1
|
Zhu R, Li J, Yang J, Sun R, Yu K. In Vivo Prediction of Breast Muscle Weight in Broiler Chickens Using X-ray Images Based on Deep Learning and Machine Learning. Animals (Basel) 2024; 14:628. [PMID: 38396595 PMCID: PMC10886402 DOI: 10.3390/ani14040628] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/15/2024] [Revised: 02/09/2024] [Accepted: 02/12/2024] [Indexed: 02/25/2024] Open
Abstract
Accurately estimating the breast muscle weight of broilers is important for poultry production. However, existing related methods are plagued by cumbersome processes and limited automation. To address these issues, this study proposed an efficient method for predicting the breast muscle weight of broilers. First, because existing deep learning models struggle to strike a balance between accuracy and memory consumption, this study designed a multistage attention enhancement fusion segmentation network (MAEFNet) to automatically acquire pectoral muscle mask images from X-ray images. MAEFNet employs the pruned MobileNetV3 as the encoder to efficiently capture features and adopts a novel decoder to enhance and fuse the effective features at various stages. Next, the selected shape features were automatically extracted from the mask images. Finally, these features, including live weight, were input to the SVR (Support Vector Regression) model to predict breast muscle weight. MAEFNet achieved the highest intersection over union (96.35%) with the lowest parameter count (1.51 M) compared to the other segmentation models. The SVR model performed best (R2 = 0.8810) compared to the other prediction models in the five-fold cross-validation. The research findings can be applied to broiler production and breeding, reducing measurement costs, and enhancing breeding efficiency.
Collapse
Affiliation(s)
- Rui Zhu
- College of Information and Electrical Engineering, China Agricultural University, Beijing 100083, China; (R.Z.); (J.L.); (J.Y.)
| | - Jiayao Li
- College of Information and Electrical Engineering, China Agricultural University, Beijing 100083, China; (R.Z.); (J.L.); (J.Y.)
| | - Junyan Yang
- College of Information and Electrical Engineering, China Agricultural University, Beijing 100083, China; (R.Z.); (J.L.); (J.Y.)
| | - Ruizhi Sun
- College of Information and Electrical Engineering, China Agricultural University, Beijing 100083, China; (R.Z.); (J.L.); (J.Y.)
- Scientific Research Base for Integrated Technologies of Precision Agriculture (Animal Husbandry), The Ministry of Agriculture, Beijing 100083, China
| | - Kun Yu
- College of Animal Science and Technology, China Agricultural University, Beijing 100193, China
| |
Collapse
|
2
|
Chacko Kaitholil SR, Mooney MH, Aubry A, Rezwan F, Shirali M. Insights into the influence of diet and genetics on feed efficiency and meat production in sheep. Anim Genet 2024; 55:20-46. [PMID: 38112204 PMCID: PMC10952161 DOI: 10.1111/age.13383] [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: 07/03/2023] [Revised: 10/06/2023] [Accepted: 11/22/2023] [Indexed: 12/21/2023]
Abstract
Feed costs and carcass yields affect the profitability and sustainability of sheep production. Therefore, it is crucial to select animals with a higher feed efficiency and high-quality meat production. This study focuses on the impact of dietary and genetic factors on production traits such as feed efficiency, carcass quality, and meat quality. Diets promote optimal sheep growth and development and provide sufficient protein can lead to higher-quality meat. However, establishing an optimized production system requires careful consideration and balance of dietary parameters. This includes ensuring adequate protein intake and feeding diets with higher intestinal absorption rates to enhance nutrient absorption in the gut. The study identifies specific genes, such as Callipyge, Calpastatin, and Myostatin, and the presence of causal mutations in these genes, as factors influencing animal growth rates, feed efficiency, and meat fatty acid profiles. Additionally, variants of other reported genes, including PIGY, UCP1, MEF2B, TNNC2, FABP4, SCD, FASN, ADCY8, ME1, CA1, GLIS1, IL1RAPL1, SOX5, SOX6, and IGF1, show potential as markers for sheep selection. A meta-analysis of reported heritability estimates reveals that residual feed intake (0.27 ± 0.07), hot carcass weight (0.26 ± 0.05), dressing percentage (0.23 ± 0.05), and intramuscular fat content (0.45 ± 0.04) are moderately to highly heritable traits. This suggests that these traits are less influenced by environmental factors and could be improved through genetic selection. Additionally, positive genetic correlations exist between body weight and hot carcass weight (0.91 ± 0.06), dressing percentage (0.35 ± 0.15), and shear force (0.27 ± 0.24), indicating that selecting for higher body weight could lead to favorable changes in carcass quality, and meat quality.
