Energy balance of dairy cows predicted by mid-infrared spectra data of milk using Bayesian approaches.

Information on dry matter intake (DMI) and energy balance (EB) at the animal and herd level is important for management and breeding decisions. However, routine recording of these traits at commercial farms can be challenging and costly. Fourier-transform mid-infrared (FT-MIR) spectroscopy is a noninvasive technique applicable to a large cohort of animals that is routinely used to analyze milk components and is convenient for predicting complex phenotypes that are typically difficult and expensive to obtain on a large scale. We aimed to develop prediction models for EB and use the predicted phenotypes for genetic analysis. First, we assessed prediction equations using 4,485 phenotypic records from 167 Holstein cows from an experimental station. The phenotypes available were body weight (BW), milk yield (MY) and milk components, weekly-averaged DMI, and FT-MIR data from all milk samples available. We implemented mixed models with Bayesian approaches and assessed them through 50 randomized replicates of a 5-fold cross-validation. Second, we used the best prediction models to obtain predicted phenotypes of EB (EBp) and DMI (DMIp) on 5 commercial farms with 2,365 phenotypic records of MY, milk components and FT-MIR data, and BW from 1,441 Holstein cows. Third, we performed a GWAS and estimated heritability and genetic correlations for energy content in milk (EnM), BW, DMIp, and EBp using the genomic information available on the cows from commercial farms. The highest correlation between the predicted and observed phenotype (ry,y^) was obtained with DMI (0.88) and EB (0.86), while predicting BW was, as anticipated, more challenging (0.69). In our study, models that included FT-MIR information performed better than models without spectra information in the 3 traits analyzed, with increments in prediction correlation ranging from 5% to 10%. For the predicted phenotypes calculated by the prediction equations and data from the commercial farms the heritability ranged between 0.11 and 0.16 for EnM, DMIp and EBp, and 0.42 for BW. The genetic correlation between EnM and BW was -0.17, with DMIp was 0.40 and with EBp was -0.39. From the GWAS, we detected one significant QTL region for EnM, and 3 for BW, but none for DMIp and EBp. The results obtained in our study support previous evidence that FT-MIR information from milk samples contribute to improve the prediction equations for DMI, BW, and EB, and these predicted phenotypes may be used for herd management and contribute to the breeding strategy for improving cow performance.

Prediction of body condition in Jersey dairy cattle from 3D-images using machine learning techniques.

The body condition of dairy cows is a crucial health and welfare indicator that is widely acknowledged. Dairy herds with a well-management body condition tend to have more fertile and functional cows. Therefore, routine recording of high-quality body condition phenotypes is required. Automated prediction of body condition from 3D images can be a cost-effective approach to current manual recording by technicians. Using 3D-images, we aimed to build a reliable prediction model of body condition for Jersey cows. The dataset consisted of 808 individual Jersey cows with 2,253 phenotypes from three herds in Denmark. Body condition was scored on a 1 to 9 scale and transformed into a 1 to 5 scale with 0.5-unit differences. The cows' back images were recorded using a 3D camera (Microsoft Xbox One Kinect v2). We used contour and back height features from 3D-images as predictors, together with class predictors (evaluator, herd, evaluation round, parity, lactation week). The performance of machine learning algorithms was assessed using H2O AutoML algorithm (h2o.ai). Based on outputs from AutoML, DeepLearning (DL; multi-layer feedforward artificial neural network) and Gradient Boosting Machine (GBM) algorithms were implemented for classification and regression tasks and compared on prediction accuracy. In addition, we compared the Partial Least Square (PLS) method for regression. The training and validation data were divided either through a random 7:3 split for 10 replicates or by allocating two herds for training and one herd for validation. The accuracy of classification models showed the DL algorithm performed better than the GBM algorithm. The DL model achieved a mean accuracy of 48.1% on the exact phenotype and 93.5% accuracy with a 0.5-unit deviation. The performances of PLS and DL regression methods were comparable, with mean coefficient of determination of 0.67 and 0.66, respectively. When we used data from two herds for training and the third herd as validation, we observed a slightly decreased prediction accuracy compared to the 7:3 split of the dataset. The accuracies for DL and PLS in the herd validation scenario were > 38% on the exact phenotype and > 87% accuracy with 0.5-unit deviation. This study demonstrates the feasibility of a reliable body condition prediction model in Jersey cows using 3D-images. The approach developed can be used for reliable and frequent prediction of cows' body condition to improve dairy farm management and genetic evaluations.

