A panel of machine learning approaches for diagnostic model development and validation in ovarian cancer
Authors:
- Shengyan ShenSSShengyan Shen
- Lingling ZhangLZLingling Zhang
- Qiran SunQSQiran Sun
- Yating HuangYHYating Huang
- Ying YangYYYing Yang
- Ningning HuNHNingning Hu
- Susu JiangSJSusu Jiang
- Liwen ZhangLZLiwen Zhang
- Xiaoqin WangXWXiaoqin Wang
- Rujun ChenRCRujun Chen
Open Access
- 1 February 2026
- journal article
- Published by AME Publishing Company in Translational Cancer Research
- Vol. 15 (2) , 123
Abstract
Background: Ovarian cancer is a lethal gynecological malignancy, with ~70% of patients diagnosed at advanced stages (5-year survival Methods: We analyzed five Gene Expression Omnibus (GEO) datasets, with GSE26712, GSE29156, and GSE40595 assigned as the training cohort, and GSE66957 and GSE119054 as independent validation cohorts. Following batch effect correction, 113 ML algorithms were systematically compared. The optimal model was further validated, and its core genes [model gene (Mgenes)] were subjected to functional enrichment and immune cell correlation analyses. Results: The least absolute shrinkage and selection operator (Lasso) + NaiveBayes model demonstrated the strongest diagnostic performance, with area under the receiver operating characteristic curve (AUC) values of 0.991 in the training set, 0.889 in GSE119054, and 0.936 in GSE66957, and achieved 100% recall in both validation cohorts. Twelve Mgenes were identified, among which CP exhibited the highest diagnostic value (AUC =0.966). Functional enrichment revealed that Mgenes were predominantly involved in cell cycle regulation and DNA replication pathways, and correlation analyses confirmed their associations with key immune subsets (e.g., MAOB with regulatory T cells, STAR with CD8+ T cells). Conclusions: The Lasso + NaiveBayes model enables robust ovarian cancer diagnosis, with high recall prioritizing the identification of all potential cases. The identified Mgenes act as both high-performance diagnostic biomarkers and functional mediators of tumorigenesis, laying a foundation for early detection strategies and mechanistic research into ovarian cancer.Keywords
This publication has 33 references indexed in Scilit:
- Robust enumeration of cell subsets from tissue expression profilesNature Methods, 2015
- GSVA: gene set variation analysis for microarray and RNA-Seq dataBMC Bioinformatics, 2013
- The sva package for removing batch effects and other unwanted variation in high-throughput experimentsBioinformatics, 2012
- Claudins: Control of Barrier Function and Regulation in Response to Oxidant StressAntioxidants & Redox Signaling, 2011
- pROC: an open-source package for R and S+ to analyze and compare ROC curvesBMC Bioinformatics, 2011
- Methylation profiles of hereditary and sporadic ovarian cancerHistopathology, 2010
- The GeneMANIA prediction server: biological network integration for gene prioritization and predicting gene functionNucleic Acids Research, 2010
- WGCNA: an R package for weighted correlation network analysisBMC Bioinformatics, 2008
- Regulation of CXCR4-Mediated Nuclear Translocation of Extracellular Signal-Related Kinases 1 and 2Molecular Pharmacology, 2006
- Peg3/Pw1 promotes p53-mediated apoptosis by inducing Bax translocation from cytosol to mitochondriaProceedings of the National Academy of Sciences, 2000