Collapse
Affiliation(s)
- Steffimol Rose Chacko Kaitholil
- Institute for Global Food Security, School of Biological SciencesQueen's University BelfastBelfastUK
- Agri‐Food and Biosciences InstituteHillsboroughUK
| | - Mark H. Mooney
- Institute for Global Food Security, School of Biological SciencesQueen's University BelfastBelfastUK
| | | | - Faisal Rezwan
- Department of Computer ScienceAberystwyth UniversityAberystwythUK
| | - Masoud Shirali
- Institute for Global Food Security, School of Biological SciencesQueen's University BelfastBelfastUK
- Agri‐Food and Biosciences InstituteHillsboroughUK
| |
Collapse
|
3
|
Zhai B, Zhao Y, Li H, Li S, Gu J, Zhang H, Zhang Y, Li H, Tian Y, Li G, Wang Y. Weighted gene co-expression network analysis identified hub genes critical to fatty acid composition in Gushi chicken breast muscle. BMC Genomics 2023; 24:594. [PMID: 37805512 PMCID: PMC10559426 DOI: 10.1186/s12864-023-09685-8] [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: 07/09/2023] [Accepted: 09/19/2023] [Indexed: 10/09/2023] Open
Abstract
BACKGROUND The composition and content of fatty acids in the breast muscle are important factors influencing meat quality. In this study, we investigated the fatty acid composition and content in the breast muscle of Gushi chickens at different developmental stages (14 weeks, 22 weeks, and 30 weeks). Additionally, we utilized transcriptomic data from the same tissue and employed WGCNA and module identification methods to identify key genes associated with the fatty acid composition in Gushi chicken breast muscle and elucidate their regulatory networks. RESULTS Among them, six modules (blue, brown, green, light yellow, purple, and red modules) showed significant correlations with fatty acid content and metabolic characteristics. Enrichment analysis revealed that these modules were involved in multiple signaling pathways related to fatty acid metabolism, including fatty acid metabolism, PPAR signaling pathway, and fatty acid biosynthesis. Through analysis of key genes, we identified 136 genes significantly associated with fatty acid phenotypic traits. Protein-protein interaction network analysis revealed that nine of these genes were closely related to fatty acid metabolism. Additionally, through correlation analysis of transcriptome data, we identified 51 key ceRNA regulatory networks, including six central genes, 7 miRNAs, and 28 lncRNAs. CONCLUSION This study successfully identified key genes closely associated with the fatty acid composition in Gushi chicken breast muscle, as well as their post-transcriptional regulatory networks. These findings provide new insights into the molecular regulatory mechanisms underlying the flavor characteristics of chicken meat and the composition of fatty acids in the breast muscle.
Collapse
Affiliation(s)
- Bin Zhai
- College of Animal Science and Technology, Henan Agricultural University, Zhengzhou, 450046, China
| | - Yinli Zhao
- College of Biological Engineering, Henan University of Technology, Zheng Zhou, Henan Province, 450001, People's Republic of China
| | - Hongtai Li
- College of Animal Science and Technology, Henan Agricultural University, Zhengzhou, 450046, China
| | - Shuaihao Li
- College of Animal Science and Technology, Henan Agricultural University, Zhengzhou, 450046, China
| | - Jinxing Gu
- College of Animal Science and Technology, Henan Agricultural University, Zhengzhou, 450046, China
| | - Hongyuan Zhang
- College of Animal Science and Technology, Henan Agricultural University, Zhengzhou, 450046, China
| | - Yanhua Zhang
- College of Animal Science and Technology, Henan Agricultural University, Zhengzhou, 450046, China
- Henan Key Laboratory for Innovation and Utilization of Chicken Germplasm Resources, Zhengzhou, 450046, P. R. China
| | - Hong Li
- College of Animal Science and Technology, Henan Agricultural University, Zhengzhou, 450046, China
- Henan Key Laboratory for Innovation and Utilization of Chicken Germplasm Resources, Zhengzhou, 450046, P. R. China
| | - Yadong Tian
- College of Animal Science and Technology, Henan Agricultural University, Zhengzhou, 450046, China
- Henan Key Laboratory for Innovation and Utilization of Chicken Germplasm Resources, Zhengzhou, 450046, P. R. China
| | - Guoxi Li
- College of Animal Science and Technology, Henan Agricultural University, Zhengzhou, 450046, China.
- Henan Key Laboratory for Innovation and Utilization of Chicken Germplasm Resources, Zhengzhou, 450046, P. R. China.
