A Comparison of Three Machine Learning Methods for Multivariate Genomic Prediction Using the Sparse Kernels Method (SKM) Library

Abstract

Genomic selection (GS) changed the way plant breeders select genotypes. GS takes advantage of phenotypic and genotypic information to training a statistical machine learning model, which is used to predict phenotypic (or breeding) values of new lines for which only genotypic information is available. Therefore, many statistical machine learning methods have been proposed for this task. Multi-trait (MT) genomic prediction models take advantage of correlated traits to improve prediction accuracy. Therefore, some multivariate statistical machine learning methods are popular for GS. In this paper, we compare the prediction performance of three MT methods: the MT genomic best linear unbiased predictor (GBLUP), the MT partial least squares (PLS) and the multi-trait random forest (RF) methods. Benchmarking was performed with six real datasets. We found that the three investigated methods produce similar results, but under predictors with genotype (G) and environment (E), that is, E + G, the MT GBLUP achieved superior performance, whereas under predictors E + G + genotypeenvironment (GE) and G + GE, random forest achieved the best results. We also found that the best predictions were achieved under the predictors E + G and E + G + GE. Here, we also provide the R code for the implementation of these three statistical machine learning methods in the sparse kernel method (SKM) library, which offers not only options for single-trait prediction with various statistical machine learning methods but also some options for MT predictions that can help to capture improved complex patterns in datasets that are common in genomic selection.

MSXFGP: combining improved sparrow search algorithm with XGBoost for enhanced genomic prediction

“…Japonica was studied by Monteverde et al [ 29 , 30 ]. The genotype data was obtained using Genotyping-by-Sequencing (GBS), and missing data was processed and filled using the FILLIN algorithm in TASSEL 5.0.…”

“…Pandey and his team used the Affymetrix GeneTitan platform to extract the genomic information of 318 lines of Groundnut and perform SNP genotyping [ 29 , 31 ]. After quality control, each genotype contained 8268 SNP markers, which were coded as 0, 1, and 2.…”

Predicting Abnormal Respiratory Patterns in Older Adults Using Supervised Machine Learning on Internet of Medical Things Respiratory Frequency Data

“…We compared the performance of the three models to discern the most effective algorithm for our predictive task [31]. This process guided us toward selecting the best model for predicting abnormal respiratory patterns in older adults.…”

A Multi-Trait Gaussian Kernel Genomic Prediction Model under Three Tunning Strategies

“…Genomic selection (GS) is frequently used for genetic improvement and has many advantages over phenotype-based selection [ 1 ]. Nevertheless, breeders face an adversity of challenges to improve the accuracy of the GS methodology, similar to multi-trait (MT) genomic prediction models, which take advantage of correlated traits to improve prediction accuracy [ 2 ] under multiple environments. Consequently, to accurately predict breeding values or phenotypic values is a challenge of primordial interest in GS, as the goal is to increase genetic gain.…”

“…Moreover, empirical evidence has shown that MT models are more efficient than single-trait (ST) models [ 13 ]. Some reasons why MT models are chosen over ST models [ 14 ] are that: (1) they capture complex relationships between correlated traits in a more efficient way, (2) they take advantage of the degree of correlation between lines and traits, (3) MT models offer better interpretability than ST models, (4) they are computationally more parsimonious to train than ST models, (5) more precise estimates of random effects of lines and genetic correlations between traits are obtained, which allows for improvement of the index selection, (6) they become more efficient for indirect selection as the precision of genetic correlation parameter estimates increases, and (7) they improve hypothesis testing because they reduce type I and II errors [ 2 ] due to a more precise estimates of parameters.…”