The body condition of dairy cows is a crucial health and welfare indicator that is widely acknowledged in dairy cattle management. Routine recording of high-quality body condition phenotypes is required for adaptation in dairy herd management. The use of machine learning to predict the body condition of dairy cows from 3D images can offer a cost-effective approach to the current manual recording performed by technicians. We aimed to build a reliable prediction, based on data from 808 Jersey cows with 2,253 body condition phenotypes from three commercial herds in Denmark. We tested different machine-learning models. All models showed high prediction accuracy, and comparable levels with other published studies on Holstein cows. In a validation test across project herds, prediction accuracy ranged between 87% and 96%.

Supervised learning techniques for dairy cattle body weight prediction from 3D digital images.

Introduction: The use of automation and sensor-based systems in livestock production allows monitoring of individual cows in real-time and provides the possibility of early warning systems to take necessary management actions against possible anomalies. Among the different RT monitoring parameters, body weight (BW) plays an important role in tracking the productivity and health status. Methods: In this study, various supervised learning techniques representing different families of methods in the machine learning space were implemented and compared for performance in the prediction of body weight from 3D image data in dairy cows. A total of 83,011 records of contour data from 3D images and body weight measurements taken from a total of 914 Danish Holstein and Jersey cows from 3 different herds were used for the predictions. Various metrics including Pearson's correlation coefficient (r), the root mean squared error (RMSE), and the mean absolute percentage error (MAPE) were used for robust evaluation of the various supervised techniques and to facilitate comparison with other studies. Prediction was undertaken separately within each breed and subsequently in a combined multi-breed dataset. Results and discussion: Despite differences in predictive performance across the different supervised learning techniques and datasets (breeds), our results indicate reasonable prediction accuracies with mean correlation coefficient (r) as high as 0.94 and MAPE and RMSE as low as 4.0 % and 33.0 (kg), respectively. In comparison to the within-breed analyses (Jersey, Holstein), prediction using the combined multi-breed data set resulted in higher predictive performance in terms of high correlation coefficient and low MAPE. Additional tests showed that the improvement in predictive performance is mainly due to increase in data size from combining data rather than the multi-breed nature of the combined data. Of the different supervised learning techniques implemented, the tree-based group of supervised learning techniques (Catboost, AdaBoost, random forest) resulted in the highest prediction performance in all the metrics used to evaluate technique performance. Reported prediction errors in our study (RMSE and MAPE) are one of the lowest in the literature for prediction of BW using image data in dairy cattle, highlighting the promising predictive value of contour data from 3D images for BW in dairy cows under commercial farm conditions.

Reliabilities of Genomic Prediction for Young Stock Survival Traits Using 54K SNP Chip Augmented With Additional Single-Nucleotide Polymorphisms Selected From Imputed Whole-Genome Sequencing Data.

