An Explainable Deep Learning Classifier of Bovine Mastitis Based on Whole-Genome Sequence Data-Circumventing the p >> n Problem.

The serious drawback underlying the biological annotation of whole-genome sequence data is the p >> n problem, which means that the number of polymorphic variants (p) is much larger than the number of available phenotypic records (n). We propose a way to circumvent the problem by combining a LASSO logistic regression with deep learning to classify cows as susceptible or resistant to mastitis, based on single nucleotide polymorphism (SNP) genotypes. Among several architectures, the one with 204,642 SNPs was selected as the best. This architecture was composed of two layers with, respectively, 7 and 46 units per layer implementing respective drop-out rates of 0.210 and 0.358. The classification of the test data resulted in AUC = 0.750, accuracy = 0.650, sensitivity = 0.600, and specificity = 0.700. Significant SNPs were selected based on the SHapley Additive exPlanation (SHAP). As a final result, one GO term related to the biological process and thirteen GO terms related to molecular function were significantly enriched in the gene set that corresponded to the significant SNPs. Our findings revealed that the optimal approach can correctly predict susceptibility or resistance status for approximately 65% of cows. Genes marked by the most significant SNPs are related to the immune response and protein synthesis.

Estimation of Genetic Parameters for Female Fertility Traits in the Polish Holstein-Friesian Population.

The objective of this study was to estimate genetic parameters for the analyzed fertility traits of Polish Holstein-Friesian primiparous and multiparous cows, as a step toward the incorporation of new traits into routine genetic evaluation. Lactation records of 116,836 Polish Holstein-Friesian cows were studied. The records cover the first three lactations of all cows. The cows, daughters of 2884 sires, were calved from 2006 to 2020. The conception rate for heifers (CRh) and for cows in the second (CR2) and third parity (CR3), the interval from first calving to first insemination (CTFI), the days open (DO), and the interval from first to successful insemination for heifers (FSh) and for cows in second (FS2) and third (FS3) parity were analyzed. The BLUPf90 package and a Bayesian method via Gibbs sampling were used to estimate (co)variance components. In general, all heritabilities were low and ranged from 0.013 (CTFI) to 0.038 (FS2). The heritability of conception rate and interval from first to successful insemination was slightly lower for heifers than for cows. Genetic correlations were moderate to high with two exceptions: correlation of CTFI with CRh (0.033) and with FSh (-0.051). The results indicate that a few analyzed traits could be used in genetic evaluation of Polish Holstein-Friesian cows. It is suggested to complement the selection index with traits for both heifers and cows, such as the interval from first to successful insemination (i.e., FSh, FS2 and FS3), in order to enable effective improvement of female fertility scores in the Polish Holstein-Friesian population.

Genome-Wide Genomic and Functional Association Study for Workability and Calving Traits in Holstein Cattle.

The goal of our study was to identify the SNPs, metabolic pathways (KEGG), and gene ontology (GO) terms significantly associated with calving and workability traits in dairy cattle. We analysed direct (DCE) and maternal (MCE) calving ease, direct (DSB) and maternal (MSB) stillbirth, milking speed (MSP), and temperament (TEM) based on a Holstein-Friesian dairy cattle population consisting of 35,203 individuals. The number of animals, depending on the trait, ranged from 22,301 bulls for TEM to 30,603 for DCE. We estimated the SNP effects (based on 46,216 polymorphisms from Illumina BovineSNP50 BeadChip Version 2) using a multi-SNP mixed model. The SNP positions were mapped to genes and the GO terms/KEGG pathways of the corresponding genes were assigned. The estimation of the GO term/KEGG pathway effects was based on a mixed model using the SNP effects as dependent variables. The number of significant SNPs comprised 59 for DCE, 25 for DSB and MSP, 17 for MCE and MSB, and 7 for TEM. Significant KEGG pathways were found for MSB (2), TEM (2), and MSP (1) and 11 GO terms were significant for MSP, 10 for DCE, 8 for DSB and TEM, 5 for MCE, and 3 for MSB. From the perspective of a better understanding of the genomic background of the phenotypes, traits with low heritabilities suggest that the focus should be moved from single genes to the metabolic pathways or gene ontologies significant for the phenotype.

The Use of Multilayer Perceptron Artificial Neural Networks to Detect Dairy Cows at Risk of Ketosis.

