The use of mid-infrared spectrometry to predict body energy status of Holstein cows

Energy balance, especially in early lactation, is known to be associated with subsequent health and fertility in dairy cows. However, its inclusion in routine management decisions or breeding programs is hindered by the lack of quick, easy, and inexpensive measures of energy balance. The objective of this study was to evaluate the potential of mid-infrared (MIR) analysis of milk, routinely available from all milk samples taken as part of large-scale milk recording and milk payment operations, to predict body energy status and related traits in lactating dairy cows. The body energy status traits investigated included energy balance and body energy content. The related traits of body condition score and energy intake were also considered. Measurements on these traits along with milk MIR spectral data were available on 17 different test days from 268 cows (418 lactations) and were used to develop the prediction equations using partial least squares regression. Predictions were externally validated on different independent subsets of the data and the results averaged. The average accuracy of predicting body energy status from MIR spectral data was as high as 75% when energy balance was measured across lactation. These predictions of body energy status were considerably more accurate than predictions obtained from the sometimes proposed fat-to-protein ratio in milk. It is not known whether the prediction generated from MIR data are a better reflection of the true (unknown) energy status than the actual energy status measures used in this study. However, results indicate that the approach described may be a viable method of predicting individual cow energy status for a large scale of application.     

Mid-infrared spectrometry of milk as a predictor of energy intake and efficiency in lactating dairy cows

Interest is increasing in the feed intake complex of individual dairy cows, both for management and animal breeding. However, energy intake data on an individual-cow basis are not routinely available. The objective of the present study was to quantify the ability of routinely undertaken mid-infrared (MIR) spectroscopy analysis of individual cow milk samples to predict individual cow energy intake and efficiency. Feed efficiency in the present study was described by residual feed intake (RFI), which is the difference between actual energy intake and energy used (e.g., milk production, maintenance, and body tissue anabolism) or supplied from body tissue mobilization. A total of 1,535 records for energy intake, RFI, and milk MIR spectral data were available from an Irish research herd across 36 different test days from 535 lactations on 378 cows. Partial least squares regression analyses were used to relate the milk MIR spectral data to either energy intake or efficiency. The coefficient of correlation (R_EX) of models to predict RFI across lactation ranged from 0.48 to 0.60 in an external validation data set; the predictive ability was, however, strongest (R_EX = 0.65) in early lactation (<60 d in milk). The inclusion of milk yield as a predictor variable improved the accuracy of predicting energy intake across lactation (R_EX = 0.70). The correlation between measured RFI and measured energy balance across lactation was 0.85, whereas the correlation between RFI and energy balance, both predicted from the MIR spectrum, was 0.65. Milk MIR spectral data are routinely generated for individual cows throughout lactation and, therefore, the prediction equations developed in the present study can be immediately (and retrospectively where MIR spectral data have been stored) applied to predict energy intake and efficiency to aid in management and breeding decisions.     

Validation of mid-infrared spectrometry in milk for predicting body energy status in Holstein-Friesian cows

Cow energy balance is known to be associated with cow health and fertility; therefore, routine access to data on energy balance can be useful in both management and breeding decisions to improve cow performance. The objective of this study was to determine if individual cow milk mid-infrared spectra (MIR) could be useful to predict cow energy balance across contrasting production systems. Direct energy balance was calculated as the differential between energy intake and energy output in milk and maintenance (maintenance was predicted using body weight). Body energy content was calculated from (change in) body weight and body condition score. Following editing, 2,992 morning, 2,742 midday, and 2,989 evening milk MIR records from 564 lactations on 337 Scottish cows, managed in a confinement system on 1 of 2 diets, were available. An additional 844 morning and 820 evening milk spectral records from 338 lactations on 244 Irish cows offered a predominantly grazed grass diet were also available. Equations were developed to predict body energy status using the milk spectral data and milk yield as predictor variables. Several different approaches were used to test the robustness of the equations calibrated in one data set and validated in another. The analyses clearly showed that the variation in the validation data set must be represented in the calibration data set. The accuracy (i.e., square root of the coefficient of multiple determinations) of predicting, from MIR, direct energy balance, body energy content, and energy intake was 0.47 to 0.69, 0.51 to 0.56, and 0.76 to 0.80, respectively. This highlights the ability of milk MIR to predict body energy balance, energy content, and energy intake with reasonable accuracy. Very high accuracy, however, was not expected, given the likely random errors in the calculation of these energy status traits using field data.     

