Fig. 1
From: Deep neural network based tissue deconvolution of circulating tumor cell RNA
The overall study designs. The neural network deep learning model was trained using GTEx RNA-seq data from TSGs identified in GTEx and TCGA normal tissue. The performance of the model was compared to the traditional NNLS method in three independent validation datasets: (1) Semi in silico dataset from GTEx; (2) Semi in silico dataset from six normal tissue RNA-seq; (3) ctcRNA-seq from a melanoma patient with metastatic tumors