Meta-Analysis and Validation of a Colorectal Cancer Risk Prediction Model Using Deep Sequenced Fecal Metagenomes

Simple Summary Colorectal cancer (CRC) is the third most common cancer in the world. The gut microbiome, which includes a collection of microbes, is a potential modifiable risk factor. The study of the microbiome is complex and many issues remain unsolved despite the scientific efforts that have been recently made. The present study aimed to build a CRC predictive model performing a meta-analyses of previously published shotgun metagenomics data, and to validate it in a new study. For that purpose, 156 participants of a CRC screening program were recruited, with an even distribution of CRCs, high-risk colonic precancerous lesions, and a control group with normal colonic mucosa. We have identified a signature of 32 bacterial species that have a good predictive accuracy to identify CRC but not precancerous lesions. This suggests that the identified microbes that were enriched or depleted in CRC are merely a consequence of the tumor. The gut microbiome is a potential modifiable risk factor for colorectal cancer (CRC). We re-analyzed all eight previously published stool sequencing data and conducted an MWAS meta-analysis. We used cross-validated LASSO predictive models to identify a microbiome signature for predicting the risk of CRC and precancerous lesions. These models were validated in a new study, Colorectal Cancer Screening (COLSCREEN), including 156 participants that were recruited in a CRC screening context. The MWAS meta-analysis identified 95 bacterial species that were statistically significantly associated with CRC (FDR < 0.05). The LASSO CRC predictive model obtained an area under the receiver operating characteristic curve (aROC) of 0.81 (95%CI: 0.78-0.83) and the validation in the COLSCREEN dataset was 0.75 (95%CI: 0.66-0.84). This model selected a total of 32 species. The aROC of this CRC-trained model to predict precancerous lesions was 0.52 (95%CI: 0.41-0.63). We have identified a signature of 32 bacterial species that have a good predictive accuracy to identify CRC but not precancerous lesions, suggesting that the identified microbes that were enriched or depleted in CRC are merely a consequence of the tumor. Further studies should focus on CRC as well as precancerous lesions with the intent to implement a microbiome signature in CRC screening programs.