Correlations of feed intake predicted with milk infrared spectra and breeding values in the Dutch Holstein population

Feed is a major cost in dairy production, and substantial genetic variation in feed efficiency exists between cows. Therefore, breeders aim to improve feed efficiency of dairy cattle. However, phenotypic data on individual feed intake on commercial farms is scarce, and accurate measurements are very costly. Several studies have shown that information from Fourier-transformed infrared spectra of milk samples (milk infrared, milk IR) can be used to predict phenotypes such as energy balance and energy intake, but this is usually based on small data sets obtained under experimental circumstances. The added value of information from milk IR spectra for estimation of breeding values is unknown. The objectives of this study were (1) to develop prediction equations for dry matter intake (DMI) and residual DMI (rDMI) from milk IR spectra; (2) to apply these for a data set of milk IR spectra from commercial Dutch dairy farms; (3) to estimate genetic parameters for these traits; and (4) to estimate correlations between these predictions and other traits in the breeding goal. We used data from feeding trials where individual feed intake was recorded daily and for which milk IR spectra were determined weekly to develop prediction equations for DMI and rDMI with partial least squares regression. This data set contained over 7,600 weekly averaged DMI records linked with milk IR spectra from 271 cows. The equations were applied for a data set with test day information from 676 Dutch dairy herds with 621,567 records of 78,488 cows. Both milk IR-predicted DMI and rDMI were analyzed with an animal model to obtain genetic parameters and sire effect estimates that could be correlated with breeding values. A partial least squares regression model with 10 components from the milk IR spectra explained around 25% of DMI variation and less than 10% of rDMI variation in the validation set. Nearly all variation in the milk IR spectra was captured by 7 components; additional components contributed marginally to the spectral variation but decreased prediction errors for both traits. Accuracies of predictions of DMI and rDMI from milk IR spectra for a large feeding experiment were 0.47 and 0.26 on average, respectively, with small differences between ration treatments (ranging from 0.43 to 0.55 and from 0.21 to 0.34, respectively) and among lactation stages (ranging from 0.24 to 0.59 and from 0.13 to 0.36, respectively), with the highest prediction accuracies in early lactation. The estimated heritabilities for predicted DMI and rDMI were 0.3 and 0.4, respectively, which suggests genetic potential for both predicted traits. The correlations of sire estimates for milk IR-predicted DMI with official Dutch breeding values were strongest with milk production (0.33), longevity (0.26), and fertility (?0.27), indicating that cows that eat more produce more, live longer, and have poorer fertility. The correlations of sire estimates for predicted DMI and rDMI with the official breeding values for DMI were low (0.14 and 0.03, respectively). This implies that the added value of including milk IR-predicted DMI information in the estimation procedure of breeding values for DMI would be considered insufficient for practical application.     

Assessing the effect of pregnancy stage on milk composition of dairy cows using mid-infrared spectra

Changes in milk production traits (i.e., milk yield, fat, and protein contents) with the pregnancy stage are well documented. To our knowledge, the effect of pregnancy on the detailed milk composition has not been studied so far. The mid-infrared (MIR) spectrum reflects the detailed composition of a milk sample and is obtained by a nonexhaustive and widely used method for milk analysis. Therefore, this study aimed to investigate the effect of pregnancy on milk MIR spectrum in addition to milk production traits (milk yield, fat, and protein contents). A model including regression on the number of days pregnant was applied on milk production traits (milk yield, fat, and protein contents) and on 212 spectral points from the MIR spectra of 9,757 primiparous Holstein cows from Walloon herds. Effects of pregnancy stage were expressed on a relative scale (effect divided by the squared root of the phenotypic variance); this allowed comparisons between effects on milk traits and on 212 spectral points. Effect of pregnancy stage on production traits were in line with previous studies indicating that the model accounted well for the pregnancy effect. Trends of the relative effect of the pregnancy stage on the 212 spectral points were consistent with known and observed effect on milk traits. The highest effect of the pregnancy was observed in the MIR spectral region from 968 to 1,577 cm^?1. For some specific wavenumbers, the effect was higher than for fat and protein contents in the beginning of the pregnancy (from 30 to 90 or 120 d pregnant). In conclusion, the effect of early pregnancy can be observed in the detailed milk composition through the analysis of the MIR spectrum of bovine milk. Further analyses are warranted to explore deeply the use of MIR spectra of bovine milk for breeding and management of dairy cow pregnancy.     

