Assessing different cross-validation schemes for predicting novel traits using sensor data: an application to dry matter intake and residual feed intake using milk spectral data

Feed efficiency is important for economic profitability of dairy farms; however, recording daily dry matter intakes (DMI) is expensive. Our objective was to investigate the potential use of milk mid-infrared (MIR) spectral data to predict proxy phenotypes for DMI based on different cross-validation schemes. We were specifically interested in comparisons between a model that included only MIR data (Model M1), a model that incorporated different energy sink predictors, such as body weight, body weight change, and milk energy (Model M2), and an extended model that incorporated both energy sinks and MIR data (Model M3). Models M2 and M3 also included various cow level variables (stage of lactation, age at calving, parity) such that any improvement in model performance from M2 to M3, whether through a smaller root mean squared error (RMSE) or a greater squared predictive correlation (R2), could indicate a potential benefit of MIR to predict residual feed intake. The data used in our study originated from a multi-institutional project on the genetics of feed efficiency in US Holsteins. Analyses were conducted on 2 different trait definitions based on different period lengths: averaged across weeks vs. averaged across 28-d. Specifically, there were 19,942 weekly records on 1,812 cows across 46 experiments or cohorts and 3,724 28-d records on 1,700 cows across 43 different cohorts. The cross-validation analyses involved 3 different k-fold schemes. First, a 10-fold cow-independent cross-validation was conducted whereby all records from any one cow were kept together in either training or test sets. Similarly, a 10-fold experiment-independent cross-validation kept entire experiments together whereas a 4-fold herd-independent cross-validation kept entire herds together in either training or test sets. Based on cow-independent cross-validation for both weekly and 28-d DMI, adding MIR predictors to energy sinks (Models M3 vs M2) significantly (P < 10-10) reduced average RMSE to 1.59 kg and increased average R2 to 0.89. However, adding MIR to energy sinks (M3) to predict DMI either within an experiment-independent or herd-independent cross-validation scheme seemed to demonstrate no merit (P > 0.05) compared with an energy sink model (M2) for either R2 or RMSE (respectively, 0.68 and 2.55 kg for M2 in herd-independent scheme). We further noted that with broader cross-validation schemes, i.e., from cow-independent to experiment-independent to herd-independent schemes, the mean and slope bias increased. Given that proxy DMI phenotypes for cows would need to be almost entirely generated in herds having no DMI or training data of their own, herd-independent cross-validation assessments of predictive performance should be emphasized. Hence, more research on predictive algorithms suitable for broader cross-validation schemes and a more earnest effort on calibration of spectrophotometers against each other should be considered.

Standardization method, testing scenario, and accuracy of the infrared prediction model affect the standardization accuracy of milk mid-infrared spectra

The widespread use of milk mid-infrared (MIR) spectroscopy for phenotype prediction has urged the application of prediction models across regions and countries. Spectra standardization is the most effective way to reduce the variability in the spectral signal provided by different instruments and labs. This study aimed to develop different standardization models for MIR spectra collected by multiple instruments, across 2 provinces of China, and investigate whether the standardization method (piecewise direct standardization, PDS, and direct standardization, DS), testing scenario (standardization of spectra collected on the same day or after 7 mo), infrared prediction model accuracy (high or low), and instrument (6 instruments from 2 brands) affect the performance of the standardization model. The results showed that the determination coefficient (R2) between absorbance values at each wavenumber provided by the primary and the secondary instruments increased from less than 0.90 to nearly 1.00 after standardization. Both PDS and DS successfully reduced spectra variation among instruments, and performed significantly better than non-standardization (P < 0.05). However, DS was more prone to overfitting than PDS. Standardization accuracy was higher when tested using spectra collected on the same time compared with those collected 7 mo after (P < 0.05), but great improvement in model transferability was obtained for both scenarios compared with the non-standardized spectra. The less accurate infrared prediction model (for C8:0 and C10:0 content) benefited the most (P < 0.05) from spectra standardization compared with the more accurate model (for total fat and protein content). For spectra collected after 7 mo from standardization, after PDS the RMSE between predictions obtained by different machines decreased on average by 86 and 94% compared with the values before standardization, for C8:0 and C10:0 respectively. The secondary instrument had no significant effect on the R2 between predictions (P > 0.05). The variation in the spectral signal provided by different instruments was successfully reduced by standardization across 2 provinces in China. This study lays the foundations for developing a national MIR spectra database to provide consistent predictions across provinces to be used in dairy farm management and breeding programs in China. Besides, this provides opportunities for data exchange and cooperation at international levels.

Prediction of likelihood of conception in dairy cows using milk mid-infrared spectra collected before the first insemination and machine learning algorithms

Accurate and ex-ante prediction of cows' likelihood of conception (LC) based on milk composition information could improve reproduction management on dairy farms. Milk composition is already routinely measured by mid-infrared (MIR) spectra, which are known to change with advancing stages of pregnancy. For lactating cows, MIR spectra may also be used for predicting the LC. Our objectives were to classify the LC at first insemination using milk MIR spectra data collected from calving to first insemination and to identify the spectral regions that contribute the most to the prediction of LC at first insemination. After quality control, 4,866 MIR spectra, milk production, and reproduction records from 3,451 Holstein cows were used. The classification accuracy and area under the curve (AUC) of 6 models comprising different predictors and 3 machine learning methods were estimated and compared. The results showed that partial least square discriminant analysis (PLS-DA) and random forest had higher prediction accuracies than logistic regression. The classification accuracy of good and poor LC cows and AUC in herd-by-herd validation of the best model were 76.35 ± 10.60% and 0.77 ± 0.11, respectively. All wavenumbers with values of variable importance in the projection higher than 1.00 in PLS-DA belonged to 3 spectral regions, namely from 1,003 to 1,189, 1,794 to 2,260, and 2,300 to 2,660 cm-1. In conclusion, the model can predict LC in dairy cows from a high productive TMR system before insemination with a relatively good accuracy, allowing farmers to intervene in advance or adjust the insemination schedule for cows with a poor predicted LC.

Genetic analysis of milk citrate predicted by milk mid-infrared spectra of Holstein cows in early lactation

Milk citrate is regarded as an early biomarker of negative energy balance in dairy cows during early lactation and serves as a suitable candidate phenotype for genomic selection due to its wide availability across a large number of cows through milk mid-infrared spectra prediction. However, its genetic background is not well known. Therefore, the objectives of this study were to (1) analyze the genetic parameters of milk citrate; (2) identify genomic regions associated with milk citrate; and (3) analyze the functional annotation of candidate genes and quantitative trait loci (QTL) related to milk citrate in Walloon Holstein cows. In total, 134,517 test-day milk-citrate phenotypes (mmol/L) collected within the first 50 d in milk on 52,198 Holstein cows were used. These milk-citrate phenotypes, predicted by milk mid-infrared spectra, were divided into 3 traits according to the first (citrate1), second (citrate2), and third to fifth parity (citrate3+). Genomic information for 566,170 SNPs was available for 4,479 animals. A multiple-trait repeatability model was used to estimate genetic parameters. A single-step GWAS was used to identify candidate genes for citrate and post-GWAS analysis was done to investigate the relationship and function of the identified candidate genes. The heritabilities estimated for citrate1, citrate2, and citrate3+ were 0.40, 0.37, and 0.35, respectively. The genetic correlations among the 3 traits ranged from 0.98 to 0.99. The genomic correlations among the 3 traits were also close to 1.00 across the genomic regions (1 Mb) in the whole genome, which means that citrate can be considered as a single trait in the first 5 parities. In total, 603 significant SNPs located on 3 genomic regions (chromosome 7, 68.569-68.575 Mb; chromosome 14, 0.15-1.90 Mb; and chromosome 20, 54.00-64.28 Mb), were identified to be associated with milk citrate. We identified 89 candidate genes including GPT, ANKH, PPP1R16A, and 32 QTL reported in the literature related to the identified significant SNPs. These identified QTL were mainly reported associated with milk fatty acids and metabolic diseases in dairy cows. This study suggests that milk citrate in Holstein cows is highly heritable and has the potential to be used as an early proxy for the negative energy balance of Holstein cows in a breeding objective.

Prediction of key milk biomarkers in dairy cows through milk mid-infrared spectra and international collaborations

