Variable prioritization in nonlinear black box methods: a genetic association case study
From MaRDI portal
Publication:2318669
centrality measuresGaussian processesgenome-wide association studiesnonlinear regressionstatistical geneticsvariable prioritization
Gaussian processes (60G15) Nonparametric regression and quantile regression (62G08) Measures of association (correlation, canonical correlation, etc.) (62H20) General nonlinear regression (62J02) Applications of statistics to biology and medical sciences; meta analysis (62P10) Genetics and epigenetics (92D10)
Abstract: The central aim in this paper is to address variable selection questions in nonlinear and nonparametric regression. Motivated by statistical genetics, where nonlinear interactions are of particular interest, we introduce a novel and interpretable way to summarize the relative importance of predictor variables. Methodologically, we develop the "RelATive cEntrality" (RATE) measure to prioritize candidate genetic variants that are not just marginally important, but whose associations also stem from significant covarying relationships with other variants in the data. We illustrate RATE through Bayesian Gaussian process regression, but the methodological innovations apply to other "black box" methods. It is known that nonlinear models often exhibit greater predictive accuracy than linear models, particularly for phenotypes generated by complex genetic architectures. With detailed simulations and two real data association mapping studies, we show that applying RATE enables an explanation for this improved performance.
Recommendations
- Bayesian variable selection regression for genome-wide association studies and other large-scale problems
- Scalable variational inference for Bayesian variable selection in regression, and its accuracy in genetic association studies
- Variable selection in Bayesian generalized linear‐mixed models: An illustration using candidate gene case‐control association studies
- Bayesian model selection in complex linear systems, as illustrated in genetic association studies
- Latent variable modeling paradigms for genotype-trait association studies
- Bayesian variable selection in structured high-dimensional covariate spaces with applications in genomics
- A Simple New Approach to Variable Selection in Regression, with Application to Genetic Fine Mapping
- Non-negative matrix factorization in genetic interaction data
- A gene-by-gene multiple comparison analysis: a predictive Bayesian approach
Cites work
- A unified framework for variance component estimation with summary statistics in genome-wide association studies
- BART: Bayesian additive regression trees
- Bayesian approximate kernel regression with variable selection
- Bayesian generalized kernel mixed models
- Bayesian variable selection regression for genome-wide association studies and other large-scale problems
- Characterizing the function space for Bayesian kernel models
- Comparison of Bayesian predictive methods for model selection
- Dynamic matrix-variate graphical models
- Gaussian processes for machine learning.
- GPU-accelerated Bayesian learning and forecasting in simultaneous graphical dynamic linear models
- scientific article; zbMATH DE number 1804115 (Why is no real title available?)
- scientific article; zbMATH DE number 3149369 (Why is no real title available?)
- scientific article; zbMATH DE number 45848 (Why is no real title available?)
- scientific article; zbMATH DE number 54139 (Why is no real title available?)
- Kernel-based approximation methods using MATLAB
- Markov-switching model selection using Kullback-Leibler divergence
- Mixtures of g Priors for Bayesian Variable Selection
- Model choice in generalised linear models: a Bayesian approach via Kullback-Leibler projections
- On the Nyström method for approximating a gram matrix for improved kernel-based learning
- Optimal predictive model selection.
- The horseshoe estimator for sparse signals
- Understanding predictive information criteria for Bayesian models
- Variable prioritization in nonlinear black box methods: a genetic association case study
Cited in
(11)- Nowcasting in a pandemic using non-parametric mixed frequency VARs
- A statistical pipeline for identifying physical features that differentiate classes of 3D shapes
- Variable prioritization in nonlinear black box methods: a genetic association case study
- Model Interpretation Through Lower-Dimensional Posterior Summarization
- Predicting clinical outcomes in glioblastoma: an application of topological and functional data analysis
- Fast, Optimal, and Targeted Predictions Using Parameterized Decision Analysis
- Non-linear dimension reduction in factor-augmented vector autoregressions
- A simple approach for local and global variable importance in nonlinear regression models
- Bayesian neural networks for macroeconomic analysis
- Gaussian Process Vector Autoregressions and Macroeconomic Uncertainty
- Calibrated Derivative-Process Sensitivity for Gaussian-Process Variable Selection
This page was built for publication: Variable prioritization in nonlinear black box methods: a genetic association case study
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2318669)
