Comparing machine learning algorithms and linear model for detecting significant SNPs for genomic evaluation of growth traits in F2 chickens | ||
| Journal of Agricultural Science and Technology | ||
| Article 7, Volume 26, Issue 6, 2024, Pages 1261-1274 PDF (6.49 M) | ||
| Document Type: Original Research | ||
| DOI: 10.22034/JAST.26.6.1261 | ||
| Authors | ||
| H. Bani Saadat1; R. Vaez Torshizi* 1; Gh. Manafiazar2; A. A. Masoudi1; A. Ehsani1; S. Shahinfar3 | ||
| 1Department of Animal Science, Faculty of Agriculture, Tarbiat Modares University, Tehran, Islamic Republic of Iran. | ||
| 2Department of Animal Science and Aquaculture, Dalhousie University, Truro, NS, Canada. | ||
| 3Agriculture Victoria Research, AgriBio, Centre for AgriBioscience, Bundoora, Victoria 3083, Australia. | ||
| Abstract | ||
| High-density Single Nucleotide Polymorphisms (SNPs) panels are expensive, especially in developing countries. However, methods have been developed to detect critical SNPs from these panels and design low-density chips for genomic evaluation at lower cost. This study aimed to determine the efficiency of Random Forest (RF) and Gradient Boosting Machine (GBM) algorithms, and Linear Model (LM) in identification of SNPs subsets to predict Genomic Estimated Breeding Values (GEBVs) for Body Weights at 6 (BW6) and 9 (BW9) weeks in broiler chickens and compare the predicted GEBVs with those obtained by the 60K SNP panel. The data were collected on 312 F2 chickens that genotyped with 60K Illumina SNP BeadChip. After applying quality control, the remaining 45,512 SNPs were ranked based on p-values, mean square error percentage, and relative influence, obtained by LM, RF and GBM methods, respectively. Then, subsets of top 400, 1,000, 3,000 and 5,000 SNPs, selected by each method, were employed to construct genomic relationship matrices for the prediction of GEBVs with genomic best linear unbiased prediction model. Results indicated that predicted accuracies by RF and GBM were generally higher than LM. A Subset of 1,000 SNPs selected by RF and GBM algorithms compared to the total SNPs increased accuracy from 0.38 to 0.64 and 0.66 for BW6, and from 0.42 to 0.60 and 0.66 for BW9, respectively. The findings of the present study provide that machine learning methods, especially GBM, can perform better than LM in selecting important SNPs and increasing the accuracy of genomic prediction in broiler chickens. | ||
| Keywords | ||
| genomic evaluation; Body weight; Broilers; Machine learning | ||
| References | ||
|
| ||
|
Statistics Article View: 162 PDF Download: 161 |
||
| Number of Journals | 45 |
| Number of Issues | 2,174 |
| Number of Articles | 24,685 |
| Article View | 25,083,483 |
| PDF Download | 17,780,532 |