Turkish Journal of Biology




Background/aim: The molecular heterogeneity of colon cancer has made classification of tumors a requirement for effective treatment. One of the approaches for molecular subtyping of colon cancer patients is the Consensus Molecular Subtypes (CMS) developed by the Colorectal Cancer Subtyping Consortium (CRCSC). CMS-specific RNA-Seq dependent classification approaches are recent with relatively low sensitivity and specificity. In this study, we aimed to classify patients into CMS groups using RNA-seq profiles. Materials and methods: We first identified subtype specific and survival associated genes using Fuzzy C-Means (FCM) algorithm and log-rank test. Then we classified patients using Support Vector Machines with Backward Elimination methodology. Results: We optimized RNA-seq based classification using 25 genes with minimum classification error rate. Here we report the classification performance using precision, sensitivity, specificity, false discovery rate and balanced accuracy metrics. Conclusion: We present the gene list for colon cancer classification with minimum classification error rates. We observed the lowest sensitivity but highest specificity with CMS3-associated genes, which is significant due to low number of patients in the clinic for this group.


Consensus Molecular Subtypes, Fuzzy C-Means, RNA-seq, colon cancer, classification, support vector machines

First Page


Last Page


Included in

Biology Commons