Deep neural networks with controlled variable selection for the identification of putative causal genetic variants
- 15 September 2022
- journal article
- research article
- Published by Springer Nature in Nature Machine Intelligence
- Vol. 4 (9) , 761-771
Abstract
Deep neural networks (DNNs) have been successfully utilized in many scientific problems for their high prediction accuracy, but their application to genetic studies remains challenging due to their poor interpretability. Here we consider the problem of scalable, robust variable selection in DNNs for the identification of putative causal genetic variants in genome sequencing studies. We identified a pronounced randomness in feature selection in DNNs due to its stochastic nature, which may hinder interpretability and give rise to misleading results. We propose an interpretable neural network model, stabilized using ensembling, with controlled variable selection for genetic studies. The merit of the proposed method includes: flexible modelling of the nonlinear effect of genetic variants to improve statistical power; multiple knockoffs in the input layer to rigorously control the false discovery rate; hierarchical layers to substantially reduce the number of weight parameters and activations, and improve computational efficiency; and stabilized feature selection to reduce the randomness in identified signals. We evaluate the proposed method in extensive simulation studies and apply it to the analysis of Alzheimer’s disease genetics. We show that the proposed method, when compared with conventional linear and nonlinear methods, can lead to substantially more discoveries.Keywords
All Related Versions
Funding Information
- U.S. Department of Health & Human Services | NIH | National Institute on Aging (AG066206)
This publication has 59 references indexed in Scilit:
- Improved ancestry inference using weights from external reference panelsBioinformatics, 2013
- The mystery of missing heritability: Genetic interactions create phantom heritabilityProceedings of the National Academy of Sciences, 2012
- Efficient BackProp2012
- Epistasis and Its Implications for Personal GeneticsThe American Journal of Human Genetics, 2009
- Detecting gene–gene interactions that underlie human diseasesNature Reviews Genetics, 2009
- Epistasis — the essential role of gene interactions in the structure and evolution of genetic systemsNature Reviews Genetics, 2008
- Prevalence of Dementia in the United States: The Aging, Demographics, and Memory StudyNeuroepidemiology, 2007
- PLINK: A Tool Set for Whole-Genome Association and Population-Based Linkage AnalysesThe American Journal of Human Genetics, 2007
- Principal components analysis corrects for stratification in genome-wide association studiesNature Genetics, 2006
- Calibrating a coalescent simulation of human genome sequence variationGenome Research, 2005