At the individual cow level, suboptimum fertility, mastitis, negative energy balance, and ketosis are major issues in dairy farming. These problems are widespread on dairy farms and have an important economic impact. The objectives of this study were (1) to assess the potential of milk mid-infrared (MIR) spectra to predict key biomarkers of energy deficit (citrate, isocitrate, glucose-6 phosphate [glucose-6P], free glucose), ketosis (β-hydroxybutyrate [BHB] and acetone), mastitis (N-acetyl-β-d-glucosaminidase activity [NAGase] and lactate dehydrogenase), and fertility (progesterone); (2) to test alternative methodologies to partial least squares (PLS) regression to better account for the specific asymmetric distribution of the biomarkers; and (3) to create robust models by merging large datasets from 5 international or national projects. Benefiting from this international collaboration, the dataset comprised a total of 9,143 milk samples from 3,758 cows located in 589 herds across 10 countries and represented 7 breeds. The samples were analyzed by reference chemistry for biomarker contents, whereas the MIR analyses were performed on 30 instruments from different models and brands, with spectra harmonized into a common format. Four quantitative methodologies were evaluated to address the strongly skewed distribution of some biomarkers. Partial least squares regression was used as the reference basis, and compared with a random modification of distribution associated with PLS (random-downsampling-PLS), an optimized modification of distribution associated with PLS (KennardStone-downsampling-PLS), and support vector machine (SVM). When the ability of MIR to predict biomarkers was too low for quantification, different qualitative methodologies were tested to discriminate low versus high values of biomarkers. For each biomarker, 20% of the herds were randomly removed within all countries to be used as the validation dataset. The remaining 80% of herds were used as the calibration dataset. In calibration, the 3 alternative methodologies outperform the PLS performances for the majority of biomarkers. However, in the external herd validation, PLS provided the best results for isocitrate, glucose-6P, free glucose, and lactate dehydrogenase (coefficient of determination in external herd validation [R2v] = 0.48, 0.58, 0.28, and 0.24, respectively). For other molecules, PLS-random-downsampling and PLS-KennardStone-downsampling outperformed PLS in the majority of cases, but the best results were provided by SVM for citrate, BHB, acetone, NAGase, and progesterone (R2v = 0.94, 0.58, 0.76, 0.68, and 0.15, respectively). Hence, PLS and SVM based on the entire dataset provided the best results for normal and skewed distributions, respectively. Complementary to the quantitative methods, the qualitative discriminant models enabled the discrimination of high and low values for BHB, acetone, and NAGase with a global accuracy around 90%, and glucose-6P with an accuracy of 83%. In conclusion, MIR spectra of milk can enable quantitative screening of citrate as a biomarker of energy deficit and discrimination of low and high values of BHB, acetone, and NAGase, as biomarkers of ketosis and mastitis. Finally, progesterone could not be predicted with sufficient accuracy from milk MIR spectra to be further considered. Consequently, MIR spectrometry can bring valuable information regarding the occurrence of energy deficit, ketosis, and mastitis in dairy cows, which in turn have major influences on their fertility and survival.

Identification of Milk Adulteration in Camel Milk Using FT-Mid-Infrared Spectroscopy and Machine Learning Models

Camel milk, esteemed for its high nutritional value, has long been a subject of interest. However, the adulteration of camel milk with cow milk poses a significant threat to food quality and safety. Fourier-transform infrared spectroscopy (FT-MIR) has emerged as a rapid method for the detection and quantification of cow milk adulteration. Nevertheless, its effectiveness in conveniently detecting adulteration in camel milk remains to be determined. Camel milk samples were collected from Alxa League, Inner Mongolia, China, and were supplemented with varying concentrations of cow milk samples. Spectra were acquired using the FOSS FT6000 spectrometer, and a diverse set of machine learning models was employed to detect cow milk adulteration in camel milk. Our results demonstrate that the Linear Discriminant Analysis (LDA) model effectively distinguishes pure camel milk from adulterated samples, maintaining a 100% detection rate even at cow milk addition levels of 10 g/100 g. The neural network quantitative model for cow milk adulteration in camel milk exhibited a detection limit of 3.27 g/100 g and a quantification limit of 10.90 g/100 g. The quantitative model demonstrated excellent precision and accuracy within the range of 10-90 g/100 g of adulteration. This study highlights the potential of FT-MIR spectroscopy in conjunction with machine learning techniques for ensuring the authenticity and quality of camel milk, thus addressing concerns related to food integrity and consumer safety.

Minerals and essential amino acids of bovine colostrum: Phenotypic variability and predictive ability of mid- and near-infrared spectroscopy

Colostrum quality and volume are fundamental for calves because it is the primary supplier of antibodies and the first source of energy, carbohydrates, lipids, proteins, minerals, and vitamins for the newborn. Assessing the detailed composition (i.e., AA and mineral content) of bovine colostrum (BC) on-line and at a reasonable cost would help dairy stakeholders such as farmers or veterinarians for precision feeding purposes and industries producing preparations containing BC such as foodstuff, supplements, and medicaments. In the present study we evaluated mid- (MIRS) and near-infrared spectroscopy (NIRS) prediction ability for AA and mineral composition of individual BC. Second, we the investigated the major factors affecting the phenotypic variability of such traits also evaluating the correlations with the Ig concentration. Results demonstrated that MIRS and NIRS were able to provide sufficiently accurate predictions for all the AA. The coefficient of determination in external validation (R2V) fell, in fact, within the range of 0.70 to 0.86, with the exception of Ile, His, and Met. Only some minerals reached a sufficient accuracy (i.e., Ca, P, S, and Mg; R2V ≥ 0.66) using MIRS, and also S (R2V = 0.87) using NIRS. Phenotypically, both parity and calving season affected the variability of these BC composition traits. Heifers' colostrum was the one with the greatest concentration of Ca and P, the 2 most abundant minerals. These minerals were however very low in cows calving in summer compared with the rest of the year. The pattern of AA across parities and calving season was not linear, likely because their variability was scarcely (or not) affected by these effects. Finally, samples characterized by high IgG concentration were those presenting on average greater concentration of AA. Findings suggest that infrared spectroscopy has the potential to be used to predict certain AA and minerals, outlining the possibility of implementing on-site analyses for the evaluation of the broad-sense BC quality.

Imputation of missing milk Fourier transform mid-infrared spectra using existing milk spectral databases: A strategy to improve the reliability of breeding values and predictive models

The use of milk Fourier transform mid-infrared (FT-MIR) spectrometry to develop management and breeding tools for dairy farmers and industry is growing and supported by the availability of numerous new predicted phenotypes to assess the nutritional quality of milk and its technological properties, but also the animal health and welfare status and its environmental fingerprint. For genetic evaluations, having a long-term and representative spectral dairy herd improvement (DHI) database improves the reliabilities of estimated breeding values (EBV) from these phenotypes. Unfortunately, most of the time, the raw spectral data used to generate these estimations are not stored. Moreover, many reference measurements of those phenotypes, needed during the FT-MIR calibration step, are available from past research activities but lack spectra records. So, it is impossible to use them to improve the FT-MIR models. Consequently, there is a strong interest in imputing those missing spectra. The innovative objective of this study was to use the existing large spectral DHI database to estimate missing spectra by selecting probable spectra using, as the match criteria, common dairy traits recorded for a long time by DHI organizations. We tested 4 match criteria combinations. Combination 1 required to have equal fat and protein contents between the sample for which a spectrum was to be estimated and the reference samples in the DHI database. Combination 2 also required an equal urea content. Combination 3 requested equal fat, protein, and lactose contents. Finally, combination 4 included all criteria. When more than one spectrum was found during the search, their average was the estimated spectrum for the query sample. Concretely, this study estimated missing spectra for 1,700 samples using 2,000,000 spectral DHI records. For assessing the effect of this spectral estimation on the prediction quality, FT-MIR equations were used to predict 11 phenotypes, selected as their quantification used different FT-MIR regions. They were related to the milk fat and mineral composition, lactoferrin content, quantity of eructed methane, body weight (BW), and dry matter intake. The accuracy between predictions obtained from actual and estimated spectra was evaluated by calculating the mean absolute error (MAE). The criteria in the fourth and second combinations were too strict to estimate a spectrum for most samples. Indeed, for many samples, no spectra with the same values for those matching criteria was found. The third match criteria combination had a poorer prediction performance for all studied traits and spectral absorptions than the first combination due to fewer matched samples available to compute the missing spectrum. By allowing a range for matching lactose content (±0.1 g/dL milk), we showed that this new combination increased the number of selected samples to compute missing spectra and predict better the infrared absorption at different wavenumbers, especially those related to the lactose quantification. The prediction performance was further improved by performing queries on the entire Walloon DHI spectral database (6,625,570 spectra), and it varied among the studied phenotypes. Without considering the traits used for the matching, the best predictions were obtained for the content of saturated fatty acids (MAE = 0.15 g/dL milk) and BW (MAE = 12.80 kg). Yet, the predictions for the unsaturated fatty acids were less accurate (MAE = 0.13 and 0.018 g/dL milk for monounsaturated and polyunsaturated fatty acids), likely because of the poorer predictions of spectral regions related to long-chain fatty acids. Similarly, poorer predictions were observed for the amount of methane eructed by dairy cows (MAE = 47.02 g/d), likely because it is not directly related to fat content or composition. Prediction accuracies for the remaining traits were also low. In conclusion, we observed that increasing the number of relevant matching criteria helps improve the quality of FT-MIR predicted phenotypes and the number of spectra used during the search. So, it would be of great interest to test in the future the suitability of the developed methodology with large-scale international spectral databases to improve the reliability of EBV from these FT-MIR-based phenotypes and the robustness of FT-MIR predictive models.

Mid-infrared spectroscopy for large-scale phenotyping of bovine colostrum gross composition and immunoglobulin concentration

Immunoglobulin G is the fundamental antibody for acquisition of passive transfer of immunity in ruminant newborns. Colostrum, in fact, must be administered as soon as possible after birth to ensure a successful transfer of IgG from the dam to the calf. Assessment of colostrum Ig concentration and gross composition via gold standards is expensive, time consuming, and hardly implementable for large-scale investigations. Therefore, in the present study we evaluated the predictive ability of mid-infrared spectroscopy (MIRS) as an indirect determination method. A total of 714 colostrum samples collected within 6 h from parturition from Italian Holstein cows, 30% primiparous and 70% pluriparous, were scanned using a benchtop spectrometer after dilution in pure water. The prediction models were developed by correlating spectral information with the reference measurements: IgG concentration (93.54 ± 33.87 g/L), total Ig concentrations (102.82 ± 35.04 g/L), and content of protein (14.71 ± 3.51%), fat (4.61 ± 3.04%), and lactose (2.36 ± 0.51 mg/100 mg). We found a good to excellent performance in prediction of colostrum IgG concentration and traditional composition traits in cross-validation (R2CV ≥ 0.92) and a promising and good predictive ability in external validation with R2V equal to 0.84, 0.89, and 0.74 for IgG, protein, and fat, respectively. In the case of IgG and protein content, for example, the coefficient of determination in external validation was greater than 0.84. The other Ig fractions, A and M, presented insufficient prediction accuracy likely due to their extremely low concentration compared with IgG (4.56 and 5.06 g/L vs. 93.54 g/L). The discriminant ability of MIRS-predicted IgG and protein content was outstanding when trying to classify samples according to the quality level (i.e., low vs. high concentration of IgG). In particular, the cut-off that better discriminate low- from high-quality colostrum was 75.40 g/L in the case of the MIRS-predicted IgG and 13.32% for the MIRS-predicted protein content. Therefore, MIRS is proposed as a rapid and cheap tool for large-scale punctual IgG, protein, and lactose quantification and for the screening of low-quality samples. From a practical perspective, there is the possibility to install colostrum models in the MIRS benchtop machineries already present in laboratories in charge of official milk testing. Colostrum phenotypes collected on an individual basis will be useful to breeders for the definition of specific selection strategies and to farmers for management scopes. Finally, our findings may be relevant for other stakeholders, given the fact that colostrum is an emerging ingredient for the animal and human food and pharmaceutical industry.