- The Shennong Laboratory, Zhengzhou, 450046, China.
| | - Yongcai Wang
- College of Animal Science and Technology, Henan Agricultural University, Zhengzhou, 450046, China.
| |
Collapse
|
4
|
Li Z, Zheng J, An B, Ma X, Ying F, Kong F, Wen J, Zhao G. Several models combined with ultrasound techniques to predict breast muscle weight in broilers. Poult Sci 2023; 102:102911. [PMID: 37494808 PMCID: PMC10393806 DOI: 10.1016/j.psj.2023.102911] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/02/2023] [Revised: 06/20/2023] [Accepted: 06/27/2023] [Indexed: 07/28/2023] Open
Abstract
The weight of breast muscle (WBM) is a highly monitored indicator in broiler breeding that can be obtained after slaughtering. Currently, due to the lack of accurate in vivo phenotypes for both genomic and phenotypic selection, genetic gains in WBM fall short of initial expectations. In this study, 1,006 market-age (42 d) broilers from 3 generations over 2 yr were randomly selected, and the breast width (BW), fossil bone length (FBL), breast muscle thickness (BMT), and live weight (LW) were measured exactly in vivo. Eight models, including multiple linear regression (MLR), ridge regression (RR), least absolute shrinkage and selection operator (LASSO), and elastic net (EN), were fitted to explore the best regression relationships between breast muscle weight and these indicators. Support vector machine (SVM) methods with both linear kernels and radial kernels were used to fit the models, while 2 decision tree-based machine learning algorithms, random forest (RF), and extreme gradient boosting (XGBoost), were used to establish the prediction model. The predictive effects of different combinations of independent variables were compared, leading to the conclusion that the EN model achieves the best predictive power when all 4 live features are used as inputs and is slightly better than the other models (R2 = 0.7696). This method could be applied in practical production and breeding work, leading to substantial cost savings and enhancements in the breeding process.
Collapse
Affiliation(s)
- Zhengda Li
- Institute of Animal Sciences, Chinese Academy of Agricultural Sciences, Beijing, China
| | - Jumei Zheng
- Institute of Animal Sciences, Chinese Academy of Agricultural Sciences, Beijing, China
| | - Bingxing An
- Institute of Animal Sciences, Chinese Academy of Agricultural Sciences, Beijing, China
| | - Xiaochun Ma
- Institute of Animal Sciences, Chinese Academy of Agricultural Sciences, Beijing, China
| | - Fan Ying
- Mile Xinguang Agricultural and Animal Industrials Corporation, Mile, China
| | - Fuli Kong
- Institute of Animal Sciences, Chinese Academy of Agricultural Sciences, Beijing, China
| | - Jie Wen
- Institute of Animal Sciences, Chinese Academy of Agricultural Sciences, Beijing, China
| | - Guiping Zhao
- Institute of Animal Sciences, Chinese Academy of Agricultural Sciences, Beijing, China.
| |
Collapse
|
5
|
Otto JR, Mwangi FW, Pewan SB, Adegboye OA, Malau-Aduli AEO. Lipogenic Gene Single Nucleotide Polymorphic DNA Markers Associated with Intramuscular Fat, Fat Melting Point, and Health-Beneficial Omega-3 Long-Chain Polyunsaturated Fatty Acids in Australian Pasture-Based Bowen Genetics Forest Pastoral Angus, Hereford, and Wagyu Beef Cattle. Genes (Basel) 2022; 13:1411. [PMID: 36011322 PMCID: PMC9407580 DOI: 10.3390/genes13081411] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/26/2022] [Revised: 08/04/2022] [Accepted: 08/05/2022] [Indexed: 12/03/2022] Open
Abstract
This study used targeted sequencing aimed at identifying single nucleotide polymorphisms (SNP) in lipogenic genes and their associations with health-beneficial omega-3 long-chain polyunsaturated fatty acids (n-3 LC-PUFA), intramuscular fat (IMF), and fat melting point (FMP) of the M. longissimus dorsi muscle in Australian pasture-based Bowen Genetics Forest Pastoral Angus, Hereford, and Wagyu cattle. It was hypothesized that SNP encoding for the fatty acid-binding protein 4 (FABP4), stearoyl-CoA desaturase (SCD), and fatty acid synthase (FASN) genes will be significantly associated with health-beneficial n-3 LC-PUFA and the meat eating quality traits of IMF and FMP in an Australian pasture-based beef production system. Two SNP mutations, g.21267406 T>C and g.21271264 C>A, in the SCD gene were significantly (p < 0.05) associated with IMF, FMP, oleic acid (18:1n-9), linoleic acid (LA) 18:2n-6, alpha-linolenic acid (ALA) 18:3n-3, eicosapentaenoic acid (EPA) 20:5n-3, docosahexaenoic acid (DHA) 22:6-n-3, and docosapentaenoic acid (DPA) 22:5n-3. Significant positive correlations (p < 0.05) between FASN SNP g. 50787138 A>G and FMP, 18:1n-9, ALA, EPA, DHA, DPA, and total n-3 LC-PUFA were also detected. An SNP (g.44678794 G>A) in the FABP4 gene was associated with FMP. These results provide significant insights into the contributions of lipogenic genes to intramuscular fat deposition and the biosynthesis of health-beneficial n-3 LC-PUFA. The findings also unravel the potential use of lipogenic gene polymorphisms in marker-assisted selection to improve the content of health-promoting n-3 LC-PUFA and meat eating quality traits in Australian pasture-based Bowen Genetics Forest Pastoral Angus, Hereford, and Wagyu beef cattle.
