Predicting Phenotypes From Novel Genomic Markers Using Deep Learning
Preprint
Abstract
Genomic selection models use Single Nucleotide Polymorphism (SNP) markers to predict phenotypes. However, these predictive models face challenges due to the high dimensionality of genome-wide SNP marker data. Thanks to recent breakthroughs in DNA sequencing and decreased sequencing cost, the study of novel genomic variants such as Structural Variations (SVs) and Transposable Elements (TEs) become increasingly prevalent. In this paper, we develop a deep convolutional neural network model, NovGMDeep , to predict phenotypes using SVs and TEs markers for genomic selection. The proposed model is trained and tested on samples of A. thaliana and O. sativa using k -fold cross-validation. The prediction accuracy is evaluated using Pearson’s Correlation Coefficient (PCC), Mean Absolute Error (MAE), and Standard Deviation (SD) of MAE. The predicted results showed higher correlation when the model is trained with SVs and TEs than with SNPs. NovGMDeep also has higher prediction accuracy when comparing with conventional statistical models. This work sheds light on the unrecognized function of SVs and TEs in genotype-to-phenotype associations, as well as their extensive significance and value in crop development.Keywords
All Related Versions
- Published version: Bioinformatics Advances, 3 (1), vbad028.
This publication has 31 references indexed in Scilit:
- Marker utility of transposable elements for plant genetics, breeding, and ecology: a reviewGenes & Genomics, 2014
- Applications of Population Genetics to Animal Breeding, from Wright, Fisher and Lush to Genomic PredictionGenetics, 2014
- Genomic Best Linear Unbiased Prediction (gBLUP) for the Estimation of Genomic Breeding Values2013
- Ridge Regression and Other Kernels for Genomic Selection with R Package rrBLUPThe Plant Genome, 2011
- Structural Variation in the Human Genome and its Role in DiseaseAnnual Review of Medicine, 2010
- GSE is now an open access journal published by BioMed CentralGenetics Selection Evolution, 2009
- Analysis of the platypus genome suggests a transposon origin for mammalian imprintingGenome Biology, 2009
- Genome-wide analysis of the interaction between the endosymbiotic bacterium Wolbachia and its Drosophila hostBMC Genomics, 2008
- Phenotypic differences in genetically identical organisms: the epigenetic perspectiveHuman Molecular Genetics, 2005
- Learning representations by back-propagating errorsNature, 1986