| Title: | ML-MAGES enables multivariate genetic association analyses with genes and effect size shrinkage |
| Journal: | Genome Research |
| Published: | 19 Nov 2025 |
| Pubmed: | https://pubmed.ncbi.nlm.nih.gov/41260926/ |
| DOI: | https://doi.org/10.1101/gr.280440.125 |
| URL: | http://genome.cshlp.org/content/early/2025/10/27/gr.280440.125.full.pdf |
Publication 18878
WARNING: the interactive features of this website use CSS3, which your browser does not support. To use the full features of this website, please update your browser.
Abstract
A fundamental goal of genetics is to identify which and how genetic variants are associated with a trait, often using the regression results from genome-wide association (GWA) studies. Important methodological challenges account for inflation in GWA effect estimates as well as in investigating more than one trait simultaneously. We leverage machine learning approaches for these two challenges, developing a computationally efficient method called ML-MAGES. First, we shrink the inflation in GWA effect sizes caused by nonindependence among variants using neural networks. We then cluster variant associations among multiple traits via variational inference. We compare the performance of shrinkage via neural networks to regularized regression and fine-mapping, two approaches used for addressing inflated effects but dealing with variants in focal regions of different sizes. Our neural network shrinkage outperforms both methods in approximating the true effect sizes in simulated data. Our infinite mixture clustering approach offers a flexible, data-driven way to distinguish different types of associations-trait-specific, shared across traits, or nonprioritized-among multiple traits based on their regularized effects. Clustering applied to our neural network shrinkage results also produces consistently higher precision and recall for distinguishing gene-level associations in simulations. We demonstrate the application of ML-MAGES on association analyses of two quantitative traits and two binary traits in the UK Biobank. Our identified associated genes from single-trait enrichment tests overlap with those having known relevant biological processes to the traits. Besides trait-specific associations, ML-MAGES identifies several variants with shared multitrait associations, suggesting putative shared genetic architecture.</p>
10 Keywords
- Cluster Analysis
- Computer Simulation
- Genome-Wide Association Study
- Humans
- Machine Learning
- Models, Genetic
- Multivariate Analysis
- Neural Networks, Computer
- Polymorphism, Single Nucleotide
- Quantitative Trait Loci
3 Authors
- Xiran Liu
- Lorin Crawford
- Sohini Ramachandran
1 Application
| Application ID | Title |
|---|---|
| 22419 | Identifying gene networks underlying complex traits in the UK Biobank |
Enabling scientific discoveries that improve human health