Methodology for the identification of relevant loci for milk traits in dairy cattle, using machine learning algorithms
Machine learning methods were considered efficient in identifying single nucleotide polymorphisms (SNP) underlying a trait of interest. This study aimed to construct predictive models using machine learning algorithms, to identify loci that best explain the variance in milk traits of dairy cattle. F...
| Main Authors: | , , , , |
|---|---|
| Format: | info:ar-repo/semantics/artículo |
| Language: | Inglés |
| Published: |
Elsevier
2022
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/20.500.12123/11954 https://www.sciencedirect.com/science/article/pii/S2215016122001145 https://doi.org/10.1016/j.mex.2022.101733 |
| _version_ | 1855036667320074240 |
|---|---|
| author | Raschia, Maria Agustina Ríos, Pablo Javier Maizon, Daniel Omar Demitrio, Daniel Arturo Poli, Mario Andres |
| author_browse | Demitrio, Daniel Arturo Maizon, Daniel Omar Poli, Mario Andres Raschia, Maria Agustina Ríos, Pablo Javier |
| author_facet | Raschia, Maria Agustina Ríos, Pablo Javier Maizon, Daniel Omar Demitrio, Daniel Arturo Poli, Mario Andres |
| author_sort | Raschia, Maria Agustina |
| collection | INTA Digital |
| description | Machine learning methods were considered efficient in identifying single nucleotide polymorphisms (SNP) underlying a trait of interest. This study aimed to construct predictive models using machine learning algorithms, to identify loci that best explain the variance in milk traits of dairy cattle. Further objectives involved validating the results by comparison with reported relevant regions and retrieving the pathways overrepresented by the genes flanking relevant SNPs. Regression models using XGBoost (XGB), LightGBM (LGB), and Random Forest (RF) algorithms were trained using estimated breeding values for milk production (EBVM), milk fat content (EBVF) and milk protein content (EBVP) as phenotypes and genotypes on 40417 SNPs as predictor variables. To evaluate their efficiency, metrics for actual vs. predicted values were determined in validation folds (XGB and LGB) and out-of-bag data (RF). Less than 4500 relevant SNPs were retrieved for each trait. Among the genes flanking them, signaling and transmembrane transporter activities were overrepresented.
The models trained:
•Predicted breeding values for animals not included in the dataset.
•Were efficient in identifying a subset of SNPs explaining phenotypic variation.
The results obtained using XGB and LGB algorithms agreed with previous results. Therefore, the method proposed could be applied for future association studies on milk traits. |
| format | info:ar-repo/semantics/artículo |
| id | INTA11954 |
| institution | Instituto Nacional de Tecnología Agropecuaria (INTA -Argentina) |
| language | Inglés |
| publishDate | 2022 |
| publishDateRange | 2022 |
| publishDateSort | 2022 |
| publisher | Elsevier |
| publisherStr | Elsevier |
| record_format | dspace |
| spelling | INTA119542022-05-26T17:41:05Z Methodology for the identification of relevant loci for milk traits in dairy cattle, using machine learning algorithms Raschia, Maria Agustina Ríos, Pablo Javier Maizon, Daniel Omar Demitrio, Daniel Arturo Poli, Mario Andres Single Nucleotide Polymorphism Dairy Cattle Milk Production Milk Protein Bioinformatics Loci Polimorfismo de un Solo Nucleótidos Ganado de Leche Producción Lechera Proteínas de la Leche Bioinformática Milk Fat Content Machine Learning Algorithms Contenido de Grasa Láctea Algoritmos de Aprendizaje Automático Machine learning methods were considered efficient in identifying single nucleotide polymorphisms (SNP) underlying a trait of interest. This study aimed to construct predictive models using machine learning algorithms, to identify loci that best explain the variance in milk traits of dairy cattle. Further objectives involved validating the results by comparison with reported relevant regions and retrieving the pathways overrepresented by the genes flanking relevant SNPs. Regression models using XGBoost (XGB), LightGBM (LGB), and Random Forest (RF) algorithms were trained using estimated breeding values for milk production (EBVM), milk fat content (EBVF) and milk protein content (EBVP) as phenotypes and genotypes on 40417 SNPs as predictor variables. To evaluate their efficiency, metrics for actual vs. predicted values were determined in validation folds (XGB and LGB) and out-of-bag data (RF). Less than 4500 relevant SNPs were retrieved for each trait. Among the genes flanking them, signaling and transmembrane transporter activities were overrepresented. The models trained: •Predicted breeding values for animals not included