1
|
Pedrosa VB, Chen SY, Gloria LS, Doucette JS, Boerman JP, Rosa GJM, Brito LF. Machine learning methods for genomic prediction of cow behavioral traits measured by automatic milking systems in North American Holstein cattle. J Dairy Sci 2024; 107:4758-4771. [PMID: 38395400 DOI: 10.3168/jds.2023-24082] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/12/2023] [Accepted: 01/18/2024] [Indexed: 02/25/2024]
Abstract
Identifying genome-enabled methods that provide more accurate genomic prediction is crucial when evaluating complex traits such as dairy cow behavior. In this study, we aimed to compare the predictive performance of traditional genomic prediction methods and deep learning algorithms for genomic prediction of milking refusals (MREF) and milking failures (MFAIL) in North American Holstein cows measured by automatic milking systems (milking robots). A total of 1,993,509 daily records from 4,511 genotyped Holstein cows were collected by 36 milking robot stations. After quality control, 57,600 SNPs were available for the analyses. Four genomic prediction methods were considered: Bayesian least absolute shrinkage and selection operator (LASSO), multiple layer perceptron (MLP), convolutional neural network (CNN), and GBLUP. We implemented the first 3 methods using the Keras and TensorFlow libraries in Python (v.3.9) but the GBLUP method was implemented using the BLUPF90+ family programs. The accuracy of genomic prediction (mean square error) for MREF and MFAIL was 0.34 (0.08) and 0.27 (0.08) based on LASSO, 0.36 (0.09) and 0.32 (0.09) for MLP, 0.37 (0.08) and 0.30 (0.09) for CNN, and 0.35 (0.09) and 0.31(0.09) based on GBLUP, respectively. Additionally, we observed a lower reranking of top selected individuals based on the MLP versus CNN methods compared with the other approaches for both MREF and MFAIL. Although the deep learning methods showed slightly higher accuracies than GBLUP, the results may not be sufficient to justify their use over traditional methods due to their higher computational demand and the difficulty of performing genomic prediction for nongenotyped individuals using deep learning procedures. Overall, this study provides insights into the potential feasibility of using deep learning methods to enhance genomic prediction accuracy for behavioral traits in livestock. Further research is needed to determine their practical applicability to large dairy cattle breeding programs.
Collapse
Affiliation(s)
- Victor B Pedrosa
- Department of Animal Sciences, Purdue University, West Lafayette, IN 47907
| | - Shi-Yi Chen
- Department of Animal Sciences, Purdue University, West Lafayette, IN 47907; Farm Animal Genetic Resources Exploration and Innovation Key Laboratory of Sichuan Province, Sichuan Agricultural University, Chengdu, Sichuan, 611130, China
| | - Leonardo S Gloria
- Department of Animal Sciences, Purdue University, West Lafayette, IN 47907
| | - Jarrod S Doucette
- Agriculture Information Technology (AgIT), Purdue University, West Lafayette, IN 47907
| | | | - Guilherme J M Rosa
- Department of Animal and Dairy Sciences, University of Wisconsin-Madison, Madison, WI, 53706
| | - Luiz F Brito
- Department of Animal Sciences, Purdue University, West Lafayette, IN 47907.
| |
Collapse
|
2
|
Yan X, Li J, He L, Chen O, Wang N, Wang S, Wang X, Wang Z, Su R. Accuracy of Genomic prediction for fleece traits in Inner Mongolia Cashmere goats. BMC Genomics 2024; 25:349. [PMID: 38589806 PMCID: PMC11000370 DOI: 10.1186/s12864-024-10249-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/17/2023] [Accepted: 03/22/2024] [Indexed: 04/10/2024] Open
Abstract
The fleece traits are important economic traits of goats. With the reduction of sequencing and genotyping cost and the improvement of related technologies, genomic selection for goats has become possible. The research collect pedigree, phenotype and genotype information of 2299 Inner Mongolia Cashmere goats (IMCGs) individuals. We estimate fixed effects, and compare the estimates of variance components, heritability and genomic predictive ability of fleece traits in IMCGs when using the pedigree based Best Linear Unbiased Prediction (ABLUP), Genomic BLUP (GBLUP) or single-step GBLUP (ssGBLUP). The fleece traits considered are cashmere production (CP), cashmere diameter (CD), cashmere length (CL) and fiber length (FL). It was found that year of production, sex, herd and individual ages had highly significant effects on the four fleece traits (P < 0.01). All of these factors should be considered when the genetic parameters of fleece traits in IMCGs are evaluated. The heritabilities of FL, CL, CP and CD with ABLUP, GBLUP and ssGBLUP methods were 0.26 ~ 0.31, 0.05 ~ 0.08, 0.15 ~ 0.20 and 0.22 ~ 0.28, respectively. Therefore, it can be inferred that the genetic progress of CL is relatively slow. The predictive ability of fleece traits in IMCGs with GBLUP (56.18% to 69.06%) and ssGBLUP methods (66.82% to 73.70%) was significantly higher than that of ABLUP (36.73% to 41.25%). For the ssGBLUP method is significantly (29% ~ 33%) higher than that with ABLUP, and which is slightly (4% ~ 14%) higher than that of GBLUP. The ssGBLUP will be as an superiors method for using genomic selection of fleece traits in Inner Mongolia Cashmere goats.
