Bayesian and Machine Learning Models for Genomic Prediction of Anterior Cruciate Ligament Rupture in the Canine Model

Baker, Louise; Momen, Mehdi; Chan, Kore; Bollig, Nathan; Lopes, Fernando Brito; Rosa, Guilherme J. M.; Todhunter, Rory J.; Binversie, Emily E.; Sample, Susannah J.; Muir, Peter

doi:10.1534/g3.120.401244

Cited by 15 publications

(8 citation statements)

References 51 publications

(74 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The genome-based selection enables early recruitment of breeding candidates and hence, potentially reducing generation time in striped catfish as expected to reduce at least a half of generation interval in dairy cattle ( Hayes et al 2009 ). Our results are consistent with those reported in farmed animal ( Baker et al 2020 ), livestock ( González-Recio and Forni 2011 ; Li et al 2018 ), and plants ( Montesinos-López et al 2018 , 2019 ; Zingaretti et al 2020 ). Despite the superiority of the machine learning methods ( i.e.…”

Section: Discussionsupporting

confidence: 92%

Accuracies of genomic predictions for disease resistance of striped catfish to Edwardsiella ictaluri using artificial intelligence algorithms

Phuc

Oanh

et al. 2021

G3 Genes|Genomes|Genetics

View full text Add to dashboard Cite

Assessments of genomic prediction accuracies using artificial intelligence (AI) algorithms (i.e.,, machine and deep learning methods) are currently not available or very limited in aquaculture species. The principal aim of this study was to examine the predictive performance of these new methods for disease resistance to Edwardsiella ictaluri in a population of striped catfish Pangasianodon hypophthalmus and to make comparisons with four common methods, i.e.,, pedigree-based best linear unbiased prediction (PBLUP), genomic-based best linear unbiased prediction (GBLUP), single-step GBLUP (ssGBLUP) and a non-linear Bayesian approach (notably BayesR). Our analyses using machine learning (i.e.,, ML-KAML) and deep learning (i.e.,, DL-MLP and DL-CNN) together with the four common methods (PBLUP, GBLUP, ssGBLUP and BayesR) were conducted for two main disease resistance traits (i.e.,, survival status coded as 0 and 1 and survival time, i.e.,, days that the animals were still alive after the challenge test) in a pedigree consisting of 560 individual animals (490 offspring and 70 parents) genotyped for 14,154 Single Nucleotide Polymorphism (SNPs). The results using 6,470 SNPs after quality control showed that machine learning methods outperformed PBLUP, GBLUP and ssGBLUP, with the increases in the prediction accuracies for both traits by 9.1–15.4%. However, the prediction accuracies obtained from machine learning methods were comparable to those estimated using BayesR. Imputation of missing genotypes using AlphaFamImpute increased the prediction accuracies by 5.3–19.2% in all the methods and data used. On the other hand, there were insignificant decreases (0.3–5.6%) in the prediction accuracies for both survival status and survival time when multivariate models were used in comparison to univariate analyses. Interestingly, the genomic prediction accuracies based on only highly significant SNPs (P < 0.00001, 318 - 400 SNPs for survival status and 1,362–1,589 SNPs for survival time) were somewhat lower (0.3 to 15.6%) than those obtained from the whole set of 6,470 SNPs. In most of our analyses, the accuracies of genomic prediction were somewhat higher for survival time than survival status (0/1 data). It is concluded that although there are prospects for the application of genomic selection to increase disease resistance to Edwardsiella ictaluri in striped catfish breeding programs, further evaluation of these methods should be made in independent families/populations when more data are accumulated in future generations to avoid possible biases in the genetic parameters estimates and prediction accuracies for the disease resistant traits studied in this population of striped catfish P. hypophthalmus.

show abstract

Section: Discussionsupporting

confidence: 92%

Accuracies of genomic predictions for disease resistance of striped catfish to Edwardsiella ictaluri using artificial intelligence algorithms

Phuc

Oanh

et al. 2021

G3 Genes|Genomes|Genetics

View full text Add to dashboard Cite

show abstract

“…The genomic selection can also shorten the breeding cycle of striped catfish as expected to reduce at least a half of generation interval in dairy cattle (Hayes et al 2009). Our results are consistent with those reported in farmed animal (Baker et al 2020), livestock (Li et al 2018; González-Recio and Forni 2011) and plants (Montesinos-López et al 2019; Montesinos-López et al 2018; Zingaretti et al 2020). Despite the superiority of the machine learning methods (i.e., ML-KAML) to PBLUP, GBLUP and ssGBLUP, they had similar predictive power to BayesR for both traits in our study.…”

Section: Discussionsupporting

confidence: 93%

Accuracies of genomic predictions for disease resistance of striped catfish to Edwardsiella ictaluri using artificial intelligence algorithms

