Multi-omics Analysis Classifies Colorectal Cancer into Distinct Methylated Immunogenic and Angiogenic Subtypes Based on Anatomical Laterality.

UNLABELLED

We employed supervised machine learning algorithms to a cohort of colorectal cancer patients from the NCI to differentiate and classify the heterogenous disease based on anatomical laterality and multi-omics stratification, in a first of its kind. Multi-omics integrative analysis shows distinct clustering of left and right colorectal cancer with disentangled representation of methylome and delineation of transcriptome and genome. We present novel multi-omics findings consistent with augmented hypermethylation of genes in right CRC, epigenomic biomarkers on the right in conjunction with immune-mediated pathway signatures, and lymphocytic invasion which unlocks unique therapeutic avenues. Contrarily, left CRC multi-omics signature is found to be marked by angiogenesis, cadherins, and epithelial-mesenchymal transition (EMT). An integrated multi-omics molecular signature of , hsa-miR-10b, and panel of , , , , and copy number altered genes have been found by the study. Overall survival analysis reveals genomic biomarkers and in 852 LCRC cases, and in 170 RCRC cases that predicts a significant survival benefit. Our study exemplifies the translational competence and robustness of machine learning in effective translational bridging of research and clinic.

SUPPLEMENTARY INFORMATION

The online version contains supplementary material available at 10.1007/s13193-023-01760-6.