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

The advent of artificial intelligence, especially the progress of deep neuralnetworks, is expected to revolutionize genetic research and offer unprecedentedpotential to decode the complex relationships between genetic variants anddisease phenotypes, which could mark a significant step toward improving ourunderstanding of the disease etiology. While deep neural networks hold greatpromise for genetic association analysis, limited research has been focused ondeveloping neural-network-based tests to dissect complex genotype-phenotypeassociations. This complexity arises from the opaque nature of neural networksand the absence of defined limiting distributions. We have previously developeda kernel-based neural network model (KNN) that synergizes the strengths oflinear mixed models with conventional neural networks. KNN adopts acomputationally efficient minimum norm quadratic unbiased estimator (MINQUE)algorithm and uses KNN structure to capture the complex relationship betweenlarge-scale sequencing data and a disease phenotype of interest. In the KNNframework, we introduce a MINQUE-based test to assess the joint association ofgenetic variants with the phenotype, which considers non-linear andnon-additive effects and follows a mixture of chi-square distributions. We alsoconstruct two additional tests to evaluate and interpret linear andnon-linear/non-additive genetic effects, including interaction effects. Oursimulations show that our method consistently controls the type I error rateunder various conditions and achieves greater power than a commonly usedsequence kernel association test (SKAT), especially when involving non-linearand interaction effects. When applied to real data from the UK Biobank, ourapproach identified genes associated with hippocampal volume, which can befurther replicated and evaluated for their role in the pathogenesis ofAlzheimer's disease.

An Association Test Based on Kernel-Based Neural Networks for Complex Genetic Association Analysis