Feature selection is an indispensable step for the analysis of high-dimensional molecular data. Despite its importance, consensus is lacking on how to choose the most appropriate feature selection methods, especially when the performance of the feature selection methods itself depends on hyper-parameters. Bayesian optimization has demonstrated its advantages in automatically configuring the settings of hyper-parameters for various models. However, it remains unclear whether Bayesian optimization can benefit feature selection methods. In this research, we conducted extensive simulation studies to compare the performance of various feature selection methods, with a particular focus on the impact of Bayesian optimization on those where hyper-parameters tuning is needed. We further utilized the gene expression data obtained from the Alzheimer's Disease Neuroimaging Initiative to predict various brain imaging-related phenotypes, where various feature selection methods were employed to mine the data. We found through simulation studies that feature selection methods with hyper-parameters tuned using Bayesian optimization often yield better recall rates, and the analysis of transcriptomic data further revealed that Bayesian optimization-guided feature selection can improve the accuracy of disease risk prediction models. In conclusion, Bayesian optimization can facilitate feature selection methods when hyper-parameter tuning is needed and has the potential to substantially benefit downstream tasks.

The detection of Parkinson’s disease (PD) in its early stages is of great importance for its treatment and management, but consensus is lacking on what information is necessary and what models should be used to best predict PD risk. In our study, we first grouped PD-associated factors based on their cost and accessibility, and then gradually incorporated them into risk predictions, which were built using eight commonly used machine learning models to allow for comprehensive assessment. Finally, the Shapley Additive Explanations (SHAP) method was used to investigate the contributions of each factor. We found that models built with demographic variables, hospital admission examinations, clinical assessment, and polygenic risk score achieved the best prediction performance, and the inclusion of invasive biomarkers could not further enhance its accuracy. Among the eight machine learning models considered, penalized logistic regression and XGBoost were the most accurate algorithms for assessing PD risk, with penalized logistic regression achieving an area under the curve of 0.94 and a Brier score of 0.08. Olfactory function and polygenic risk scores were the most important predictors for PD risk. Our research has offered a practical framework for PD risk assessment, where necessary information and efficient machine learning tools were highlighted.

Introduction: The comorbidity between major depressive disorder (MDD) and coronavirus disease of 2019 (COVID-19) related traits have long been identified in clinical settings, but their shared genetic foundation and causal relationships are unknown. Here, we investigated the genetic mechanisms behind COVID-19 related traits and MDD using the cross-trait meta-analysis, and evaluated the underlying causal relationships between MDD and 3 different COVID-19 outcomes (severe COVID-19, hospitalized COVID-19, and COVID-19 infection).Methods: In this study, we conducted a comprehensive analysis using the most up-to-date and publicly available GWAS summary statistics to explore shared genetic etiology and the causality between MDD and COVID-19 outcomes. We first used genome-wide cross-trait meta-analysis to identify the pleiotropic genomic SNPs and the genes shared by MDD and COVID-19 outcomes, and then explore the potential bidirectional causal relationships between MDD and COVID-19 outcomes by implementing a bidirectional MR study design. We further conducted functional annotations analyses to obtain biological insight for shared genes from the results of cross-trait meta-analysis.Results: We have identified 71 SNPs located on 25 different genes are shared between MDD and COVID-19 outcomes. We have also found that genetic liability to MDD is a causal factor for COVID-19 outcomes. In particular, we found that MDD has causal effect on severe COVID-19 (OR = 1.832, 95% CI = 1.037–3.236) and hospitalized COVID-19 (OR = 1.412, 95% CI = 1.021–1.953). Functional analysis suggested that the shared genes are enriched in Cushing syndrome, neuroactive ligand-receptor interaction.Discussion: Our findings provide convincing evidence on shared genetic etiology and causal relationships between MDD and COVID-19 outcomes, which is crucial to prevention, and therapeutic treatment of MDD and COVID-19.

Type 2 diabetes (T2D) is often comorbid with cardiovascular diseases (CVDs). The direction of causation between T2D and CVD is difficult to determine; however, there may be a common underlying pathway attributable to shared genetic factors. We aimed to determine whether there is a shared genetic susceptibility to T2D and CVD. This study utilizes large-scale datasets from the UK Biobank (UKB) and DIAGRAM consortium to investigate the genetic association between T2D and CVD through phenotypic association analyses, linkage disequilibrium score (LDSC) analysis, and polygenic risk score (PRS) analysis. LDSC analysis demonstrates significant genetic associations between T2D and various CVD subtypes, including angina, heart failure (HF), myocardial infarction (MI), peripheral vascular disease (PVD), and stroke. Although the genetic association between T2D and atrial fibrillation (AF) was not significant, individuals in the high-T2D PRS group had a significantly increased risk of CVD. These findings suggest a common genetic basis and suggest that genetic susceptibility to T2D may be a potential predictor of CVD risk.

While the high-dimensional biological data have provided unprecedented data resources for the identification of biomarkers, consensus is still lacking on how to best analyze them. The recently developed Gaussian mirror (GM) and Model-X (MX) knockoff-based methods have much related model assumptions, which makes them appealing for the detection of new biomarkers. However, there are no guidelines for their practical use. In this research, we systematically compared the performance of MX-based and GM methods, where the impacts of the distribution of explanatory variables, their relatedness and the signal-to-noise ratio were evaluated. MX with knockoff generated using the second-order approximates (MX-SO) has the best performance as compared to other MX-based methods. MX-SO and GM have similar levels of power and computational speed under most of the simulations, but GM is more robust in the control of false discovery rate (FDR). In particular, MX-SO can only control the FDR well when there are weak correlations among explanatory variables and the sample size is at least moderate. On the contrary, GM can have the desired FDR as long as explanatory variables are not highly correlated. We further used GM and MX-based methods to detect biomarkers that are associated with the Alzheimer’s disease-related PET-imaging trait and the Parkinson’s disease-related T-tau of cerebrospinal fluid. We found that MX-based and GM methods are both powerful for the analysis of big biological data. Although genes selected from MX-based methods are more similar as compared to those from the GM method, both MX-based and GM methods can identify the well-known disease-associated genes for each disease. While MX-based methods can have a slightly higher power than that of the GM method, it is less robust, especially for data with small sample sizes, unknown distributions, and high correlations.

Brain imaging outcomes are important for Alzheimer’s disease (AD) detection, and their prediction based on both genetic and demographic risk factors can facilitate the ongoing prevention and treatment of AD. Existing studies have identified numerous significantly AD-associated SNPs. However, how to make the best use of them for prediction analyses remains unknown. In this research, we first explored the relationship between genetic architecture and prediction accuracy of linear mixed models via visualizing the Manhattan plots generated based on the data obtained from the Wellcome Trust Case Control Consortium, and then constructed prediction models for eleven AD-related brain imaging outcomes using data from United Kingdom Biobank and Alzheimer’s Disease Neuroimaging Initiative studies. We found that the simple Manhattan plots can be informative for the selection of prediction models. For traits that do not exhibit any significant signals from the Manhattan plots, the simple genomic best linear unbiased prediction (gBLUP) model is recommended due to its robust and accurate prediction performance as well as its computational efficiency. For diseases and traits that show spiked signals on the Manhattan plots, the latent Dirichlet process regression is preferred, as it can flexibly accommodate both the oligogenic and omnigenic models. For the prediction of AD-related traits, the Manhattan plots suggest their polygenic nature, and gBLUP has achieved robust performance for all these traits. We found that for these AD-related traits, genetic factors themselves only explain a very small proportion of the heritability, and the well-known AD risk factors can substantially improve the prediction model.