Interpretation of the Transcriptome-Based Signature of Tumor-Initiating Cells, the Core of Cancer Development, and the Construction of a Machine Learning-Based Classifier

Tumor-initiating cells (TICs) constitute a subpopulation of cancer cells with stem-like properties contributing to tumorigenesis, progression, recurrence, and therapeutic resistance. Despite their biological importance, their molecular signatures that distinguish them from non-TICs remain incompletely characterized. This study aimed to comprehensively analyze transcriptomic differences between TICs and non-TICs, identify TIC-specific gene expression patterns, and construct a machine learning-based classifier that could accurately predict TIC status. RNA sequencing data were obtained from four human cell lines representing TIC (TS10 and TS32) and non-TIC (32A and Epi). Transcriptomic profiles were analyzed via principal component, hierarchical clustering, and differential expression analysis. Gene-Ontology and Kyoto-Encyclopedia of Genes and Genomes pathway enrichment analyses were conducted for functional interpretation. A logistic-regression model was trained on differentially expressed genes to predict TIC status. Model performance was validated using synthetic data and external projection. TICs exhibited distinct transcriptomic signatures, including enrichment of non-coding RNAs (e.g., MIR4737 and SNORD19) and selective upregulation of metabolic transporters (e.g., SLC25A1, SLC16A1, and FASN). Functional pathway analysis revealed TIC-specific activation of oxidative phosphorylation, PI3K-Akt signaling, and ribosome-related processes. The logistic-regression model achieved perfect classification (area under the curve of 1.00), and its key features indicated metabolic and translational reprogramming unique to TICs. Transcriptomic state-space embedding analysis suggested reversible transitions between TIC and non-TIC states driven by transcriptional and epigenetic regulators. This study reveals a unique transcriptomic landscape defining TICs and establishes a highly accurate machine learning-based TIC classifier. These findings enhance our understanding of TIC biology and show promising strategies for TIC-targeted diagnostics and therapeutic interventions.