Effectiveness of mid-infrared spectroscopy for the prediction of cow milk metabolites

Proton nuclear magnetic resonance (¹H NMR) spectroscopy is acknowledged as one of the most powerful analytical methods with cross-cutting applications in dairy foods. To date, the use of ¹H NMR spectroscopy for the collection of milk metabolic profile is hindered by costly and time-consuming sample preparation and analysis. The present study aimed at evaluating the accuracy of mid-infrared spectroscopy (MIRS) as a rapid method for the prediction of cow milk metabolites determined through ¹H NMR spectroscopy. Bulk milk (n = 72) and individual milk samples (n = 482) were analyzed through one-dimensional ¹H NMR spectroscopy and MIRS. Nuclear magnetic resonance spectroscopy identified 35 milk metabolites, which were quantified in terms of relative abundance, and MIRS prediction models were developed on the same 35 milk metabolites, using partial least squares regression analysis. The best MIRS prediction models were developed for galactose-1-phosphate, glycerophosphocholine, orotate, choline, galactose, lecithin, glutamate, and lactose, with coefficient of determination in external validation from 0.58 to 0.85, and ratio of performance to deviation in external validation from 1.50 to 2.64. The remaining 27 metabolites were poorly predicted. This study represents a first attempt to predict milk metabolome. Further research is needed to specifically address whether developed prediction models may find practical application in the dairy sector, with particular regard to the screening of dairy cows' metabolic status, the quality control of dairy foods, and the identification of processed milk or incorrectly stored milk.

Evaluation of the adulteration of camel milk by non-camel milk using multispectral image, fluorescence and infrared spectroscopy

In the present study, the focus was to evaluate the potential of three spectroscopic techniques (Middle Infrared -MIR-, fluorescence, and multispectral imaging -MSI-) to check the level of adulteration in camel milk with goat, cow, and ewe milks. Camel milk was adulterated with goat, ewe, and cow milks, respectively, at 6 different levels viz. 0.5, 1, 2, 5, 10, and 15%. After preprocessing the data with standard normal variate (SNV), multiplicative scattering correction (MSC), and normalization (area under spectrum = 1), partial least squares regression (PLSR) and partial least squares discriminant analysis (PLSDA) were used to predict the adulteration level and their belonging group, respectively. The PLSR and PLSDA models, validated using external data, highlighted that fluorescence spectroscopy was the most accurate technique giving a Rp² ranging between 0.63 and 0.96 and an accuracy ranging between 67 and 83%. However, no technique has allowed the construction of robust PLSR and PLSDA models for the simultaneous prediction of contamination of camel milk by the three milks.

Estimation of body condition score change in dairy cows in a seasonal calving pasture-based system using routinely available milk mid-infrared spectra and machine learning techniques

Body condition score (BCS) is a subjective estimate of body reserves in cows. Body condition score and its change in early lactation have been associated with cow fertility and health. The aim of the present study was to estimate change in BCS (ΔBCS) using mid-infrared spectra of the milk, with a particular focus on estimating ΔBCS in cows losing BCS at the fastest rate (i.e., the cows most of interest to the producer). A total of 73,193 BCS records (scale 1 to 5) from 6,572 cows were recorded. Daily BCS was interpolated from cubic splines fitted through the BCS records, and subsequently used to calculate daily ΔBCS. Body condition score change records were merged with milk mid-infrared spectra recorded on the same week. Both morning (a.m.) and evening (p.m.) spectra were available. Two different statistical methods were used to estimate ΔBCS: partial least squares regression and a neural network (NN). Several combinations of variables were included as model features, such as days in milk (DIM) only, a.m. spectra only and DIM, p.m. spectra only and DIM, and a.m. and p.m. spectra as well as DIM. The data used to estimate ΔBCS were either based on the first 120 DIM or all 305 DIM. Daily ΔBCS had a standard deviation of 1.65 × 10^-3 BCS units in the 305 DIM data set and of 1.98 × 10^-3 BCS units in the 120 DIM data set. Each data set was divided into 4 sub-data sets, 3 of which were used for training the prediction model and the fourth to test it. This process was repeated until all the sub-data sets were considered as the test data set once. Using all 305 DIM, the lowest root mean square error of validation (RMSEV; 0.96 × 10^-3 BCS units) and the strongest correlation between actual and estimated ΔBCS (0.82) was achieved with NN using a.m. and p.m. spectra and DIM. Using the 120 DIM data, the lowest RMSEV (0.98 × 10^-3 BCS units) and the strongest correlation between actual and estimated ΔBCS (0.87) was achieved with NN using DIM and either a.m. spectra only or a.m. and p.m. spectra together. The RMSEV for records in the lowest 2.5% ΔBCS percentile per DIM in early lactation was reduced up to a maximum of 13% when spectra and DIM were both considered in the model compared with a model that considered just DIM. The performance of the NN using DIM and a.m. spectra only with the 120 DIM data was robust across different strata of farm, parity, year of sampling, and breed. Results from the present study demonstrate the ability of mid-infrared spectra of milk coupled with machine learning techniques to estimate ΔBCS; specifically, the inclusion of spectral data reduced the RMSEV over and above using DIM alone, particularly for cows losing BCS at the fastest rate. This approach can be used to routinely generate estimates of ΔBCS that can subsequently be used for farm decisions.

Prediction of detailed blood metabolic profile using milk infrared spectra and machine learning methods in dairy cattle

The adoption of preventive management decisions is crucial to dealing with metabolic impairments in dairy cattle. Various serum metabolites are known to be useful indicators of the health status of cows. In this study, we used milk Fourier-transform mid-infrared (FTIR) spectra and various machine learning (ML) algorithms to develop prediction equations for a panel of 29 blood metabolites, including those related to energy metabolism, liver function/hepatic damage, oxidative stress, inflammation/innate immunity, and minerals. For most traits, the data set comprised observations from 1,204 Holstein-Friesian dairy cows belonging to 5 herds. An exception was represented by β-hydroxybutyrate prediction, which contained observations from 2,701 multibreed cows pertaining to 33 herds. The best predictive model was developed using an automatic ML algorithm that tested various methods, including elastic net, distributed random forest, gradient boosting machine, artificial neural network, and stacking ensemble. These ML predictions were compared with partial least squares regression, the most commonly used method for FTIR prediction of blood traits. Performance of each model was evaluated using 2 cross-validation (CV) scenarios: 5-fold random (CV_r) and herd-out (CV_h). We also tested the best model's ability to classify values precisely in the 2 extreme tails, namely, the 25th (Q25) and 75th (Q75) percentiles (true-positive prediction scenario). Compared with partial least squares regression, ML algorithms achieved more accurate performance. Specifically, elastic net increased the R² value from 5% to 75% for CV_r and 2% to 139% for CV_h, whereas the stacking ensemble increased the R² value from 4% to 70% for CV_r and 4% to 150% for CV_h. Considering the best model, with the CV_r scenario, good prediction accuracies were obtained for glucose (R² = 0.81), urea (R² = 0.73), albumin (R² = 0.75), total reactive oxygen metabolites (R² = 0.79), total thiol groups (R² = 0.76), ceruloplasmin (R² = 0.74), total proteins (R² = 0.81), globulins (R² = 0.87), and Na (R² = 0.72). Good prediction accuracy in classifying extreme values was achieved for glucose (Q25 = 70.8%, Q75 = 69.9%), albumin (Q25 = 72.3%), total reactive oxygen metabolites (Q25 = 75.1%, Q75 = 74%), thiol groups (Q75 = 70.4%), total proteins (Q25 = 72.4%, Q75 = 77.2.%), globulins (Q25 = 74.8%, Q75 = 81.5%), and haptoglobin (Q75 = 74.4%). In conclusion, our study shows that FTIR spectra can be used to predict blood metabolites with relatively good accuracy, depending on trait, and are a promising tool for large-scale monitoring.

Novel prediction models for hyperketonemia using bovine milk Fourier-transform infrared spectroscopy

Metabolic diseases driven by negative energy balance in dairy cattle contribute to reduced milk production, increased disease incidence, culling, and death. Cow side tests for negative energy balance markers are available but are labor-intensive. Milk sample analysis using Fourier transform infrared spectroscopy (FTIR) allows for sampling numerous cows simultaneously. FTIR prediction models have moderate accuracy for hyperketonemia diagnosis (beta-hydroxybutyrate (BHB) ≥ 1.2 mmol/L). Most research using FTIR has focused on homogenous datasets and conventional prediction models, including partial least squares, linear discriminant analysis, and ElasticNet. Our objective was to evaluate more diverse modeling options, such as deep learning, gradient boosting machine models, and model ensembles for hyperketonemia classification. We compiled a sizable, heterogeneous dataset including milk FTIR and concurrent blood samples. Blood samples were tested for blood BHB, and wavenumber data was obtained from milk FTIR analysis. Using this dataset, we trained conventional prediction models and other options listed above. We demonstrate prediction model performance is similar for convolutional neural networks and ensemble models to simpler algorithm options. Results obtained from this study indicate that deep learning and model ensembles are potential algorithm options for predicting hyperketonemia in dairy cattle. Additionally, our results indicate hyperketonemia prediction models can be developed using heterogeneous datasets.

