Fig. 2From: Using a machine learning approach to identify key prognostic molecules for esophageal squamous cell carcinomaNetBox and Machine learning model. a Molecular interaction network constructed by NetBox and STRING; b The occurrence frequencies of each molecule in top 1000 classifiers across 5 machine learning algorithms; c The intersection of the optimal genes from five machine learning algorithms; d Pearson correlation analysis between protein and mRNA expression levels of SFN detected by WB and RT-PCR, respectively. LR: logical regression; SVM: support vector machine; ANN: artificial neural network; RF: random forest; XGBoost: eXtreme gradient boosting; WB: Western boltBack to article page