) LoF mutations in each of the indicated genes can be predicted using a risk index as a classifier (y-axis). The central black bar indicates the median, and the thin black bars represent the 25th and 75th percentiles. (C) ROC curves were generated for each of the indicated mutations using a 10-fold cross-validation (blue dotted lines). The average of the 10-fold cross-validation curves is represented as a thick black line. (D) Differences in the mean abundances of a subset of the taxa predicted to interact differentially with tumors with a LoF mutation relative to those without the indicated mutation. This subset represents those taxa that had a mean difference in abundance of greater than 0.1%, proportionally.

Fig 3. Pathways harboring prevalent LoF mutations correlate with changes in the abundances of sets of microbial taxa.

(A) A heatmap of the scaled abundances values (cells) for a subset of taxa (columns) that are found significantly associated with KEGG pathways harboring LoF mutations (rows). Scaled abundances are from the patients with mutations in the indicated pathways. (B) LoF mutations in each of the indicated pathways can be predicted using a risk index as a classifier (y-axis). The central black bar indicates the median, and the thin black bars represent the 2nd and 4th quartiles. (C) ROC curves were generated for each of the indicated pathways using a 10-fold cross-validation (blue dotted lines). The average of the 10-fold cross-validation curves is represented as a thick black line. (D) Differences in the mean abundances of a subset of the taxa predicted to interact differentially with tumors harboring mutations in the indicated pathways relative to those without a mutation. This subset represents those taxa that had a mean difference in abundance of greater than 0.1%, proportionally. (E—F) Identically structured visualizations as in (A—D), but for PID pathway data rather than the KEGG pathways.

Fig 4. Interaction networks among bacteria are defined by host tumor mutations.

(A) SparCC analysis of the microbial abundances of the taxa identified by LEfSe for tumors with LoF mutations in APC (left) and without mutation (right) produce distinct patterns of correlations (edges) between a common set of taxa (nodes). Direct correlations are indicated as red edges and inverse correlations as blue edges (SparCC R > = 0.25, P < = 0.05 for displayed edges). (B) SparCC analysis was run simultaneously for all taxa identified by LEfSe when predicting interactions with mutations in PID pathways. There are interactions (dashed edges) between the taxa (grey nodes) associated with mutations across sets of PID pathways (green nodes). The solid edges indicate SparCC R-values (red for direct and blue for inverse correlations). The grey taxon nodes are scaled to the average abundance of the taxa in the associated tumor set. Edge color indicates the direction of the interaction, red for negative and blue for positive. Note that while several of the pathways (green nodes) have closely related general functions (e.g. “Canonical Wnt signaling pathway” and “Degradation of beta-catenin”), the underlying gene sets that comprise these pathways are distinct and result in independent correlations with microbial taxa.