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

Imaging genetic studies aim to find associations between genetic variants andimaging quantitative traits. Traditional genome-wide association studies (GWAS)are based on univariate statistical tests, but when multiple traits areanalyzed together they suffer from a multiple-testing problem and from nottaking into account correlations among the traits. An alternative approach tomulti-trait GWAS is to reverse the functional relation between genotypes andtraits, by fitting a multivariate regression model to predict genotypes frommultiple traits simultaneously. However, current reverse genotype predictionapproaches are mostly based on linear models. Here, we evaluated random forestregression (RFR) as a method to predict SNPs from imaging QTs and identifybiologically relevant associations. We learned machine learning models topredict 518,484 SNPs using 56 brain imaging QTs. We observed that genotyperegression error is a better indicator of permutation p-value significance thangenotype classification accuracy. SNPs within the known Alzheimer disease (AD)risk gene APOE had lowest RMSE for lasso and random forest, but not ridgeregression. Moreover, random forests identified additional SNPs that were notprioritized by the linear models but are known to be associated withbrain-related disorders. Feature selection identified well-known brain regionsassociated with AD,like the hippocampus and amygdala, as important predictorsof the most significant SNPs. In summary, our results indicate that non-linearmethods like random forests may offer additional insights intophenotype-genotype associations compared to traditional linear multi-variateGWAS methods.

rfPhen2Gen: A machine learning based association study of brain imaging phenotypes to genotypes