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

Integrating mid-infrared spectroscopy, machine learning, and graphical bias correction for fatty acid prediction in water buffalo milk

BACKGROUND

Buffalo milk, constituting 15% of global production, has higher fatty acids content than Holstein milk. Fourier-transform mid-infrared (FT-MIR) spectroscopy is widely used for dairy analysis, but its application to buffalo milk, with larger fat globules, remains understudied. The ultimate goal of this study is to develop machine learning models based on FT-MIR spectroscopy for predicting fatty acids in buffalo milk and to assess the accuracy of commercial milk analyzers. This research provides a convenient, fast, and environmentally friendly method for detecting the fatty acid composition in buffalo milk.

RESULTS

We employed six machine learning algorithms to establish a detection model for 34 fatty acids in buffalo milk. The predictive models demonstrated robust capabilities for high-content fatty acids [C14:0, C15:0, C16:0, C17:0, C18:0, C18:1, saturated fatty acid (SFA), monounsaturated fatty acid (MUFA)], with errors within a 15% range. Traditional FT6000 detection methods exhibited limitations in measuring SFAs and polyunsaturated fatty acids (PUFA). Implementing a mean difference correction of 0.21 for MUFAs and applying regression equations (SFA × 1.0639 + 0.0705; PUFA × 0.5472 + 0.0047) significantly improved measurement accuracy.

CONCLUSION

This study successfully developed a predictive model for fatty acids in Mediterranean buffalo milk based on FT-MIR spectroscopy. Additionally, a correction was applied to the existing measurement device, FT6000, enabling more accurate measurements of fatty acids in buffalo milk. The findings have practical implications for the food industry, offering a faster and more reliable approach to assess and monitor fatty acid composition in buffalo milk, potentially influencing product development and quality control processes. © 2024 Society of Chemical Industry.

Predicted essential fatty acid intakes for a group of dairy cows also apply at individual animal level

The ruminant requirements for essential fatty acids (EFAs), particularly linoleic acid (LA) and alpha-linolenic acid (ALA), have not been fully determined, although evidence suggests that an adequate supply of polyunsaturated fatty acids (FAs) could improve immunity and reproduction in transition cows. In previous studies, we predicted EFA intake for a group of cows based on animal characteristics and milk EFA secretions. However, to support precision livestock feeding, we need to match the nutrient requirements and intakes of each cow as closely as possible. Our group-level predictions may not be accurate enough to estimate the EFA intake of an individual cow, due to inter-individual variations in EFA digestion and metabolism related to differences in feed intake, intake patterns, and the composition and functioning of the rumen microbiota. To address this issue, here we set out to establish specific equations that predict EFA intake for an individual cow based on the difference (i.e. the residuals) between observed EFA intake and the predicted EFA intake based on our group-level equations. We studied a database of individual dairy cows (26 experiments; 503 datapoints from three research teams) and we predicted the residuals from (1) dietary and animal-related factors (i.e. full predictions) and (2) animal-related factors only (i.e. field predictions), which are considered more field-amenable. The variance of predicted LA and log ALA intake was explained to 68% by observed LA intake and 66% by observed log ALA intake, respectively. The residuals of LA intake were predicted by dietary ALA content, total FA intake, BW, milk yield and fat content in full predictions, and by BW, feeding level, milk yield and fat content, and sum of milk C4:0 to C14:0 FA in field predictions. The log residuals of ALA intake were predicted by dietary NDF and total FA contents, NDF intake, BW, milk protein, LA and ALA contents, and fat yield in full predictions, and by BW, DM intake, milk LA and ALA contents, and fat yield in field predictions. The field predictions showed a moderate loss of accuracy compared to full predictions based on RMSE of prediction (from 38 to 54 g/d for LA and from 0.090 to 0.12 log (g/d) for ALA). This work is the first to predict the EFA intake of an individual cow based on previously established group-level predictions of EFA intake adjusted for dietary and animal-related factors.

Cheese yield and nutrients recovery in the curd predicted by Fourier-transform spectra from individual sheep milk samples

The objectives of this study were to explore the use of Fourier-transform infrared (FTIR) spectroscopy on individual sheep milk samples for predicting cheese-making traits, and to test the effect of the farm variability on their prediction accuracy. For each of 121 ewes from 4 farms, a laboratory model cheese was produced, and 3 actual cheese yield traits (fresh cheese, cheese solids, and cheese water) and 4 milk nutrient recovery traits (fat, protein, total solids, and energy) in the curd were measured. Calibration equations were developed using a Bayesian approach with 2 different scenarios: (1) a random cross-validation (80% calibration; 20% validation set), and (2) a leave-one-out validation (3 farms used as calibration, and the remaining one as validation set) to assess the accuracy of prediction of samples from external farms, not included in calibration set. The best performance was obtained for predicting the yield and recovery of total solids, justifying for the practical application of the method at sheep population and dairy industry levels. Performances for the remaining traits were lower, but still useful for the monitoring of the milk processing in the case of fresh curd and recovery of energy. Insufficient accuracies were found for the recovery of protein and fat, highlighting the complex nature of the relationships among the milk nutrients and their recovery in the curd. The leave-one-out validation procedure, as expected, showed lower prediction accuracies, as a result of the characteristics of the farming systems, which were different between calibration and validation sets. In this regard, the inclusion of information related to the farm could help to improve the prediction accuracy of these traits. Overall, a large contribution to the prediction of the cheese-making traits came from the areas known as "water" and "fingerprint" regions. These findings suggest that, according to the traits studied, the inclusion of water regions for the development of the prediction equation models is fundamental to maintain a high prediction accuracy. However, further studies are necessary to better understand the role of specific absorbance peaks and their contribution to the prediction of cheese-making traits, to offer reliable tools applicable along the dairy ovine chain.

A Portable Infrared Attenuated Total Reflection Spectrometer for Food Analysis

The analytical performance of a compact infrared attenuated total reflection spectrometer using a pyroelectric detector array has been evaluated and compared to a conventional laboratory Fourier transform infrared system for applications in food analysis. Analytical characteristics including sensitivity, repeatability, linearity of the calibration functions, signal-to-noise ratio, and spectral resolution have been derived for both approaches. Representative analytes of relevance in food industries (i.e., organic solvents, fatty acids, and mycotoxins) have been used for the assessment of the performance of the device and to discuss the potential of this technology in food and feed analysis.