Estimating fatty acid content in cow milk using mid-infrared spectrometry

Interest in the fatty acid composition of dairy products is increasing; however, the measurement of fatty acids requires using gas-liquid chromatography. Although this method is suitable, it involves a time-consuming procedure, expensive reagents, and qualified staff. By comparison, the mid-infrared (MIR) spectrometry method could be a good alternative for assessing the fatty acid profile of dairy products. The objective of this study was to explore the calibration of MIR spectrometry for estimating fatty acid concentrations in milk and milk fat. Estimated concentrations in milk fat were less reliable than those for the same fatty acids in milk. Results also showed that when the fatty acid concentrations in milk increased, the efficiency of the infrared analysis method in predicting these values simultaneously increased. Selected prediction equations must have a high cross-validation coefficient of determination, a high ratio of standard error of cross-validation to standard deviation, and good repeatability of chromatographic data. Results from this study showed that the calibration equations predicting 12:0, 14:0, 16:0, 16:1cis-9, 18:1, and saturated and monounsaturated fatty acids in milk could be used. Thus, with its potential for use in regular milk recording, this infrared analysis method offers the possibility of assessing and improving the quality of milk produced. Indeed, it enables the fatty acid composition in milk to be estimated for each cow and the estimates to be used as indicator traits to determine the genetic values of underlying fatty acid concentrations. The knowledge of these genetic values would open up opportunities for animal selection aimed at improving the nutritional quality of cow milk.     

Mid-infrared spectroscopy predictions as indicator traits in breeding programs for enhanced coagulation properties of milk

The aims of this study were to investigate variation of milk coagulation property (MCP) measures and their predictions obtained by mid-infrared spectroscopy (MIR), to investigate the genetic relationship between measures of MCP and MIR predictions, and to estimate the expected response from a breeding program focusing on the enhancement of MCP using MIR predictions as indicator traits. Individual milk samples were collected from 1,200 Brown Swiss cows (progeny of 50 artificial insemination sires) reared in 30 herds located in northern Italy. Rennet coagulation time (RCT, min) and curd firmness (a₃₀, mm) were measured using a computerized renneting meter. The MIR data were recorded over the spectral range of 4,000 to 900 cm⁻¹. Prediction models for RCT and a₃₀ based on MIR spectra were developed using partial least squares regression. A cross-validation procedure was carried out. The procedure involved the partition of available data into 2 subsets: a calibration subset and a test subset. The calibration subset was used to develop a calibration equation able to predict individual MCP phenotypes using MIR spectra. The test subset was used to validate the calibration equation and to estimate heritabilities and genetic correlations for measured MCP and their predictions obtained from MIR spectra and the calibration equation. Point estimates of heritability ranged from 0.30 to 0.34 and from 0.22 to 0.24 for RCT and a₃₀, respectively. Heritability estimates for MCP predictions were larger than those obtained for measured MCP. Estimated genetic correlations between measures and predictions of RCT were very high and ranged from 0.91 to 0.96. Estimates of the genetic correlation between measures and predictions of a₃₀ were large and ranged from 0.71 to 0.87. Predictions of MCP provided by MIR techniques can be proposed as indicator traits for the genetic enhancement of MCP. The expected response of RCT and a₃₀ ensured by the selection using MIR predictions as indicator traits was equal to or slightly less than the response achievable through a single measurement of these traits. Breeding strategies for the enhancement of MCP based on MIR predictions as indicator traits could be easily and immediately implemented for dairy cattle populations where routine acquisition of spectra from individual milk samples is already performed.     

Genetic variability of milk components based on mid-infrared spectral data

The aim of this study was to estimate the genetic parameters of the mid-infrared (MIR) milk spectrum represented by 1,060 data points per sample. The dimensionality of traits was reduced by principal components analysis. Therefore, 46 principal components describing 99.03% of the phenotypic variability were used to create 46 new traits. Variance components were estimated using canonical transformation. Heritability ranged from 0 to 0.35. Twenty-five out of 46 studied traits showed a permanent environment variance greater than genetic variance. Eight traits showed heritability greater than 0.10. Variances of original spectral traits were obtained by back transformation. Heritabilities for each spectral data points ranged from 0.003 to 0.42. In particular, 3 MIR regions showing moderate to high heritability estimates were of potential genetic interest. Heritabilities for specific wave numbers, linked with common milk traits (e.g., lipids, lactose), were similar to those estimated for these traits. This research confirms the genetic variability of the MIR milk spectrum and, therefore, the genetic variation of milk components. The objective of this study was to better understand the genetics of milk composition and, maybe in the future, to select animals to improve milk quality.     

