Modeling between-study heterogeneity for improved replicability in gene signature selection and clinical prediction
From MaRDI portal
Publication:5120652
Abstract: In the genomic era, the identification of gene signatures associated with disease is of significant interest. Such signatures are often used to predict clinical outcomes in new patients and aid clinical decision-making. However, recent studies have shown that gene signatures are often not replicable. This occurrence has practical implications regarding the generalizability and clinical applicability of such signatures. To improve replicability, we introduce a novel approach to select gene signatures from multiple datasets whose effects are consistently non-zero and account for between-study heterogeneity. We build our model upon some rank-based quantities, facilitating integration over different genomic datasets. A high dimensional penalized Generalized Linear Mixed Model (pGLMM) is used to select gene signatures and address data heterogeneity. We compare our method to some commonly used strategies that select gene signatures ignoring between-study heterogeneity. We provide asymptotic results justifying the performance of our method and demonstrate its advantage in the presence of heterogeneity through thorough simulation studies. Lastly, we motivate our method through a case study subtyping pancreatic cancer patients from four gene expression studies.
Recommendations
- Multi-subgroup gene screening using semi-parametric hierarchical mixture models and the optimal discovery procedure: application to a randomized clinical trial in multiple myeloma
- An integrative pathway-based clinical-genomic model for cancer survival prediction
- Applications of Bayesian gene selection and classification with mixtures of generalized singular g-priors
- Something Borrowed, Something New: Precise Prediction of Outcomes from Diverse Genomic Profiles
- Incorporation of gene exchangeabilities improves the reproducibility of gene set rankings
Cites work
- An adaptively weighted statistic for detecting differential gene expression when combining multiple transcriptomic studies
- Bayesian sensitivity analysis of statistical models with missing data
- Coordinate descent algorithms for nonconvex penalized regression, with applications to biological feature selection
- Fixed and Random Effects Selection in Mixed Effects Models
- Frozen robust multiarray analysis (fRMA)
- Group descent algorithms for nonconvex penalized linear and logistic regression models with grouped predictors
- Joint variable selection for fixed and random effects in linear mixed-effects models
- Maximum Likelihood Algorithms for Generalized Linear Mixed Models
- Meta-analysis based variable selection for gene expression data
- Model Selection and Estimation in Regression with Grouped Variables
- Nearly unbiased variable selection under minimax concave penalty
- Random Effects Selection in Linear Mixed Models
- Rank discriminants for predicting phenotypes from RNA expression
- Tuning parameter selectors for the smoothly clipped absolute deviation method
- Variable selection in linear mixed effects models
- Variable Selection via Nonconcave Penalized Likelihood and its Oracle Properties
Cited in
(9)- Hierarchical resampling for bagging in multistudy prediction with applications to human neurochemical sensing
- Something Borrowed, Something New: Precise Prediction of Outcomes from Diverse Genomic Profiles
- Addressing patient heterogeneity in disease predictive model development
- Defining replicability of prediction rules
- Optimal ensemble construction for multistudy prediction with applications to mortality estimation
- Cross-validation approaches for multi-study predictions
- Efficient computation of high-dimensional penalized piecewise constant hazard random effects models
- Meta-analyzing multiple functional data with functional fixed-effects model
- Multi-task learning for sparsity pattern heterogeneity: statistical and computational perspectives
This page was built for publication: Modeling between-study heterogeneity for improved replicability in gene signature selection and clinical prediction
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5120652)
