A large-scale study of indicators of sub-clinical mastitis in dairy cattle by attribute weighting analysis of milk composition features: highlighting the predictive power of lactose and electrical conductivity

Revealing microbial diversity in buffalo milk with high somatic cell counts: implications for mastitis diagnosis and treatment

Mastitis is one of the most serious diseases that threatens the health of dairy animals. The somatic cell count (SCC) in milk is widely used to monitor mastitis. This study aimed to reveal the diversity of microorganisms in buffalo milk with high somatic cell count (SCC ≥ 3 × 105 cells/mL, n = 30) and low somatic cell count (SCC ≤ 5 × 104 cells/mL, n = 10), and identify the dominant bacteria that cause mastitis in a local buffalo farm. We also investigated the potential method to treat bacterial mastitis. The V3-V4 region of 16 S rDNA was sequenced. Results showed that, compared to the milk with low SCC, the high SCC samples showed lower microbial diversity, but a high abundance of bacteria and operational taxonomic units (OTUs). By in vitro isolation and culture, Escherichia coli, Staphylococcus aureus, and Klebsiella pneumoniae were found to be the leading pathogens, which is consistent with the 16 S rDNA sequencing data. We further isolated 3 of the main pathogens and established a pathogen detection method based on ELISA. In addition, the antibacterial effects of 10 antimicrobials and 15 Chinese herbal extracts were also investigated. Results showed that the microbial has developed tolerance to several of the antimicrobials. While the water extracts of Chinese herbal medicine such as Galla Chinensis, Coptis chinensis Franch, Terminalia chebula Retz, and Sanguisorba officinalis L can effectively inhibit the growth of main pathogens. This study provides novel insight into the microbial diversity in buffalo milk and a reference for the prevention, diagnosis, and treatment of mastitis.

Current Trends in Artificial Intelligence and Bovine Mastitis Research: A Bibliometric Review Approach

Mastitis, an important disease in dairy cows, causes significant losses in herd profitability. Accurate diagnosis is crucial for adequate control. Studies using artificial intelligence (AI) models to classify, identify, predict, and diagnose mastitis show promise in improving mastitis control. This bibliometric review aimed to evaluate AI and bovine mastitis terms in the most relevant Scopus-indexed papers from 2011 to 2021. Sixty-two documents were analyzed, revealing key terms, prominent researchers, relevant publications, main themes, and keyword clusters. "Mastitis" and "machine learning" were the most cited terms, with an increasing trend from 2018 to 2021. Other terms, such as "sensors" and "mastitis detection", also emerged. The United States was the most cited country and presented the largest collaboration network. Publications on mastitis and AI models notably increased from 2016 to 2021, indicating growing interest. However, few studies utilized AI for bovine mastitis detection, primarily employing artificial neural network models. This suggests a clear potential for further research in this area.

Interpretable machine learning reveals microbiome signatures strongly associated with dairy cow milk urea nitrogen

The gut microbiome plays an important role in the healthy and efficient farming of dairy cows. However, high-dimensional microbial information is difficult to interpret in a simplified manner. We collected fecal samples from 161 cows and performed 16S amplicon sequencing. We developed an interpretable machine learning framework to classify individuals based on their milk urea nitrogen (MUN) concentrations. In this framework, we address the challenge of handling high-dimensional microbial data imbalances and identify 9 microorganisms strongly correlated with MUN. We introduce the Shapley Additive Explanations (SHAP) method to provide insights into the machine learning predictions. The results of the study showed that the performance of the machine learning model improved (accuracy = 72.7%) after feature selection on high-dimensional data. Among the 9 microorganisms, g__Firmicutes_unclassified had the greatest impact in the model. This study provides a reference for precision animal husbandry.

Transcriptomic signature of cancer cachexia by integration of machine learning, literature mining and meta-analysis

BACKGROUND

Cancer cachexia is a severe metabolic syndrome marked by skeletal muscle atrophy. A successful clinical intervention for cancer cachexia is currently lacking. The study of cachexia mechanisms is largely based on preclinical animal models and the availability of high-throughput transcriptomic datasets of cachectic mouse muscles is increasing through the extensive use of next generation sequencing technologies.