The relationships between early lactation energy status indicators and endocrine fertility traits in dairy cows

The relationships between dairy cow milk-based energy status (ES) indicators and fertility traits were studied during periods 8 to 21, 22 to 35, 36 to 49, and 50 to 63 d in milk. Commencement of luteal activity (C-LA) and interval from calving to the first heat (CFH), based on frequent measurements of progesterone by the management tool Herd Navigator (DeLaval), were used as fertility traits. Energy status indicator traits were milk β-hydroxybutyrate (BHB) concentration provided by Herd Navigator and milk fat:protein ratio, concentration of C18:1 cis-9, the ratio of fatty acids (FA) C18:1 cis-9 and C10:0 in test-day milk samples, and predicted plasma concentration of nonesterified fatty acids (NEFA) on test days. Plasma NEFA predictions were based either directly on milk mid-infrared spectra (MIR) or on milk fatty acids based on MIR spectra (NEFA_mir and NEFA_fa, respectively). The average (standard deviation) C-LA was 39.3 (±16.6) days, and the average CFH was 50.7 (±17.2) days. The correlations between fertility traits and ES indicators tended to be higher for multiparous (r < 0.28) than for primiparous (r < 0.16) cows. All correlations were lower in the last period than in the other periods. In period 1, correlations of C-LA with NEFA_fa and BHB, respectively, were 0.15 and 0.14 for primiparous and 0.26 and 0.22 for multiparous cows. The associations between fertility traits and ES indicators indicated that negative ES during the first weeks postpartum may delay the onset of luteal activity. Milk FPR was not as good an indicator for cow ES as other indicators. According to these findings, predictions of plasma NEFA and milk FA based on milk MIR spectra of routine test-day samples and the frequent measurement of milk BHB by Herd Navigator gave equally good predictions of cow ES during the first weeks of lactation. Our results indicate that routinely measured milk traits can be used for ES evaluation in early lactation.     

The use of milk mid-infrared spectroscopy to improve genomic prediction accuracy of serum biomarkers

Breeding objectives in the dairy industry have shifted from being solely focused on production to including fertility, animal health, and environmental impact. Increased serum concentrations of candidate biomarkers of health and fertility, such as β-hydroxybutyric acid (BHB), fatty acids, and urea are difficult and costly to measure, and thus limit the number of records. Accurate genomic prediction requires a large reference population. The inclusion of milk mid-infrared (MIR) spectroscopic predictions of biomarkers may increase genomic prediction accuracy of these traits. Our objectives were to (1) estimate the heritability of, and genetic correlations between, selected serum biomarkers and their respective MIR predictions, and (2) evaluate genomic prediction accuracies of either only measured serum traits, or serum traits plus MIR-predicted traits. The MIR-predicted traits were either fitted in a single trait model, assuming the measured trait and predicted trait were the same trait, or in a multitrait model, where measured and predicted trait were assumed to be correlated traits. We performed all analyses using relationship matrices constructed from pedigree (A matrix), genotypes (G matrix), or both pedigree and genotypes (H matrix). Our data set comprised up to 2,198 and 9,657 Holstein cows with records for serum biomarkers and MIR-predicted traits, respectively. Heritabilities of measured serum traits ranged from 0.04 to 0.07 for BHB, from 0.13 to 0.21 for fatty acids, and from 0.10 to 0.12 for urea. Heritabilities for MIR-predicted traits were not significantly different from those for the measured traits. Genetic correlations between measured traits and MIR-predicted traits were close to 1 for urea. For BHB and fatty acids, genetic correlations were lower and had large standard errors. The inclusion of MIR predicted urea substantially increased prediction accuracy for urea. For BHB, including MIR-predicted BHB reduced the genomic prediction accuracy, whereas for fatty acids, prediction accuracies were similar with either measured fatty acids, MIR-predicted fatty acids, or both. The high genetic correlation between urea and MIR-predicted urea, in combination with the increased prediction accuracy, demonstrated the potential of using MIR-predicted urea for genomic prediction of urea. For BHB and fatty acids, further studies with larger data sets are required to obtain more accurate estimates of genetic correlations.     

