Fig. 2From: Mining influential genes based on deep learningPerformance evaluation of the AutoEncoder model in both gene (a) and sample dimensions (b). a The density plots of the predictive error (MAE) and the similarity (PCC) of all genes. b The circular diagram of clustering for three types of samples, including normal (Normal), lung adenocarcinoma (ADC) and lung squamous cell carcinoma (SCC)Back to article page