METHODS

Cachectic mouse muscle transcriptomic datasets of ten different studies were combined and mined by seven attribute weighting models, which analysed both categorical variables and numerical variables. The transcriptomic signature of cancer cachexia was identified by attribute weighting algorithms and was used to evaluate the performance of eleven pattern discovery models. The signature was employed to find the best combination of drugs (drug repurposing) for developing cancer cachexia treatment strategies, as well as to evaluate currently used cachexia drugs by literature mining.

RESULTS

Attribute weighting algorithms ranked 26 genes as the transcriptomic signature of muscle from mice with cancer cachexia. Deep Learning and Random Forest models performed better in differentiating cancer cachexia cases based on muscle transcriptomic data. Literature mining revealed that a combination of melatonin and infliximab has negative interactions with 2 key genes (Rorc and Fbxo32) upregulated in the transcriptomic signature of cancer cachexia in muscle.

CONCLUSIONS

The integration of machine learning, meta-analysis and literature mining was found to be an efficient approach to identifying a robust transcriptomic signature for cancer cachexia, with implications for improving clinical diagnosis and management of this condition.

The Prediction of Clinical Mastitis in Dairy Cows Based on Milk Yield, Rumination Time, and Milk Electrical Conductivity Using Machine Learning Algorithms

In commercial dairy farms, mastitis is associated with increased antimicrobial use and associated resistance, which may affect milk production. This study aimed to develop sensor-based prediction models for naturally occurring clinical bovine mastitis using nine machine learning algorithms with data from 447 mastitic and 2146 healthy cows obtained from five commercial farms in Northeast China. The variables were related to daily activity, rumination time, and daily milk yield of cows, as well as milk electrical conductivity. Both Z-standardized and non-standardized datasets pertaining to four specific stages of lactation were used to train and test prediction models. For all four subgroups, the Z-standardized dataset yielded better results than those of the non-standardized one, with the multilayer artificial neural net algorithm showing the best performance. Variables of importance had a similar rank in this algorithm, indicating the consistency of these variables as predictors for bovine mastitis in commercial farms with similar automatic systems. Moreover, the peak milk yield (PMY) of mastitic cows was significantly higher than that of healthy cows (p < 0.005), indicating that high-yielding cattle are more prone to mastitis. Our results show that machine learning algorithms are effective tools for predicting mastitis in dairy cows for immediate intervention and management in commercial farms.

Assessing the relationship between somatic cell count and the milk mid-infrared spectrum in Chinese Holstein cows

BACKGROUND

Milk produced by dairy cows is a complex combination of many components, but the effect of mastitis has only been investigated for a few of these components. Milk mid-infrared (MIR) spectra can reflect the global composition of milk, and this study aimed to detect the relationships between milk MIR spectral wavenumbers and milk somatic cell count (SCC)-a sensitive biomarker for mastitis.

METHODS

Pearson correlation analysis was used to calculate the correlation coefficient between somatic count score (SCS) and spectral wavenumbers. A general linear mixed model was applied to investigate the effect of three different classes of SCC (low, middle and high) on spectral wavenumbers.

RESULTS

The mean correlation coefficient between the 'fingerprint region' (wavenumbers 925-1582 cm-1 ) and the SCS was higher than that for other regions of the MIR spectrum, and the specific wavenumber with the strongest correlation with the SCS was within the 'fingerprint region'. SCC class had a significant (p < 0.05) effect on 639 spectral wavenumbers. In particular, some spectral wavenumbers within the 'fingerprint region' were highly affected by the SCC class.

LIMITATION

The data were collected from only one province in China, so the generalisability of the findings may be limited.

CONCLUSION

SCC had close relationships with milk spectral wavenumbers related to important milk components or chemical bonds.

Droplet digital PCR quantification of selected microRNAs in raw mastitic cow's milk from the west of Poland

Introduction

MicroRNAs (miRNAs), a class of noncoding small RNAs, have been recognised as potential biomarkers of mammary gland conditions, including bovine mastitis diagnosis. The aim of this study was to quantify selected miRNAs in the milk of mastitic cows.

