Skip to main content
Fig. 2 | BioData Mining

Fig. 2

From: DeepAutoGlioma: a deep learning autoencoder-based multi-omics data integration and classification tools for glioma subtyping

Fig. 2

Architecture of autoencoder: The autoencoder used in DeepAutoGlioma consists of an encoder and a decoder made from 2 hidden layers and one bottleneck layer. The autoencoder has two input layers for DNA methylation and gene expression; in the first hidden layer, data is concatenated, and is passed to another hidden layer and finally compressed in the bottleneck layer. In the decoder part, the latent variables from the bottleneck layer are reconstructed to the initial ones

Back to article page

BioData Mining

ISSN: 1756-0381