Abstract
BackgroundLung 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.ResultsHere, 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.ConclusionsVAEs 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.
Highlights
Lung cancer is one of the most malignant tumors, causing over 1,000,000 deaths each year worldwide
Histological subtypes of lung cancer, lung adenocarci- In recent years, deep learning has been performed noma (LUAD) and lung squamous cell carcinoma (LUSC). and achieved state-of-art performances in many domains, In order to understand the heterogeneity of lung can- including speech, image classification, text and natucer, many researchers have done a lot of work based ral language processing, but has seen slow adoption on immune-response genes, DNA mutations and DNA for in bioinformatics[5]
In order to verify the feasibility of Variational autoencoders (VAEs) to extract a biologically meaningful latent space from DNA methylation data, we employed a VAE model on the top 300,000 probes that were chosen by median absolute deviation (MAD) of methylation beta values across 917 samples containing Lung adenocarcinoma (LUAD) and LUSC subtypes
Summary
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. Lung cancer is one of the most malignant tumors with increasing, more efficient methods are needed for precithe fastest growth in morbidity and mortality, causing sion medicine finding ways to target subtypes for effective over 1,000,000 deaths each year. Histological subtypes of lung cancer, lung adenocarci- In recent years, deep learning has been performed noma (LUAD) and lung squamous cell carcinoma (LUSC). As a well-defined epigenetic factor, have revealed interesting results by training deep models.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