Material and Methods

Milk samples (n = 90) were collected from healthy and mastitic dairy cows originating from local dairy cattle farms located in the west of Poland. MicroRNAs of the miR-21a, miR-92a, miR-146a and miR-383 species were quantified using the highly sensitive droplet digital PCR method. Direct measurement of somatic cell count (SCC) was performed using a cell counter. Cows were divided into three groups: those with an SCC below 200,000/mL were designated Low (n = 25), those with an SCC between 200,000 and 999,999 were Medium (n = 34), and those with an SCC of 1,000,000 or higher were High (n = 31). Microbiological analyses were performed using standard culture testing.

Results

The level of miR-383 was very low and this miRNA was excluded from analysis. The miR-92a was used to normalise miR-21a and miR-146a expression levels. The obtained results of expression of miR-21a and miR-146a correlated with somatic cell number (R = 0.53 and 0.79, respectively).

Conclusion

These results show that ddPCR is a useful method for quantifying miRNAs in raw cow milk. It seems that miR-146a is a promising marker for bovine mastitis, although further studies are needed to select a panel of miRNAs that can be used in mastitis monitoring in Poland.

Indirect Sensing of Subclinical Intramammary Infections in Dairy Herds with a Milking Robot

This study determined the impact of subclinical intramammary infections (IMIs), such as the major and minor udder pathogens (MaPs and MiPs), on the somatic cell count (SCC) in cow milk and investigated the possibilities of indirect sensing of the udder pathogens using the mastitis detection index (MDi) (DeLaval, Tumba, Sweden). The MDi incorporates quarter-level milk electrical conductivity, blood in milk, and milking interval. The case group (n = 21; MDi ≥ 1.4) was compared with the control group (n = 24; MDi < 1.4) for the presence of IMIs. The microbiological investigation of udder quarter foremilk samples was performed two times with an interval of 10 to 14 days. The case and control groups differed in terms of the occurrence of MaPs and MiPs in milk. During the continuous subclinical IMI and the episodic MaP infection, a higher SCC was detected compared with the episodic MiP infection or quarters without IMI. The novel finding of this study was that by using the milk quality sensor for the sensing of subclinical IMIs, there was an indication for the successful detection of episodic MaPs. However, the sensing of the continuous subclinical IMIs was not possible in the current study and still needs to be investigated.

Mastitis in Dairy Cattle: On-Farm Diagnostics and Future Perspectives

Mastitis is one of the most important diseases in dairy cattle farms, and it can affect the health status of the udder and the quantity and quality of milk yielded. The correct management of mastitis is based both on preventive and treatment action. With the increasing concern for antimicrobial resistance, it is strongly recommended to treat only the mammary quarters presenting intramammary infection. For this reason, a timely and accurate diagnosis is fundamental. The possibility to detect and characterize mastitis directly on farm would be very useful to choose the correct management protocol. Some on-field diagnostic tools are already routinely applied to detect mastitis, such as the California Mastitis Test and on-farm culture. Other instruments are emerging to perform a timely diagnosis and to characterize mastitis, such as Infra-Red Thermography, mammary ultrasound evaluation and blood gas analysis, even if their application still needs to be improved. The main purpose of this article is to present an overview of the methods currently used to control, detect, and characterize mastitis in dairy cows, in order to perform a timely diagnosis and to choose the most appropriate management protocol, with a specific focus on on-farm diagnostic tools.

Transcriptome-wide mapping of milk somatic cells upon subclinical mastitis infection in dairy cattle

BACKGROUND

Subclinical intramammary infection (IMI) represents a significant problem in maintaining dairy cows' health. Disease severity and extent depend on the interaction between the causative agent, environment, and host. To investigate the molecular mechanisms behind the host immune response, we used RNA-Seq for the milk somatic cells (SC) transcriptome profiling in healthy cows (n = 9), and cows naturally affected by subclinical IMI from Prototheca spp. (n = 11) and Streptococcus agalactiae (S. agalactiae; n = 11). Data Integration Analysis for Biomarker discovery using Latent Components (DIABLO) was used to integrate transcriptomic data and host phenotypic traits related to milk composition, SC composition, and udder health to identify hub variables for subclinical IMI detection.

