Carcass traits and morphometry, typification of the Longissimus dorsi muscle and non-carcass components of hair lambs: can biscuit bran completely replace corn? A machine learning approach.

Biscuit bran (BB) is a co-product with worldwide distribution, with Brazil as the second largest cookie producer in the world with 1,157,051 tons. We evaluate the impact of completely replacing corn with BB on the characteristics and morphometry of carcass of purebred and crossbred Morada Nova lambs using machine learning techniques as an auxiliary method. Twenty male lambs from two genetic groups (GG) were used: purebred red-coated Morada Nova (MNR) and crossbred MNR × white-coated Morada Nova (MNF1). Supervised and unsupervised machine learning techniques were used. No interaction (P > 0.05) was observed between diets (D) and genetic groups (GG) and no simple isolated effect was observed for carcass characteristics, qualitative-quantitative typification of the Longissimus dorsi muscle, weight of non-carcass components, weight and yield of commercial cuts and carcass morphometric measurements. The formation of two horizontal clusters was verified: (i) crossed lambs with corn and BB and (ii) purebred lambs fed corn and BB. Vertically, three clusters were formed based on carcass and meat characteristics of native lambs: (i) thermal insulation, body capacity, true yield, and commercial cuts; (ii) choice, performance, physical carcass traits, and palatability; and (iii) yield cuts and non-carcass components. The heatmap also allowed us to observe that pure MN lambs had a greater body capacity when fed BB, while those fed corn showed superiority in commercial cuts, true yields, and non-carcass components. Crossbred lambs, regardless of diet, showed a greater association of physical characteristics of the carcass, performance, palatability, and less noble cuts. Crossbred lambs, regardless of diet, showed a greater association of physical characteristics of the carcass, performance, palatability, and less noble cuts. BB can be considered an alternative energy source in total replacement of corn. Integrating of machine learning techniques is a useful statistical tool for studies with large numbers of variables, especially when it comes to analyzing complex data with multiple effects in the search for data patterns and insights in decision-making on the farm.

(Quasi) multitask support vector regression with heuristic hyperparameter optimization for whole-genome prediction of complex traits: a case study with carcass traits in broilers.

This study investigates nonlinear kernels for multitrait (MT) genomic prediction using support vector regression (SVR) models. We assessed the predictive ability delivered by single-trait (ST) and MT models for 2 carcass traits (CT1 and CT2) measured in purebred broiler chickens. The MT models also included information on indicator traits measured in vivo [Growth and feed efficiency trait (FE)]. We proposed an approach termed (quasi) multitask SVR (QMTSVR), with hyperparameter optimization performed via genetic algorithm. ST and MT Bayesian shrinkage and variable selection models [genomic best linear unbiased predictor (GBLUP), BayesC (BC), and reproducing kernel Hilbert space (RKHS) regression] were employed as benchmarks. MT models were trained using 2 validation designs (CV1 and CV2), which differ if the information on secondary traits is available in the testing set. Models' predictive ability was assessed with prediction accuracy (ACC; i.e. the correlation between predicted and observed values, divided by the square root of phenotype accuracy), standardized root-mean-squared error (RMSE*), and inflation factor (b). To account for potential bias in CV2-style predictions, we also computed a parametric estimate of accuracy (ACCpar). Predictive ability metrics varied according to trait, model, and validation design (CV1 or CV2), ranging from 0.71 to 0.84 for ACC, 0.78 to 0.92 for RMSE*, and between 0.82 and 1.34 for b. The highest ACC and smallest RMSE* were achieved with QMTSVR-CV2 in both traits. We observed that for CT1, model/validation design selection was sensitive to the choice of accuracy metric (ACC or ACCpar). Nonetheless, the higher predictive accuracy of QMTSVR over MTGBLUP and MTBC was replicated across accuracy metrics, besides the similar performance between the proposed method and the MTRKHS model. Results showed that the proposed approach is competitive with conventional MT Bayesian regression models using either Gaussian or spike-slab multivariate priors.

A Random Forest-Based Genome-Wide Scan Reveals Fertility-Related Candidate Genes and Potential Inter-Chromosomal Epistatic Regions Associated With Age at First Calving in Nellore Cattle.

This study aimed to perform a genome-wide association analysis (GWAS) using the Random Forest (RF) approach for scanning candidate genes for age at first calving (AFC) in Nellore cattle. Additionally, potential epistatic effects were investigated using linear mixed models with pairwise interactions between all markers with high importance scores within the tree ensemble non-linear structure. Data from Nellore cattle were used, including records of animals born between 1984 and 2015 and raised in commercial herds located in different regions of Brazil. The estimated breeding values (EBV) were computed and used as the response variable in the genomic analyses. After quality control, the remaining number of animals and SNPs considered were 3,174 and 360,130, respectively. Five independent RF analyses were carried out, considering different initialization seeds. The importance score of each SNP was averaged across the independent RF analyses to rank the markers according to their predictive relevance. A total of 117 SNPs associated with AFC were identified, which spanned 10 autosomes (2, 3, 5, 10, 11, 17, 18, 21, 24, and 25). In total, 23 non-overlapping genomic regions embedded 262 candidate genes for AFC. Enrichment analysis and previous evidence in the literature revealed that many candidate genes annotated close to the lead SNPs have key roles in fertility, including embryo pre-implantation and development, embryonic viability, male germinal cell maturation, and pheromone recognition. Furthermore, some genomic regions previously associated with fertility and growth traits in Nellore cattle were also detected in the present study, reinforcing the effectiveness of RF for pre-screening candidate regions associated with complex traits. Complementary analyses revealed that many SNPs top-ranked in the RF-based GWAS did not present a strong marginal linear effect but are potentially involved in epistatic hotspots between genomic regions in different autosomes, remarkably in the BTAs 3, 5, 11, and 21. The reported results are expected to enhance the understanding of genetic mechanisms involved in the biological regulation of AFC in this cattle breed.

