Evaluating dimensionality reduction for genomic prediction

Authors

Vamsi Manthena, University of Nebraska-Lincoln
Diego Jarquín, University of Florida
Rajeev K. Varshney, Murdoch University, International Crops Research Institute for the Semi-Arid Tropics
Manish Roorkiwal, International Crops Research Institute for the Semi-Arid Tropics, United Arab Emirates University
Girish Prasad Dixit, ICAR-Indian Institute of Pulses Research
Chellapilla Bharadwaj, ICAR-Indian Agricultural Research Institute
Reka Howard, University of Nebraska-LincolnFollow

Date of this Version

10-14-2022

Citation

Manthena V, Jarquín D, Varshney RK, Roorkiwal M, Dixit GP, Bharadwaj C and Howard R (2022), Evaluating dimensionality reduction for genomic prediction. Front. Genet. 13:958780. doi: 10.3389/fgene.2022.958780

Comments

Open access

Abstract

The development of genomic selection (GS) methods has allowed plant breeding programs to select favorable lines using genomic data before performing field trials. Improvements in genotyping technology have yielded high-dimensional genomic marker data which can be difficult to incorporate into statistical models. In this paper, we investigated the utility of applying dimensionality reduction (DR) methods as a pre-processing step for GS methods. We compared five DR methods and studied the trend in the prediction accuracies of each method as a function of the number of features retained. The effect of DR methods was studied using three models that involved the main effects of line, environment, marker, and the genotype by environment interactions. The methods were applied on a real data set containing 315 lines phenotyped in nine environments with 26,817 markers each. Regardless of the DR method and prediction model used, only a fraction of features was sufficient to achieve maximum correlation. Our results underline the usefulness of DR methods as a key pre-processing step in GS models to improve computational efficiency in the face of ever-increasing size of genomic data.