Research Paper Volume 16, Issue 16 pp 11824—11842
Identifying novel circadian rhythm biomarkers for diagnosis and prognosis of melanoma by an integrated bioinformatics and machine learning approach
Figure 5. Expression and ROC analysis of key CRGs. (A) Expression comparison of key CRGs between melanoma and normal tissues in the training set (combined GSE15605 and GSE114445 datasets). (B) Expression comparison of key CRGs between melanoma and normal tissues in GSE15605 dataset. (C) Expression comparison of key CRGs between melanoma and normal tissues in GSE114445 dataset. (D) Expression comparison of key CRGs between melanoma and normal tissues in GSE46517 dataset. (E) ROC curves of key CRGs in the training set. (F) ROC curves of key CRGs in GSE15605 dataset. (G) ROC curves of key CRGs in GSE114445 dataset. (H) ROC curves of key CRGs in GSE46517 dataset.