Research Paper Volume 16, Issue 20 pp 13076—13103
A lactate metabolism-related gene signature to diagnose osteoarthritis based on machine learning combined with experimental validation
Figure 3. SLC2A1 and NDUFB9 were co-determined by bioinformatical analyses and machine learning algorithms. (A) The construction and analyses of the PPI network. (B) 13 genes were identified by the LASSO regression. (C) 13 genes were determined by the SVM-RFE algorithm. (D) Boruta algorithm showed that 44 genes were of high diagnosis value. (E) SLC2A1 and NDUFB9 were co-determined by the LASSO, SVM-RFE, Boruta, univariate logistic regression, and PPI network analysis. Abbreviations: LASSO, least absolute shrinkage and selection operator; SVM-RFE, supporter vector machine-recursive feature elimination; PPI, protein-protein interaction.