Importance of Mid-Infrared Spectra Regions for the Prediction of Mastitis and Ketosis in Dairy Cows

Mid-infrared (MIR) spectroscopy is routinely applied to determine major milk components, such as fat and protein. Moreover, it is used to predict fine milk composition and various traits pertinent to animal health. MIR spectra indicate an absorbance value of infrared light at 1060 specific wavenumbers from 926 to 5010 cm−1. According to research, certain parts of the spectrum do not contain sufficient information on traits of dairy cows. Hence, the objective of the present study was to identify specific regions of the MIR spectra of particular importance for the prediction of mastitis and ketosis, performing variable selection analysis. Partial least squares discriminant analysis (PLS-DA) along with three other statistical methods, support vector machine (SVM), least absolute shrinkage and selection operator (LASSO), and random forest (RF), were compared. Data originated from the Austrian milk recording and associated health monitoring system (GMON). Test-day data and corresponding MIR spectra were linked to respective clinical mastitis and ketosis diagnoses. Certain wavenumbers were identified as particularly relevant for the prediction models of clinical mastitis (23) and ketosis (61). Wavenumbers varied across four distinct statistical methods as well as concerning different traits. The results indicate that variable selection analysis could potentially be beneficial in the process of modeling.

Predicting milk protein fractions using infrared spectroscopy and a gradient boosting machine for breeding purposes in Holstein cattle

In recent years, increasing attention has been focused on the genetic evaluation of protein fractions in cow milk with the aim of improving milk quality and technological characteristics. In this context, advances in high-throughput phenotyping by Fourier transform infrared (FTIR) spectroscopy offer the opportunity for large-scale, efficient measurement of novel traits that can be exploited in breeding programs as indicator traits. We took milk samples from 2,558 Holstein cows belonging to 38 herds in northern Italy, operating under different production systems. Fourier transform infrared spectra were collected on the same day as milk sampling and stored for subsequent analysis. Two sets of data (i.e., phenotypes and FTIR spectra) collected in 2 different years (2013 and 2019-2020) were compiled. The following traits were assessed using HPLC: true protein, major casein fractions [α_S1-casein (CN), α_S2-CN, β-CN, κ-CN, and glycosylated-κ-CN], and major whey proteins (β-lactoglobulin and α-lactalbumin), all of which were measured both in grams per liter (g/L) and proportion of total nitrogen (% N). The FTIR predictions were calculated using the gradient boosting machine technique and tested by 3 different cross-validation (CRV) methods. We used the following CRV scenarios: (1) random 10-fold, which randomly split the whole into 10-folds of equal size (9-folds for training and 1-fold for validation); (2) herd/date-out CRV, which assigned 80% of herd/date as the training set with independence of 20% of herd/date assigned as the validation set; (3) forward/backward CRV, which split the data set in training and validation set according with the year of milk sampling (FTIR and gold standard data assessed in 2013 or 2019-2020) using the "old" and "new" databases for training and validation, and vice-versa with independence among them; (4) the CRV for genetic parameters (CRV-gen), where animals without pedigree as assigned as a fixed training population and animals with pedigree information was split in 5-folds, in which 1-fold was assigned to the fixed training population, and 4-folds were assigned to the validation set (independent from the training set). The results (i.e., measures and predictions) of CRV-gen were used to infer the genetic parameters for gold standard laboratory measurements (i.e., proteins assessed with HPLC) and FTIR-based predictions considering the CRV-gen scenario from a bi-trait animal model using single-step genomic BLUP. We found that the prediction accuracies of the gradient boosting machine equations differed according to the way in which the proteins were expressed, achieving higher accuracy when expressed in g/L than when expressed as % N in all CRV scenarios. Concerning the reproducibility of the equations over the different years, the results showed no relevant differences in predictive ability between using "old" data as the training set and "new" data as the validation set and vice-versa. Comparing the additive genetic variance estimates for milk protein fractions between the FTIR predicted and HPLC measures, we found reductions of -19.7% for milk protein fractions expressed in g/L, and -21.19% expressed as % N. Although we found reductions in the heritability estimates, they were small, with values ranging from -1.9 to -7.25% for g/L, and -1.6 to -7.9% for % N. The posterior distributions of the additive genetic correlations (r_a) between the FTIR predictions and the laboratory measurements were generally high (>0.8), even when the milk protein fractions were expressed as % N. Our results show the potential of using FTIR predictions in breeding programs as indicator traits for the selection of animals to enhance milk protein fraction contents. We expect acceptable responses to selection due to the high genetic correlations between HPLC measurements and FTIR predictions.

Spectroscopic technologies and data fusion: Applications for the dairy industry

Increasing consumer awareness, scale of manufacture, and demand to ensure safety, quality and sustainability have accelerated the need for rapid, reliable, and accurate analytical techniques for food products. Spectroscopy, coupled with Artificial Intelligence-enabled sensors and chemometric techniques, has led to the fusion of data sources for dairy analytical applications. This article provides an overview of the current spectroscopic technologies used in the dairy industry, with an introduction to data fusion and the associated methodologies used in spectroscopy-based data fusion. The relevance of data fusion in the dairy industry is considered, focusing on its potential to improve predictions for processing traits by chemometric techniques, such as principal component analysis (PCA), partial least squares regression (PLS), and other machine learning algorithms.

Predicting nitrogen use efficiency, nitrogen loss and dry matter intake of individual dairy cows in late lactation by including mid-infrared spectra of milk samples

BACKGROUND

Nitrate leaching to groundwater and surface water and ammonia volatilization from dairy farms have negative impacts on the environment. Meanwhile, the increasing demand for dairy products will result in more pollution if N losses are not controlled. Therefore, a more efficient, and environmentally friendly production system is needed, in which nitrogen use efficiency (NUE) of dairy cows plays a key role. To genetically improve NUE, extensively recorded and cost-effective proxies are essential, which can be obtained by including mid-infrared (MIR) spectra of milk in prediction models for NUE. This study aimed to develop and validate the best prediction model of NUE, nitrogen loss (NL) and dry matter intake (DMI) for individual dairy cows in China.

RESULTS

A total of 86 lactating Chinese Holstein cows were used in this study. After data editing, 704 records were obtained for calibration and validation. Six prediction models with three different machine learning algorithms and three kinds of pre-processed MIR spectra were developed for each trait. Results showed that the coefficient of determination (R²) of the best model in within-herd validation was 0.66 for NUE, 0.58 for NL and 0.63 for DMI. For external validation, reasonable prediction results were only observed for NUE, with R² ranging from 0.58 to 0.63, while the R² of the other two traits was below 0.50. The infrared waves from 973.54 to 988.46 cm^-1 and daily milk yield were the most important variables for prediction.

CONCLUSION

The results showed that individual NUE can be predicted with a moderate accuracy in both within-herd and external validations. The model of NUE could be used for the datasets that are similar to the calibration dataset. The prediction models for NL and 3-day moving average of DMI (DMI_a) generated lower accuracies in within-herd validation. Results also indicated that information of MIR spectra variables increased the predictive ability of models. Additionally, pre-processed MIR spectra do not result in higher accuracy than original MIR spectra in the external validation. These models will be applied to large-scale data to further investigate the genetic architecture of N efficiency and further reduce the adverse impacts on the environment after more data is collected.

Fourier transform mid-infrared milk screening to improve milk production and processing

Milk mid-infrared spectrometry has been used for many years to quantify major milk compounds. Recently, much research has been conducted to extend the use of this technology to predict new, relevant phenotypes to assess the animals' welfare and the nutritional quality of milk, as well as its technological quality and environmental footprint. The transition from the research stage to field implementation is not easy, due to intrinsic and extrinsic constraints, but some developments can be considered to address these issues.

Defining a nitrogen efficiency index in Holstein cows and assessing its potential effect on the breeding program of bulls

The purposes of this study were (1) to explore the relationship between 3 milk mid-infrared predicted features including nitrogen intake (NINT), milk true protein N (MTPN), and milk urea-N yield (MUNY); (2) to integrate these 3 features into an N efficiency index (NEI) and analyses approximate genetic correlations between the NEI and 37 traits (indices) of interest; and (3) to assess the potential effect of including the NEI into breeding programs of bulls. The edited data were 1,043,171 test-day records on 342,847 cows in 1,931 herds and 143,595 test-day records on 53,660 cows in 766 herds used for estimating breeding values (EBV) and variance components, respectively. The used records were within 5 to 50 d in milk. The records were grouped into primiparous and multiparous. The genetic parameters for the included mid-infrared features and EBV of the animals included in the pedigree were estimated using a multiple-trait repeatability animal model. Then, the EBV of the NINT, MTPN, MUNY were integrated into the NEI using a selection index assuming weights based on the N partitioning. The approximate genetic correlations between the NEI and 37 traits of interest were estimated using the EBV of the selected bulls. The bulls born from 2011 to 2014 with NEI were selected and the NEI distribution of these bulls having EBV for the 8 selected traits (indices) was checked. The heritability and repeatability estimates for NINT, MTPN, and MUNY ranged from 0.09 to 0.13, and 0.37 to 0.65, respectively. The genetic and phenotypic correlations between NINT, MTPN, and MUNY ranged from -0.31 to 0.87, and -0.02 to 0.42, respectively. The NEI ranged from -13.13 to 12.55 kg/d. In total, 736 bulls with reliability ≥0.50 for all included traits (NEI and 37 traits) and at least 10 daughters distributed in at least 10 herds were selected to investigate genetic aspects of the NEI. The NEI had positive genetic correlations with production yield traits (0.08-0.46), and negative genetic correlations with the investigated functional traits and indices (-0.71 to -0.07), except for the production economic index and functional type economic index. The daughters of bulls with higher NEI had lower NINT and MUNY, and higher MTPN. Furthermore, 26% of the bulls (n = 50) with NEI born between 2011 to 2014 had higher NEI and global economic index than the average in the selected bulls. Finally, the developed NEI has the advantage of large-scale prediction and therefore has the potential for routine application in dairy cattle breeding in the future.

