Fig. 1
From: Molecular signature comprising 11 platelet-genes enables accurate blood-based diagnosis of NSCLC
Panel of 11 genes performs equivalent to panel of 1000 genes. AUC (Area under the curve) plots representing the comparative performance of 1000 gene and 11 gene panels respectively on platelet transcriptomes from healthy and NSCLC patients. The predictive power of the gene-sets was evaluated using three widely used classification algorithms namely Gradient Boosting Machines (GB), Random Forest (RF), and Linear Discriminant Analysis (LDA)