Collapse
Affiliation(s)
- Xiaochun Yan
- College of Animal Science, Inner Mongolia Agricultural University, Hohhot, Inner Mongolia Autonomous Region, 010018, China
| | - Jinquan Li
- College of Animal Science, Inner Mongolia Agricultural University, Hohhot, Inner Mongolia Autonomous Region, 010018, China
- Inner Mongolia Key Laboratory of Sheep & Goat Genetics Breeding and Reproduction, Hohhot, Inner Mongolia Autonomous Region, 010018, China
- Key Laboratory Of Mutton Sheep & Goat Genetics And Breeding, Ministry of Agriculture And Rural Affairs, Hohhot, Inner Mongolia Autonomous Region, 010018, China
- Engineering Research Centre for Goat Genetics and Breeding, Inner Mongolia Autonomous Region, Hohhot, Inner Mongolia Autonomous Region, 010018, China
| | - Libing He
- Inner Mongolia Jinlai Livestock Technology Co., Ltd, Hohhot, Inner Mongolia Autonomous Region, 010018, China
| | - Oljibilig Chen
- Inner Mongolia Yiwei White Cashmere Goat Co., Ltd, Ordos, Inner Mongolia Autonomous Region, 010018, China
| | - Na Wang
- Inner Mongolia Yiwei White Cashmere Goat Co., Ltd, Ordos, Inner Mongolia Autonomous Region, 010018, China
| | - Shuai Wang
- Inner Mongolia Yiwei White Cashmere Goat Co., Ltd, Ordos, Inner Mongolia Autonomous Region, 010018, China
| | - Xiuyan Wang
- Livestock Improvement Center of Alxa Left Banner, Alxa League, Inner Mongolia Autonomous Region, 75000, China
| | - Zhiying Wang
- College of Animal Science, Inner Mongolia Agricultural University, Hohhot, Inner Mongolia Autonomous Region, 010018, China.
| | - Rui Su
- College of Animal Science, Inner Mongolia Agricultural University, Hohhot, Inner Mongolia Autonomous Region, 010018, China.
| |
Collapse
|
3
|
Yan X, Zhang J, Li J, Wang N, Su R, Wang Z. Impacts of reference population size and methods on the accuracy of genomic prediction for fleece traits in Inner Mongolia Cashmere Goats. Front Vet Sci 2024; 11:1325831. [PMID: 38374988 PMCID: PMC10875101 DOI: 10.3389/fvets.2024.1325831] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/22/2023] [Accepted: 01/08/2024] [Indexed: 02/21/2024] Open
Abstract
Introduction Inner Mongolia Cashmere Goats (IMCGs) are famous for its cashmere quality and it's a unique genetic resource in China. Therefore, it is necessary to use genomic selection to improve the accuracy of selection for fleece traits in Inner Mongolia cashmere goats. The aim of this study was to determine the effect of methods (GBLUP, BayesA, BayesB, Bayesian LASSO, Bayesian Ridge Region) and the reference population size on accuracy of genomic selection in IMCGs. Methods This study fully utilizes the pedigree and phenotype records of fleece traits in 2255 individuals, genotype of 50794 SNPs after quality control, and environmental data to perform genomic selection of fleece traits. Then GBLUP and Bayes series methods (BayesA, BayesB, Bayesian LASSO, Bayesian Ridge Region) were used to perform estimates of genetic parameter and genomic breeding value. And the accuracy of genomic estimated breeding value (GEBV) is evaluated using the five-fold cross validation method. And the analysis of variance and multiple comparison methods were used to determine the best method for genomic selection in fleece traits of IMCGs. Further the different reference population sizes (500, 1000, 1500, and 2000) was set. Then the best method was applied to estimate genome breeding values, and evaluate the impact of reference population sizes on the accuracy of genome selection for fleece traits in IMCGs. Results It was found that the genomic prediction accuracy for each fleece trait in IMCGs by GBLUP method is highest, and it is significantly higher than that obtained by Bayesian method. The accuracy of breeding value estimation is 58.52% -68.49%. Also, it was found that the size of the reference population has a significant impact on the accuracy of genome prediction of fleece traits. When the reference population size is 2000, the accuracy of genomic prediction for each fleece trait is significantly higher than other levels, with accuracy of 55.47% -67.87%. This provides a theoretical basis for design a reasonable genome selection plan for Inner Mongolia cashmere goats in the later stag.
