Development of a miRNA‐based classifier for detection of colorectal cancer molecular subtypes

Abstract

Previously, colorectal cancer (CRC) has been classified into four distinct molecular subtypes based on transcriptome data. These consensus molecular subtypes (CMSs) have implications for our understanding of tumor heterogeneity and the prognosis of patients. So far, this classification has been based on the use of messenger RNAs (mRNAs), although microRNAs (miRNAs) have also been shown to play a role in tumor heterogeneity and biological differences between CMSs. In contrast to mRNAs, miRNAs have a smaller size and increased stability, facilitating their detection. Therefore, we built a miRNA‐based CMS classifier by converting the existing mRNA‐based CMS classification using machine learning (training dataset of n = 271). The performance of this miRNA‐assigned CMS classifier (CMS‐miRaCl) was evaluated in several datasets, achieving an overall accuracy of ~ 0.72 (0.6329–0.7987) in the largest dataset (n = 158). To gain insight into the biological relevance of CMS‐miRaCl, we evaluated the most important features in the classifier. We found that miRNAs previously reported to be relevant in microsatellite‐instable CRCs or Wnt signaling were important features for CMS‐miRaCl. Following further studies to validate its robustness, this miRNA‐based alternative might simplify the implementation of CMS classification in clinical workflows.

Circ-TRIO promotes TNBC progression by regulating the miR-432-5p/CCDC58 axis

“…As a type of noncoding RNA, miRNAs participate in a variety of cellular biological processes and can combine with the 3ʹUTR and regulate the expression of target genes [50,51]. It is acknowledged that the controlled expression of miRNAs is indispensable for normal cells, while the aberrant expression of miRNAs may lead to diseases, including cancers [52,53].…”

Characterizing the molecular heterogeneity of clear cell renal cell carcinoma subgroups classified by miRNA expression profile

“…The Consensus Molecular Subtypes (CMSs) have implications for our understanding of tumor heterogeneity and the prognosis of patients (Guo et al, 2021;Zhong et al, 2021). So far, the classification has been widely based on the use of messenger RNAs (mRNAs), although miRNAs have been shown to play vital roles in tumor heterogeneity and biological differences between CMSs (Lu et al, 2005;Adam et al, 2022). In contrast to mRNAs, miRNAs have a smaller size and increased stability, facilitating their detection and thus became an important matter for biomarker researchers.…”

Molecular Classification of Colorectal Cancer by microRNA Profiling: Correlation with the Consensus Molecular Subtypes (CMS) and Validation of miR-30b Targets

“…MicroRNAs expression data (miRNA-Seq) from TCGA-COAD were classified using miRaCl classifier [ 12 ] available at Github/rsmadam/CMS-miRaCl. Subtype association between miRNA and mRNA classification was determined using Chi-square test (χ 2 ).…”

“…This can be an important advance, since it would allow the search of the relevant miRs in serum/plasma of patients and their classification, as other authors have reported for pancreatic adenocarcinoma [ 11 ], without the need to obtain biopsies or fragments of the tumor, facilitating real-time analysis of the course of the disease and of the response to the treatment. A just released report, develops a miR classifier using supervised analysis to predict four miR subtypes assigned from the four mRNA CMS subtypes [ 12 ]. Using in silico machine learning the study of Adam et al [ 12 ] converts the four mRNA-CMS subtypes to four miR-subtypes.…”

“…A just released report, develops a miR classifier using supervised analysis to predict four miR subtypes assigned from the four mRNA CMS subtypes [ 12 ]. Using in silico machine learning the study of Adam et al [ 12 ] converts the four mRNA-CMS subtypes to four miR-subtypes. This procedure is different than ours.…”