RESULTS

A total of 1,682 and 2,427 differentially expressed genes (DEGs) were identified when comparing Prototheca spp. and S. agalactiae to healthy animals, respectively. Pathogen-specific pathway analyses evidenced that Prototheca's infection upregulated antigen processing and lymphocyte proliferation pathways while S. agalactiae induced a reduction of energy-related pathways like the tricarboxylic acid cycle, and carbohydrate and lipid metabolism. The integrative analysis of commonly shared DEGs between the two pathogens (n = 681) referred to the core-mastitis response genes, and phenotypic data evidenced a strong covariation between those genes and the flow cytometry immune cells (r² = 0.72), followed by the udder health (r² = 0.64) and milk quality parameters (r² = 0.64). Variables with r ≥ 0.90 were used to build a network in which the top 20 hub variables were identified with the Cytoscape cytohubba plug-in. The genes in common between DIABLO and cytohubba (n = 10) were submitted to a ROC analysis which showed they had excellent predictive performances in terms of discriminating healthy and mastitis-affected animals (sensitivity > 0.89, specificity > 0.81, accuracy > 0.87, and precision > 0.69). Among these genes, CIITA could play a key role in regulating the animals' response to subclinical IMI.

CONCLUSIONS

Despite some differences in the enriched pathways, the two mastitis-causing pathogens seemed to induce a shared host immune-transcriptomic response. The hub variables identified with the integrative approach might be included in screening and diagnostic tools for subclinical IMI detection.

A Literature Review of Modeling Approaches Applied to Data Collected in Automatic Milking Systems

Automatic milking systems (AMS) have played a pioneering role in the advancement of Precision Livestock Farming, revolutionizing the dairy farming industry on a global scale. This review specifically targets papers that focus on the use of modeling approaches within the context of AMS. We conducted a thorough review of 60 articles that specifically address the topics of cows' health, production, and behavior/management Machine Learning (ML) emerged as the most widely used method, being present in 63% of the studies, followed by statistical analysis (14%), fuzzy algorithms (9%), deterministic models (7%), and detection algorithms (7%). A significant majority of the reviewed studies (82%) primarily focused on the detection of cows' health, with a specific emphasis on mastitis, while only 11% evaluated milk production. Accurate forecasting of dairy cow milk yield and understanding the deviation between expected and observed milk yields of individual cows can offer significant benefits in dairy cow management. Likewise, the study of cows' behavior and herd management in AMSs is under-explored (7%). Despite the growing utilization of machine learning (ML) techniques in the field of dairy cow management, there remains a lack of a robust methodology for their application. Specifically, we found a substantial disparity in adequately balancing the positive and negative classes within health prediction models.

Early detection of subclinical mastitis in lactating dairy cows using cow-level features

Subclinical mastitis in cows affects their health, well-being, longevity, and performance, leading to reduced productivity and profit. Early prediction of subclinical mastitis can enable dairy farmers to perform interventions to mitigate its effect. The present study investigated how well predictive models built using machine learning techniques can detect subclinical mastitis up to 7 d before its occurrence. The data set used consisted of 1,346,207 milk-day (i.e., a day when milk was collected on both morning and evening) records spanning 9 yr from 2,389 cows producing on 7 Irish research farms. Individual cow composite milk yield and maximum milk flow were available twice daily, whereas milk composition (i.e., fat, lactose, protein) and somatic cell count (SCC) were collected once per week. Other features describing parity, calving dates, predicted transmitting ability for SCC, body weight, and history of subclinical mastitis were also available. The results of the study showed that a gradient boosting machine model trained to predict the onset of subclinical mastitis 7 d before a subclinical case occurs achieved a sensitivity and specificity of 69.45 and 95.64%, respectively. Reduced data collection frequency, where milk composition and SCC were recorded only every 15, 30, 45, and 60 d was simulated by masking data, to reflect the frequency of recording of this data on commercial dairy farms in Ireland. The sensitivity and specificity scores reduced as recording frequency reduced with respective scores of 66.93 and 80.43% when milk composition and SCC were recorded just every 60 d. Results demonstrate that models built on data that could be recorded routinely available on commercial dairy farms, can achieve useful predictive ability of subclinical mastitis even with reduced frequency of milk composition and SCC recording.