Selective breeding can contribute to bovine tuberculosis control and eradication

Bovine tuberculosis (bTB) persists in many countries having a significant impact on public health and livestock industry finances. The incidence and prevalence of new cases in parts of the UK and elsewhere over the past decades warrant intensified efforts towards achieving Officially Tuberculosis Free (OTF) status in the respective regions. Genetic selection aiming to identify and remove inherently susceptible animals from breeding has been proposed as an additional measure in ongoing programmes towards controlling the disease. The presence of genetic variation among individual animals in their capacity to respond to Mycobacterium bovis exposure has been documented and heritability estimates of 0.06-0.18 have been reported. Despite their moderate magnitude, these estimates suggest that host resistance to bTB is amenable to improvement with selective breeding. Although relatively slow, genetic progress can be constant, cumulative and permanent, thereby complementing ongoing disease control measures. Importantly, mostly no antagonistic genetic correlations have been found between bTB resistance and other animal traits suggesting that carefully incorporating the former in breeding decisions should not adversely affect bovine productivity. Simulation studies have demonstrated the potential impact of genetic selection on reducing the probability of a breakdown to occur or the duration and severity of a breakdown that has already been declared. Furthermore, research on the bovine genome has identified multiple genomic markers and genes associated with bTB resistance. Nevertheless, the combined outcomes of these studies suggest that host resistance to bTB is a complex, polygenic trait, with no single gene alone explaining the inherent differences between resistant and susceptible animals. Such results support the development of accurate genomic breeding values that duly capture the collective effect of multiple genes to underpin selective breeding programmes. In addition to improving host resistance to bTB, scientists and practitioners have considered the possibility of reducing host infectivity. Ongoing studies have suggested the presence of genetic variation for infectivity and confirmed that bTB eradication would be accelerated if selective breeding considered both host resistance and infectivity traits. In conclusion, research activity on bTB genetics has generated knowledge and insights to support selective breeding as an additional measure towards controlling and eradicating the disease.

Correlation between breeding values for milk fatty acids and Nordic Total Merit index traits for Danish Holstein and Danish Jersey

Milk fatty acid composition is gaining interest in the Danish dairy industry both to develop new dairy products and as a management tool. To be able to implement milk fatty acid (FA) composition in the breeding program, it is important to know the correlations with the traits in the breeding goal. To estimate these correlations, we measured milk fat composition in Danish Holstein (DH) and Danish Jersey (DJ) cattle breeds using mid-infrared spectroscopy. Breeding values were estimated for specific FA and for groups of FA. Correlations with the estimated breeding values (EBV) underlying the Nordic Total Merit index (NTM) were calculated within breed. For both DH and DJ, we showed that FA EBV had moderate correlations with the NTM and production traits. For both DH and DJ, the correlation of FA EBV and NTM were in the same direction, except for C16:0 (0 in DH, 0.23 in DJ). A few correlations differed between DH and DJ. The correlation between claw health index and C18:0 was negative in DH (-0.09) but positive in DJ (0.12). In addition, some correlations were not significant in DH but were significant in DJ. The correlations between udder health index and long-chain FA, trans FA, C16:0, and C18:0 were not significant in DH (-0.05 to 0.02), but were significant in DJ (-0.17, -0.15, 0.14, and -0.16, respectively). For both DH and DJ, the correlations between FA EBV and nonproduction traits were low. This implies that it is possible to breed for a different fat composition in the milk without affecting the nonproduction traits in the breeding goal.

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.

Using QTL to Identify Genes and Pathways Underlying the Regulation and Production of Milk Components in Cattle

Milk is a complex liquid, and the concentrations of many of its components are under genetic control. Many genes and pathways are known to regulate milk composition, and the purpose of this review is to highlight how the discoveries of quantitative trait loci (QTL) for milk phenotypes can elucidate these pathways. The main body of this review focuses primarily on QTL discovered in cattle (Bos taurus) as a model species for the biology of lactation, and there are occasional references to sheep genetics. The following section describes a range of techniques that can be used to help identify the causative genes underlying QTL when the underlying mechanism involves the regulation of gene expression. As genotype and phenotype databases continue to grow and diversify, new QTL will continue to be discovered, and although proving the causality of underlying genes and variants remains difficult, these new data sets will further enhance our understanding of the biology of lactation.

Using machine learning methods to predict dry matter intake from milk mid-infrared spectroscopy data on Swedish dairy cattle

In this research communication we compare three different approaches for developing dry matter intake (DMI) prediction models based on milk mid-infrared spectra (MIRS), using data collected from a research herd over five years. In dairy production, knowledge of individual DMI could be important and useful, but DMI can be difficult and expensive to measure on most commercial farms as cows are commonly group-fed. Instead, this parameter is often estimated based on the age, body weight, stage of lactation and body condition score of the cow. Recently, milk MIRS have also been used as a tool to estimate DMI. There are different methods available to create prediction models from large datasets. The main data used were total DMI calculated as a 3-d average, coupled with milk MIRS data available fortnightly. Data on milk yield and lactation stage parameters were also available for each animal. We compared the performance of three prediction approaches: partial least-squares regression, support vector machine regression and random forest regression. The full milk MIRS alone gave low to moderate prediction accuracy (R2 = 0.07-0.40), regardless of prediction modelling approach. Adding more variables to the model improved R2 and decreased the prediction error. Overall, partial least-squares regression proved to be the best method for predicting DMI from milk MIRS data, while MIRS data together with milk yield and concentrate DMI at 3-30 d in milk provided good prediction accuracy (R2 = 0.52-0.65) regardless of the prediction tool used.

Comparison of milk and grass composition from grazing Irish dairy herds with and without milk fat depression

BACKGROUND

This study investigated the factors relating to pasture chemical and fatty acid (FA) composition that influence the milk fat percentage of spring calving, grazing dairy cows. The relationship between milk fat percentage and FA composition of the milk in these herds was also investigated.

RESULTS

Milk protein percentage, milk casein percentage and cheddar cheese yield were increased in milk from HMF herds. Cows from LMF herds did not have negatively altered milk processability including rennet coagulation time (RCT), pH and ethanol stability. Crude protein, NDF, ADF, ether extract and total FA content of pasture was not different between LMF and HMF herds. Milk fat concentration of conjugated linoleic acid (CLA) t10, c12 was not different between HMF and LMF herds. Pre-grazing herbage mass and pasture content of crude protein, neutral detergent fibre (NDF) and total FA were similar between HMF and LMF herds. Pasture offered to LMF herds had a higher concentration of monounsaturated fatty acids (MUFA). A strong negative relationship (r = -0.40) was evident between milk fat percentage and pasture crude protein content for MMF herds (3.31-3.94% milk fat).

CONCLUSIONS

This research reports improved milk protein percentage, milk casein percentage and cheddar cheese yield from HMF herds compared to LMF herds. Milk processability was not impacted by low milk fat percentage. Pasture NDF and total fatty acid content was similar in HMF herds and LMF herds. Milk fat percentage had a strong negative association (r = -0.40) with pasture crude protein content in MMF herds (MF 3.31-3.94%). Correlation values between pasture chemical and FA composition and milk fat percentage in LMF herds and HMF herds were low, indicating that diet is not the only causative factor for variation in milk fat of grazing dairy cows. Comparison of milk fatty acid composition from herds with and without milk fat depression suggests that there may be other fatty acids apart from CLA t10, c12 that contribute to the inhibition of milk fat synthesis during milk fat depression in grazing herds.