Collapse
Affiliation(s)
- Xiaochun Yan
- College of Animal Science, Inner Mongolia Agricultural University, Hohhot, China
| | - Jiaxin Zhang
- College of Animal Science, Inner Mongolia Agricultural University, Hohhot, China
| | - Jinquan Li
- College of Animal Science, Inner Mongolia Agricultural University, Hohhot, China
- Inner Mongolia Key Laboratory of Sheep and Goat Genetics Breeding and Reproduction, Hohhot, China
- Key Laboratory of Mutton Sheep and Goat Genetics and Breeding, Ministry of Agriculture And Rural Affairs, Hohhot, China
- Engineering Research Centre for Goat Genetics and Breeding, Inner Mongolia Autonomous Region, Hohhot, China
| | - Na Wang
- Inner Mongolia Yiwei White Cashmere Goat Co., Ltd., Hohhot, China
| | - Rui Su
- College of Animal Science, Inner Mongolia Agricultural University, Hohhot, China
| | - Zhiying Wang
- College of Animal Science, Inner Mongolia Agricultural University, Hohhot, China
| |
Collapse
|
4
|
Freitas LA, Savegnago RP, Alves AAC, Stafuzza NB, Pedrosa VB, Rocha RA, Rosa GJM, Paz CCP. Genome-enabled prediction of indicator traits of resistance to gastrointestinal nematodes in sheep using parametric models and artificial neural networks. Res Vet Sci 2024; 166:105099. [PMID: 38091815 DOI: 10.1016/j.rvsc.2023.105099] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/12/2023] [Revised: 11/15/2023] [Accepted: 11/19/2023] [Indexed: 01/01/2024]
Abstract
This study aimed to assess the predictive ability of parametric models and artificial neural network method for genomic prediction of the following indicator traits of resistance to gastrointestinal nematodes in Santa Inês sheep: packed cell volume (PCV), fecal egg count (FEC), and Famacha© method (FAM). After quality control, the number of genotyped animals was 551 (PCV), 548 (FEC), and 565 (FAM), and 41,676 SNP. The average prediction accuracy (ACC) calculated by Pearson correlation between observed and predicted values and mean squared errors (MSE) were obtained using genomic best unbiased linear predictor (GBLUP), BayesA, BayesB, Bayesian least absolute shrinkage and selection operator (BLASSO), and Bayesian regularized artificial neural network (three and four hidden neurons, BRANN_3 and BRANN_4, respectively) in a 5-fold cross-validation technique. The average ACC varied from moderate to high according to the trait and models, ranging between 0.418 and 0.546 (PCV), between 0.646 and 0.793 (FEC), and between 0.414 and 0.519 (FAM). Parametric models presented nearly the same ACC and MSE for the studied traits and provided better accuracies than BRANN. The GBLUP, BayesA, BayesB and BLASSO models provided better accuracies than the BRANN_3 method, increasing by around 23% for PCV, and 18.5% for FEC. In conclusion, parametric models are suitable for genome-enabled prediction of indicator traits of resistance to gastrointestinal nematodes in sheep. Due to the small differences in accuracy found between them, the use of the GBLUP model is recommended due to its lower computational costs.
Collapse
Affiliation(s)
- L A Freitas
- University of Sao Paulo, Department of Genetics, Ribeirão Preto, São Paulo 14049-900, Brazil; University of Wisconsin, Department of Animal and Dairy Sciences, Madison 53706, USA.
| | - R P Savegnago
- Michigan State University, Department of Animal Science, MI 48864, USA.
| | - A A C Alves
- University of Wisconsin, Department of Animal and Dairy Sciences, Madison 53706, USA.
| | - N B Stafuzza
- Sustainable Livestock Research Center, Animal Science Institute, São José do Rio Preto, São Paulo 15130-000, Brazil
| | - V B Pedrosa
- State University of Ponta Grossa, Ponta Grossa, Paraná 84030-900, Brazil.
| | - R A Rocha
- State University of Ponta Grossa, Ponta Grossa, Paraná 84030-900, Brazil.
| | - G J M Rosa
- University of Wisconsin, Department of Animal and Dairy Sciences, Madison 53706, USA.