in the dataset. •Were efficient in identifying a subset of SNPs explaining phenotypic variation. The results obtained using XGB and LGB algorithms agreed with previous results. Therefore, the method proposed could be applied for future association studies on milk traits. Instituto de Genética Fil: Raschia, Maria Agustina. Instituto Nacional de Tecnología Agropecuaria (INTA). Instituto de Genética; Argentina Fil: Ríos, Pablo J. Universidad de Buenos Aires; Argentina Fil: Ríos, Pablo J. Universidad Nacional de La Plata. Facultad de Ciencias Exactas; Argentina Fil: Maizon, Daniel Omar. Instituto Nacional de Tecnología Agropecuaria (INTA). Estación Experimental Agropecuaria Anguil; Argentina Fil: Maizon, Daniel Omar. Universidad Nacional de La Pampa. Facultad de Agronomía; Argentina Fil: Demitrio, Daniel Arturo. Instituto Nacional de Tecnología Agropecuaria (INTA). Dirección General de Sistemas de Información, Comunicación y Procesos. Gerencia de Informática y Gestión de la Información; Argentina Fil: Demitrio, Daniel Arturo. Universidad Nacional de La Plata. Facultad de Ciencias Exactas; Argentina Fil: Poli, Mario Andres. Instituto Nacional de Tecnología Agropecuaria (INTA). Instituto de Genética; Argentina Fil: Poli, Mario Andres. Universidad del Salvador. Facultad de Ciencias Agrarias y Veterinaria; Argentina 2022-05-26T17:34:45Z 2022-05-26T17:34:45Z 2022 info:ar-repo/semantics/artículo info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion http://hdl.handle.net/20.500.12123/11954 https://www.sciencedirect.com/science/article/pii/S2215016122001145 2215-0161 https://doi.org/10.1016/j.mex.2022.101733 eng info:eu-repograntAgreement/INTA/2019-PE-E6-I145-001/2019-PE-E6-I145-001/AR./Mejora genética objetiva para aumentar la eficiencia de los sistemas de producción animal. info:eu-repograntAgreement/INTA/2019-PT-E9-I180-001/2019-PT-E9-I180-001/AR./TICs y gestión de Big Data info:eu-repograntAgreement/INTA/2019-PT-E6-I513-001/2019-PT-E6-I513-001/AR./Plataforma de mejoramiento animal info:eu-repo/semantics/openAccess http://creativecommons.org/licenses/by-nc-sa/4.0/ Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0) application/pdf Elsevier MethodsX 9 : 101733 (2022) |
| spellingShingle | Single Nucleotide Polymorphism Dairy Cattle Milk Production Milk Protein Bioinformatics Loci Polimorfismo de un Solo Nucleótidos Ganado de Leche Producción Lechera Proteínas de la Leche Bioinformática Milk Fat Content Machine Learning Algorithms Contenido de Grasa Láctea Algoritmos de Aprendizaje Automático Raschia, Maria Agustina Ríos, Pablo Javier Maizon, Daniel Omar Demitrio, Daniel Arturo Poli, Mario Andres Methodology for the identification of relevant loci for milk traits in dairy cattle, using machine learning algorithms |
| title | Methodology for the identification of relevant loci for milk traits in dairy cattle, using machine learning algorithms |
| title_full | Methodology for the identification of relevant loci for milk traits in dairy cattle, using machine learning algorithms |
| title_fullStr | Methodology for the identification of relevant loci for milk traits in dairy cattle, using machine learning algorithms |
| title_full_unstemmed | Methodology for the identification of relevant loci for milk traits in dairy cattle, using machine learning algorithms |
| title_short | Methodology for the identification of relevant loci for milk traits in dairy cattle, using machine learning algorithms |
| title_sort | methodology for the identification of relevant loci for milk traits in dairy cattle using machine learning algorithms |
| topic | Single Nucleotide Polymorphism Dairy Cattle Milk Production Milk Protein Bioinformatics Loci Polimorfismo de un Solo Nucleótidos Ganado de Leche Producción Lechera Proteínas de la Leche Bioinformática Milk Fat Content Machine Learning Algorithms Contenido de Grasa Láctea Algoritmos de Aprendizaje Automático |
| url | http://hdl.handle.net/20.500.12123/11954 https://www.sciencedirect.com/science/article/pii/S2215016122001145 https://doi.org/10.1016/j.mex.2022.101733 |
| work_keys_str_mv | AT raschiamariaagustina methodologyfortheidentificationofrelevantlociformilktraitsindairycattleusingmachinelearningalgorithms AT riospablojavier methodologyfortheidentificationofrelevantlociformilktraitsindairycattleusingmachinelearningalgorithms AT maizondanielomar methodologyfortheidentificationofrelevantlociformilktraitsindairycattleusingmachinelearningalgorithms AT demitriodanielarturo methodologyfortheidentificationofrelevantlociformilktraitsindairycattleusingmachinelearningalgorithms AT polimarioandres methodologyfortheidentificationofrelevantlociformilktraitsindairycattleusingmachinelearningalgorithms |