Dry Matter Intake Prediction from Milk Spectra in Sarda Dairy Sheep

Individual dry matter intake (DMI) is a relevant factor for evaluating feed efficiency in livestock. However, the measurement of this trait on a large scale is difficult and expensive. DMI, as well as other phenotypes, can be predicted from milk spectra. The aim of this work was to predict DMI from the milk spectra of 24 lactating Sarda dairy sheep ewes. Three models (Principal Component Regression, Partial Least Squares Regression, and Stepwise Regression) were iteratively applied to three validation schemes: records, ewes, and days. DMI was moderately correlated with the wavenumbers of the milk spectra: the largest correlations (around ±0.30) were observed at ~1100-1330 cm^-1 and ~2800-3000 cm^-1. The average correlations between real and predicted DMI were 0.33 (validation on records), 0.32 (validation on ewes), and 0.23 (validation on days). The results of this preliminary study, even if based on a small number of animals, demonstrate that DMI can be routinely estimated from the milk spectra.

Effects of Protein Supplementation Strategy and Genotype on Milk Production and Nitrogen Utilisation Efficiency in Late-Lactation, Spring-Calving Grazing Dairy Cows

The objectives of this study were to evaluate the effects of (1) protein supplementation strategy, (2) cow genotype and (3) an interaction between protein supplementation strategy and cow genotype on milk production and nitrogen (N) utilisation efficiency (milk N output/ total dietary N intake × 100; NUE) in late-lactation, spring-calving grazing dairy cows. A 2 × 2 factorial arrangement experiment, with two feeding strategies [13% (lower crude protein; LCP) and 18% CP (higher CP; HCP) supplements with equal metabolisable protein supply] offered at 3.6 kg dry matter/cow perday, and two cow genotype groups [lower milk genotype (LM) and higher milk genotype (HM)], was conducted over 53 days. Cows were offered 15 kg dry matter of grazed herbage/cow/day. Herbage intake was controlled using electric strip wires which allowed cows to graze their daily allocation-only. There was an interaction for herbage dry matter intake within cows offered HCP, where higher milk genotype (HM) cows had increased herbage dry matter intake (+0.58 kg) compared to lower milk genotype (LM) cows. Offering cows LCP decreased fat + protein yield (-110 g) compared to offering cows HCP. Offering cows LCP decreased the total feed N proportion that was recovered in the urine (-0.007 proportion units) and increased the total feed N proportion that was recovered in the faeces (+0.008 proportion units) compared to offering cows HCP. In conclusion, our study shows that reducing the supplementary CP concentration from 18% to 13% resulted in decreased milk production (-9.8%), reduced partitioning of total feed N to urine (-0.9%) and increased partitioning of total feed N to faeces (+14%) in late lactation, grazing dairy cows.

Predictions of Milk Fatty Acid Contents by Mid-Infrared Spectroscopy in Chinese Holstein Cows

Genetic improvement of milk fatty acid content traits in dairy cattle is of great significance. However, chromatography-based methods to measure milk fatty acid content have several disadvantages. Thus, quick and accurate predictions of various milk fatty acid contents based on the mid-infrared spectrum (MIRS) from dairy herd improvement (DHI) data are essential and meaningful to expand the amount of phenotypic data available. In this study, 24 kinds of milk fatty acid concentrations were measured from the milk samples of 336 Holstein cows in Shandong Province, China, using the gas chromatography (GC) technique, which simultaneously produced MIRS values for the prediction of fatty acids. After quantification by the GC technique, milk fatty acid contents expressed as g/100 g of milk (milk-basis) and g/100 g of fat (fat-basis) were processed by five spectral pre-processing algorithms: first-order derivative (DER1), second-order derivative (DER2), multiple scattering correction (MSC), standard normal transform (SNV), and Savitzky-Golsy convolution smoothing (SG), and four regression models: random forest regression (RFR), partial least square regression (PLSR), least absolute shrinkage and selection operator regression (LassoR), and ridge regression (RidgeR). Two ranges of wavebands (4000~400 cm^-1 and 3017~2823 cm^-1/1805~1734 cm^-1) were also used in the above analysis. The prediction accuracy was evaluated using a 10-fold cross validation procedure, with the ratio of the training set and the test set as 3:1, where the determination coefficient (R²) and residual predictive deviation (RPD) were used for evaluations. The results showed that 17 out of 31 milk fatty acids were accurately predicted using MIRS, with RPD values higher than 2 and R² values higher than 0.75. In addition, 16 out of 31 fatty acids were accurately predicted by RFR, indicating that the ensemble learning model potentially resulted in a higher prediction accuracy. Meanwhile, DER1, DER2 and SG pre-processing algorithms led to high prediction accuracy for most fatty acids. In summary, these results imply that the application of MIRS to predict the fatty acid contents of milk is feasible.

Prediction of fresh and ripened cheese yield using detailed milk composition and udder health indicators from individual Brown Swiss cows

The composition of raw milk is of major importance for dairy products, especially fat, protein, and casein (CN) contents, which are used worldwide in breeding programs for dairy species because of their role in human nutrition and in determining cheese yield (%CY). The aim of the study was to develop formulas based on detailed milk composition to disentangle the role of each milk component on %CY traits. To this end, 1,271 individual milk samples (1.5 L/cow) from Brown Swiss cows were processed according to a laboratory model cheese-making procedure. Fresh %CY (%CY_CURD), total solids and water retained in the fresh cheese (%CY_SOLIDS and %CY_WATER), and 60-days ripened cheese (%CY_RIPENED) were the reference traits and were used as response variables. Training-testing linear regression modeling was performed: 80% of observations were randomly assigned to the training set, 20% to the validation set, and the procedure was repeated 10 times. Four groups of predictive equations were identified, in which different combinations of predictors were tested separately to predict %CY traits: (i) basic composition, i.e., fat, protein, and CN, tested individually and in combination; (ii) udder health indicators (UHI), i.e., fat + protein or CN + lactose and/or somatic cell score (SCS); (iii) detailed protein profile, i.e., fat + protein fractions [CN fractions, whey proteins, and nonprotein nitrogen (NPN) compounds]; (iv) detailed protein profile + UHI, i.e., fat + protein fractions + NPN compounds and/or UHI. Aside from the positive effect of fat, protein, and total casein on %CY, our results allowed us to disentangle the role of each casein fraction and whey protein, confirming the central role of β-CN and κ-CN, but also showing α-lactalbumin (α-LA) to have a favorable effect, and β-lactoglobulin (β-LG) a negative effect. Replacing protein or casein with individual milk protein and NPN fractions in the statistical models appreciably increased the validation accuracy of the equations. The cheese industry would benefit from an improvement, through genetic selection, of traits related to cheese yield and this study offers new insights into the quantification of the influence of milk components in composite selection indices with the aim of directly enhancing cheese production.

