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

Due to the complexity of cancer, clustering algorithms have been used todisentangle the observed heterogeneity and identify cancer subtypes that can betreated specifically. While kernel based clustering approaches allow the use ofmore than one input matrix, which is an important factor when considering amultidimensional disease like cancer, the clustering results remain hard toevaluate and, in many cases, it is unclear which piece of information had whichimpact on the final result. In this paper, we propose an extension of multiplekernel learning clustering that enables the characterization of each identifiedpatient cluster based on the features that had the highest impact on theresult. To this end, we combine feature clustering with multiple kerneldimensionality reduction and introduce FIPPA, a score which measures thefeature cluster impact on a patient cluster. Results: We applied the approachto different cancer types described by four different data types with the aimof identifying integrative patient subtypes and understanding which featureswere most important for their identification. Our results show that our methoddoes not only have state-of-the-art performance according to standard measures(e.g., survival analysis), but, based on the high impact features, it alsoproduces meaningful explanations for the molecular bases of the subtypes. Thiscould provide an important step in the validation of potential cancer subtypesand enable the formulation of new hypotheses concerning individual patientgroups. Similar analysis are possible for other disease phenotypes.

An interpretable multiple kernel learning approach for the discovery of integrative cancer subtypes