Prediction of Acute and Chronic Mastitis in Dairy Cows Based on Somatic Cell Score and Mid-Infrared Spectroscopy of Milk

Simple Summary

Mid-infrared (MIR) spectroscopy is the method of choice to determine milk components like fat, protein and urea. We examined the potential of MIR spectra analyses for the prediction of clinical mastitis events of dairy cows additionally, or alternatively, to somatic cell count, which is routinely used as an indicator for mastitis monitoring. Prediction models based on MIR spectra and a somatic cell count-derived score (SCS) were developed and compared. A model based on MIR spectra and SCS proved more accurate at predicting mastitis than models based on either indicator alone. Consequently, MIR spectra analyses add extra value in the prediction of clinical mastitis, making them potentially useful for dairy farm management and as an auxiliary trait for the genetic evaluation of udder health.

Abstract

Monitoring for mastitis on dairy farms is of particular importance, as it is one of the most prevalent bovine diseases. A commonly used indicator for mastitis monitoring is somatic cell count. A supplementary tool to predict mastitis risk may be mid-infrared (MIR) spectroscopy of milk. Because bovine health status can affect milk composition, this technique is already routinely used to determine standard milk components. The aim of the present study was to compare the performance of models to predict clinical mastitis based on MIR spectral data and/or somatic cell count score (SCS), and to explore differences of prediction accuracies for acute and chronic clinical mastitis diagnoses. Test-day data of the routine Austrian milk recording system and diagnosis data of its health monitoring, from 59,002 cows of the breeds Fleckvieh (dual purpose Simmental), Holstein Friesian and Brown Swiss, were used. Test-day records within 21 days before and 21 days after a mastitis diagnosis were defined as mastitis cases. Three different models (MIR, SCS, MIR + SCS) were compared, applying Partial Least Squares Discriminant Analysis. Results of external validation in the overall time window (−/+21 days) showed area under receiver operating characteristic curves (AUC) of 0.70 when based only on MIR, 0.72 when based only on SCS, and 0.76 when based on both. Considering as mastitis cases only the test-day records within 7 days after mastitis diagnosis, the corresponding areas under the curve were 0.77, 0.83 and 0.85. Hence, the model combining MIR spectral data and SCS was performing best. Mastitis probabilities derived from the prediction models are potentially valuable for routine mastitis monitoring for farmers, as well as for the genetic evaluation of the trait udder health.

Pregnancy status predicted using milk mid-infrared spectra from dairy cattle

Accurate and timely pregnancy diagnosis is an important component of effective herd management in dairy cattle. Predicting pregnancy from Fourier-transform mid-infrared (FT-MIR) spectroscopy data is of particular interest because the data are often already available from routine milk testing. The purpose of this study was to evaluate how well pregnancy status could be predicted in a large data set of 1,161,436 FT-MIR milk spectra records from 863,982 mixed-breed pasture-based New Zealand dairy cattle managed within seasonal calving systems. Three strategies were assessed for defining the nonpregnant cows when partitioning the records according to pregnancy status in the training population. Two of these used records for cows with a subsequent calving only, whereas the third also included records for cows without a subsequent calving. For each partitioning strategy, partial least squares discriminant analysis models were developed, whereby spectra from all the cows in 80% of herds were used to train the models, and predictions on cows in the remaining herds were used for validation. A separate data set was also used as a secondary validation, whereby pregnancy diagnosis had been assigned according to the presence of pregnancy-associated glycoproteins (PAG) in the milk samples. We examined different ways of accounting for stage of lactation in the prediction models, either by including it as an effect in the prediction model, or by pre-adjusting spectra before fitting the model. For a subset of strategies, we also assessed prediction accuracies from deep learning approaches, utilizing either the raw spectra or images of spectra. Across all strategies, prediction accuracies were highest for models using the unadjusted spectra as model predictors. Strategies for cows with a subsequent calving performed well in herd-independent validation with sensitivities above 0.79, specificities above 0.91 and area under the receiver operating characteristic curve (AUC) values over 0.91. However, for these strategies, the specificity to predict nonpregnant cows in the external PAG data set was poor (0.002-0.04). The best performing models were those that included records for cows without a subsequent calving, and used unadjusted spectra and days in milk as predictors, with consistent results observed across the training, herd-independent validation and PAG data sets. For the partial least squares discriminant analysis model, sensitivity was 0.71, specificity was 0.54 and AUC values were 0.68 in the PAG data set; and for an image-based deep learning model, the sensitivity was 0.74, specificity was 0.52 and the AUC value was 0.69. Our results demonstrate that in pasture-based seasonal calving herds, confounding between pregnancy status and spectral changes associated with stage of lactation can inflate prediction accuracies. When the effect of this confounding was reduced, prediction accuracies were not sufficiently high enough to use as a sole indicator of pregnancy status.

Opportunities to Harness High-Throughput and Novel Sensing Phenotypes to Improve Feed Efficiency in Dairy Cattle

Simple Summary

Sensors, routinely collected on-farm tests, and other repeatable, high-throughput measurements can provide novel phenotype information on a frequent basis. Information from these sensors and high-throughput measurements could be harnessed to monitor or predict individual dairy cow feed intake. Predictive algorithms would allow for genetic selection of animals that consume less feed while producing the same amount of milk. Improved monitoring of feed intake could reduce the cost of milk production, improve animal health, and reduce the environmental impact of the dairy industry. Moreover, data from these information sources could aid in animal management (e.g., precision feeding and health detection). In order to implement tools, the relationship of measurements with feed intake needs to be established and prediction equations developed. Lastly, consideration should be given to the frequency of data collection, the need for standardization of data and other potential limitations of tools in the prediction of feed intake. This review summarizes measurements of feed efficiency, factors that may impact the efficiency and feed consumption of an animal, tools that have been researched and new traits that could be utilized for the prediction of feed intake and efficiency, and prediction equations for feed intake and efficiency presented in the literature to date.

Abstract

Feed for dairy cattle has a major impact on profitability and the environmental impact of farms. Sustainable dairy production relies on continued improvement in feed efficiency as a way to reduce costs and nutrient loss from feed. Advances in breeding, feeding and management have led to the dilution of maintenance energy and thus more efficient dairy cattle. Still, many additional opportunities are available to improve individual animal feed efficiency. Sensing technologies such as wearable sensors, image-based and high-throughput phenotyping technologies (e.g., milk testing) are becoming more available on commercial farm. The application of these technologies as indicator traits for feed intake and efficiency related traits would be advantageous to provide additional information to predict and manage feed efficiency. This review focuses on precision livestock technologies and high-throughput phenotyping in use today as well as those that could be developed in the future as possible indicators of feed intake. Several technologies such as milk spectral data, activity, rumen measures, and image-based phenotypes have been associated with feed intake. Future applications will depend on the ability to repeatably measure and calibrate these data across locations, so that they can be integrated for use in predicting and managing feed intake and efficiency on farm.

Routine Monitoring of Instrument Stability in a Milk Testing Laboratory With ASCA: A Pilot Study

Mid-infrared spectroscopy has been developed as a reliable and rapid tool for routine analysis of fat, protein, lactose and other components in liquid milk. However, variations within and between FTIR instruments, even within the same milk testing laboratory, present a challenge to the accuracy of measurement of particularly minor components in the milk, such as individual fatty acids or proteins. In this study we have used Analysis of variance–Simultaneous Component Analysis (ASCA), to monitor the spectral variation between and within each of four different FOSS FTIR spectrometers over each week in an independent milk testing laboratory over 4 years, between August 2017 and March 2021 (223 weeks). On everyday of each week, spectra of the same pilot milk sample were recorded approximately every hour on each of the four instruments. Overall, variations between instruments had the largest effect on spectral variation over each week, making a significant contribution every week. Within each instrument, day-to-day variations over the week were also significant for all but two of the weeks measured, however it contributed less to the variance overall. At certain times other factors not explained by weekday variation or inter-instrument variation dominated the variance in the spectra. Examination of the scores and loadings of the weekly ASCA analysis allowed identification of changes in the spectral regions affected by drifts in each instrument over time. This was found to particularly affect some of the fatty acid predictions.