Collapse
Affiliation(s)
- John R. Otto
- Animal Genetics and Nutrition, Veterinary Sciences Discipline, College of Public Health, Medical and Veterinary Sciences, Division of Tropical Health and Medicine, James Cook University, Townsville, QLD 4811, Australia
| | - Felista W. Mwangi
- Animal Genetics and Nutrition, Veterinary Sciences Discipline, College of Public Health, Medical and Veterinary Sciences, Division of Tropical Health and Medicine, James Cook University, Townsville, QLD 4811, Australia
| | - Shedrach B. Pewan
- Animal Genetics and Nutrition, Veterinary Sciences Discipline, College of Public Health, Medical and Veterinary Sciences, Division of Tropical Health and Medicine, James Cook University, Townsville, QLD 4811, Australia
- National Veterinary Research Institute, PMB 01, Vom 930001, Plateau State, Nigeria
| | - Oyelola A. Adegboye
- Public Health and Tropical Medicine Discipline, College of Public Health, Medical and Veterinary Sciences, Division of Tropical Health and Medicine, James Cook University, Townsville, QLD 4811, Australia
| | - Aduli E. O. Malau-Aduli
- Animal Genetics and Nutrition, Veterinary Sciences Discipline, College of Public Health, Medical and Veterinary Sciences, Division of Tropical Health and Medicine, James Cook University, Townsville, QLD 4811, Australia
| |
Collapse
|
6
|
Towards Sustainable Sources of Omega-3 Long-Chain Polyunsaturated Fatty Acids in Northern Australian Tropical Crossbred Beef Steers through Single Nucleotide Polymorphisms in Lipogenic Genes for Meat Eating Quality. SUSTAINABILITY 2022. [DOI: 10.3390/su14148409] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 02/04/2023]
Abstract
This study aimed to identify single nucleotide polymorphisms (SNP) in lipogenic genes of northern Australian tropically adapted crossbred beef cattle and to evaluate associations with healthy lipid traits of the Longissimus dorsi (loin eye) muscle. The hypothesis tested was that there are significant associations between SNP loci encoding for the fatty acid binding protein 4 (FABP4), stearoyl-CoA desaturase (SCD) and fatty acid synthase (FASN) genes and human health beneficial omega-3 long-chain polyunsaturated fatty acids (ω3 LC-PUFA) within the loin eye muscle of northern Australian crossbred beef cattle. Brahman, Charbray, and Droughtmaster crossbred steers were fed on Rhodes grass hay augmented with desmanthus, lucerne, or both, for 140 days and the loin eye muscle sampled for intramuscular fat (IMF), fat melting point (FMP), and fatty acid composition. Polymorphisms in FABP4, SCD, and FASN genes with significant effects on lipid traits were identified with next-generation sequencing. The GG genotype at the FABP4 g.44677239C>G locus was associated with higher proportion of linoleic acid than the CC and CG genotypes (p < 0.05). Multiple comparisons of genotypes at the SCD g.21266629G>T locus indicated that the TT genotype had significantly higher eicosapentaenoic, docosapentaenoic, and docosahexaenoic acids than GG genotype (p < 0.05). Significant correlations (p < 0.05) between FASN SNP and IMF, saturated and monounsaturated fatty acids were observed. These results provide insights into the contribution of lipogenic genes to intramuscular fat deposition and SNP marker-assisted selection for improvement of meat-eating quality, with emphasis on alternate and sustainable sources of ω3 LC-PUFA, in northern Australian tropical crossbred beef cattle, hence an acceptance of the tested hypothesis.
