Identification of Novel Diagnostic and Prognostic Gene Signature Biomarkers for Breast Cancer Using Artificial Intelligence and Machine Learning Assisted Transcriptomics Analysis

SIMPLE SUMMARY: Breast cancer is the most fatal female cancer, which the existing clinical and pathological information sometimes fails to diagnose accurately. Recent artificial intelligence-based studies have shown the capability of identifying molecular biomarkers using high-throughput genomics data. Our aim was to apply machine learning methods to a large cohort of transcriptomics data for gene reduction and the construction of a diagnostic model for cancer classification. Advanced statistical methods and cross-validation with another set of machine learning methods increased the accuracy of the diagnostic model and predicted a novel diagnostic nine-gene signature. Further, survival analysis revealed a novel prognostic model of eight-gene signatures. Experimental validation confirmed the expression of the identified gene signatures in breast cancer patients and increased the reliability of the study. The identified gene signature biomarkers have the potential to improve healthcare management with precise diagnosis and prognosis at a reduced cost. ABSTRACT: Background: Breast cancer (BC) is one of the most common female cancers. Clinical and histopathological information is collectively used for diagnosis, but is often not precise. We applied machine learning (ML) methods to identify the valuable gene signature model based on differentially expressed genes (DEGs) for BC diagnosis and prognosis. Methods: A cohort of 701 samples from 11 GEO BC microarray datasets was used for the identification of significant DEGs. Seven ML methods, including RFECV-LR, RFECV-SVM, LR-L1, SVC-L1, RF, and Extra-Trees were applied for gene reduction and the construction of a diagnostic model for cancer classification. Kaplan–Meier survival analysis was performed for prognostic signature construction. The potential biomarkers were confirmed via qRT-PCR and validated by another set of ML methods including GBDT, XGBoost, AdaBoost, KNN, and MLP. Results: We identified 355 DEGs and predicted BC-associated pathways, including kinetochore metaphase signaling, PTEN, senescence, and phagosome-formation pathways. A hub of 28 DEGs and a novel diagnostic nine-gene signature (COL10A, S100P, ADAMTS5, WISP1, COMP, CXCL10, LYVE1, COL11A1, and INHBA) were identified using stringent filter conditions. Similarly, a novel prognostic model consisting of eight-gene signatures (CCNE2, NUSAP1, TPX2, S100P, ITM2A, LIFR, TNXA, and ZBTB16) was also identified using disease-free survival and overall survival analysis. Gene signatures were validated by another set of ML methods. Finally, qRT-PCR results confirmed the expression of the identified gene signatures in BC. Conclusion: The ML approach helped construct novel diagnostic and prognostic models based on the expression profiling of BC. The identified nine-gene signature and eight-gene signatures showed excellent potential in BC diagnosis and prognosis, respectively.