Phuc²,

Oanh³

et al. 2021

Preprint

View full text Add to dashboard Cite

Assessments of genomic prediction accuracies using machine and deep learning methods are currently not available or very limited in aquaculture species. The principal aim of this study was to examine the predictive performance of these new methods for disease resistance to Edwardsiella ictaluri in a population of striped catfish Pangasianodon hypophthalmus and to make comparisons with four common methods, i.e., pedigree-based best linear unbiased prediction (PBLUP), genomic-based best linear unbiased prediction (GBLUP), single-step GBLUP (ssGBLUP) and a non-linear Bayesian approach (notably BayesR). Our analyses using machine learning (i.e., KAML) and deep learning (i.e., DeepGP) together with the four common methods (PBLUP, GBLUP, ssGBLUP and BayesR) were conducted for two main disease resistance traits (i.e., survival status coded as 0 and 1 and survival time, i.e., days that the animals were still alive after the challenge test) in a pedigree consisting of 560 individual animals (490 offspring and 70 parents) genotyped for 14,154 Single Nucleotide Polymorphism (SNPs). The results showed that KAML outperformed GBLUP and ssGBLUP, with the increases in the prediction accuracies for both traits by 5.1 - 47.7%. However, the prediction accuracies obtained from KAML were comparable to those estimated using BayesR. Imputation of missing genotypes using AlphaFamImpute increased the prediction accuracies by 0.2 33.2% in all the methods used. On the other hand, there were no significant increases in the prediction accuracies for both survival status and survival time when multivariate models were used in comparison to univariate analyses. Interestingly, the genomic prediction accuracies based on only highly significant SNPs (P < 0.00001) were not largely different from those obtained from the whole set of 14,154 SNPs. In all our analyses, the accuracies of genomic prediction were somewhat higher for survival time than survival status (0/1 data). It is concluded that there are prospects for the application of genomic selection to increase disease resistance to Edwardsiella ictaluri in striped catfish breeding programs

show abstract

“…The GBLUP method assumes that each marker has a genetic effect on the target trait, while the BayesC approach assumes that only some markers have a genetic effect on the trait. The results in this study indicated that the average prediction accuracy from cross-validation was not significantly different between GBLUP and BayesC in CHD and RCCL, which is consistent with previous studies ( Zhu et al, 2012 ; Sánchez-Molano et al, 2014 ; Sánchez-Molano et al, 2015 ; Baker et al, 2020 ).…”

Section: Discussionsupporting

confidence: 92%

Genomic Prediction of Two Complex Orthopedic Traits Across Multiple Pure and Mixed Breed Dogs

Jiang

Hayward

et al. 2021

Front. Genet.

View full text Add to dashboard Cite

Canine hip dysplasia (CHD) and rupture of the cranial cruciate ligament (RCCL) are two complex inherited orthopedic traits of dogs. These two traits may occur concurrently in the same dog. Genomic prediction of these two diseases would benefit veterinary medicine, the dog’s owner, and dog breeders because of their high prevalence, and because both traits result in painful debilitating osteoarthritis in affected joints. In this study, 842 unique dogs from 6 breeds with hip and stifle phenotypes were genotyped on a customized Illumina high density 183 k single nucleotide polymorphism (SNP) array and also analyzed using an imputed dataset of 20,487,155 SNPs. To implement genomic prediction, two different statistical methods were employed: Genomic Best Linear Unbiased Prediction (GBLUP) and a Bayesian method called BayesC. The cross-validation results showed that the two methods gave similar prediction accuracy (r = 0.3–0.4) for CHD (measured as Norberg angle) and RCCL in the multi-breed population. For CHD, the average correlation of the AUC was 0.71 (BayesC) and 0.70 (GBLUP), which is a medium level of prediction accuracy and consistent with Pearson correlation results. For RCCL, the correlation of the AUC was slightly higher. The prediction accuracy of GBLUP from the imputed genotype data was similar to the accuracy from DNA array data. We demonstrated that the genomic prediction of CHD and RCCL with DNA array genotype data is feasible in a multiple breed population if there is a genetic connection, such as breed, between the reference population and the validation population. Albeit these traits have heritability of about one-third, higher accuracy is needed to implement in a natural population and predicting a complex phenotype will require much larger number of dogs within a breed and across breeds. It is possible that with higher accuracy, genomic prediction of these orthopedic traits could be implemented in a clinical setting for early diagnosis and treatment, and the selection of dogs for breeding. These results need continuous improvement in model prediction through ongoing genotyping and data sharing. When genomic prediction indicates that a dog is susceptible to one of these orthopedic traits, it should be accompanied by clinical and radiographic screening at an acceptable age with appropriate follow-up.

show abstract

Bayesian and Machine Learning Models for Genomic Prediction of Anterior Cruciate Ligament Rupture in the Canine Model

Cited by 15 publications

References 51 publications

Accuracies of genomic predictions for disease resistance of striped catfish to Edwardsiella ictaluri using artificial intelligence algorithms

Accuracies of genomic predictions for disease resistance of striped catfish to Edwardsiella ictaluri using artificial intelligence algorithms

Accuracies of genomic predictions for disease resistance of striped catfish to Edwardsiella ictaluri using artificial intelligence algorithms

Genomic Prediction of Two Complex Orthopedic Traits Across Multiple Pure and Mixed Breed Dogs

Contact Info

Product

Resources

About