Extracting a biologically latent space of lung cancer epigenetics with variational autoencoders.

Extracting a biologically latent space of lung cancer epigenetics with variational autoencoders.

Publication date: Nov 25, 2019

Lung cancer is one of the most malignant tumors, causing over 1,000,000 deaths each year worldwide. Deep learning has brought success in many domains in recent years. DNA methylation, an epigenetic factor, is used for model training in many studies. There is an opportunity for deep learning methods to analyze the lung cancer epigenetic data to determine their subtypes for appropriate treatment.

Here, we employ variational autoencoders (VAEs), an unsupervised deep learning framework, on 450K DNA methylation data of TCGA-LUAD and TCGA-LUSC to learn latent representations of the DNA methylation landscape. We extract a biologically relevant latent space of LUAD and LUSC samples. It is showed that the bivariate classifiers on the further compressed latent features could classify the subtypes accurately. Through clustering of methylation-based latent space features, we demonstrate that the VAEs can capture differential methylation patterns about subtypes of lung cancer.

VAEs can distinguish the original subtypes from manually mixed methylation data frame with the encoded features of latent space. Further applications about VAEs should focus on fine-grained subtypes identification for precision medicine.

Open Access PDF

Wang, Z. and Wang, Y. Extracting a biologically latent space of lung cancer epigenetics with variational autoencoders. 05839. 2019 BMC Bioinformatics (20):Suppl 18.

Concepts Keywords
BMC Lung cancer
Clustering Branches of biology
Deep Learning Epigenetics
Differential Autoencoder
Epigenetic Unsupervised learning
Epigenetics Methylation
Latent Space
Lung
Lung Cancer
Malignant
Methylation
Precision Medicine

Semantics

Type Source Name
disease MESH lung cancer
disease MESH tumors
drug DRUGBANK Spinosad
pathway REACTOME DNA methylation
disease MESH growth
disease MESH noma
disease MESH squamous carcinoma
disease MESH diagnosis
disease MESH melanoma
pathway KEGG Melanoma
drug DRUGBANK Cysteamine
disease MESH dif
drug DRUGBANK Fenamole
disease MESH tic
drug DRUGBANK L-Valine
drug DRUGBANK Aspartame
drug DRUGBANK Ademetionine
drug DRUGBANK Saquinavir
drug DRUGBANK Hyaluronic acid
disease MESH multiple
disease MESH multi
drug DRUGBANK Trestolone
drug DRUGBANK Coenzyme M
drug DRUGBANK (S)-Des-Me-Ampa
drug DRUGBANK Guanosine

Similar

Original Article

Leave a Comment

Your email address will not be published. Required fields are marked *