Machine learning-identified stemness features and constructed stemness-related subtype with prognosis, chemotherapy, and immunotherapy responses for non-small cell lung cancer patients

• Published in: Stem cell research & therapy Vol. 14; no. 1; pp. 1 - 15
• Main Authors: Liu, Mingshan, Zhou, Ruihao, Zou, Wei, Yang, Zhuofan, Li, Quanjin, Chen, Zhiguo, jiang, Lei, Zhang, Jingtao
• Format: Journal Article
• Language: English
• Published: London BioMed Central Ltd 07.09.2023; BioMed Central; BMC
• Subjects: Algorithms; Analysis; B cells; Cancer; Cancer stem cell; Cancer therapies; Chemotherapy; Clustering; Consensus clustering; Copy number; Datasets; Genes; Genetic aspects; Genomes; Genomics; Immune checkpoint; Immunotherapy; Learning algorithms; Lung cancer; Lung cancer, Non-small cell; Lung cancer, Small cell; Machine learning; Medical prognosis; Microenvironments; Mutation; Non-small cell lung cancer; Non-small cell lung carcinoma; Patients; Radiation therapy; Regression analysis; Small cell lung carcinoma; Stem cells; Stemness index; Thoracic surgery; Taiwan
• DOI: 10.1186/s13287-023-03406-4
• ISSN: 1757-6512

Aim This study aimed to explore a novel subtype classification method based on the stemness characteristics of patients with non-small cell lung cancer (NSCLC). Methods Based on the Cancer Genome Atlas database to calculate the stemness index (mRNAsi) of NSCLC patients, an unsupervised consensus clustering method was used to classify patients into two subtypes and analyze the survival differences, somatic mutational load, copy number variation, and immune characteristics differences between them. Subsequently, four machine learning methods were used to construct and validate a stemness subtype classification model, and cell function experiments were performed to verify the effect of the signature gene ARTN on NSCLC. Results Patients with Stemness Subtype I had better PFS and a higher somatic mutational burden and copy number alteration than patients with Stemness Subtype II. In addition, the two stemness subtypes have different patterns of tumor immune microenvironment. The immune score and stromal score and overall score of Stemness Subtype II were higher than those of Stemness Subtype I, suggesting a relatively small benefit to immune checkpoints. Four machine learning methods constructed and validated classification model for stemness subtypes and obtained multiple logistic regression equations for 22 characteristic genes. The results of cell function experiments showed that ARTN can promote the proliferation, invasion, and migration of NSCLC and is closely related to cancer stem cell properties. Conclusion This new classification method based on stemness characteristics can effectively distinguish patients' characteristics and thus provide possible directions for the selection and optimization of clinical treatment plans. Keywords: Non-small cell lung cancer, Cancer stem cell, Stemness index, Consensus clustering, Immunotherapy, Machine learning