Estimates of Genetic Parameters for Milk, the Occurrence of and Susceptibility to Clinical Lameness and Claw Disorders in Dairy Goats

The New Zealand goat industry accesses niche markets for high-value products, mainly formula for infants and young children. This study aimed to estimate the genetic parameters of occurrence and susceptibility of clinical lameness and selected claw disorders and establish their genetic associations with milk production traits. Information on pedigree, lameness, claw disorders, and milk production was collected on three farms between June 2019 and July 2020. The dataset contained 1637 does from 174 sires and 1231 dams. Estimates of genetic and residual (co)variances, heritabilities, and genetic and phenotypic correlations were obtained with uni- and bi-variate animal models. The models included the fixed effects of farm and parity, deviation from the median kidding date as a covariate, and the random effects of animal and residual error. The heritability (h²) estimates for lameness occurrence and susceptibility were 0.07 and 0.13, respectively. The h² estimates for claw disorder susceptibilities ranged from 0.02 to 0.23. The genotypic correlations ranged from weak to very strong between lameness and milk production traits (-0.94 to 0.84) and weak to moderate (0.23 to 0.84) between claw disorder and milk production traits.

Exploiting machine learning methods with monthly routine milk recording data and climatic information to predict subclinical mastitis in Italian Mediterranean buffaloes

Mastitis has detrimental effects on the world's dairy industry, reducing animal health, milk production and quality, as well as income for farmers. In addition, consumers' growing interest in food safety and rational usage of antibiotics highlights the need to develop novel strategies to improve mastitis detection, prevention, and management. In the present study we applied machine learning (ML) analyses to predict presence or absence of subclinical mastitis in Italian Mediterranean buffaloes, exploiting information collected the previous month during routine milk recording procedures, as well as climatic data. The data set included 3,891 records of 1,038 buffaloes from 6 herds located in Basilicata Region (South Italy). Prediction models were developed using 4 different ML algorithms (Generalized Linear Model, Support Vector Machines, Random Forest, and Neural Network) and 2 data set splitting approaches for the creation of the training and test sets (by record or by animal ID number, always with 80% of the data used for model training and the remaining 20% for model testing). Support Vector Machine was the best method to predict high or low somatic cell count at the subsequent test-day record in the validation set, and therefore it was used to estimate the contribution of each feature to the best model. Independently from the data set splitting approach, the most important features were somatic cell score, differential somatic cell count, electrical conductivity, and milk production. Among climatic data, the most informative were temperature and relative humidity. When the data were split by animal ID, an improvement in models' predictive performance on the test set was observed, suggesting this as the most appropriate data splitting approach in data sets with repeated measures to avoid data leakage. According to different metrics, Neural Network was the best method for making predictions on the test set. Our findings confirmed the promising role of ML methods to improve prevention and surveillance of subclinical mastitis, exploiting the large amount of data currently available to identify animals that would possibly have high somatic cell count the subsequent month.