Phenotyping metabolic status of dairy cows using clustering of time profiles of energy balance peripartum

Due to a combination of a relatively low energy intake and a high demand of energy required for milk production, dairy cows experience a negative energy balance (EB) at the start of lactation. This energy deficit causes body weight reduction and an increased risk for metabolic diseases. Severity and length of negative EB can differ among cows. Peripartum time profiles of EB for dairy cows are not described yet in the literature. Creating EB-derived time profiles with corresponding metabolic status and disease treatments could improve understanding the relationship between EB and metabolic status, as well as enhance identification of cows at risk for compromised metabolic status. In this research we propose a novel method to cluster EB time series and examine associated metabolic status and disease treatments of dairy cows in the peripartum period. In this study, data of 3 earlier experiments were merged and examined. Four dairy cow clusters for time profiles of EB from wk ?3 until +7 relative to calving were generated by the global alignment kernel algorithm. For each cluster, mean of body weight prepartum was distinguishable, indicating this might be a possible on-farm biomarker for the peripartum EB profile. Moreover, cows with severe EB drop postpartum were more treated for milk fever and had high plasma nonesterified fatty acids and β-hydroxybutyrate concentration, and low IGF-1, insulin, and glucose concentration in the first 7 wk of lactation. Overall, this study demonstrated that cows can be clustered based on EB time profiles and that characteristics such as prepartum body weight, and postpartum nonesterified fatty acids and glucose concentration are promising biomarkers to identify the time profile of EB and potentially the risk for metabolic diseases.     

Limits to prediction of energy balance from milk composition measures at individual cow level

Frequently updated energy balance (EB) estimates for individual cows are especially useful for dairy herd management, and individual-level estimates form the basis for group-level EB estimates. The accuracy of EB estimates determines the value of this information for management decision support. This study aimed to assess EB accuracy through ANOVA components and by comparing EB estimates based either on milk composition (EBalMilk) or on body condition score (BCS) and body weight (BW) (EBalBody). Energy balance based on milk composition was evaluated using data in which milk composition was measured at each milking. Three breeds (Danish Red, Holstein-Friesian, and Jersey) of cows (299 cows, 623 lactations) in parities 1 to 4 were used. Milk data were smoothed using a rolling local regression. Energy balance based on milk composition was calculated using a partial least squares (PLS) model based on milk fat, protein, and lactose contents and yields, and the daily change in these variables at each day. Energy balance based on BCS and BW was calculated from changes in body condition and BW scored weekly or fortnightly. Equations for calculation of EBalMilk and EBalBody used no common variables and were, therefore, assumed mathematically independent. Traits were analyzed within 3 stages of lactation expected to have high mobilization of body tissue (1, early), almost balanced (2), and deposition of body energy (3, mid to late lactation). In general, EBalMilk and EBalBody followed similar expected changes through lactation. Estimates of covariance were obtained using single-trait mixed models with random regression terms describing the change with time and used for calculation of repeatability as intraclass correlations. Within stage, EBalMilk was less repeatable than EBalBody (0.53, 0.41, 0.43 vs. 0.93, 0.91, 0.86, respectively, for stages 1, 2, and 3), mainly because of a larger residual variance for EBalMilk. Correlations between individual-level estimates of EBalMilk and EBalBody were close to zero. However, correlations between EB estimates in different lactation stages tended to be stronger for EBalMilk than for EBalBody, although correlations for both EB traits were small. It is concluded that EB estimates based on milk composition are less accurate than those based on body traits, but EBalMilk can compensate partly for this inaccuracy by being updated more frequently.     

Effect of genetic merit for energy balance on luteal activity and subsequent reproductive performance in primiparous Holstein-Friesian cows

Postpartum energy status is critically important to fertility. However, studies dealing with the relationship between both traits are rare and most refer only to the phenotypic level. In this study, random regression models were used to generate cow-specific lactation curves for daily breeding values (BV) of energy balance (EB) to assess the effect of genetic merit for energy status on different traits derived from progesterone profiles and on subsequent reproductive performance of high-producing dairy cows. Individual feed intake, milk yield, and live weight were recorded for lactation d 11 to 180, and EB was estimated on a daily basis. The results provided the basis for the estimation of BV for 824 primiparous Holstein-Friesian cows. For a subset of these cows (n = 334), progesterone profiles for the resumption of ovarian activity were available. Four different traits describing the genetic merit for EB were defined to evaluate their relationship with fertility. Two EB traits referred to the period in which the average daily EB across all cows was negative (d 11 to 55 postpartum), and 2 parameters were designed considering only daily BV for d 11 to 180 in lactation that were negative. We found that cows with a high genetic merit for EB had a significantly earlier resumption of ovarian activity postpartum. Thus, an EB (indicator) trait should be included in future breeding programs to reduce the currently prolonged anovulatory intervals after parturition.     

