Systematic Evaluation of Genomic Prediction Algorithms for Genomic Prediction and Breeding of Aquatic Animals

Abstract

The extensive use of genomic selection (GS) in livestock and crops has led to a series of genomic-prediction (GP) algorithms despite the lack of a single algorithm that can suit all the species and traits. A systematic evaluation of available GP algorithms is thus necessary to identify the optimal GP algorithm for selective breeding in aquaculture species. In this study, a systematic comparison of ten GP algorithms, including both traditional and machine-learning algorithms, was conducted using publicly available genotype and phenotype data of eight traits, including weight and disease resistance traits, from five aquaculture species. The study aimed to provide insights into the optimal algorithm for GP in aquatic animals. Notably, no algorithm showed the best performance in all traits. However, reproducing kernel Hilbert space (RKHS) and support-vector machine (SVM) algorithms achieved relatively high prediction accuracies in most of the tested traits. Bayes A and random forest (RF) better prevented noise interference in the phenotypic data compared to the other algorithms. The prediction performances of GP algorithms in the Crassostrea gigas dataset were improved by using a genome-wide association study (GWAS) to select subsets of significant SNPs. An R package, “ASGS,” which integrates the commonly used traditional and machine-learning algorithms for efficiently finding the optimal algorithm, was developed to assist the application of genomic selection breeding of aquaculture species. This work provides valuable information and a tool for optimizing algorithms for GP, aiding genetic breeding in aquaculture species.

Integrating Bioinformatics and Machine Learning for Genomic Prediction in Chickens

“…On the other hand, surprisingly, both locus filtering based on MAF and LD pruning appeared to have no significant effect on predictive accuracy. Within our study population, MAF was used as a preliminary criterion for judging whether loci were affected by artificial selection, although this was not precise [ 51 , 52 ]. It is generally considered that loci under strong artificial selection would show reduced polymorphism, reflected in lower MAF values [ 53 , 54 ].…”

The Future of Orthodontics: Deep Learning Technologies

“…Finally, overfitting is a prevalent problem in AI, characterized by models performing well on training data but poorly on testing data. Techniques such as enhancing data samples, data augmentation, cross-validation, and selecting appropriate algorithms can mitigate overfitting [ 83 ]. However, not all studies in this review have addressed overfitting concerns.…”

Application of Artificial Intelligence in Orthodontics: Current State and Future Perspectives

“…This means the model performs excessively well in the training datasets but shows unsatisfactory performance in the testing dataset [187]. Factors like data insufficiency, low data heterogeneity and excessive variables could all lead to overfitting [188]. Methods like improving data samples, data augmentation, regularization, cross-validation and specific algorithms have all been reported to prevent overfitting [171,[189][190][191].…”