OVsignGenes: A Gene Expression-Based Neural Network Model Estimated Molecular Subtype of High-Grade Serous Ovarian Carcinoma

Background/Objectives: High-grade serous carcinomas (HGSCs) are highly heterogeneous tumors, both among patients and within a single tumor. Differences in molecular mechanisms significantly describe this heterogeneity. Four molecular subtypes have been previously described by the Cancer Genome Atlas Consortium: differentiated, immunoreactive, mesenchymal, and proliferative. These subtypes may have varying degrees of progression, relapse-free survival, and overall survival, as well as response to therapy. The precise determination of these subtypes is certainly necessary both for diagnosis and future development of targeted therapies within personalized medicine. Methods: In this study, we analyzed gene expression data based on bulk RNA-seq, scRNA-seq, and spatial transcriptomic data from six cohorts (totaling 535 samples, including 60 single-cell samples). Differential expression analysis was performed using the edgeR package. The KEGG database and GSVA package were used for pathways enrichment analysis. As a predictive model, a deep neural network was created using the keras and tensorflow libraries. Results: We identified 357 differentially expressed genes among the four subtypes: 96 differentiated, 33 immunoreactive, 91 mesenchymal, and 137 proliferative. Based on these, we created OVsignGenes, a neural network model resistant to the effects of platform (test dataset AUC = 0.969). We then ran data from five more cohorts through our model, including scRNA-seq and spatial transcriptomics. Conclusions: Because the differentiated subtype is located at the intersection of the other three subtypes based on PCA and does not have a unique profile of differentially expressed genes or enriched pathways, it can be considered an initiating subtype of tumor that will develop into one of the three other subtypes.