A comparison of principal component regression and genomic REML for genomic prediction across populations

Abstract

BackgroundGenomic prediction faces two main statistical problems: multicollinearity and n ≪ p (many fewer observations than predictor variables). Principal component (PC) analysis is a multivariate statistical method that is often used to address these problems. The objective of this study was to compare the performance of PC regression (PCR) for genomic prediction with that of a commonly used REML model with a genomic relationship matrix (GREML) and to investigate the full potential of PCR for genomic prediction.MethodsThe PCR model used either a common or a semi-supervised approach, where PC were selected based either on their eigenvalues (i.e. proportion of variance explained by SNP (single nucleotide polymorphism) genotypes) or on their association with phenotypic variance in the reference population (i.e. the regression sum of squares contribution). Cross-validation within the reference population was used to select the optimum PCR model that minimizes mean squared error. Pre-corrected average daily milk, fat and protein yields of 1609 first lactation Holstein heifers, from Ireland, UK, the Netherlands and Sweden, which were genotyped with 50 k SNPs, were analysed. Each testing subset included animals from only one country, or from only one selection line for the UK.ResultsIn general, accuracies of GREML and PCR were similar but GREML slightly outperformed PCR. Inclusion of genotyping information of validation animals into model training (semi-supervised PCR), did not result in more accurate genomic predictions. The highest achievable PCR accuracies were obtained across a wide range of numbers of PC fitted in the regression (from one to more than 1000), across test populations and traits. Using cross-validation within the reference population to derive the number of PC, yielded substantially lower accuracies than the highest achievable accuracies obtained across all possible numbers of PC.ConclusionsOn average, PCR performed only slightly less well than GREML. When the optimal number of PC was determined based on realized accuracy in the testing population, PCR showed a higher potential in terms of achievable accuracy that was not capitalized when PC selection was based on cross-validation. A standard approach for selecting the optimal set of PC in PCR remains a challenge.Electronic supplementary materialThe online version of this article (doi:10.1186/s12711-014-0060-x) contains supplementary material, which is available to authorized users.

Near Infrared Spectroscopy technology for prediction of chemical composition of natural fresh pastures

“…PLS. The effect of various methods for extracting and selecting PCs in PCR for predicting genomic breeding values in cattle has been investigated by Dadousis et al (2014).…”

Incorporating Prior Knowledge of Principal Components in Genomic Prediction

“…They concluded that reduction in computational complexity via multivariate methods did not counterbalance their lower accuracy compared with BayesB. Accuracies of genomic predictions obtained using PCR and G-BLUP models was also investigated by Dadousis et al ( 2014 ), who reported across test datasets and traits, G-BLUP outperformed the PCR model. However, in the present study Bayesian estimation of effects and variances of PC scores led to accuracies similar to BayesB and better accuracies than PCR-Eigen where PC variances were proportional to the eigenvalues.…”

Genomic breed composition of Ningxiang pig via different SNP panels

“…Moreover, the estimation accuracy no longer improves as the SNP density increasing. The reason may be that there is a high degree of linkage disequilibrium among higher density SNPs, which is manifested as multicollinearity in statistics (Dadousis et al, 2014). There is a general correlation in the selected SNPs, and the results obtained are similar to a certain extent (Kuehn et al, 2007).…”