GSAE: an autoencoder with embedded gene-set nodes for genomics functional characterization
Preprint
Abstract
Bioinformatics tools have been developed to interpret gene expression data at the gene set level, and these gene set based analyses improve the biologists' capability to discover functional relevance of their experiment design. While elucidating gene set individually, inter gene sets association is rarely taken into consideration. Deep learning, an emerging machine learning technique in computational biology, can be used to generate an unbiased combination of gene set, and to determine the biological relevance and analysis consistency of these combining gene sets by leveraging large genomic data sets. In this study, we proposed a gene superset autoencoder (GSAE), a multi-layer autoencoder model with the incorporation of a priori defined gene sets that retain the crucial biological features in the latent layer. We introduced the concept of the gene superset, an unbiased combination of gene sets with weights trained by the autoencoder, where each node in the latent layer is a superset. Trained with genomic data from TCGA and evaluated with their accompanying clinical parameters, we showed gene supersets' ability of discriminating tumor subtypes and their prognostic capability. We further demonstrated the biological relevance of the top component gene sets in the significant supersets. Using autoencoder model and gene superset at its latent layer, we demonstrated that gene supersets retain sufficient biological information with respect to tumor subtypes and clinical prognostic significance. Superset also provides high reproducibility on survival analysis and accurate prediction for cancer subtypes.Keywords
All Related Versions
This publication has 37 references indexed in Scilit:
- Mapping the Mouse Cell Atlas by Microwell-SeqCell, 2018
- The Human Cell Atlas: from vision to realityNature, 2017
- Prognostic significance of TCF21 mRNA expression in patients with lung adenocarcinomaScientific Reports, 2017
- Sensitive detection of rare disease-associated cell subsets via representation learningNature Communications, 2017
- Visualization and analysis of single-cell RNA-seq data by kernel-based similarity learningNature Methods, 2017
- Density-Based Clustering Based on Hierarchical Density Estimates2013
- Trabectedin in patients with advanced non-small-cell lung cancer (NSCLC) with XPG and/or ERCC1 overexpression and BRCA1 underexpression and pretreated with platinumLung Cancer, 2011
- The UCSC Cancer Genomics BrowserNature Methods, 2009
- Systematic and integrative analysis of large gene lists using DAVID bioinformatics resourcesNature Protocols, 2008
- Expression of E1AF/PEA3, an Ets-related transcription factor in human non-small-cell lung cancers: Its relevance in cell motility and invasionInternational Journal of Cancer, 2001