This study investigated effects of integrating single-nucleotide polymorphisms (SNPs) selected based on previous genome-wide association studies (GWASs), from imputed whole-genome sequencing (WGS) data, in the conventional 54K chip on genomic prediction reliability of young stock survival (YSS) traits in dairy cattle. The WGS SNPs included two groups of SNP sets that were selected based on GWAS in the Danish Holstein for YSS index (YSS_SNPs, n = 98) and SNPs chosen as peaks of quantitative trait loci for the traits of Nordic total merit index in Denmark-Finland-Sweden dairy cattle populations (DFS_SNPs, n = 1,541). Additionally, the study also investigated the possibility of improving genomic prediction reliability for survival traits by modeling the SNPs within recessive lethal haplotypes (LET_SNP, n = 130) detected from the 54K chip in the Nordic Holstein. De-regressed proofs (DRPs) were obtained from 6,558 Danish Holstein bulls genotyped with either 54K chip or customized LD chip that includes SNPs in the standard LD chip and some of the selected WGS SNPs. The chip data were subsequently imputed to 54K SNP together with the selected WGS SNPs. Genomic best linear unbiased prediction (GBLUP) models were implemented to predict breeding values through either pooling the 54K and selected WGS SNPs together as one genetic component (a one-component model) or considering 54K SNPs and selected WGS SNPs as two separate genetic components (a two-component model). Across all the traits, inclusion of each of the selected WGS SNP sets led to negligible improvements in prediction accuracies (0.17 percentage points on average) compared to prediction using only 54K. Similarly, marginal improvement in prediction reliability was obtained when all the selected WGS SNPs were included (0.22 percentage points). No further improvement in prediction reliability was observed when considering random regression on genotype code of recessive lethal alleles in the model including both groups of the WGS SNPs. Additionally, there was no difference in prediction reliability from integrating the selected WGS SNP sets through the two-component model compared to the one-component GBLUP.

Genetic parameters of semen quality traits and genetic correlations with service sire nonreturn rate in Nordic Holstein bulls.

Despite the importance of the quality of semen used in artificial insemination to the reproductive success of dairy herds, few studies have estimated the extent of genetic variability in semen quality traits. Even fewer studies have quantified the correlation between semen quality traits and male fertility. In this study, records of 100,058 ejaculates collected from 2,885 Nordic Holstein bulls were used to estimate genetic parameters for semen quality traits, including pre- and postcryopreservation semen concentration, sperm motility and viability, ejaculate volume, and number of doses per ejaculate. Additionally, summary data on nonreturn rate (NRR) obtained from insemination of some of the bulls (n = 2,142) to cows in different parities (heifers and parities 1-3 or more) were used to estimate correlations between the semen quality traits and service sire NRR. In the study, low to moderate heritability (0.06-0.45) was estimated for semen quality traits, indicating the possibility of improving these traits through selective breeding. The study also showed moderate to high genetic and phenotypic correlations between service sire NRR and some of the semen quality traits, including sperm viability pre- and postcryopreservation, motility postcryopreservation, and sperm concentration precryopreservation, indicating the predictive values of these traits for service sire NRR. The positive moderate to high genetic correlations between semen quality and service sire NRR traits also indicated that selection for semen quality traits might be favorable for improving service sire NRR.

Vitamin B12 and transcobalamin in bovine milk: Genetic variation and genome-wide association with loci along the genome.

In human nutrition, bovine milk is an essential source of bioavailable vitamin B12 and B12-binding proteins, including transcobalamin. In this study, we estimated genetic parameters for milk content of vitamin B12 and transcobalamin using milk samples from 341 and 663 Danish Holstein cows, respectively. Additionally, we conducted whole-genome association analysis to identify SNP and genes associated with vitamin B12 and transcobalamin. Our results indicated moderate to high heritability for vitamin B12 (0.37 ± 0.18) and transcobalamin (0.61 ± 0.13) content in the Danish Holstein. With a significance threshold of -log10 P-value > 5.87, significant associations were detected between SNP in Bos taurus autosome (BTA)17 and the log-transformed transcobalamin content of milk; no significant association was detected for vitamin B12. The significant region in BTA17 was imputed to full sequence for further fine mapping, and the SNP with the most significant associations to transcobalamin were assigned to the transcobalamin 2 (TCN2) gene.

Novel approach to incorporate information about recessive lethal genes increases the accuracy of genomic prediction for mortality traits.

The genetic underpinnings of calf mortality can be partly polygenic and partly due to deleterious effects of recessive lethal alleles. Prediction of the genetic merits of selection candidates should thus take into account both genetic components contributing to calf mortality. However, simultaneously modeling polygenic risk and recessive lethal allele effects in genomic prediction is challenging due to effects that behave differently. In this study, we present a novel approach where mortality risk probabilities from polygenic and lethal allele components are predicted separately to compute the total risk probability of an individual for its future offspring as a basis for selection. We present methods for transforming genomic estimated breeding values of polygenic effect into risk probabilities using normal density and cumulative distribution functions and show computations of risk probability from recessive lethal alleles given sire genotypes and population recessive allele frequencies. Simulated data were used to test the novel approach as implemented in probit, logit, and linear models. In the simulation study, the accuracy of predicted risk probabilities was computed as the correlation between predicted mortality probabilities and observed calf mortality for validation sires. The results indicate that our novel approach can greatly increase the accuracy of selection for mortality traits compared with the accuracy of predictions obtained without distinguishing polygenic and lethal gene effects.