Regulatory Role of microRNA of Milk Exosomes in Mastitis of Dairy Cows

The aim of this study was to compare the cargos of miRNA in exosomes isolated from the milk of healthy (H) cows, cows at risk of mastitis (ARM), and cows with subclinical mastitis (SCM). Based on the number of somatic cells and the percentage of polymorphonuclear cells, 10 cows were assigned to group H, 11 to group ARM, and 11 to group SCM. After isolating exosomes in milk by isoelectric precipitation and ultracentrifugation, the extracted RNA was sequenced to 50 bp long single reads, and these were mapped against Btau_5.0.1. The resulting 225 miRNAs were uploaded to the miRNet suite, and target genes for Bos taurus were identified based on the miRTarBase and miRanda databases. The list of differentially expressed target genes resulting from the comparisons of the three groups was enriched using the Function Explorer of the Kyoto Encyclopedia of Genes and Genomes. A total of 38, 18, and 12 miRNAs were differentially expressed (DE, p < 0.05) in the comparisons of H vs. ARM, ARM vs. SCM, and H vs. SCM, respectively. Only 1 DE miRNA was shared among the three groups (bta-mir-221), 1 DE miRNA in the H vs. SCM comparison, 9 DE miRNAs in the ARM vs. SCM comparison, and 21 DE miRNAs in the H vs. ARM comparison. A comparison of the enriched pathways of target genes from the H, SCM, and ARM samples showed that 19 pathways were differentially expressed in the three groups, while 56 were expressed in the H vs. SCM comparison and 57 in the H vs. ARM comparison. Analyzing milk exosome miRNA cargos can be considered as a promising approach to study the complex molecular machinery set in motion in response to mastitis in dairy cows.

Relationships between body- and udder-related type traits with somatic cell counts and potential use for an early selection method for water buffaloes (Bubalus bubalis)

Water buffalo milk is a reliable source of high-quality nutrients; however, the susceptibility of mastitis in buffaloes must be taken into consideration. An animal with somatic cell count (SCC) of greater than 250,000 cells/mL is reported to be likely to have mastitis which has serious adverse effects on animal health, reproduction, milk yield, and milk quality. Type traits (TTs) of water buffalo can affect SCC in animal milk to some extent, but few reports on the correlation between SCC and TTs are available. In this study, a total of 1908 records collected from 678 water buffaloes were investigated. The general linear model was used to identify factors associated with phenotypic variation of the somatic cell score (SCS) trait, including parity, lactation length, calving year, and calving season as fixed effects. Using PROC CORR analysis method, taking calving year and lactation length as covariates, the correlation co-efficient between TT and SCS was obtained. Our results showed that correlation co-efficients between the 45 TTs with SCS ranged from 0.003 to 0.443 (degree of correlation). The correlation between udder traits and SCS was greater than that between body structure traits and SCS. Among udder traits, distance between teats (including front and rear teat distance [r = 0.308], front teat distance [r = 0.211], and teat crossing distance [r = 0.412]) and teat circumference (r = 0.443) had the highest correlation with SCS, followed by the leg traits including rear leg height (r = -0.354) and hock bend angle (r = -0.170). Animal with high rear legs (>48 cm) and short teat crossing distance (<17 cm), and narrow teat circumference (<11 cm) exhibited low SCS. Using four nonlinear models (Von Bertalanffy, Brody, Logistic, and Gompertz), the optimal growth curves of the TTs highly correlated with the SCS (rear leg height and teat crossing distance) were fitted, and the correction co-efficients of these two TTs rear leg height and teat crossing distance of animal from young age (2 mo old) to first lactation (35 mo old) were attained for establishment of early selection method for water buffaloes with low SCS. This study provides theoretical support for early selection of low-SCS water buffaloes and lays a foundation for improving milk quality and promoting healthy development of water buffalo's dairy industry.

Long-Term Calorie Restriction Alters Anxiety-like Behaviour and the Brain and Adrenal Gland Transcriptomes of the Ageing Male Rat