Invited review: Effect of subacute ruminal acidosis on gut health of dairy cows

Subacute ruminal acidosis (SARA) is assumed to be a common disease in high-yielding dairy cows. Despite this, the epidemiological evidence is limited by the lack of survey data. The prevalence of SARA has mainly been determined by measuring the pH of ruminal fluid collected using rumenocentesis. This may not be sufficiently accurate, because the symptoms of SARA are not solely due to ruminal pH depression, and ruminal pH varies among sites in the rumen, throughout a 24-h period, and among days. The impact of SARA has mainly been studied by conducting SARA challenges in cows, sheep, and goats based on a combination of feed restriction and high-grain feeding. The methodologies of these challenges vary considerably among studies. Variations include differences in the duration and amount of grain feeding, type of grain, amount and duration of feed restriction, number of experimental cows, and sensitivity of cows to SARA challenges. Grain-based SARA challenges affect gut health. These effects include depressing the pH in, and increasing the toxin content of, digesta. They also include altering the taxonomic composition of microbiota, reducing the functionality of the epithelia throughout the gastrointestinal tract (GIT), and a moderate inflammatory response. The effects on the epithelia include a reduction in its barrier function. Effects on microbiota include reductions in their richness and diversity, which may reduce their functionality and reflect dysbiosis. Changes in the taxonomic composition of gut microbiota throughout the GIT are evident at the phylum level, but less evident and more variable at the genus level. Effects at the phylum level include an increase in the Firmicutes to Bacteroidetes ratio. More studies on the effects of a SARA challenge on the functionality of gut microbiota are needed. The inflammatory response resulting from grain-based SARA challenges is innate and moderate and mainly consists of an acute phase response. This response is likely a combination of systemic inflammation and inflammation of the epithelia of the GIT. The systemic inflammation is assumed to be caused by translocation of immunogenic compounds, including bacterial endotoxins and bioamines, through the epithelia into the interior circulation. This translocation is increased by the increase in concentrations of toxins in digesta and a reduction of the barrier function of epithelia. Severe SARA can cause rumenitis, but moderate SARA may activate an immune response in the epithelia of the GIT. Cows grazing highly fermentable pastures with high sugar contents can also have a low ruminal pH indicative of SARA. This is not accompanied by an inflammatory response but may affect milk production and gut microbiota. Grain-based SARA affects several aspects of gut health, but SARA resulting from grazing high-digestible pastures and insufficient coarse fiber less so. We need to determine which method for inducing SARA is the most representative of on-farm conditions.

Molecular Approaches Reduce Saturates and Eliminate trans Fats in Food Oils

Vegetable oils composed of triacylglycerols (TAG) are a major source of calories in human diets. However, the fatty acid compositions of these oils are not ideal for human nutrition and the needs of the food industry. Saturated fatty acids contribute to health problems, while polyunsaturated fatty acids (PUFA) can become rancid upon storage or processing. In this review, we first summarize the pathways of fatty acid metabolism and TAG synthesis and detail the problems with the oil compositions of major crops. Then we describe how transgenic expression of desaturases and downregulation of the plastid FatB thioesterase have provided the means to lower oil saturates. The traditional solution to PUFA rancidity uses industrial chemistry to reduce PUFA content by partial hydrogenation, but this results in the production of trans fats that are even more unhealthy than saturated fats. We detail the discoveries in the biochemistry and molecular genetics of oil synthesis that provided the knowledge and tools to lower oil PUFA content by blocking their synthesis during seed development. Finally, we describe the successes in breeding and biotechnology that are giving us new, high-oleic, low PUFA varieties of soybean, canola and other oilseed crops.

Genetic variants associated with two major bovine milk fatty acids offer opportunities to breed for altered milk fat composition

Background

Although bovine milk is regarded as healthy and nutritious, its high content of saturated fatty acids (FA) may be harmful to cardiovascular health. Palmitic acid (C16:0) is the predominant saturated FA in milk with adverse health effects that could be countered by substituting it with higher levels of unsaturated FA, such as oleic acid (C18:1cis-9). In this work, we performed genome-wide association analyses for milk fatty acids predicted from FTIR spectroscopy data using 1811 Norwegian Red cattle genotyped and imputed to a high-density 777k single nucleotide polymorphism (SNP)-array. In a follow-up analysis, we used imputed whole-genome sequence data to detect genetic variants that are involved in FTIR-predicted levels of C16:0 and C18:1cis-9 and explore the transcript profile and protein level of candidate genes.

Results

Genome-wise significant associations were detected for C16:0 on Bos taurus (BTA) autosomes 11, 16 and 27, and for C18:1cis-9 on BTA5, 13 and 19. Closer examination of a significant locus on BTA11 identified the PAEP gene, which encodes the milk protein β-lactoglobulin, as a particularly attractive positional candidate gene. At this locus, we discovered a tightly linked cluster of genetic variants in coding and regulatory sequences that have opposing effects on the levels of C16:0 and C18:1cis-9. The favourable haplotype, linked to reduced levels of C16:0 and increased levels of C18:1cis-9 was also associated with a marked reduction in PAEP expression and β-lactoglobulin protein levels. β-lactoglobulin is the most abundant whey protein in milk and lower levels are associated with important dairy production parameters such as improved cheese yield.

Conclusions

The genetic variants detected in this study may be used in breeding to produce milk with an improved FA health-profile and enhanced cheese-making properties.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12711-022-00731-9.

Challenging Sustainable and Innovative Technologies in Cheese Production: A Review

It is well known that cheese yield and quality are affected by animal genetics, milk quality (chemical, physical, and microbiological), production technology, and the type of rennet and dairy cultures used in production. Major differences in the same type of cheese (i.e., hard cheese) are caused by the rennet and dairy cultures, which affect the ripening process. This review aims to explore current technological advancements in animal genetics, methods for the isolation and production of rennet and dairy cultures, along with possible applications of microencapsulation in rennet and dairy culture production, as well as the challenge posed to current dairy technologies by the preservation of biodiversity. Based on the reviewed scientific literature, it can be concluded that innovative approaches and the described techniques can significantly improve cheese production.

Random regression test-day models to describe milk production and fatty acid traits in first lactation Walloon Holstein cows

We investigated the use of different Legendre polynomial orders to estimate genetic parameters for milk production and fatty acid (FA) traits in the first lactation Walloon Holstein cows. The data set comprised 302,684 test-day records of milk yield, fat and protein contents, and FAs generated by mid-infrared (MIR) spectroscopy, C16:0 (palmitic acid), C18:1 cis-9 (oleic acid), LCFAs (long-chain FAs), SFAs (saturated FAs) and UFAs (unsaturated FAs) were studied. The models included random regression coefficients for herd-year of calving (h), additive genetic (a) and permanent environment (p) effects. The selection of the best random regression model (RRM) was based on the deviance information criterion (DIC), and genetic parameters were estimated via a Bayesian approach. For all analysed random effects, DIC values decreased as the order of the Legendre polynomials increased. Best-fit models had fifth-order (degree 4) for the p effect and ranged from second- to fifth-order (degree 1-4) for the a and h effects (LEGhap: LEG555 for milk yield and protein content; LEG335 for fat content and SFA; LEG545 for C16:0 and UFA; and LEG535 for C18:1 cis-9 and LCFA). Based on the best-fit models, an effect of overcorrection was observed in early lactation (5-35 days in milk [DIM]). On the contrary, third-order (LEG333; degree 2) models showed flat residual trajectories throughout lactation. In general, the estimates of genetic variance tended to increase over DIM, for all traits. Heritabilities for milk production traits ranged from 0.11 to 0.58. Milk FA heritabilities ranged from low-to-high magnitude (0.03-0.56). High Spearman correlations (>0.90 for all bulls and >0.97 for top 100) were found among breeding values for 155 and 305 DIM between the best RRM and LEG333 model. Therefore, third-order Legendre polynomials seem to be most parsimonious and sufficient to describe milk production and FA traits in Walloon Holstein cows.

