Dissecting Crucial Gene Markers Involved in HPV-Associated Oropharyngeal Squamous Cell Carcinoma from RNA-Sequencing Data through Explainable Artificial Intelligence.

Background: The incidence rate of oropharyngeal squamous cell carcinoma (OPSCC) worldwide is alarming. In the clinical community, there is a pressing necessity to comprehend the etiology of the OPSCC to facilitate the administration of effective treatments.
Methods: This study confers an integrative genomics approach for identifying key oncogenic drivers involved in the OPSCC pathogenesis. The dataset contains RNA-Sequencing (RNA-Seq) samples of 46 Human papillomavirus-positive head and neck squamous cell carcinoma and 25 normal Uvulopalatopharyngoplasty cases. The differential marker selection is performed between the groups with a log2FoldChange (FC) score of 2, adjusted p -value < 0.01, and screened 714 genes. The Particle Swarm Optimization (PSO) algorithm selects the candidate gene subset, reducing the size to 73. The state-of-the-art machine learning algorithms are trained with the differentially expressed genes and candidate subsets of PSO.
Results: The analysis of predictive models using Shapley Additive exPlanations revealed that seven genes significantly contribute to the model's performance. These include ECT2 , LAMC2 , and DSG2 , which predominantly influence differentiating between sample groups. They were followed in importance by FAT1 , PLOD2 , COL1A1 , and PLAU . The Random Forest and Bayes Net algorithms also achieved perfect validation scores when using PSO features. Furthermore, gene set enrichment analysis, protein-protein interactions, and disease ontology mining revealed a significant association between these genes and the target condition. As indicated by Shapley Additive exPlanations (SHAPs), the survival analysis of three key genes unveiled strong over-expression in the samples from "The Cancer Genome Atlas".
Conclusions: Our findings elucidate critical oncogenic drivers in OPSCC, offering vital insights for developing targeted therapies and enhancing understanding its pathogenesis.
Competing Interests: The authors declare no conflict of interest.
(© 2024 The Author(s). Published by IMR Press.)