English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Bioinformatics tools have been developed to interpret gene expression data atthe gene set level, and these gene set based analyses improve the biologists'capability to discover functional relevance of their experiment design. Whileelucidating gene set individually, inter gene sets association is rarely takeninto consideration. Deep learning, an emerging machine learning technique incomputational biology, can be used to generate an unbiased combination of geneset, and to determine the biological relevance and analysis consistency ofthese combining gene sets by leveraging large genomic data sets. In this study,we proposed a gene superset autoencoder (GSAE), a multi-layer autoencoder modelwith the incorporation of a priori defined gene sets that retain the crucialbiological features in the latent layer. We introduced the concept of the genesuperset, an unbiased combination of gene sets with weights trained by theautoencoder, where each node in the latent layer is a superset. Trained withgenomic data from TCGA and evaluated with their accompanying clinicalparameters, we showed gene supersets' ability of discriminating tumor subtypesand their prognostic capability. We further demonstrated the biologicalrelevance of the top component gene sets in the significant supersets. Usingautoencoder model and gene superset at its latent layer, we demonstrated thatgene supersets retain sufficient biological information with respect to tumorsubtypes and clinical prognostic significance. Superset also provides highreproducibility on survival analysis and accurate prediction for cancersubtypes.

GSAE: an autoencoder with embedded gene-set nodes for genomics functional characterization