No abstract

Elevated intraocular pressure (IOP) is a major risk factor for glaucoma, the leading cause of irreversible blindness worldwide. IOP is also the only modifiable risk factor for glaucoma. Previous genome-wide association studies have established the contribution of common genetic variants to IOP. The role of rare variants for IOP was unknown. Using whole exome sequencing data from 110,260 participants in the UK Biobank (UKB), we conducted the largest exome-wide association study of IOP to date. In addition to confirming known IOP genes, we identified 40 novel rare-variant genes for IOP, such as BOD1L1, ACAD10 and HLA-B, demonstrating the power of including and aggregating rare variants in gene discovery. About half of these IOP genes are also associated with glaucoma phenotypes in UKB and the FinnGen cohort. Six of these genes, i.e. ADRB1, PTPRB, RPL26, RPL10A, EGLN2, and MTOR, are drug targets that are either established for clinical treatment or in clinical trials. Furthermore, we constructed a rare-variant polygenic risk score and showed its significant association with glaucoma in independent participants (n = 312,825). We demonstrated the value of rare variants to enhance our understanding of the biological mechanisms regulating IOP and uncovered potential therapeutic targets for glaucoma.

Alzheimer’s disease (AD) is the most common late-onset neurodegenerative disorder. Identifying individuals at increased risk of developing AD is important for early intervention. Using data from the Alzheimer Disease Genetics Consortium, we constructed polygenic risk scores (PRSs) for AD and age-at-onset (AAO) of AD for the UK Biobank participants. We then built machine learning (ML) models for predicting development of AD, and explored feature importance among PRSs, conventional risk factors, and ICD-10 codes from electronic health records, a total of > 11,000 features using the UK Biobank dataset. We used eXtreme Gradient Boosting (XGBoost) and SHapley Additive exPlanations (SHAP), which provided superior ML performance as well as aided ML model explanation. For participants age 40 and older, the area under the curve for AD was 0.88. For subjects of age 65 and older (late-onset AD), PRSs were the most important predictors. This is the first observation that PRSs constructed from the AD risk and AAO play more important roles than age in predicting AD. The ML model also identified important predictors from EHR, including urinary tract infection, syncope and collapse, chest pain, disorientation and hypercholesterolemia, for developing AD. Our ML model improved the accuracy of AD risk prediction by efficiently exploring numerous predictors and identified novel feature patterns.