GSAE: an autoencoder with embedded gene-set nodes for genomics functional characterization
This work addresses the need for better functional characterization of genomics data for biologists, though it is incremental as it builds on existing autoencoder and gene set analysis methods.
The authors tackled the problem of interpreting gene expression data by considering inter-gene set associations, which are often overlooked, and proposed GSAE, an autoencoder model that creates unbiased gene supersets. They demonstrated its ability to discriminate tumor subtypes and predict prognosis using TCGA data, showing high reproducibility and accuracy in survival analysis and subtype prediction.
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.