| | - C C P Paz
- University of Sao Paulo, Department of Genetics, Ribeirão Preto, São Paulo 14049-900, Brazil; Sustainable Livestock Research Center, Animal Science Institute, São José do Rio Preto, São Paulo 15130-000, Brazil.
| |
Collapse
|
5
|
Haque MA, Lee YM, Ha JJ, Jin S, Park B, Kim NY, Won JI, Kim JJ. Genomic Predictions in Korean Hanwoo Cows: A Comparative Analysis of Genomic BLUP and Bayesian Methods for Reproductive Traits. Animals (Basel) 2023; 14:27. [PMID: 38200758 PMCID: PMC10778388 DOI: 10.3390/ani14010027] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/03/2023] [Revised: 12/07/2023] [Accepted: 12/18/2023] [Indexed: 01/12/2024] Open
Abstract
This study aimed to predict the accuracy of genomic estimated breeding values (GEBVs) for reproductive traits in Hanwoo cows using the GBLUP, BayesB, BayesLASSO, and BayesR methods. Accuracy estimates of GEBVs for reproductive traits were derived through fivefold cross-validation, analyzing a dataset comprising 11,348 animals and employing an Illumina Bovine 50K SNP chip. GBLUP showed an accuracy of 0.26 for AFC, while BayesB, BayesLASSO, and BayesR demonstrated values of 0.28, 0.29, and 0.29, respectively. For CI, GBLUP attained an accuracy of 0.19, whereas BayesB, BayesLASSO, and BayesR scored 0.21, 0.24, and 0.25, respectively. The accuracy for GL was uniform across GBLUP, BayesB, and BayesR at 0.31, whereas BayesLASSO showed a slightly higher accuracy of 0.33. For NAIPC, GBLUP showed an accuracy of 0.24, while BayesB, BayesLASSO, and BayesR recorded 0.22, 0.27, and 0.30, respectively. The variation in genomic prediction accuracy among methods indicated Bayesian approaches slightly outperformed GBLUP. The findings suggest that Bayesian methods, notably BayesLASSO and BayesR, offer improved predictive capabilities for reproductive traits. Future research may explore more advanced genomic approaches to enhance predictive accuracy and genetic gains in Hanwoo cattle breeding programs.
Collapse
Affiliation(s)
- Md Azizul Haque
- Department of Biotechnology, Yeungnam University, Gyeongsan 38541, Republic of Korea; (M.A.H.); (Y.-M.L.)
| | - Yun-Mi Lee
- Department of Biotechnology, Yeungnam University, Gyeongsan 38541, Republic of Korea; (M.A.H.); (Y.-M.L.)
| | - Jae-Jung Ha
- Gyeongbuk Livestock Research Institute, Yeongju 36052, Republic of Korea;
| | - Shil Jin
- Hanwoo Research Institute, National Institute of Animal Science, Pyeongchang 25340, Republic of Korea; (S.J.); (B.P.); (N.-Y.K.)
| | - Byoungho Park
- Hanwoo Research Institute, National Institute of Animal Science, Pyeongchang 25340, Republic of Korea; (S.J.); (B.P.); (N.-Y.K.)
| | - Nam-Young Kim
- Hanwoo Research Institute, National Institute of Animal Science, Pyeongchang 25340, Republic of Korea; (S.J.); (B.P.); (N.-Y.K.)
| | - Jeong-Il Won
- Hanwoo Research Institute, National Institute of Animal Science, Pyeongchang 25340, Republic of Korea; (S.J.); (B.P.); (N.-Y.K.)
| | - Jong-Joo Kim
- Department of Biotechnology, Yeungnam University, Gyeongsan 38541, Republic of Korea; (M.A.H.); (Y.-M.L.)
| |
Collapse
|
6
|
Singh V, Krause M, Sandhu D, Sekhon RS, Kaundal A. Salinity stress tolerance prediction for biomass-related traits in maize (Zea mays L.) using genome-wide markers. THE PLANT GENOME 2023; 16:e20385. [PMID: 37667417 DOI: 10.1002/tpg2.20385] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 04/05/2023] [Revised: 07/18/2023] [Accepted: 08/14/2023] [Indexed: 09/06/2023]
Abstract
Maize (Zea mays L.) is the third most important cereal crop after rice (Oryza sativa) and wheat (Triticum aestivum). Salinity stress significantly affects vegetative biomass and grain yield and, therefore, reduces the food and silage productivity of maize. Selecting salt-tolerant genotypes is a cumbersome and time-consuming process that requires meticulous phenotyping. To predict salt tolerance in maize, we estimated breeding values for four biomass-related traits, including shoot length, shoot weight, root length, and root weight under salt-stressed and controlled conditions. A five-fold cross-validation method was used to select the best model among genomic best linear unbiased prediction (GBLUP), ridge-regression BLUP (rrBLUP), extended GBLUP, Bayesian Lasso, Bayesian ridge regression, BayesA, BayesB, and BayesC. Examination of the effect of different marker densities on prediction accuracy revealed that a set of low-density single nucleotide polymorphisms obtained through filtering based on a combination of analysis of variance and linkage disequilibrium provided the best prediction accuracy for all the traits. The average prediction accuracy in cross-validations ranged from 0.46 to 0.77 across the four derived traits. The GBLUP, rrBLUP, and all Bayesian models except BayesB demonstrated comparable levels of prediction accuracy that were superior to the other modeling approaches. These findings provide a roadmap for the deployment and optimization of genomic selection in breeding for salt tolerance in maize.
