Tulpan, D. | Search bioRxiv

bioRxiv2021

Machine Learning based Genome-Wide Association Studies for Uncovering QTL Underlying Soybean Yield and its Components

Genome-wide association study (GWAS) is currently one of the important approaches for discovering quantitative trait loci (QTL) associated with traits of interest. However, insufficient statistical power is the limiting factor in current conventional GWAS methods for characterizing quantitative traits, especially in narrow genetic bases plants such as soybean. In this study, we evaluated the potential use of machine learning (ML) algorithms such as support vector machine (SVR) and random forest (RF) in GWAS, compared with two conventional methods of mixed linear models (MLM) and fixed and random model circulating probability unification (FarmCPU), for identifying QTL associated with soybean yield components. In this study, important soybean yield component traits, including the number of reproductive nodes (RNP), non-reproductive nodes (NRNP), total nodes (NP), and total pods (PP) per plant along with yield and maturity were assessed using 227 soybean genotypes evaluated across four environments. Our results indicated SVR-mediated GWAS outperformed RF, MLM and FarmCPU in discovering the most relevant QTL associated with the traits, supported by the functional annotation of candidate gene analyses. This study for the first time demonstrated the potential benefit of using sophisticated mathematical approaches such as ML algorithms in GWAS for identifying QTL suitable for genomic-based breeding programs.

plant biology↗

bioRxiv2020

In Pursuit of a Better Broiler: Growth, Efficiency and Mortality of 16 Strains of Broiler Chickens

To meet the growing consumer demand for chicken meat, the poultry industry has selected broiler chickens for increasing efficiency and breast yield. While this high productivity means affordable and consistent product, it has come at a cost to broiler welfare. There has been increasing advocacy and consumer pressure on primary breeders, producers, processors and retailers to improve the welfare of the billions of chickens processed annually. Several small-scale studies have reported better welfare outcomes for slower growing strains compared to fast growing, conventional strains. However, these studies often housed birds with range access or used strains with vastly different growth rates. Additionally, there may be traits other than growth, such as body conformation, that influence welfare. As the global poultry industries consider the implications of using slower growing strains, there was a need for a comprehensive, multidisciplinary examination of broiler chickens with a wide range of genotypes differing in growth rate and other phenotypic traits. To meet this need, our team designed a study to benchmark data on conventional and slower growing strains of broiler chickens reared in standardized laboratory conditions. Over a two-year period, we studied 7,528 broilers from 16 different genetic strains. In this paper, we compare the growth, efficiency and mortality of broilers to one of two target weights (TW): 2.1 kg (TW1) and 3.2 kg (TW2). We categorized strains by their growth rate to TW2 as conventional (CONV), fastest slow strains (FAST), moderate slow strains (MOD) and slowest slow strains (SLOW). When incubated, hatched, housed, managed and fed the same, the categories of strains differed in body weights, growth rates, feed intake and feed efficiency. At 48 days of age, strains in the CONV category were 835-1264 g heavier than strains in the other categories. By TW2, differences in body weights and feed intake resulted in a 22 to 43-point difference in feed conversion ratios. Categories of strains did not differ in their overall mortality rates.

physiology↗