Effect of supplement crude protein concentration on milk production over the main grazing season and on nitrogen excretion in late-lactation grazing dairy cows

The objectives of this study are to evaluate the effects of (1) a potential interaction between supplement crude protein (CP) concentration and differing cow genotypes on milk production, (2) differing cow genotypes on milk production, and (3) decreasing the supplement CP concentration on milk production and N excretion during the main grazing season within a spring-calving herd. A 2 × 2 factorial arrangement experiment, with 2 feeding strategies [14%; n = 30 (lower CP; LCP) and 18%; n = 28 (higher CP; HCP) CP concentrate supplements] offered at varying levels according to pasture availability and days in milk (DIM) was conducted over the main grazing season from April 3 to September 3, 2019, at University College Dublin Lyons Farm. Cows were also grouped into 2 genotype groups: lower milk genotype; n = 30 [LM; milk kg predicted transmitting ability (PTA): 45 ± 68.6 (mean ± SD); fat kg PTA: 10 ± 4.9; and protein kg PTA: 7 ± 2.3] and higher milk genotype; n = 28 [HM; milk kg PTA: 203 ± 55.0; fat kg PTA: 13 ± 3.8; and protein kg PTA: 10 ± 2.4]. A total of 46 multiparous and 12 primiparous (total; 58) Holstein Friesian dairy cows were blocked on parity and balanced on DIM, body condition score, and Economic Breeding Index. Cows were offered a basal diet of grazed perennial ryegrass pasture. The N partitioning study took place from August 25 to 30, 2019 (187 ± 15.2 DIM). No interactions were observed for any milk production or milk composition parameter. No effect of supplement CP concentration was observed for any total accumulated milk production, daily milk production, or milk composition parameter measured. The HM cows had increased daily milk yield (+1.9 kg), fat and protein (+0.15 kg), and energy-corrected milk (+1.7 kg), compared with the LM cows. Furthermore, HM cows had decreased milk protein concentration (-0.1%) compared with LM cows. For the N partitioning study, cows offered LCP had increased pasture dry matter intake (PDMI; +0.9 kg/d), dietary N intake (+0.022 kg/d), feces N excretion (+0.016 kg/d), and decreased N partitioning to milk (-2%), and N utilization efficiency (-2.3%). In conclusion, offering cows LCP had no negative influence on milk production or milk composition over the main grazing season where high pasture quality was maintained. However, any potential negative effects of offering LCP on milk production may have been offset by the increased PDMI. Furthermore, offering cows LCP decreased N utilization efficiency due to the higher PDMI and feed N intake associated with cows on this treatment in our study.s.

Application of machine-learning methods to milk mid-infrared spectra for discrimination of cow milk from pasture or total mixed ration diets

The prevalence of "grass-fed" labeled food products on the market has increased in recent years, often commanding a premium price. To date, the majority of methods used for the authentication of grass-fed source products are driven by auditing and inspection of farm records. As such, the ability to verify grass-fed source claims to ensure consumer confidence will be important in the future. Mid-infrared (MIR) spectroscopy is widely used in the dairy industry as a rapid method for the routine monitoring of individual herd milk composition and quality. Further harnessing the data from individual spectra offers a promising and readily implementable strategy to authenticate the milk source at both farm and processor levels. Herein, a comprehensive comparison of the robustness, specificity, and accuracy of 11 machine-learning statistical analysis methods were tested for the discrimination of grass-fed versus non-grass-fed milks based on the MIR spectra of 4,320 milk samples collected from cows on pasture or indoor total mixed ration-based feeding systems over a 3-yr period. Linear discriminant analysis and partial least squares discriminant analysis (PLS-DA) were demonstrated to offer the greatest level of accuracy for the prediction of cow diet from MIR spectra. Parsimonious strategies for the selection of the most discriminating wavelengths within the spectra are also highlighted.

Prediction of fatty acid composition using milk spectral data and its associations with various mid-infrared spectral regions in Michigan Holsteins

Fatty acid composition in milk is not only reflective of nutritional quality but also potentially predictive of other attributes (e. g. including the cow's energy balance and its relative output of methane emissions). Furthermore, a higher ratio of long-chain to short-chain fatty acids or mean carbon number has been associated with negative energy balance in dairy cows, whereas enhanced nutritional properties have been generally associated with higher levels of unsaturation. We set out to directly compare Bayesian regression strategies with partial least squares for the prediction of various milk fatty acids using Fourier-transform infrared spectrum data on 777 milk samples taken from 579 cows on 4 Michigan dairy herds between 5 and 90 d in milk. We also set out to identify those spectral regions that might be associated with fatty acids and whether carbon number or level of unsaturation might contribute to the strength of these associations. These associations were based on adaptively clustered windows of wavenumbers to mitigate the distorting effects of severe multicollinearity on marginal associations involving individual wavenumbers. In general, Bayesian regression methods, particularly the variable selection method BayesB, outperformed partial least squares regression for cross-validation prediction accuracy for both individual fatty acids and fatty acid groups. Strong signals for wavenumber associations using BayesB were well distributed throughout the mid-infrared spectrum, particularly between 910 and 3,998 cm^-1. Carbon number appeared to be linearly related to strength of wavenumber associations for 38 moderately to highly predicted fatty acids within the spectral regions of 2,286 to 2,376 and 2,984 to 3,100 cm^-1, whereas nonlinear associations were determined within 1,141 to 1,205; 1,570 to 1,630; and 1,727 to 1,768 cm^-1. However, no such associations were detected with level of unsaturation. Spectral regions where there were significant relationships between strength of association and carbon number may be useful targets for inferring the relative proportion of long-chain to short-chain fatty acids, and hence energy balance.

Fatty Acid Prediction in Bovine Milk by Attenuated Total Reflection Infrared Spectroscopy after Solvent-Free Lipid Separation

In the present study, a novel approach for mid-infrared (IR)-based prediction of bovine milk fatty acid composition is introduced. A rapid, solvent-free, two-step centrifugation method was applied in order to obtain representative milk fat fractions. IR spectra of pure milk lipids were recorded with attenuated total reflection Fourier-transform infrared (ATR-FT-IR) spectroscopy. Comparison to the IR transmission spectra of whole milk revealed a higher amount of significant spectral information for fatty acid analysis. Partial least squares (PLS) regression models were calculated to relate the IR spectra to gas chromatography/mass spectrometry (GC/MS) reference values, providing particularly good predictions for fatty acid sum parameters as well as for the following individual fatty acids: C10:0 (R²_P = 0.99), C12:0 (R²_P = 0.97), C14:0 (R²_P = 0.88), C16:0 (R²_P = 0.81), C18:0 (R²_P = 0.93), and C18:1cis (R²_P = 0.95). The IR wavenumber ranges for the individual regression models were optimized and validated by calculation of the PLS selectivity ratio. Based on a set of 45 milk samples, the obtained PLS figures of merit are significantly better than those reported in literature using whole milk transmission spectra and larger datasets. In this context, direct IR measurement of the milk fat fraction inherently eliminates covariation structures between fatty acids and total fat content, which poses a common problem in IR-based milk fat profiling. The combination of solvent-free lipid separation and ATR-FT-IR spectroscopy represents a novel approach for fast fatty acid prediction, with the potential for high-throughput application in routine lab operation.

