Deep learning-based polygenic risk analysis for Alzheimer's disease prediction

BACKGROUND

The polygenic nature of Alzheimer's disease (AD) suggests that multiple variants jointly contribute to disease susceptibility. As an individual's genetic variants are constant throughout life, evaluating the combined effects of multiple disease-associated genetic risks enables reliable AD risk prediction. Because of the complexity of genomic data, current statistical analyses cannot comprehensively capture the polygenic risk of AD, resulting in unsatisfactory disease risk prediction. However, deep learning methods, which capture nonlinearity within high-dimensional genomic data, may enable more accurate disease risk prediction and improve our understanding of AD etiology. Accordingly, we developed deep learning neural network models for modeling AD polygenic risk.

METHODS

We constructed neural network models to model AD polygenic risk and compared them with the widely used weighted polygenic risk score and lasso models. We conducted robust linear regression analysis to investigate the relationship between the AD polygenic risk derived from deep learning methods and AD endophenotypes (i.e., plasma biomarkers and individual cognitive performance). We stratified individuals by applying unsupervised clustering to the outputs from the hidden layers of the neural network model.

RESULTS

The deep learning models outperform other statistical models for modeling AD risk. Moreover, the polygenic risk derived from the deep learning models enables the identification of disease-associated biological pathways and the stratification of individuals according to distinct pathological mechanisms.

CONCLUSION

Our results suggest that deep learning methods are effective for modeling the genetic risks of AD and other diseases, classifying disease risks, and uncovering disease mechanisms.

An IL1RL1 genetic variant lowers soluble ST2 levels and the risk effects of APOE-ε4 in female patients with Alzheimer's disease

Changes in the levels of circulating proteins are associated with Alzheimer's disease (AD), whereas their pathogenic roles in AD are unclear. Here, we identified soluble ST2 (sST2), a decoy receptor of interleukin-33-ST2 signaling, as a new disease-causing factor in AD. Increased circulating sST2 level is associated with more severe pathological changes in female individuals with AD. Genome-wide association analysis and CRISPR-Cas9 genome editing identified rs1921622 , a genetic variant in an enhancer element of IL1RL1, which downregulates gene and protein levels of sST2. Mendelian randomization analysis using genetic variants, including rs1921622 , demonstrated that decreased sST2 levels lower AD risk and related endophenotypes in females carrying the Apolipoprotein E (APOE)-ε4 genotype; the association is stronger in Chinese than in European-descent populations. Human and mouse transcriptome and immunohistochemical studies showed that rs1921622 /sST2 regulates amyloid-beta (Aβ) pathology through the modulation of microglial activation and Aβ clearance. These findings demonstrate how sST2 level is modulated by a genetic variation and plays a disease-causing role in females with AD.

Large-scale plasma proteomic profiling identifies a high-performance biomarker panel for Alzheimer's disease screening and staging

Introduction

Blood proteins are emerging as candidate biomarkers for Alzheimer's disease (AD). We systematically profiled the plasma proteome to identify novel AD blood biomarkers and develop a high‐performance, blood‐based test for AD.

Methods

We quantified 1160 plasma proteins in a Hong Kong Chinese cohort by high‐throughput proximity extension assay and validated the results in an independent cohort. In subgroup analyses, plasma biomarkers for amyloid, tau, phosphorylated tau, and neurodegeneration were used as endophenotypes of AD.

Results

We identified 429 proteins that were dysregulated in AD plasma. We selected 19 “hub proteins” representative of the AD plasma protein profile, which formed the basis of a scoring system that accurately classified clinical AD (area under the curve  = 0.9690–0.9816) and associated endophenotypes. Moreover, specific hub proteins exhibit disease stage‐dependent dysregulation, which can delineate AD stages.

Discussion

This study comprehensively profiled the AD plasma proteome and serves as a foundation for a high‐performance, blood‐based test for clinical AD screening and staging.

Genetic and polygenic risk score analysis for Alzheimer's disease in the Chinese population

INTRODUCTION

Dozens of Alzheimer's disease (AD)-associated loci have been identified in European-descent populations, but their effects have not been thoroughly investigated in the Hong Kong Chinese population.

METHODS

TaqMan array genotyping was performed for known AD-associated variants in a Hong Kong Chinese cohort. Regression analysis was conducted to study the associations of variants with AD-associated traits and biomarkers. Lasso regression was applied to establish a polygenic risk score (PRS) model for AD risk prediction.

RESULTS

SORL1 is associated with AD in the Hong Kong Chinese population. Meta-analysis corroborates the AD-protective effect of the SORL1 rs11218343 C allele. The PRS is developed and associated with AD risk, cognitive status, and AD-related endophenotypes. TREM2 H157Y might influence the amyloid beta 42/40 ratio and levels of immune-associated proteins in plasma.

DISCUSSION

SORL1 is associated with AD in the Hong Kong Chinese population. The PRS model can predict AD risk and cognitive status in this population.