Tumor microenvironment-aware, single-transcriptome prediction of microsatellite instability in colorectal cancer using meta-analysis.

ABSTRACT: Detecting microsatellite instability (MSI) in colorectal cancers (CRCs) is essential because it is the determinant of treatment strategies, including immunotherapy and chemotherapy. Yet, no attempt has been made to exploit transcriptomic profile and tumor microenvironment (TME) of it to unveil MSI status in CRC. Hence, we developed a novel TME-aware, single-transcriptome predictor of MSI for CRC, called MAP (Microsatellite instability Absolute single sample Predictor). MAP was developed utilizing recursive feature elimination-random forest with 466 CRC samples from The Cancer Genome Atlas, and its performance was validated in independent cohorts, including 1118 samples. MAP showed robustness and predictive power in predicting MSI status in CRC. Additional advantages for MAP were demonstrat

SUBMITTER: Seo MK 

PROVIDER: S-EPMC9012745 | biostudies-literature | 2022 Apr

REPOSITORIES: biostudies-literature