An attempt at predicting blood β-hydroxybutyrate from Fourier-transform mid-infrared spectra of milk using multivariate mixed models in Polish dairy cattle

Fourier transform mid-infrared (FT-MIR) spectra of milk are commonly used for phenotyping of traits of interest through links developed between the traits and milk FT-MIR spectra. Predicted traits are then used in genetic analysis for ultimate phenotypic prediction using a single-trait mixed model that account for cows' circumstances at a given test day. Here, this approach is referred to as indirect prediction (IP). Alternatively, FT-MIR spectral variable can be kept multivariate in the form of factor scores in REML and BLUP analyses. These BLUP predictions, including phenotype (predicted factor scores), were converted to single-trait through calibration outputs; this method is referred to as direct prediction (DP). The main aim of this study was to verify whether mixed modeling of milk spectra in the form of factors scores (DP) gives better prediction of blood β-hydroxybutyrate (BHB) than the univariate approach (IP). Models to predict blood BHB from milk spectra were also developed. Two data sets that contained milk FT-MIR spectra and other information on Polish dairy cattle were used in this study. Data set 1 (n = 826) also contained BHB measured in blood samples, whereas data set 2 (n = 158,028) did not contain measured blood values. Part of data set 1 was used to calibrate a prediction model (n = 496) and the remaining part of data set 1 (n = 330) was used to validate the calibration models, as well as to evaluate the DP and IP approaches. Dimensions of FT-MIR spectra in data set 2 were reduced either into 5 or 10 factor scores (DP) or into a single trait (IP) with calibration outputs. The REML estimates for these factor scores were found using WOMBAT. The BLUP values and predicted BHB for observations in the validation set were computed using the REML estimates. Blood BHB predicted from milk FT-MIR spectra by both approaches were regressed on reference blood BHB that had not been used in the model development. Coefficients of determination in cross-validation for untransformed blood BHB were from 0.21 to 0.32, whereas that for the log-transformed BHB were from 0.31 to 0.38. The corresponding estimates in validation were from 0.29 to 0.37 and 0.21 to 0.43, respectively, for untransformed and logarithmic BHB. Contrary to expectation, slightly better predictions of BHB were found when univariate variance structure was used (IP) than when multivariate covariance structures were used (DP). Conclusive remarks on the importance of keeping spectral data in multivariate form for prediction of phenotypes may be found in data sets where the trait of interest has strong relationships with spectral variables.     

Predicting pregnancy status from mid-infrared spectroscopy in dairy cow milk using deep learning

Accurately identifying pregnancy status is imperative for a profitable dairy enterprise. Mid-infrared (MIR) spectroscopy is routinely used to determine fat and protein concentrations in milk samples. Mid-infrared spectra have successfully been used to predict other economically important traits, including fatty acid content, mineral content, body energy status, lactoferrin, feed intake, and methane emissions. Machine learning has been used in a variety of fields to find patterns in vast quantities of data. This study aims to use deep learning, a sub-branch of machine learning, to establish pregnancy status from routinely collected milk MIR spectral data. Milk spectral data were obtained from National Milk Records (Chippenham, UK), who collect large volumes of data continuously on a monthly basis. Two approaches were followed: using genetic algorithms for feature selection and network design (model 1), and transfer learning with a pretrained DenseNet model (model 2). Feature selection in model 1 showed that the number of wave points in MIR data could be reduced from 1,060 to 196 wave points. The trained model converged after 162 epochs with validation accuracy and loss of 0.89 and 0.18, respectively. Although the accuracy was sufficiently high, the loss (in terms of predicting only 2 labels) was considered too high and suggested that the model would not be robust enough to apply to industry. Model 2 was trained in 2 stages of 100 epochs each with spectral data converted to gray-scale images and resulted in accuracy and loss of 0.97 and 0.08, respectively. Inspection on inference data showed prediction sensitivity of 0.89, specificity of 0.86, and prediction accuracy of 0.88. Results indicate that milk MIR data contains features relating to pregnancy status and the underlying metabolic changes in dairy cows, and such features can be identified by means of deep learning. Prediction equations from trained models can be used to alert farmers of nonviable pregnancies as well as to verify conception dates.     