Developing a predictive model for beta-hydroxybutyrate and non-esterified fatty acids using milk fourier-transform infrared spectroscopy in dairy cows

Negative energy balance following parturition predisposes dairy cattle to numerous metabolic disorders. Current diagnostics are limited by their labor requirements and inability to measure multiple metabolic markers simultaneously. Fourier-transform Infrared spectroscopy (FTIR) data, measured from milk samples, could improve the detection of metabolic disorders using routine milk samples from dairy farms. The objective of this study was to develop a predictive model for numeric values of blood beta-hydroxybutyrate (BHB) and blood non-esterified fatty acids (NEFA). The study utilized a dataset comprised of 622 observations with known blood BHB and blood NEFA values measured concurrently with the milk FTIR data. Using ElasticNet regression on milk FTIR data and production information, we built regression models for numeric blood BHB and blood NEFA prediction and classification models for blood BHB values greater than 1.2 mmol/L and blood NEFA values greater than 0.7 mmol/L. The R² of the best fitting model was 0.56 and 0.51 for log-transformed BHB and log-transformed NEFA, respectively. The BHB classification model had a 90 % sensitivity and 83 % specificity and the NEFA classification model achieved a sensitivity of 73 % and specificity of 74 %. We applied our numeric prediction models to an external dataset (n = 9660) with known blood metabolites to validate the prediction accuracy of log-transformed blood BHB and log-transformed blood NEFA models. Log-transformed BHB root mean square error (RMSE) was 0.4018 and log-transformed NEFA RMSE was 0.4043. The second objective of this study was to develop a categorization for cows as either metabolically disordered or healthy. Responses to negative energy balance in transition cows are related to blood levels of BHB and NEFA. Cows suffering from metabolic disorders without elevated blood BHB values remain unidentified when detection is focused on blood BHB alone. To account for this differentiated metabolic response, we categorized cows as either 'metabolically healthy' or suffering a 'metabolic disorder' by using a combination of blood BHB, blood NEFA, and milk fat to protein quotient. We obtained a balanced accuracy of 94 % for the prediction of cow metabolic status. Direct prediction of metabolic status can be used to identify hyperketonemic cows in addition to cows exhibiting metabolic response patterns not detected by elevated blood BHB alone.

Multiple Breeds and Countries' Predictions of Mineral Contents in Milk from Milk Mid-Infrared Spectrometry

Measuring the mineral composition of milk is of major interest in the dairy sector. This study aims to develop and validate robust multi-breed and multi-country models predicting the major minerals through milk mid-infrared spectrometry using partial least square regressions. A total of 1281 samples coming from five countries were analyzed to obtain spectra and in ICP-AES to measure the mineral reference contents. Models were built from records coming from four countries (n = 1181) and validated using records from the fifth country, Austria (n = 100). The importance of including local samples was tested by integrating 30 Austrian samples in the model while validating with the remaining 70 samples. The best performances were achieved using this second set of models, confirming the need to cover the spectral variability of a country before making a prediction. Validation root mean square errors were 54.56, 63.60, 7.30, 59.87, and 152.89 mg/kg for Na, Ca, Mg, P, and K, respectively. The built models were applied on the Walloon milk recording large-scale spectral database, including 3,510,077. The large-scale predictions on this dairy herd improvement database provide new insight regarding the minerals' variability in the population, as well as the effect of parity, stage of lactation, breeds, and seasons.

Sequence-based genome-wide association study of individual milk mid-infrared wavenumbers in mixed-breed dairy cattle

BACKGROUND

Fourier-transform mid-infrared (FT-MIR) spectroscopy provides a high-throughput and inexpensive method for predicting milk composition and other novel traits from milk samples. While there have been many genome-wide association studies (GWAS) conducted on FT-MIR predicted traits, there have been few GWAS for individual FT-MIR wavenumbers. Using imputed whole-genome sequence for 38,085 mixed-breed New Zealand dairy cattle, we conducted GWAS on 895 individual FT-MIR wavenumber phenotypes, and assessed the value of these direct phenotypes for identifying candidate causal genes and variants, and improving our understanding of the physico-chemical properties of milk.

RESULTS

Separate GWAS conducted for each of 895 individual FT-MIR wavenumber phenotypes, identified 450 1-Mbp genomic regions with significant FT-MIR wavenumber QTL, compared to 246 1-Mbp genomic regions with QTL identified for FT-MIR predicted milk composition traits. Use of mammary RNA-seq data and gene annotation information identified 38 co-localized and co-segregating expression QTL (eQTL), and 31 protein-sequence mutations for FT-MIR wavenumber phenotypes, the latter including a null mutation in the ABO gene that has a potential role in changing milk oligosaccharide profiles. For the candidate causative genes implicated in these analyses, we examined the strength of association between relevant loci and each wavenumber across the mid-infrared spectrum. This revealed shared association patterns for groups of genomically-distant loci, highlighting clusters of loci linked through their biological roles in lactation and their presumed impacts on the chemical composition of milk.

CONCLUSIONS

This study demonstrates the utility of FT-MIR wavenumber phenotypes for improving our understanding of milk composition, presenting a larger number of QTL and putative causative genes and variants than found from FT-MIR predicted composition traits. Examining patterns of significance across the mid-infrared spectrum for loci of interest further highlighted commonalities of association, which likely reflects the physico-chemical properties of milk constituents.

Infrared spectroscopy combined with random forest to determine tylosin residues in powdered milk

The contamination of milk by antibiotic residues is a worldwide health and food safety problem. There is a need to develop new methods for the rapid determination of antibiotic residues in milk. A method has been developed for determining tylosin residues directly in powdered milk using Fourier Transformed Infrared spectroscopy (FTIR). Tylosin is a broad-spectrum macrolide antibiotic. The spectra obtained were submitted to chemometric analysis to obtain a prediction model for tylosin concentration in powdered milk. Using the Boruta algorithm, the absorption bands related to the milk contamination by the antibiotic were identified. Random forest was shown to be adequate for the prediction of tylosin residues in milk at low concentrations (≤ 100 μg L^-1) and the prediction model generated showed high correlation and determination coefficients (greater than 0.95). The proposed methodology proved to be efficient for the investigation of antibiotic residues in powdered milk.

Multiple Country Approach to Improve the Test-Day Prediction of Dairy Cows' Dry Matter Intake

Simple Summary

Dry matter intake, related to the number of nutrients available to an animal to meet its production and health needs, is crucial for the economic, environmental, and welfare management of dairy herds. Because the equipment required to weigh the ingested food at an individual level is not broadly available, we propose some new ways to approach the actual dry matter consumed by a dairy cow for a given day. To do so, we used regression models using parity (number of lactations), week of lactation, milk yield, milk mid-infrared spectrum, and prediction of bodyweight, fat, protein, lactose, and fatty acids content in milk. We chose these elements to predict individual dry matter intake because they are either easily accessible or routinely provided by regional dairy organizations (often called “dairy herd improvement” associations). We succeeded in producing a model whose dry matter intake predictions were moderately related to the actual values.

Abstract

We predicted dry matter intake of dairy cows using parity, week of lactation, milk yield, milk mid-infrared (MIR) spectrum, and MIR-based predictions of bodyweight, fat, protein, lactose, and fatty acids content in milk. The dataset comprised 10,711 samples of 534 dairy cows with a geographical diversity (Australia, Canada, Denmark, and Ireland). We set up partial least square (PLS) regressions with different constructs and a one-hidden-layer artificial neural network (ANN) using the highest contribution variables. In the ANN, we replaced the spectra with their projections to the 25 first PLS factors explaining 99% of the spectral variability to reduce the model complexity. Cow-independent 10 × 10-fold cross-validation (CV) achieved the best performance with root mean square errors (RMSE_CV) of 3.27 ± 0.08 kg for the PLS regression and 3.25 ± 0.13 kg for ANN. Although the available data were significantly different, we also performed a country-independent validation (CIV) to measure the models’ performance fairly. We found RMSE_CIV varying from 3.73 to 6.03 kg for PLS and 3.69 to 5.08 kg for ANN. Ultimately, based on the country-independent validation, we discussed the developed models’ performance with those achieved by the National Research Council’s equation.

Validation of Dairy Cow Bodyweight Prediction Using Traits Easily Recorded by Dairy Herd Improvement Organizations and Its Potential Improvement Using Feature Selection Algorithms

Knowing the body weight (BW) of a cow at a specific moment or measuring its changes through time is of interest for management purposes. The current work aimed to validate the feasibility of predicting BW using the day in milk, parity, milk yield, and milk mid-infrared (MIR) spectrum from a multiple-country dataset and reduce the number of predictors to limit the risk of over-fitting and potentially improve its accuracy. The BW modeling procedure involved feature selections and herd-independent validation in identifying the most interesting subsets of predictors and then external validation of the models. From 1849 records collected in 9 herds from 360 Holstein cows, the best performing models achieved a root mean square error (RMSE) for the herd-independent validation between 52 ± 2.34 kg to 56 ± 3.16 kg, including from 5 to 62 predictors. Among these models, three performed remarkably well in external validation using an independent dataset (N = 4067), resulting in RMSE ranging from 52 to 56 kg. The results suggest that multiple optimal BW predictive models coexist due to the high correlations between adjacent spectral points.

FTIR spectroscopy with chemometrics for determination of tylosin residues in milk

BACKGROUND

Contamination of milk by antibiotic residues represents risks to the health of consumers; therefore they should be monitored. The objective of this study was to propose a methodology for the determination of tylosin residues directly in fluid milk based on mid-infrared spectroscopy associated with chemometrics, using attenuated total reflection Fourier transform infrared (ATR-FTIR) spectroscopy associated with multilayer perceptron network (MLP) and partial least squares (PLS).

RESULTS

MLP was shown to be adequate for the discrimination of milk samples contaminated with tylosin below or equal to or above the maximum residue limit (MRL), with an accuracy greater than 99%, using FTIR spectra data. PLS was shown to be appropriate for the prediction of the very low concentrations (0-100 μg L^-1 ) of tylosin residues in milk using FTIR spectra data. PLS models with high correlation coefficients (R > 0.99) were generated.