Genetic analysis on infrared-predicted milk minerals for Danish dairy cattle

A group of milk components that has shown potential to be predicted with milk spectra is milk minerals. Milk minerals are important for human health and cow health. Having an inexpensive and fast way to measure milk mineral concentrations would open doors for research, herd management, and selective breeding. The first aim of this study was to predict milk minerals with infrared milk spectra. Additionally, milk minerals were predicted with infrared-predicted fat, protein, and lactose content. The second aim was to perform a genetic analysis on infrared-predicted milk minerals, to identify QTL, and estimate variance components. For training and validating a multibreed prediction model for individual milk minerals, 264 Danish Jersey cows and 254 Danish Holstein cows were used. Partial least square regression prediction models were built for Ca, Cu, Fe, K, Mg, Mn, Na, P, Se, and Zn based on 80% of the cows, selected randomly. Prediction models were externally validated with 8 herds based on the remaining 20% of the cows. The prediction models were applied on a population of approximately 1,400 Danish Holstein cows with 5,600 infrared spectral records and 1,700 Danish Jersey cows with 7,200 infrared spectral records. Cows from this population had 50k imputed genotypes. Prediction accuracy was good for P and Ca, with external R² ≥ 0.80 and a relative prediction error of 5.4% for P and 6.3% for Ca. Prediction was moderately good for Na with an external R² of 0.63, and a relative error of 18.8%. Prediction accuracies of milk minerals based on infrared-predicted fat, protein, and lactose content were considerably lower than those based on the infrared milk spectra. This shows that the milk infrared spectrum contains valuable information on milk minerals, which is currently not used. Heritability for infrared-predicted Ca, Na, and P varied from low (0.13) to moderate (0.36). Several QTL for infrared-predicted milk minerals were observed that have been associated with gold standard milk minerals previously. In conclusion, this study has shown infrared milk spectra were good at predicting Ca, Na, and P in milk. Infrared-predicted Ca, Na, and P had low to moderate heritability estimates.

Application of genetic algorithm and multivariate methods for the detection and measurement of milk-surfactant adulteration by attenuated total reflection and near-infrared spectroscopy

BACKGROUND

The adulteration of milk by hazardous chemicals like surfactants has recently increased. It conceals the quality of the product to gain profit. As milk and milk-based products are consumed by many people, novel analytical procedures are needed to detect these adulterants. This study focused on Fourier-transform infrared (FTIR) spectroscopy equipped with an attenuated total reflection (ATR) accessory, and near-infrared (NIR) spectroscopy for the determination of milk-surfactant adulteration using a genetic algorithm (GA) coupled with multivariate methods. The model surfactant was sodium dodecyl sulfate (SDS), and its concentration varied from 1.94-19.4 gkg^-1 in adulterated samples.

RESULTS

Prominent peaks in the spectral range of 5500-6400 cm^-1 , 1160-1260 cm^-1 and 1049-1080 cm^-1 may correspond to the sulfonate group in SDS. A genetic algorithm could significantly reduce the number of variables to almost one third by selecting the specific wavenumber region. Principal component analysis (PCA) for ATR and NIR data indicated separate clusters of samples in terms of the concentration level of SDS (P ≤ 0.05). Partial least squares regression (PLSR) was used to determine the maximum R² value for ATR and NIR data for calibration, cross-validation and prediction, which were 0.980, 0.972, 0.980, and 0.970, 0.937, and 0.956 respectively. The results showed apparent differences between unadulterated and adulterated samples using partial least squares-discriminant analysis (PLS-DA), which was validated by the permutation test.

CONCLUSION

The results clearly show the successful application of the proposed methods with multivariate analysis in the selection of variables, classification, clustering, and identification of the adulterant in amounts as low as 1.94 gkg^-1 in milk. © 2020 Society of Chemical Industry.

Predicting cow milk quality traits from routinely available milk spectra using statistical machine learning methods

Numerous statistical machine learning methods suitable for application to highly correlated features, as those that exist for spectral data, could potentially improve prediction performance over the commonly used partial least squares approach. Milk samples from 622 individual cows with known detailed protein composition and technological trait data accompanied by mid-infrared spectra were available to assess the predictive ability of different regression and classification algorithms. The regression-based approaches were partial least squares regression (PLSR), ridge regression (RR), least absolute shrinkage and selection operator (LASSO), elastic net, principal component regression, projection pursuit regression, spike and slab regression, random forests, boosting decision trees, neural networks (NN), and a post-hoc approach of model averaging (MA). Several classification methods (i.e., partial least squares discriminant analysis (PLSDA), random forests, boosting decision trees, and support vector machines (SVM)) were also used after stratifying the traits of interest into categories. In the regression analyses, MA was the best prediction method for 6 of the 14 traits investigated [curd firmness at 60 min, α_S1-casein (CN), α_S2-CN, κ-CN, α-lactalbumin, and β-lactoglobulin B], whereas NN and RR were the best algorithms for 3 traits each (rennet coagulation time, curd-firming time, and heat stability, and curd firmness at 30 min, β-CN, and β-lactoglobulin A, respectively), PLSR was best for pH, and LASSO was best for CN micelle size. When traits were divided into 2 classes, SVM had the greatest accuracy for the majority of the traits investigated. Although the well-established PLSR-based method performed competitively, the application of statistical machine learning methods for regression analyses reduced the root mean square error compared with PLSR from between 0.18% (κ-CN) to 3.67% (heat stability). The use of modern statistical machine learning methods for trait prediction from mid-infrared spectroscopy may improve the prediction accuracy for some traits.

The effect of nutritional management in early lactation and dairy cow genotype on milk production, metabolic status, and uterine recovery in a pasture-based system

High levels of milk production coupled with low feed intake cause negative energy balance in early lactation, especially in the first month postpartum (PP). Therefore, specific nutritional management at this time may improve nutritional and metabolic status with the possibility of contrasting genotypes responding differently. Thus, the objective of this study was to compare the effects of nutritional management strategies and dairy cow genotype on milk production, metabolic status, and some fertility parameters during early lactation in a pasture-based system. Sixty Holstein Friesian cows were blocked on parity and genotype [low-fertility high-milk (LFHM) and high-fertility low-milk (HFLM)] and were randomly assigned to 1 of 2 treatments in a 2 × 2 factorial arrangement, in a randomized complete block design based on calving date, previous 305-d milk yield, and precalving body condition score (BCS). The nutritional management treatments were: (1) ad libitum access to fresh pasture plus an allowance of 3 kg of concentrates per day (CTR, n = 30); and (2) ab libitum access to a tailored total mixed ration (TMR, n = 30). These diets were offered for the first 30 d PP. Following the first 30 d PP, cows fed TMR joined the CTR treatment and were managed similarly until 100 d PP. Blood samples were taken at d 7, 14, 21, and 28 PP to determine metabolic status. Milk samples for composition analysis were collected weekly and BCS assessed every 2 wk. Genotype had a significant effect on milk output, whereas LFHM had increased fat (+0.28 kg/d) and fat-plus-protein (+0.17 kg/d) yield in the first 30 d PP compared with HFLM cows. The LFHM group also exhibited higher protein and lactose yields over the first 100 d PP. Nutritional management did create significant differences in milk composition in the first 30 d: TMR cows had lower protein, milk urea nitrogen, and casein concentration and higher lactose concentration than CTR cows. Over the first 100 d PP, TMR cows had higher fat-plus-protein and lactose yields. Feeding TMR reduced concentrations of nonesterified fatty acids (-0.12 mmol/L) and β-hydroxybutyric acid (-0.10 mmol/L) compared with the CTR group. Cows fed TMR had smaller BCS losses from calving to 60 d PP. There was no effect of any treatment on uterine recovery. Cows in the LFHM group demonstrated greater milk production in the first 30 and 100 d in milk. These results demonstrate that feeding cows a TMR for the first month of lactation has positive effects on milk output, metabolic status, and BCS profile.