Analysis of the genetic architecture of energy balance and its major determinants dry matter intake and energy-corrected milk yield in primiparous Holstein cows

The focus of modern dairy cow breeding programs has shifted from being mainly yield based toward balanced goals that increasingly consider functional traits such as fertility, metabolic stability, and longevity. To improve these traits, a less pronounced energy deficit postpartum is considered a key challenge. On the other hand, feed efficiency and methane emissions are gaining importance, possibly leading to conflicts in the design of breeding goals. Dry matter intake (DMI) is one of the major determinants of energy balance (EB), and recently some efforts were undertaken to include DMI in genomic breeding programs. However, there is not yet a consensus on how this should be achieved as there are different goals in the course of lactation (i.e., reducing energy deficit postpartum vs. subsequently improving feed efficiency). Thus, the aim of this study was to gain more insight into the genetic architecture of energy metabolism across lactation by genetically dissecting EB and its major determinants DMI and energy-corrected milk (ECM) yield at different lactation stages applying random regression methodology and univariate and multivariate genomic analyses to data from 1,174 primiparous Holstein cows. Daily heritability estimates ranged from 0.29 to 0.49, 0.26 to 0.37, and 0.58 to 0.68 for EB, DMI, and ECM, respectively, across the first 180 d in milk (DIM). Genetic correlations between ECM and DMI were positive, ranging from 0.09 (DIM 11) to 0.36 (DIM 180). However, ECM and EB were negatively correlated (r_g = ?0.26 to ?0.59). The strongest relationship was found at the onset of lactation, indicating that selection for increased milk yield at this stage will result in a more severe energy deficit postpartum. The results also indicate that EB is more affected by DMI (r_g = 0.71 to 0.81) than by its other major determinant, ECM. Thus, breeding for a higher DMI in early lactation seems to be a promising strategy to improve the energy status of dairy cows. We found evidence that genetic regulation of energy homeostasis is complex, with trait- and lactation stage-specific quantitative trait loci suggesting that the trajectories of the analyzed traits can be optimized as mentioned above. Especially from the multivariate genomic analyses, we were able to draw some conclusions on the mechanisms involved and identified the genes encoding fumarate hydratase and adiponectin as highly promising candidates for EB, which will be further analyzed.     

Comparison between genetic parameters of cheese yield and nutrient recovery or whey loss traits measured from individual model cheese-making methods or predicted from unprocessed bovine milk samples using Fourier-transform infrared spectroscopy

Cheese yield is an important technological trait in the dairy industry. The aim of this study was to infer the genetic parameters of some cheese yield-related traits predicted using Fourier-transform infrared (FTIR) spectral analysis and compare the results with those obtained using an individual model cheese-producing procedure. A total of 1,264 model cheeses were produced using 1,500-mL milk samples collected from individual Brown Swiss cows, and individual measurements were taken for 10 traits: 3 cheese yield traits (fresh curd, curd total solids, and curd water as a percent of the weight of the processed milk), 4 milk nutrient recovery traits (fat, protein, total solids, and energy of the curd as a percent of the same nutrient in the processed milk), and 3 daily cheese production traits per cow (fresh curd, total solids, and water weight of the curd). Each unprocessed milk sample was analyzed using a MilkoScan FT6000 (Foss, Hillerød, Denmark) over the spectral range, from 5,000 to 900 wavenumber × cm⁻¹. The FTIR spectrum-based prediction models for the previously mentioned traits were developed using modified partial least-square regression. Cross-validation of the whole data set yielded coefficients of determination between the predicted and measured values in cross-validation of 0.65 to 0.95 for all traits, except for the recovery of fat (0.41). A 3-fold external validation was also used, in which the available data were partitioned into 2 subsets: a training set (one-third of the herds) and a testing set (two-thirds). The training set was used to develop calibration equations, whereas the testing subsets were used for external validation of the calibration equations and to estimate the heritabilities and genetic correlations of the measured and FTIR-predicted phenotypes. The coefficients of determination between the predicted and measured values in cross-validation results obtained from the training sets were very similar to those obtained from the whole data set, but the coefficient of determination of validation values for the external validation sets were much lower for all traits (0.30 to 0.73), and particularly for fat recovery (0.05 to 0.18), for the training sets compared with the full data set. For each testing subset, the (co)variance components for the measured and FTIR-predicted phenotypes were estimated using bivariate Bayesian analyses and linear models. The intraherd heritabilities for the predicted traits obtained from our internal cross-validation using the whole data set ranged from 0.085 for daily yield of curd solids to 0.576 for protein recovery, and were similar to those obtained from the measured traits (0.079 to 0.586, respectively). The heritabilities estimated from the testing data set used for external validation were more variable but similar (on average) to the corresponding values obtained from the whole data set. Moreover, the genetic correlations between the predicted and measured traits were high in general (0.791 to 0.996), and they were always higher than the corresponding phenotypic correlations (0.383 to 0.995), especially for the external validation subset. In conclusion, we herein report that application of the cross-validation technique to the whole data set tended to overestimate the predictive ability of FTIR spectra, give more precise phenotypic predictions than the calibrations obtained using smaller data sets, and yield genetic correlations similar to those obtained from the measured traits. Collectively, our findings indicate that FTIR predictions have the potential to be used as indicator traits for the rapid and inexpensive selection of dairy populations for improvement of cheese yield, milk nutrient recovery in curd, and daily cheese production per cow.     

