Back to Search
Start Over
Integrating genomic and infrared spectral data improves the prediction of milk protein composition in dairy cattle
- Source :
- Genetics Selection Evolution, Vol 53, Iss 1, Pp 1-14 (2021), Genetics Selection Evolution, Genetics Selection Evolution, BioMed Central, 2021, 53 (1), pp.29. ⟨10.1186/s12711-021-00620-7⟩, Genetics, Selection, Evolution : GSE
- Publication Year :
- 2021
- Publisher :
- BMC, 2021.
-
Abstract
- BackgroundOver the past decade, Fourier transform infrared (FTIR) spectroscopy has been used to predict novel milk protein phenotypes. Genomic data might help predict these phenotypes when integrated with milk FTIR spectra. The objective of this study was to investigate prediction accuracy for milk protein phenotypes when heterogeneous on-farm, genomic, and pedigree data were integrated with the spectra. To this end, we used the records of 966 Italian Brown Swiss cows with milk FTIR spectra, on-farm information, medium-density genetic markers, and pedigree data. True and total whey protein, and five casein, and two whey protein traits were analyzed. Multiple kernel learning constructed from spectral and genomic (pedigree) relationship matrices and multilayer BayesB assigning separate priors for FTIR and markers were benchmarked against a baseline partial least squares (PLS) regression. Seven combinations of covariates were considered, and their predictive abilities were evaluated by repeated random sub-sampling and herd cross-validations (CV).ResultsAddition of the on-farm effects such as herd, days in milk, and parity to spectral data improved predictions as compared to those obtained using the spectra alone. Integrating genomics and/or the top three markers with a large effect further enhanced the predictions. Pedigree data also improved prediction, but to a lesser extent than genomic data. Multiple kernel learning and multilayer BayesB increased predictive performance, whereas PLS did not. Overall, multilayer BayesB provided better predictions than multiple kernel learning, and lower prediction performance was observed in herd CV compared to repeated random sub-sampling CV.ConclusionsIntegration of genomic information with milk FTIR spectral can enhance milk protein trait predictions by 25% and 7% on average for repeated random sub-sampling and herd CV, respectively. Multiple kernel learning and multilayer BayesB outperformed PLS when used to integrate heterogeneous data for phenotypic predictions.
- Subjects :
- Whey protein
lcsh:QH426-470
[SDV.SA.ZOO]Life Sciences [q-bio]/Agricultural sciences/Zootechny
Biology
Breeding
03 medical and health sciences
Genetic
Models
Statistics
Covariate
Partial least squares regression
Spectroscopy, Fourier Transform Infrared
Genetics
Animals
Spectroscopy
Ecology, Evolution, Behavior and Systematics
Dairy cattle
030304 developmental biology
lcsh:SF1-1100
2. Zero hunger
0303 health sciences
Multiple kernel learning
Models, Genetic
0402 animal and dairy science
food and beverages
04 agricultural and veterinary sciences
General Medicine
Genomics
Milk Proteins
040201 dairy & animal science
Regression
Pedigree
lcsh:Genetics
Fourier Transform Infrared
Herd
Animal Science and Zoology
Cattle
lcsh:Animal culture
Brown Swiss
Research Article
Subjects
Details
- Language :
- German
- ISSN :
- 12979686 and 0999193X
- Volume :
- 53
- Issue :
- 1
- Database :
- OpenAIRE
- Journal :
- Genetics Selection Evolution
- Accession number :
- edsair.doi.dedup.....1350db0db8a654ab2aee504777ebb452