Collapse
Affiliation(s)
- Vishal Singh
- Plants, Soils, and Climate, College of Agricultural and Applied Sciences, Utah State University, Logan, Utah, USA
- ICAR-Indian Institute of Maize Research, Ludhiana, Punjab, India
| | - Margaret Krause
- Plants, Soils, and Climate, College of Agricultural and Applied Sciences, Utah State University, Logan, Utah, USA
| | - Devinder Sandhu
- US Salinity Laboratory (USDA-ARS), Riverside, California, USA
| | - Rajandeep S Sekhon
- Department of Genetics and Biochemistry, Clemson University, Clemson, South Carolina, USA
| | - Amita Kaundal
- Plants, Soils, and Climate, College of Agricultural and Applied Sciences, Utah State University, Logan, Utah, USA
| |
Collapse
|
7
|
Mancin E, Mota LFM, Tuliozi B, Verdiglione R, Mantovani R, Sartori C. Improvement of Genomic Predictions in Small Breeds by Construction of Genomic Relationship Matrix Through Variable Selection. Front Genet 2022; 13:814264. [PMID: 35664297 PMCID: PMC9158133 DOI: 10.3389/fgene.2022.814264] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/13/2021] [Accepted: 03/22/2022] [Indexed: 11/13/2022] Open
Abstract
Genomic selection has been increasingly implemented in the animal breeding industry, and it is becoming a routine method in many livestock breeding contexts. However, its use is still limited in several small-population local breeds, which are, nonetheless, an important source of genetic variability of great economic value. A major roadblock for their genomic selection is accuracy when population size is limited: to improve breeding value accuracy, variable selection models that assume heterogenous variance have been proposed over the last few years. However, while these models might outperform traditional and genomic predictions in terms of accuracy, they also carry a proportional increase of breeding value bias and dispersion. These mutual increases are especially striking when genomic selection is performed with a low number of phenotypes and high shrinkage value—which is precisely the situation that happens with small local breeds. In our study, we tested several alternative methods to improve the accuracy of genomic selection in a small population. First, we investigated the impact of using only a subset of informative markers regarding prediction accuracy, bias, and dispersion. We used different algorithms to select them, such as recursive feature eliminations, penalized regression, and XGBoost. We compared our results with the predictions of pedigree-based BLUP, single-step genomic BLUP, and weighted single-step genomic BLUP in different simulated populations obtained by combining various parameters in terms of number of QTLs and effective population size. We also investigated these approaches on a real data set belonging to the small local Rendena breed. Our results show that the accuracy of GBLUP in small-sized populations increased when performed with SNPs selected via variable selection methods both in simulated and real data sets. In addition, the use of variable selection models—especially those using XGBoost—in our real data set did not impact bias and the dispersion of estimated breeding values. We have discussed possible explanations for our results and how our study can help estimate breeding values for future genomic selection in small breeds.
Collapse
Affiliation(s)
- Enrico Mancin
- Department of Agronomy, Food, Natural Resources, Animals and Environment, University of Padua, Legnaro, Italy
| | - Lucio Flavio Macedo Mota
- Department of Agronomy, Food, Natural Resources, Animals and Environment, University of Padua, Legnaro, Italy
| | - Beniamino Tuliozi
- Department of Agronomy, Food, Natural Resources, Animals and Environment, University of Padua, Legnaro, Italy
| | - Rina Verdiglione
- Department of Agronomy, Food, Natural Resources, Animals and Environment, University of Padua, Legnaro, Italy
| | - Roberto Mantovani
- Department of Agronomy, Food, Natural Resources, Animals and Environment, University of Padua, Legnaro, Italy
| | - Cristina Sartori
- Department of Agronomy, Food, Natural Resources, Animals and Environment, University of Padua, Legnaro, Italy
| |
Collapse
|