Predictive ability of host genetics and rumen microbiome for subclinical ketosis.

Subclinical metabolic disorders such as ketosis cause substantial economic losses for dairy farmers in addition to the serious welfare issues they pose for dairy cows. Major hurdles in genetic improvement against metabolic disorders such as ketosis include difficulties in large-scale phenotype recording and low heritability of traits. Milk concentrations of ketone bodies, such as acetone and ß-hydroxybutyric acid (BHB), might be useful indicators to select cows for low susceptibility to ketosis. However, heritability estimates reported for milk BHB and acetone in several dairy cattle breeds were low. The rumen microbial community has been reported to play a significant role in host energy homeostasis and metabolic and physiologic adaptations. The current study aims at investigating the effects of cows' genome and rumen microbial composition on concentrations of acetone and BHB in milk, and identifying specific rumen microbial taxa associated with variation in milk acetone and BHB concentrations. We determined the concentrations of acetone and BHB in milk using nuclear magnetic resonance spectroscopy on morning milk samples collected from 277 Danish Holstein cows. Imputed high-density genotype data were available for these cows. Using genomic and microbial prediction models with a 10-fold resampling strategy, we found that rumen microbial composition explains a larger proportion of the variation in milk concentrations of acetone and BHB than do host genetics. Moreover, we identified associations between milk acetone and BHB with some specific bacterial and archaeal operational taxonomic units previously reported to have low to moderate heritability, presenting an opportunity for genetic improvement. However, higher covariation between specific microbial taxa and milk acetone and BHB concentrations might not necessarily indicate a causal relationship; therefore further validation is needed before considering implementation in selection programs.

Reliability of genomic prediction for milk fatty acid composition by using a multi-population reference and incorporating GWAS results.

BACKGROUND: Large-scale phenotyping for detailed milk fatty acid (FA) composition is difficult due to expensive and time-consuming analytical techniques. Reliability of genomic prediction is often low for traits that are expensive/difficult to measure and for breeds with a small reference population size. An effective method to increase reference population size could be to combine datasets from different populations. Prediction models might also benefit from incorporation of information on the biological underpinnings of quantitative traits. Genome-wide association studies (GWAS) show that genomic regions on Bos taurus chromosomes (BTA) 14, 19 and 26 underlie substantial proportions of the genetic variation in milk FA traits. Genomic prediction models that incorporate such results could enable improved prediction accuracy in spite of limited reference population sizes. In this study, we combine gas chromatography quantified FA samples from the Chinese, Danish and Dutch Holstein populations and implement a genomic feature best linear unbiased prediction (GFBLUP) model that incorporates variants on BTA14, 19 and 26 as genomic features for which random genetic effects are estimated separately. Prediction reliabilities were compared to those estimated with traditional GBLUP models. RESULTS: Predictions using a multi-population reference and a traditional GBLUP model resulted in average gains in prediction reliability of 10% points in the Dutch, 8% points in the Danish and 1% point in the Chinese populations compared to predictions based on population-specific references. Compared to the traditional GBLUP, implementation of the GFBLUP model with a multi-population reference led to further increases in prediction reliability of up to 38% points in the Dutch, 23% points in the Danish and 13% points in the Chinese populations. Prediction reliabilities from the GFBLUP model were moderate to high across the FA traits analyzed. CONCLUSIONS: Our study shows that it is possible to predict genetic merits for milk FA traits with reasonable accuracy by combining related populations of a breed and using models that incorporate GWAS results. Our findings indicate that international collaborations that facilitate access to multi-population datasets could be highly beneficial to the implementation of genomic selection for detailed milk composition traits.