CONCLUSION

FTIR with chemometrics proved to be a non-destructive, efficient and low-cost method for the investigation and quantification of tylosin residues directly in fluid milk. © 2020 Society of Chemical Industry.

Development of a subacute ruminal acidosis risk score and its prediction using milk mid-infrared spectra in early-lactation cows

A routine monitoring for subacute ruminal acidosis (SARA) on the individual level could support the minimization of economic losses and the ensuring of animal welfare in dairy cows. The objectives of this study were (1) to develop a SARA risk score (SRS) by combining information from different data acquisition systems to generate an integrative indicator trait, (2) the investigation of associations of the SRS with feed analysis data, blood characteristics, performance data, and milk composition, including the fatty acid (FA) profile, (3) the development of a milk mid-infrared (MIR) spectra-based prediction equation for this novel reference trait SRS, and (4) its application to an external data set consisting of MIR data of test day records to investigate the association between the MIR-based predictions of the SRS and the milk FA profile. The primary data set, which was used for the objectives (1) to (3), consisted of data collected from 10 commercial farms with a total of 100 Holstein cows in early lactation. The data comprised barn climate parameters, pH and temperature logging from intrareticular measurement boluses, as well as jaw movement and locomotion behavior recordings of noseband-sensor halters and pedometers. Further sampling and data collection included feed samples, blood samples, milk performance, and milk samples, whereof the latter were used to get the milk MIR spectra and to estimate the main milk components, the milk FA profile, and the lactoferrin content. Because all measurements were characterized by different temporal resolutions, the data preparation consisted of an aggregation into values on a daily basis and merging it into one data set. For the development of the SRS, a total of 7 traits were selected, which were derived from measurements of pH and temperature in the reticulum, chewing behavior, and milk yield. After adjustment for fixed effects and standardization, these 7 traits were combined into the SRS using a linear combination and directional weights based on current knowledge derived from literature studies. The secondary data set was used for objective (4) and consisted of test day records of the entire herds, including performance data, milk MIR spectra and MIR-predicted FA. At farm level, it could be shown that diets with higher proportions of concentrated feed resulted in both lower daily mean pH and higher SRS values. On the individual level, an increased SRS could be associated with a modified FA profile (e.g., lower levels of short- and medium-chain FA, higher levels of C17:0, odd- and branched-chain FA). Furthermore, a milk MIR-based partial least squares regression model with a moderate predictability was established for the SRS. This work provides the basis for the development of routine SARA monitoring and demonstrates the high potential of milk composition-based assessment of the health status of lactating cows.

Estimation of genetic parameters for predicted nitrogen use efficiency and losses in early lactation of Holstein cows

The objective of this study was to estimate genetic parameters of predicted N use efficiency (PNUE) and N losses (PNL) as proxies of N use and loss for Holstein cows. Furthermore, we have assessed approximate genetic correlations between PNUE, PNL, and dairy production, health, longevity, and conformation traits. These traits are considered important in many countries and are currently evaluated by the International Bull Evaluation Service (Interbull). The values of PNUE and PNL were obtained by using the combined milk mid-infrared (MIR) spectrum, parity, and milk yield-based prediction equations on test-day MIR records with days in milk (DIM) between 5 and 50 d. After editing, the final data set comprised 46,163 records of 21,462 cows from 154 farms in 5 countries. Each trait was divided into primiparous and multiparous (including second to fifth parity) groups. Genetic parameters and breeding values were estimated by using a multitrait (2-trait, 2-parity classes) repeatability model. Herd-year-season of calving, DIM, age of calving, and parity were used as fixed effects. Random effects were defined as parity (within-parity permanent environment), nongenetic cow (across-parity permanent environment), additive genetic animal, and residual effects. The estimated heritability of PNUE and PNL in the first and later parity were 0.13, 0.12, 0.14, and 0.13, and the repeatability values were 0.49, 0.40, 0.55, and 0.43, respectively. The estimated approximate genetic correlations between PNUE and PNL were negative and high (from -0.89 to -0.53), whereas the phenotypic correlations were also negative but relatively low (from -0.45 to -0.11). At a level of reliability of more than 0.30 for all novel traits, a total of 504 bulls born after 1995 had also publishable Interbull multiple-trait across-country estimated breeding values (EBV). The approximate genetic correlations between PNUE and the other 30 traits of interest, estimated as corrected correlations between EBV of bulls, ranged from -0.46 (udder depth) to 0.47 (milk yield). Obtained results showed the complex genetic relationship between efficiency, production, and other traits: for instance, more efficient cows seem to give more milk, which is linked to deeper udders, but seem to have lower health, fertility, and longevity. Additionally, the approximate genetic correlations between PNL, lower values representing less loss of N, and the 30 other traits, were from -0.32 (angularity) to 0.57 (direct calving ease). Even if further research is needed, our results provided preliminary evidence that the PNUE and PNL traits used as proxies could be included in genetic improvement programs in Holstein cows and could help their management.

Validation of milk mid-infrared spectroscopy for predicting the metabolic status of lactating dairy cows in Australia

Increased concentrations of some serum biomarkers are known to be associated with impaired health of dairy cows. Therefore, being able to predict these biomarkers, especially in the early stage of lactation, would enable preventive management decision. Some health biomarkers may also be used as phenotypes for genetic improvement for improved animal health. In this study, we validated the accuracy and robustness of models for predicting serum concentrations of β-hydroxybutyrate (BHB), fatty acids, and urea nitrogen, using milk mid-infrared (MIR) spectroscopy. The data included 3,262 blood samples of 3,027 lactating Holstein-Friesian cows from 19 dairy herds in Southeastern Australia, collected in the period from July 2017 to April 2020. The models were developed using partial least squares regression and were validated using 10-fold random cross-validation, herd-year by herd-year external validation, and year by year validation. The coefficients of determination (R²) for prediction of serum BHB, fatty acids, and urea obtained through random cross-validation were 0.60, 0.42, and 0.87, respectively. For the herd-year by herd-year external validation, the prediction accuracies held up comparatively well, with R² values of 0.49, 0.33, and 0.67 for of serum BHB, fatty acids, and urea, respectively. When the models were developed using data from a single year to predict data collected in future years, the R² remained comparable, however, the root mean squared errors increased substantially (4-10 times larger than compared with that of herd-year by herd-year external validation) which could be due to machine differences in spectral response, the change in spectral response of individual machines over time, or other differences associated with farm management between seasons. In conclusion, the mid-infrared equations for predicting serum BHB, fatty acids, and urea have been validated. The prediction equations could be used to help farmers detect cows with metabolic disorders in early lactation in addition to generating novel phenotypes for genetic improvement purposes.

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.

Predicting bovine tuberculosis status of dairy cows from mid-infrared spectral data of milk using deep learning

Bovine tuberculosis (bTB) is a zoonotic disease in cattle that is transmissible to humans, distributed worldwide, and considered endemic throughout much of England and Wales. Mid-infrared (MIR) analysis of milk is used routinely to predict fat and protein concentration, and is also a robust predictor of several other economically important traits including individual fatty acids and body energy. This study predicted bTB status of UK dairy cows using their MIR spectral profiles collected as part of routine milk recording. Bovine tuberculosis data were collected as part of the national bTB testing program for Scotland, England, and Wales; these data provided information from over 40,500 bTB herd breakdowns. Corresponding individual cow life-history data were also available and provided information on births, movements, and deaths of all cows in the study. Data relating to single intradermal comparative cervical tuberculin (SICCT) skin-test results, culture, slaughter status, and presence of lesions were combined to create a binary bTB phenotype labeled 0 to represent nonresponders (i.e., healthy cows) and 1 to represent responders (i.e., bTB-affected cows). Contemporaneous individual milk MIR spectral data were collected as part of monthly routine milk recording and matched to bTB status of individual animals on the single intradermal comparative cervical tuberculin test date (±15 d). Deep learning, a sub-branch of machine learning, was used to train artificial neural networks and develop a prediction pipeline for subsequent use in national herds as part of routine milk recording. Spectra were first converted to 53 × 20-pixel PNG images, then used to train a deep convolutional neural network. Deep convolutional neural networks resulted in a bTB prediction accuracy (i.e., the number of correct predictions divided by the total number of predictions) of 71% after training for 278 epochs. This was accompanied by both a low validation loss (0.71) and moderate sensitivity and specificity (0.79 and 0.65, respectively). To balance data in each class, additional training data were synthesized using the synthetic minority over sampling technique. Accuracy was further increased to 95% (after 295 epochs), with corresponding validation loss minimized (0.26), when synthesized data were included during training of the network. Sensitivity and specificity also saw a 1.22- and 1.45-fold increase to 0.96 and 0.94, respectively, when synthesized data were included during training. We believe this study to be the first of its kind to predict bTB status from milk MIR spectral data. We also believe it to be the first study to use milk MIR spectral data to predict a disease phenotype, and posit that the automated prediction of bTB status at routine milk recording could provide farmers with a robust tool that enables them to make early management decisions on potential reactor cows, and thus help slow the spread of bTB.

An Innovative Concept for a Multivariate Plausibility Assessment of Simultaneously Recorded Data

The aim of this work was to develop an innovative multivariate plausibility assessment (MPA) algorithm in order to differentiate between 'physiologically normal', 'physiologically extreme' and 'implausible' observations in simultaneously recorded data. The underlying concept is based on the fact that different measurable parameters are often physiologically linked. If physiologically extreme observations occur due to disease, incident or hormonal cycles, usually more than one measurable trait is affected. In contrast, extreme values of a single trait are most likely implausible if all other traits show values in a normal range. For demonstration purposes, the MPA was applied on a time series data set which was collected on 100 cows in 10 commercial dairy farms. Continuous measurements comprised climate data, intra-reticular pH and temperature, jaw movement and locomotion behavior. Non-continuous measurements included milk yield, milk components, milk mid-infrared spectra and blood parameters. After the application of the MPA, in particular the pH data showed the most implausible observations with approximately 5% of the measured values. The other traits showed implausible values up to 2.5%. The MPA showed the ability to improve the data quality for downstream analyses by detecting implausible observations and to discover physiologically extreme conditions even within complex data structures. At this stage, the MPA is not a fully developed and validated management tool, but rather corresponds to a basic concept for future works, which can be extended and modified as required.

