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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Polygenic risk scores (PRS) estimate the genetic risk of an individual for acomplex disease based on many genetic variants across the whole genome. In thisstudy, we compared a series of computational models for estimation of breastcancer PRS. A deep neural network (DNN) was found to outperform alternativemachine learning techniques and established statistical algorithms, includingBLUP, BayesA and LDpred. In the test cohort with 50% prevalence, the Area Underthe receiver operating characteristic Curve (AUC) were 67.4% for DNN, 64.2% forBLUP, 64.5% for BayesA, and 62.4% for LDpred. BLUP, BayesA, and LPpred allgenerated PRS that followed a normal distribution in the case population.However, the PRS generated by DNN in the case population followed a bi-modaldistribution composed of two normal distributions with distinctly differentmeans. This suggests that DNN was able to separate the case population into ahigh-genetic-risk case sub-population with an average PRS significantly higherthan the control population and a normal-genetic-risk case sub-population withan average PRS similar to the control population. This allowed DNN to achieve18.8% recall at 90% precision in the test cohort with 50% prevalence, which canbe extrapolated to 65.4% recall at 20% precision in a general population with12% prevalence. Interpretation of the DNN model identified salient variantsthat were assigned insignificant p-values by association studies, but wereimportant for DNN prediction. These variants may be associated with thephenotype through non-linear relationships.

Deep neural network improves the estimation of polygenic risk scores for breast cancer