Modeling heterogeneous (co)variances from adjacent-SNP groups improves genomic prediction for milk protein composition traits.

BACKGROUND: Accurate genomic prediction requires a large reference population, which is problematic for traits that are expensive to measure. Traits related to milk protein composition are not routinely recorded due to costly procedures and are considered to be controlled by a few quantitative trait loci of large effect. The amount of variation explained may vary between regions leading to heterogeneous (co)variance patterns across the genome. Genomic prediction models that can efficiently take such heterogeneity of (co)variances into account can result in improved prediction reliability. In this study, we developed and implemented novel univariate and bivariate Bayesian prediction models, based on estimates of heterogeneous (co)variances for genome segments (BayesAS). Available data consisted of milk protein composition traits measured on cows and de-regressed proofs of total protein yield derived for bulls. Single-nucleotide polymorphisms (SNPs), from 50K SNP arrays, were grouped into non-overlapping genome segments. A segment was defined as one SNP, or a group of 50, 100, or 200 adjacent SNPs, or one chromosome, or the whole genome. Traditional univariate and bivariate genomic best linear unbiased prediction (GBLUP) models were also run for comparison. Reliabilities were calculated through a resampling strategy and using deterministic formula. RESULTS: BayesAS models improved prediction reliability for most of the traits compared to GBLUP models and this gain depended on segment size and genetic architecture of the traits. The gain in prediction reliability was especially marked for the protein composition traits ß-CN, κ-CN and ß-LG, for which prediction reliabilities were improved by 49 percentage points on average using the MT-BayesAS model with a 100-SNP segment size compared to the bivariate GBLUP. Prediction reliabilities were highest with the BayesAS model that uses a 100-SNP segment size. The bivariate versions of our BayesAS models resulted in extra gains of up to 6% in prediction reliability compared to the univariate versions. CONCLUSIONS: Substantial improvement in prediction reliability was possible for most of the traits related to milk protein composition using our novel BayesAS models. Grouping adjacent SNPs into segments provided enhanced information to estimate parameters and allowing the segments to have different (co)variances helped disentangle heterogeneous (co)variances across the genome.

Estimation of genetic parameters and detection of chromosomal regions affecting the major milk proteins and their post translational modifications in Danish Holstein and Danish Jersey cattle.

BACKGROUND: In the Western world bovine milk products are an important protein source in human diet. The major proteins in bovine milk are the four caseins (CN), αS1-, αS2-, ß-, and k-CN and the two whey proteins, ß-LG and α-LA. It has been shown that both the amount of specific CN and their isoforms including post-translational modifications (PTM) influence technological properties of milk. Therefore, the aim of this study was to 1) estimate genetic parameters for individual proteins in Danish Holstein (DH) (n = 371) and Danish Jersey (DJ) (n = 321) milk, and 2) detect genomic regions associated with specific milk protein and their different PTM forms using a genome-wide association study (GWAS) approach. RESULTS: For DH, high heritability estimates were found for protein percentage (0.47), casein percentage (0.43), k-CN (0.77), ß-LG (0.58), and α-LA (0.40). For DJ, high heritability estimates were found for protein percentage (0.70), casein percentage (0.52), and α-LA (0.44). The heritability for G-k-CN, U-k-CN and GD was higher in the DH compared to the DJ, whereas the heritability for the PD of αS1-CN was lower in DH compared to DJ, whereas the PD for αS2-CN was higher in DH compared to DJ. The GWAS results for the main milk proteins were in line what has been earlier published. However, we showed that there were SNPs specifically regulating G-k-CN in DH. Some of these SNPs were assigned to casein protein kinase genes (CSNK1G3, PRKCQ). CONCLUSION: The genetic analysis of the major milk proteins and their PTM forms revealed that these were heritable in both DH and DJ. In DH, genomic regions specific for glycosylation of k-CN were detected. Furthermore, genomic regions for the major milk proteins confirmed the regions on BTA6 (casein cluster), BTA11 (PEAP), and BTA14 (DGAT1) as important regions influencing protein composition in milk. The results from this study provide confidence that it is possible to breed for specific milk protein including the different PTM forms.