Subclinical ketosis is one of the most dominant metabolic disorders in dairy herds during lactation. Cows suffering from ketosis experience elevated ketone body levels in blood and milk, including ß-hydroxybutyric acid (BHB), acetone (ACE) and acetoacetic acid. Ketosis causes serious financial losses to dairy cattle breeders and milk producers due to the costs of diagnosis and management as well as animal welfare reasons. Recent years have seen a growing interest in the use of artificial neural networks (ANNs) in various fields of science. ANNs offer a modeling method that enables the mapping of highly complex functional relationships. The purpose of this study was to determine the relationship between milk composition and blood BHB levels associated with subclinical ketosis in dairy cows, using feedforward multilayer perceptron (MLP) artificial neural networks. The results were verified based on the estimated sensitivity and specificity of selected network models, an optimum cut-off point was identified for the receiver operating characteristic (ROC) curve and the area under the ROC curve (AUC). The study demonstrated that BHB, ACE and lactose (LAC) levels, as well as the fat-to-protein ratio in milk, were important input variables in the network training process. For the identification of cows at risk of subclinical ketosis, variables such as BHB and ACE levels in milk were of particular relevance, with a sensitivity and specificity of 0.84 and 0.61, respectively. It was found that the back propagation algorithm offers opportunities to integrate artificial intelligence and dairy cattle welfare within a computerized decision support tool.

Genetic Parameters of Workability Traits in the Population of Polish Holstein-Friesian Cows Based on Conventional and Genomic Data.

Heritabilities of workability (WT) traits-milking speed (MS) and temperament (MT)-as well as genetic and phenotypic correlations between these traits in the population of Polish Holstein-Friesian (PHF) cows were estimated. The estimation of genetic parameters was performed twice: first with the use of pedigree data; and second with the use of pedigree and genomic data. Phenotypic data from routinely conducted MS and MT evaluations for 1,045,511 cows born from 2004 to 2013 were available; the cows were evaluated from 2011 to 2015. The main dataset was reduced based on imposed restrictions (e.g., on age of calving, stage of lactation and day of first trial milking). The dataset prepared in this manner comprised 391,615 cows. It was then reduced to daughters of 10% randomly selected sires for computational reasons. Finally, for genetic parameter estimation, 13,280 records of cows were used. The linear observation model included additive random effects of animal, fixed effects of herd-year-season of calving subclass (HYS) and lactation phase, fixed regressions on cow age at calving and the percent of HF breed genes in the cow genotype. Heritabilities estimated based on pedigree data were 0.12 (±0.0067) for MS and 0.08 (±0.0063) for MT, the genetic correlation between MS and MT was estimated at 0.05 (±0.0002) and the phenotypic correlation coefficient was estimated at 0.14 (±0.0004). The inclusion of genomic information of sire bulls had no clear effect on the size of the estimated WT genetic parameters. The heritabilities of MS and MT were 0.11 (±0.0065) and 0.09 (±0.0012), respectively. The genetic and phenotypic correlation coefficients were 0.07 (±0.0003) and 0.12 (±0.0005), respectively. The sizes of the obtained heritabilities of WT and of the genetic and phenotypic correlation between these traits indicate the possibility of effective population improvement for both WT traits.

The effect of dietary supplementation with dried fruit and vegetable pomaces on production parameters and meat quality in fattening pigs.

The presence of biologically active substances in feed mixture is discussed to have beneficial effect on animals' health and products. The purpose of the study was to determine the effect of dietary supplementation with dried apple, chokeberry, black currant, strawberry and carrot pomaces on production parameters and meat quality in fattening pigs. The use of dried pomaces of chokeberry showed tendencies for increased feed intake and reduced fattening period. The dried pomaces had no impact on saturated and monounsaturated fatty acids profile in meat, however in some groups an elevated level of polyunsaturated fatty acids from n-3 family and a decline in total cholesterol level was observed (P≤0.05). The highest oxidative stability and vitamin E content was found after supplementation with black currant (P≤0.05). Summarizing, the used dried pomaces improved several parameters related to meat quality, what might positively influence consumers' health.

Genetic correlations between basal and maximum metabolic rates in a wild rodent: consequences for evolution of endothermy.

According to the aerobic capacity model, endothermy in birds and mammals evolved as a correlated response to selection for an ability of sustained locomotor activity, rather than in a response to direct selection for thermoregulatory capabilities. A key assumption of the model is that aerobic capacity is functionally linked to basal metabolic rate (BMR). The assumption has been tested in several studies at the level of phenotypic variation among individuals or species, but none has provided a clear answer whether the traits are genetically correlated. Here we present results of a genetic analysis based on measurements of the basal and the maximum swim- and cold-induced oxygen consumption in about 1000 bank voles from six generations of a laboratory colony, reared from animals captured in the field. Narrow sense heritability (h2) was about 0.5 for body mass, about 0.4 for mass-independent basal and maximum metabolic rates, and about 0.3 for factorial aerobic scopes. Dominance genetic and common environmental (= maternal) effects were not significant. Additive genetic correlation between BMR and the swim-induced aerobic capacity was high and positive, whereas correlation resulting from specific-environmental effects was negative. However, BMR was not genetically correlated with the cold-induced aerobic capacity. The results are consistent with the aerobic capacity model of the evolution of endothermy in birds and mammals.