Large-scale phenotyping in dairy sector using milk MIR spectra: Key factors affecting the quality of predictions

Methods and technologies enabling the estimation at large scale of important traits for the dairy sector are of great interest. Those phenotypes are necessary to improve herd management, animal genetic evaluation, and milk quality control. In the recent years, the research was very active to predict new phenotypes from the mid-infrared (MIR) analysis of milk. Models were developed to predict phenotypes such as fine milk composition, milk technological properties or traits related to cow health, fertility and environmental impact. Most of models were developed within research contexts and often not designed for routine use. The implementation of models at a large scale to predict new traits of interest brings new challenges as the factors influencing the robustness of models are poorly documented. The first objective of this work is to highlight the impact on prediction accuracy of factors such as the variability of the spectral and reference data, the spectral regions used and the complexity of models. The second objective is to emphasize methods and indicators to evaluate the quality of models and the quality of predictions generated under routine conditions. The last objective is to outline the issues and the solutions linked with the use and transfer of models on large number of instruments. Based on partial least square regression and 10 datasets including milk MIR spectra and reference quantitative values for 57 traits of interest, the impact of the different factors is illustrated by evaluating the influence on the validation root mean square error of prediction (RMSEP). In the displayed examples, all factors, when well set up, increase the quality of predictions, with an improvement of the RMSEP ranging from 12% to 43%. This work also aims to underline the need for and the complementarity between different validation procedures, statistical parameters and quality assurance methods. Finally, when using and transferring models, the impact of the spectral standardization on the prediction reproducibility is highlighted with an improvement up to 86% with the tested models, and the monitoring of individual spectrometer stability over time appears essential. This list inspired from our experience is of course not exhaustive. The displayed results are only examples and not general rules and other aspects play a role in the quality of final predictions. However, this work highlights good practices, methods and indicators to increase and evaluate quality of phenotypes predicted at a large scale. The results obtained argue for the development of guidelines at international levels, as well as international collaborations in order to constitute large and robust datasets and enable the use of models in routine conditions.

Use of near and mid infra-red spectroscopy for analysis of protein, fat, lactose and total solids in raw cow and camel milk

Milk samples (150 cow and 217 camel milk samples) were analyzed for protein, fat, lactose and total solids by near and mid-infrared transmission spectroscopy. Excellent positive correlations between the two methods were obtained for both types of milk (p < 0.001); for protein (r ≥ 0.96), fat (r ≥ 0.99), lactose (r = 0.82) and total solids (r = 0.90). The mean of the relative difference ((MIR values - NIR values)/0.5 (MIR values + NIR values) × 100%) for cow and camel milk were, for protein (+8.2 & +13.4%), fat (-9.3 & +0.9%), lactose (-5.4 &-0.7%) and total solids (-2.2 &-3.4%), respectively. The difference between the two methods may be due to the effects of differences in milk homogeneity, especially with respect to casein micelles and fat globules.

The use of milk Fourier transform mid-infrared spectra and milk yield to estimate heat production as a measure of efficiency of dairy cows

Background

Transformation of feed energy ingested by ruminants into milk is accompanied by energy losses via fecal and urine excretions, fermentation gases and heat. Heat production may differ among dairy cows despite comparable milk yield and body weight. Therefore, heat production can be considered an indicator of metabolic efficiency and directly measured in respiration chambers. The latter is an accurate but time-consuming technique. In contrast, milk Fourier transform mid-infrared (FTIR) spectroscopy is an inexpensive high-throughput method and used to estimate different physiological traits in cows. Thus, this study aimed to develop a heat production prediction model using heat production measurements in respiration chambers, milk FTIR spectra and milk yield measurements from dairy cows.

Methods

Heat production was computed based on the animal’s consumed oxygen, and produced carbon dioxide and methane in respiration chambers. Heat production data included 168 24-h-observations from 64 German Holstein and 20 dual-purpose Simmental cows. Animals were milked twice daily at 07:00 and 16:30 h in the respiration chambers. Milk yield was determined to predict heat production using a linear regression. Milk samples were collected from each milking and FTIR spectra were obtained with MilkoScan FT 6000. The average or milk yield-weighted average of the absorption spectra from the morning and afternoon milking were calculated to obtain a computed spectrum. A total of 288 wavenumbers per spectrum and the corresponding milk yield were used to develop the heat production model using partial least squares (PLS) regression.

Results

Measured heat production of studied animals ranged between 712 and 1470 kJ/kg BW^0.75. The coefficient of determination for the linear regression between milk yield and heat production was 0.46, whereas it was 0.23 for the FTIR spectra-based PLS model. The PLS prediction model using weighted average spectra and milk yield resulted in a cross-validation variance of 57% and a root mean square error of prediction of 86.5 kJ/kg BW^0.75. The ratio of performance to deviation (RPD) was 1.56.

Conclusion

The PLS model using weighted average FTIR spectra and milk yield has higher potential to predict heat production of dairy cows than models applying FTIR spectra or milk yield only.

Mid-infrared spectroscopic analysis of raw milk to predict the blood nonesterified fatty acid concentrations in dairy cows

In high-yielding dairy cattle, severe postpartum negative energy balance is often associated with metabolic and infectious disorders that negatively affect production, fertility, and welfare. Mobilization of adipose tissue associated with negative energy balance is reflected through an increased level of nonesterified fatty acids (NEFA) in the blood plasma. Earlier, identification of negative energy balance through detection of increased blood plasma NEFA concentration required laborious and stressful blood sampling. More recently, attempts have been made to predict blood NEFA concentration from milk samples. In this study, we aimed to develop and validate a model to predict blood plasma NEFA concentration using the milk mid-infrared (MIR) spectra that are routinely measured in the context of milk recording. To this end, blood plasma and milk samples were collected in wk 2, 3, and 20 postpartum for 192 lactations in 3 herds. The blood plasma samples were taken in the morning, and representative milk samples were collected during the morning and evening milk sessions on the same day. To predict plasma NEFA concentration from the milk MIR spectra, partial least squares regression models were trained on part of the observations from the first herd. The models were then thoroughly validated on all other observations of the first herd and on the observations of the 2 independent herds to explore their robustness and wide applicability. The final model could accurately predict blood plasma NEFA concentrations <0.6 mmol/L with a root mean square error of prediction of <0.143 mmol/L. However, for blood plasma with >1.2 mmol/L NEFA, the model clearly underestimated the true level. Additionally, we found that morning blood plasma NEFA levels were predicted with significantly higher accuracy using MIR spectra of evening milk samples compared with MIR spectra of morning samples, with root mean square error of prediction values of, respectively, 0.182 and 0.197 mmol/L, and R² values of 0.613 and 0.502. These results suggest a time delay between variations in blood plasma NEFA and related milk biomarkers. Based on the MIR spectra of evening milk samples, cows at risk for negative energy status, indicated by detrimental morning blood plasma NEFA levels (>0.6 mmol/L), could be identified with a sensitivity and specificity of, respectively, 0.831 and 0.800. As this model can be applied to millions of historical and future milk MIR spectra, it opens an opportunity for regular metabolic screening and improved resilience phenotyping.

Mid-infrared spectrometry prediction of the cheese-making properties of raw Montbéliarde milks from herds and cheese dairy vats used for the production of Protected Designation of Origin and Protected Geographical Indication cheeses in Franche-Comté

Franche-Comté is the primary producing region of Protected Designation of Origin cheeses in France. Normally, mid-infrared (MIR) prediction models for cheese-making property (CMP) traits are developed using individual bovine milks. However, considering the requests of all actors in the dairy sector, the present study aimed to assess the feasibility of MIR spectroscopy to develop CMP equations of Montbéliarde herd and dairy vat milks. For this purpose, 22 CMP traits were analyzed on samples collected in 2016 (half in February-March and half in May-June) from 100 commercial herds and 70 dairy vats (55 cheese dairies) located in Franche-Comté. These characteristics included 11 rennet coagulation traits and 8 lactic acidification traits measured in either soft cheese or pressed cooked cheese conditions and 3 laboratory curd yields. Models of MIR prediction for each of the 22 CMP traits were built using partial least squares regression with external validation by dividing the data set into calibration (70%) and validation (30%) sets. We confirmed that the variability of milk traits depends largely on the production scale and is higher for individual milk than for herd milk and even higher for vat milk. The best prediction models were obtained in herd milk samples for curd yields expressed in dry matter or fresh, with a coefficient of determination (R²) in external validation of 0.78 and 0.77, respectively. As with individual milk, these traits are closely related to the gross composition of the milk and therefore easier to predict by MIR spectroscopy. However, these curd yield traits were poorly predicted (R² = 0.58) in vat milk samples due to their lower variability. In herd milk samples, prediction models of other CMP traits were poorly accurate except for the ratio of the time to obtain a standard firmness to the rennet coagulation time in soft cheese or pressed cooked cheese conditions, which showed R² > 0.66 in external validation. Such trait is important in qualifying the behavior of milk during cheese production. Prediction models of other CMP traits for either herd or vat milk samples had poor accuracy, and further work is needed to improve their performance.