Fourier Transform Infrared Spectroscopy as a Tool to Study Milk Composition Changes in Dairy Cows Attributed to Housing Modifications to Improve Animal Welfare

Animal welfare status is assessed today through visual evaluations requiring an on-farm visit. A convenient alternative would be to detect cow welfare status directly in milk samples, already routinely collected for milk recording. The objective of this study was to propose a novel approach to demonstrate that Fourier transform infrared (FTIR) spectroscopy can detect changes in milk composition related to cows subjected to movement restriction at the tie stall with four tie-rail configurations varying in height and position (TR1, TR2, TR3 and TR4). Milk mid-infrared spectra were collected on weekly basis. Long-term average spectra were calculated for each cow using spectra collected in weeks 8–10 of treatment. Principal component analysis was applied to spectral averages and the scores of principal components (PCs) were tested for treatment effect by mixed modelling. PC7 revealed a significant treatment effect (p = 0.01), particularly for TR3 (configuration with restricted movement) vs. TR1 (recommended configuration) (p = 0.03). The loading spectrum of PC7 revealed high loadings at wavenumbers that could be assigned to biomarkers related to negative energy balance, such as β-hydroxybutyrate, citrate and acetone. This observation suggests that TR3 might have been restrictive for cows to access feed. Milk FTIR spectroscopy showed promising results in detecting welfare status and housing conditions in dairy cows.

Appropriate Data Quality Checks Improve the Reliability of Values Predicted from Milk Mid-Infrared Spectra

Simple Summary

There is a growing interest in using milk mid-infrared (MIR) spectrometry to obtain new phenotypes to assist in the complex management of dairy farms. These predictive values can be erroneous for many reasons, even if the prediction equations used are accurate. Unfortunately, there is no quality protocol routinely implemented to detect those abnormal predictive values in the database recorded by dairy herd improvement (DHI) organizations, except for fat and protein contents. However, for financial and practical reasons, it is unfeasible to adapt the quality protocol commonly used in milk laboratories to improve the accuracy of those traits. So, this study proposes three different statistical methods that would be easy to implement by DHI organizations to detect abnormal values and limit the spectral extrapolation in order to improve the accuracy of MIR-based predictive values.

Abstract

The use of abnormal milk mid-infrared (MIR) spectrum strongly affects prediction quality, even if the prediction equations used are accurate. So, this record must be detected after or before the prediction process to avoid erroneous spectral extrapolation or the use of poor-quality spectral data by dairy herd improvement (DHI) organizations. For financial or practical reasons, adapting the quality protocol currently used to improve the accuracy of fat and protein contents is unfeasible. This study proposed three different statistical methods that would be easy to implement by DHI organizations to solve this issue: the deletion of 1% of the extreme high and low predictive values (M1), the deletion of records based on the Global-H (GH) distance (M2), and the deletion of records based on the absolute fat residual value (M3). Additionally, the combinations of these three methods were investigated. A total of 346,818 milk samples were analyzed by MIR spectrometry to predict the contents of fat, protein, and fatty acids. Then, the same traits were also predicted externally using their corresponded standardized MIR spectra. The interest in cleaning procedures was assessed by estimating the root mean square differences (RMSDs) between those internal and external predicted phenotypes. All methods allowed for a decrease in the RMSD, with a gain ranging from 0.32% to 41.39%. Based on the obtained results, the “M1 and M2” combination should be preferred to be more parsimonious in the data loss, as it had the higher ratio of RMSD gain to data loss. This method deleted the records based on the 2% extreme predictions and a GH threshold set at 5. However, to ensure the lowest RMSD, the “M2 or M3” combination, considering a GH threshold of 5 and an absolute fat residual difference set at 0.30 g/dL of milk, was the most relevant. Both combinations involved M2 confirming the high interest of calculating the GH distance for all samples to predict. However, if it is impossible to estimate the GH distance due to a lack of relevant information to compute this statistical parameter, the obtained results recommended the use of M1 combined with M3. The limitation used in M3 must be adapted by the DHI, as this will depend on the spectral data and the equation used. The methodology proposed in this study can be generalized for other MIR-based phenotypes.

Goat farm variability affects milk Fourier-transform infrared spectra used for predicting coagulation properties

Driven by the large amount of goat milk destined for cheese production, and to pioneer the goat cheese industry, the objective of this study was to assess the effect of farm in predicting goat milk-coagulation and curd-firmness traits via Fourier-transform infrared spectroscopy. Spectra from 452 Sarda goats belonging to 14 farms in central and southeast Sardinia (Italy) were collected. A Bayesian linear regression model was used, estimating all spectral wavelengths' effects simultaneously. Three traditional milk-coagulation properties [rennet coagulation time (min), time to curd firmness of 20 mm (min), and curd firmness 30 min after rennet addition (mm)] and 3 curd-firmness measures modeled over time [rennet coagulation time estimated according to curd firmness change over time (RCT_eq), instant curd-firming rate constant, and asymptotical curd firmness] were considered. A stratified cross validation (SCV) was assigned, evaluating each farm separately (validation set; VAL) and keeping the remaining farms to train (calibration set) the statistical model. Moreover, a SCV, where 20% of the goats randomly taken (10 replicates per farm) from the VAL farm entered the calibration set, was also considered (SCV₈₀). To assess model performance, coefficient of determination (R²_VAL) and the root mean squared error of validation were recorded. The R²_VAL varied between 0.14 and 0.45 (instant curd-firming rate constant and RCT_eq, respectively), albeit the standard deviation was approximating half of the mean for all the traits. Although average results of the 2 SCV procedures were similar, in SCV₈₀, the maximum R²_VAL increased at about 15% across traits, with the highest observed for time to curd firmness of 20 mm (20%) and the lowest for RCT_eq (6%). Further investigation evidenced important variability among farms, with R²_VAL for some of them being close to 0. Our work outlined the importance of considering the effect of farm when developing Fourier-transform infrared spectroscopy prediction equations for coagulation and curd-firmness traits in goats.

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.