The importance of maternal lineage on milk yield traits of dairy cattle.

Maternal lineage effects on milk yield traits, considered indicative of cytoplasmic inheritance, were evaluated with animal models. Cattle were from a selection experiment begun in 1968. Maternal pedigrees were traced to the first female member in the Holstein-Friesian Herdbook; purchased cows entering the herd, considered foundation females, were assigned to maternal lineage groups. All models accounted for year-season of calving, parity, and selection lines. Maternal lineage effects were included in a repeated records model with cow effects and preadjustment for sire and maternal grandsire transmitting abilities. Maternal lineage accounted for 5.2, 4.1, and 10.5% of phenotypic variation of preadjusted records of milk yield, fat yield, and fat percentage, respectively. Maternal lineage was evaluated as a fixed effect in an animal model including random animal and permanent environmental effects. Maternal lineage significantly affected fat percentage but not milk yield. Maternal genetic (nuclear) effects and their covariance with additive animal effects did not significantly account for additional variation nor did they influence maternal lineage estimates. Maternal lineage affected calculated net energy of milk but was not important for SNF yield or concentration. Maternal lineage influenced fat percentage, energy concentration, and, to a lesser extent, fat yield in milk of dairy cattle.     

Liability to diseases and their relation to dry matter intake and energy balance in German Holstein and Fleckvieh dairy cows

Dairy cow efficiency is increasingly important for future breeding decisions. The efficiency is determined mostly by dry matter intake (DMI). Reducing DMI seems to increase efficiency if milk yield remains the same, but resulting negative energy balance (EB) may cause health problems, especially in early lactation. Objectives of this study were to examine relationships between DMI and liability to diseases. Therefore, cow effects for DMI and EB were correlated with cow effects for 4 disease categories throughout lactation. Disease categories were mastitis, claw and leg diseases, metabolic diseases, and all diseases. In addition, this study presents relative percentages of diseased cows per days in milk (DIM), repeatability, and cow effect correlations for disease categories across DIM. A total of 1,370 German Holstein (GH) and 287 Fleckvieh (FV) primiparous and multiparous dairy cows from 12 dairy research farms in Germany were observed over a period of 2 yr. Farm staff and veterinarians recorded health data. We modeled health and production data with threshold random regression models and linear random regression models. From DIM 2 to 305 average daily DMI was 22.1 kg/d in GH and 20.2 kg/d in FV. Average weekly EB was 2.8 MJ of NE_L/d in GH and 0.6 MJ of NE_L/d in FV. Most diseases occurred in the first 20 DIM. Multiparous cows were more susceptible to diseases than primiparous cows. Relative percentages of diseased cows were highest for claw and leg diseases, followed by metabolic diseases and mastitis. Repeatability of disease categories and production traits was moderate to high. Cow effect correlations for disease categories were higher for adjacent lactation stages than for more distant lactation stages. Pearson correlation coefficients between cow effects for DMI, as well as EB, and disease categories were estimated from DIM 2 to 305. Almost all correlations were negative in GH, especially in early lactation. In FV, the course of correlations was similar to GH, but correlations were mostly more negative in early lactation. For the first 20 DIM, correlations ranged from ?0.31 to 0.00 in GH and from ?0.42 to ?0.01 in FV. The results illustrate that future breeding for dairy cow efficiency should focus on DMI and EB in early lactation to avoid health problems.