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 Plus annual

Presents the access of premium content as premium feature

Premium Content

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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Recent advances in high-throughput sequencing technologies have enabled theextraction of multiple features that depict patient samples at diverse andcomplementary molecular levels. The generation of such data has led to newchallenges in computational biology regarding the integration ofhigh-dimensional and heterogeneous datasets that capture the interrelationshipsbetween multiple genes and their functions. Thanks to their versatility andability to learn synthetic latent representations of complex data, deeplearning methods offer promising perspectives for integrating multi-omics data.These methods have led to the conception of many original architectures thatare primarily based on autoencoder models. However, due to the difficulty ofthe task, the integration strategy is fundamental to take full advantage of thesources' particularities without losing the global trends. This paper presentsa novel strategy to build a customizable autoencoder model that adapts to thedataset used in the case of high-dimensional multi-source integration. We willassess the impact of integration strategies on the latent representation andcombine the best strategies to propose a new method, CustOmics(https://github.com/HakimBenkirane/CustOmics). We focus here on the integrationof data from multiple omics sources and demonstrate the performance of theproposed method on test cases for several tasks such as classification andsurvival analysis.

CustOmics: A versatile deep-learning based strategy for multi-omics integration