Genetic Parameters of Bovine Milk Fatty Acid Profile, Yield, Composition, Total and Differential Somatic Cell Count

The growing interest of consumers for milk and dairy products of high nutritional value has pushed researchers to evaluate the feasibility of including fatty acids (FA) in selection programs to modify milk fat profile and improve its nutritional quality. Therefore, the aim of this study was to estimate genetic parameters of FA profile predicted by mid-infrared spectroscopy, milk yield, composition, and total and differential somatic cell count. Edited data included 35,331 test-day records of 25,407 Italian Holstein cows from 652 herds. Variance components and heritability were estimated using single-trait repeatability animal models, whereas bivariate repeatability animal models were used to estimate genetic and phenotypic correlations between traits, including the fixed effects of stage of lactation, parity, and herd-test-date, and the random effects of additive genetic animal, cow permanent environment and the residual. Heritabilities and genetic correlations obtained in the present study reflected both the origins of FA (extracted from the blood or synthesized de novo by the mammary gland) and their grouping according to saturation or chain length. In addition, correlations among FA groups were in line with correlation among individual FA. Moderate negative genetic correlations between FA and milk yield and moderate to strong positive correlations with fat, protein, and casein percentages suggest that actual selection programs are currently affecting all FA groups, not only the desired ones (e.g., polyunsaturated FA). The absence of association with differential somatic cell count and the weak association with somatic cell score indicate that selection on FA profile would not affect selection on resistance to mastitis and vice versa. In conclusion, our findings suggest that genetic selection on FA content is feasible, as FA are variable and moderately heritable. Nevertheless, in the light of correlations with other milk traits estimated in this study, a clear breeding goal should first be established.

Changes in Retinol Binding Protein 4 Level in Undernourished Children After a Nutrition Intervention Are Positively Associated With Mother's Weight but Negatively With Mother's Height, Intake of Whole Milk, and Markers of Systemic Inflammation: Results From a Community-Based Intervention Study

Background:

The changes of plasma retinol binding protein 4 (RBP4) level after a nutrition intervention can indicate the metabolic changes associated with the delivered intervention.

Objective:

We investigated the changes in plasma RBP4 level among 12- to 18-month-old children after a nutrition intervention and measured its association with subcutaneous adiposity, maternal characteristics, and inflammation.

Methods:

Data of 520 undernourished children (250 of them had length-for-age Z score [LAZ] <−1 to −2 and 270 had LAZ score <−2) were collected from the Bangladesh Environmental Enteric Dysfunction study conducted in Dhaka, Bangladesh. Multivariable linear regression and generalized estimation equations (GEE) modeling techniques were used to measure the association.

Results:

At baseline, median RBP4 level was 19.9 mg/L (interquartile range [IQR]: 7.96), and at the end of the intervention, it was 20.6 mg/L (IQR: 9.06). Percentage changes in plasma RBP4 level were not significantly associated (P > .05) with the percentage changes in child’s height, weight, and subcutaneous adiposity. But maternal height (regression coefficient, β = −1.62, P = .002) and milk intake (β = −0.05, P = .01) were negatively and maternal weight was positively associated (β = 0.56, P = .03) with the changes in RBP4 levels. The GEE models revealed negative association of RBP4 levels with C-reactive protein (CRP; β = −0.14, P < .05) and α-1-acid glycoprotein (AGP; β = −0.03, P < .05).

Conclusion:

Children whose mothers were taller experienced less increase in plasma RBP4 level, and children whose mothers had a higher weight experienced more increase in the RBP4 level from baseline. We have also found that CRP and AGP levels and intake of whole milk were negatively associated with the plasma RBP4 level.

Integration of Wet-Lab Measures, Milk Infrared Spectra, and Genomics to Improve Difficult-to-Measure Traits in Dairy Cattle Populations

The objective of this study was to evaluate the contribution of Fourier-transformed infrared spectroscopy (FTIR) data for dairy cattle breeding through two different approaches: (i) estimating the genetic parameters for 30 measured milk traits and their FTIR predictions and investigating the additive genetic correlation between them and (ii) evaluating the effectiveness of FTIR-derived phenotyping to replicate a candidate bull’s progeny testing or breeding value prediction at birth. Records were available from 1,123 cows phenotyped using gold standard laboratory methodologies (LAB data). This included phenotypes related to fine milk composition and milk technological characteristics, milk acidity, and milk protein fractions. The dataset used to generate FTIR predictions comprised 729,202 test-day records from 51,059 Brown Swiss cows (FIELD data). A first approach consisted of estimating genetic parameters for phenotypes available from LAB and FIELD datasets. To do so, a set of bivariate animal models were run, and genetic correlations between LAB and FIELD phenotypes were estimated using FIELD information obtained at the population level. Heritability estimates were generally higher for FIELD predictions than for the corresponding LAB measures. The additive genetic correlations (r_a) between LAB and FIELD phenotypes had different magnitudes across traits but were generally strong. Overall, these results demonstrated the potential of using FIELD information as indicator traits for the indirect genetic improvement of LAB measures. In the second approach, we included genotype information for 1,011 cows from the LAB dataset, 1,493 cows from the FIELD dataset, 181 sires with daughters in both LAB and FIELD datasets, and 540 sires with daughters in the FIELD dataset only. Predictions were obtained using the single-step GBLUP method. A four fold cross-validation was used to assess the predictive ability of the different models, assessed as the ability to predict masked LAB records from daughters of progeny testing bulls. The correlation between observed and predicted LAB measures in validation was averaged over the four training-validation sets. Different sets of phenotypic information were used sequentially in cross-validation schemes: (i) LAB cows from the training set; (ii) FIELD cows from the training set; and (iii) FIELD cows from the validation set. Models that included FIELD records showed an improvement for the majority of traits. This study suggests that breeding programs for difficult-to-measure traits could be implemented using FTIR information. While these programs should use progeny testing, acceptable values of accuracy can be achieved also for bulls without phenotyped progeny. Robust calibration equations are, deemed as essential.

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.

Infrared Spectrometry as a High-Throughput Phenotyping Technology to Predict Complex Traits in Livestock Systems

High-throughput phenotyping technologies are growing in importance in livestock systems due to their ability to generate real-time, non-invasive, and accurate animal-level information. Collecting such individual-level information can generate novel traits and potentially improve animal selection and management decisions in livestock operations. One of the most relevant tools used in the dairy and beef industry to predict complex traits is infrared spectrometry, which is based on the analysis of the interaction between electromagnetic radiation and matter. The infrared electromagnetic radiation spans an enormous range of wavelengths and frequencies known as the electromagnetic spectrum. The spectrum is divided into different regions, with near- and mid-infrared regions being the main spectral regions used in livestock applications. The advantage of using infrared spectrometry includes speed, non-destructive measurement, and great potential for on-line analysis. This paper aims to review the use of mid- and near-infrared spectrometry techniques as tools to predict complex dairy and beef phenotypes, such as milk composition, feed efficiency, methane emission, fertility, energy balance, health status, and meat quality traits. Although several research studies have used these technologies to predict a wide range of phenotypes, most of them are based on Partial Least Squares (PLS) and did not considered other machine learning (ML) techniques to improve prediction quality. Therefore, we will discuss the role of analytical methods employed on spectral data to improve the predictive ability for complex traits in livestock operations. Furthermore, we will discuss different approaches to reduce data dimensionality and the impact of validation strategies on predictive quality.