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

Motivation: How do we integratively analyze large-scale multi-platformgenomic data that are high dimensional and sparse? Furthermore, how can weincorporate prior knowledge, such as the association between genes, in theanalysis systematically? Method: To solve this problem, we propose a ScalableNetwork Constrained Tucker decomposition method we call SNeCT. SNeCT adoptsparallel stochastic gradient descent approach on the proposed parallelizablenetwork constrained optimization function. SNeCT decomposition is applied totensor constructed from large scale multi-platform multi-cohort cancer data,PanCan12, constrained on a network built from PathwayCommons database. Results:The decomposed factor matrices are applied to stratify cancers, to search fortop-k similar patients, and to illustrate how the matrices can be used forpersonalized interpretation. In the stratification test, combined twelve-cohortdata is clustered to form thirteen subclasses. The thirteen subclasses have ahigh correlation to tissue of origin in addition to other interestingobservations, such as clear separation of OV cancers to two groups, and highclinical correlation within subclusters formed in cohorts BRCA and UCEC. In thetop-k search, a new patient's genomic profile is generated and searched againstexisting patients based on the factor matrices. The similarity of the top-kpatient to the query is high for 23 clinical features, includingestrogen/progesterone receptor statuses of BRCA patients with average precisionvalue ranges from 0.72 to 0.86 and from 0.68 to 0.86, respectively. We alsoprovide an illustration of how the factor matrices can be used forinterpretable personalized analysis of each patient.

SNeCT: Scalable network constrained Tucker decomposition for integrative multi-platform data analysis