Collapse
|
7
|
Malau-Aduli AEO, Curran J, Gall H, Henriksen E, O'Connor A, Paine L, Richardson B, van Sliedregt H, Smith L. Genetics and nutrition impacts on herd productivity in the Northern Australian beef cattle production cycle. Vet Anim Sci 2022; 15:100228. [PMID: 35024494 PMCID: PMC8724957 DOI: 10.1016/j.vas.2021.100228] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/24/2022] Open
Abstract
Genetics and nutrition drive herd productivity due to significant impacts on all components of the beef cattle production cycle. In northern Australia, the beef production system is largely extensive and relies heavily on tropical cattle grazing low quality, phosphorus-deficient pastures with seasonal variations in nutritive value. The existing feedlots are predominantly grain-based; providing high-energy rations, faster turn-off and finishing of backgrounded cattle to meet market specifications. This review focusses on the beef cattle production cycle components of maternal nutrition, foetal development, bull fertility, post-natal to weaning, backgrounding, feedlotting, rumen microbes and carcass quality as influenced by genetics and nutrition. This student-driven review identified the following knowledge gaps in the published literature on northern Australian beef cattle production cycle: 1. Long-term benefits and effects of maternal supplementation to alter foetal enzymes on the performance and productivity of beef cattle; 2. Exogenous fibrolytic enzymes to increase nutrient availability from the cell wall and better utilisation of fibrous and phosphorus deficient pasture feedbase during backgrounding; 3. Supplementation with novel encapsulated calcium butyrate and probiotics to stimulate the early development of rumen papillae and enhance early weaning of calves; 4. The use of single nucleotide polymorphisms as genetic markers for the early selection of tropical beef cattle for carcass and meat eating quality traits prior to feedlotting; The review concludes by recommending future research in whole genome sequencing to target specific genes associated with meat quality characteristics in order to explore the development of breeds with superior genes more suited to the North Australian beef industry. Further research into diverse nutritional strategies of phosphorus supplementation and fortifying tropically adapted grasses with protein-rich legumes and forages for backgrounding and supplementing lot-fed beef cattle with omega-3 oil of plant origin will ensure sustainable production of beef with a healthy composition, tenderness, taste and eating quality.
Collapse
Affiliation(s)
- Aduli E O Malau-Aduli
- Animal Genetics and Nutrition, Veterinary Science Discipline, College of Public Health, Medical and Veterinary Sciences, Division of Tropical Health and Medicine, James Cook University, Townsville, Queensland 4811, Australia
| | - Jessica Curran
- Animal Genetics and Nutrition, Veterinary Science Discipline, College of Public Health, Medical and Veterinary Sciences, Division of Tropical Health and Medicine, James Cook University, Townsville, Queensland 4811, Australia
| | - Holly Gall
- Animal Genetics and Nutrition, Veterinary Science Discipline, College of Public Health, Medical and Veterinary Sciences, Division of Tropical Health and Medicine, James Cook University, Townsville, Queensland 4811, Australia
| | - Erica Henriksen
- Animal Genetics and Nutrition, Veterinary Science Discipline, College of Public Health, Medical and Veterinary Sciences, Division of Tropical Health and Medicine, James Cook University, Townsville, Queensland 4811, Australia
| | - Alina O'Connor
- Animal Genetics and Nutrition, Veterinary Science Discipline, College of Public Health, Medical and Veterinary Sciences, Division of Tropical Health and Medicine, James Cook University, Townsville, Queensland 4811, Australia
| | - Lydia Paine
- Animal Genetics and Nutrition, Veterinary Science Discipline, College of Public Health, Medical and Veterinary Sciences, Division of Tropical Health and Medicine, James Cook University, Townsville, Queensland 4811, Australia
| | - Bailey Richardson
- Animal Genetics and Nutrition, Veterinary Science Discipline, College of Public Health, Medical and Veterinary Sciences, Division of Tropical Health and Medicine, James Cook University, Townsville, Queensland 4811, Australia
| | - Hannake van Sliedregt
- Animal Genetics and Nutrition, Veterinary Science Discipline, College of Public Health, Medical and Veterinary Sciences, Division of Tropical Health and Medicine, James Cook University, Townsville, Queensland 4811, Australia
| | - Lucy Smith
- Animal Genetics and Nutrition, Veterinary Science Discipline, College of Public Health, Medical and Veterinary Sciences, Division of Tropical Health and Medicine, James Cook University, Townsville, Queensland 4811, Australia
| |
Collapse
|