Description
pathDNN webserver which can effectively predict the drug sensitivity to cancer cells using a pathway-guided deep neural network model. Figure 1 shows the illustrative diagram of the data sources and structure of the pathway-guided deep neural network. The first hidden layer is composed of the pathway nodes that connected to the input genes compiled from genome-wide expression profiles and drug targets, the mask matrix is used to encode the relation between gene nodes and pathway nodes. The second and third hidden layers are full-connected, and single node in the output layer output the quantitative drug sensitivity.
Current Version
* Current Version Number: 1.1 * Release Date of Current Version: 01/30/2020
Contact Info
E-mail:leideng(at)csu.edu.cn
References [1]