Investigating potential causal relationships among carcass and meat quality traits using structural equation model in Nellore cattle.

The objective of this study was to investigate potential causal relationships among hot carcass weight (HCW), longissimus muscle area (LMA), backfat thickness (BF), Warner-Bratzler shear force (WBSF), and marbling score (MB) traits in Nellore cattle using structural equation models (SEM). The SEM fitted comprises the following links between traits: WBSF → LMA, WBSF → HCW, HCW → LMA, BF → HCW, and BF → MB, where the arrows indicate the causal direction between traits, with structural coefficients posterior means (posterior standard deviation) equal to -0.29 cm2/kg (0.09), 0.43 kg/kg (0.29), 0.10 cm2/kg (0.006), 1.92 kg/mm (0.28), and 0.03 score-grade/mm (0.006), respectively. The final SEM revealed some important putative causal relationships among the traits studied here. The implied causal effects suggest that interventions on meat tenderness and fat content would affect overall growth and muscle deposition. Knowledge regarding potential causal relationships inferred among the traits studied here can have important implications for the genetic selection and management of Nellore cattle for improvement of carcass and meat quality.

Publisher Correction: Uncovering Sub-Structure and Genomic Profiles in Across-Countries Subpopulations of Angus Cattle.

An amendment to this paper has been published and can be accessed via a link at the top of the paper.

Genome-wide prediction for complex traits under the presence of dominance effects in simulated populations using GBLUP and machine learning methods.

The aim of this study was to compare the predictive performance of the Genomic Best Linear Unbiased Predictor (GBLUP) and machine learning methods (Random Forest, RF; Support Vector Machine, SVM; Artificial Neural Network, ANN) in simulated populations presenting different levels of dominance effects. Simulated genome comprised 50k SNP and 300 QTL, both biallelic and randomly distributed across 29 autosomes. A total of six traits were simulated considering different values for the narrow and broad-sense heritability. In the purely additive scenario with low heritability (h2 = 0.10), the predictive ability obtained using GBLUP was slightly higher than the other methods whereas ANN provided the highest accuracies for scenarios with moderate heritability (h2 = 0.30). The accuracies of dominance deviations predictions varied from 0.180 to 0.350 in GBLUP extended for dominance effects (GBLUP-D), from 0.06 to 0.185 in RF and they were null using the ANN and SVM methods. Although RF has presented higher accuracies for total genetic effect predictions, the mean-squared error values in such a model were worse than those observed for GBLUP-D in scenarios with large additive and dominance variances. When applied to prescreen important regions, the RF approach detected QTL with high additive and/or dominance effects. Among machine learning methods, only the RF was capable to cover implicitly dominance effects without increasing the number of covariates in the model, resulting in higher accuracies for the total genetic and phenotypic values as the dominance ratio increases. Nevertheless, whether the interest is to infer directly on dominance effects, GBLUP-D could be a more suitable method.

Uncovering Sub-Structure and Genomic Profiles in Across-Countries Subpopulations of Angus Cattle.

Highlighting genomic profiles for geographically distinct subpopulations of the same breed may provide insights into adaptation mechanisms to different environments, reveal genomic regions divergently selected, and offer initial guidance to joint genomic analysis. Here, we characterized similarities and differences between the genomic patterns of Angus subpopulations, born and raised in Canada (N = 382) and Brazil (N = 566). Furthermore, we systematically scanned for selection signatures based on the detection of autozygosity islands common between the two subpopulations, and signals of divergent selection, via FST and varLD tests. The principal component analysis revealed a sub-structure with a close connection between the two subpopulations. The averages of genomic relationships, inbreeding coefficients, and linkage disequilibrium at varying genomic distances were rather similar across them, suggesting non-accentuated differences in overall genomic diversity. Autozygosity islands revealed selection signatures common to both subpopulations at chromosomes 13 (63.77-65.25 Mb) and 14 (22.81-23.57 Mb), which are notably known regions affecting growth traits. Nevertheless, further autozygosity islands along with FST and varLD tests unravel particular sites with accentuated population subdivision at BTAs 7 and 18 overlapping with known QTL and candidate genes of reproductive performance, thermoregulation, and resistance to infectious diseases. Our findings indicate overall genomic similarity between Angus subpopulations, with noticeable signals of divergent selection in genomic regions associated with the adaptation in different environments.