Further examination of the molecular regulators of long-term calorie restriction (CR), reported to have an anxiolytic effect, may highlight novel therapeutic targets for anxiety disorders. Here, adult male Hooded Wistar rats were exposed to a 25% CR whilst anxiety-like behaviour was assessed at 6-, 12-, and 18-months of age via the elevated plus maze, open field, and acoustic startle tests. Next-generation sequencing was then used to measure transcriptome-wide gene expression in the hypothalamus, amygdala, pituitary, and adrenal glands. Results showed an anxiolytic behavioural profile across early, middle, and late adulthood by CR, with the strongest effects noted at 6-months. Transcriptomic analysis by seven attribute weighting algorithms, including Info Gain Ratio, Rule, Chi Squared, Gini Index, Uncertainty, Relief, and Info Gain, led to the development of a signature of long-term CR, independent of region. Complement C1q A chain (C1qa), an extracellular protein, expression was significantly decreased by CR in most regions examined. Furthermore, text mining highlighted the positive involvement of C1qa in anxiety, depression, neurodegeneration, stress, and ageing, collectively identifying a suitable biomarker candidate for CR. Overall, the current study identified anxiety-related phenotypic changes and a novel transcriptome signature of long-term CR, indicating potential therapeutic targets for anxiety, depression, and neurodegeneration.

Composition, coagulation properties, and predicted cheesemaking traits of bulk goat milk from different farming systems, breeds, and stages of production

At the global level, the quantity of goat milk produced and its gross production value have increased considerably over the last 2 decades. Although many scientific papers on this topic have been published, few studies have been carried out on bulk goat milk samples. The aim of the present study was to investigate in the field the effects of farming system, breed type, individual flock, and stage of production on the composition, coagulation properties (MCP), curd firming over time parameters (CF_t), predicted cheese yield (CY%), and nutrient recovery traits (REC) of 432 bulk milk samples from 161 commercial goat farms in Sardinia, Italy. We found that the variance due to individual flock was of the same order as the residual variance for almost all composition and cheesemaking traits. With regard to the fixed effects, the effect of farming system on bulk milk variability was not highly significant for the majority of traits (it was lower than individual flock), whereas the effects of breed type and stage of production were much higher. More specifically, the intensive farms produced milk with the best concentrations of almost all constituents, whereas extensive farms exhibited faster rennet coagulation times, a slower rate of curd firming, lower potential curd firmness, and lower percentages of fat and energy recoveries in the fresh curd. Farms rearing the local breed, Sarda, alone or together with the Maltese breed, produced milk with the best concentrations of fat and protein, superior curd firmness, and better predicted percentage of fresh curd (CY_CURD) and recovery traits. The results show the potential of both types of breed, either for their quantitative (specialized breeds) or their qualitative (local breeds) attributes. As expected, the concentrations of fat, protein fractions, and lactose were influenced by the stage of production, with samples collected in the early stage of production (in February and March) having a greater quantity of the main constituents. Somatic cells reached the highest levels in the late stage of production, which corresponds to the goats' advanced stage of lactation (June-July), although no differences were present in the logarithmic bacterial counts between the early and late stages. Regarding cheesemaking potential, bulk milk samples of the late stage were characterized by delayed rennet coagulation and curd firming times, the lowest values of curd firmness, and a general reduction in CY%, and REC traits. In conclusion, we highlight several issues regarding the effects of the most important sources of variation on bulk goat milk, and point to some critical factors relevant for improving dairy goat farming and milk production.

Prevalence and Risk Factors of Staphylococcal Subclinical Mastitis in Dairy Animals of Chitwan, Nepal

Subclinical mastitis (SCM), the asymptomatic inflammation of breast tissue, is the most common form of mastitis in livestock. SCM prevalence and risk factors in dairy animals in Western Chitwan, Bagmati Province, Nepal, were the primary objectives of this study. Out of 243 dairy animals, 104 representing 42.8% were positive for SCM in the California mastitis test (CMT) in the study area. At the quarter level, out of 972 active quarters tested for SCM, 188 (19.3%) were positive to CMT test. The prevalence of Staphylococcal SCM was 39.92% (97/243) and 18.21% (177/972) at animal level and quarter level, respectively. Coagulase Negative Staphylococcus (CNS) (46.33%) was the most prevalent Staphylococcus to cause SCM at quarter level. While at animal level, SCM due to occurrence of both S. aureus and CNS (36.08%) in an individual was more common. High susceptibility towards Amikacin, Ceftriaxone and Gentamicin was seen against both isolates. Low resistance against Amikacin and Ceftriaxone was seen against both isolates. Ciprofloxacin (41.2% vs 27.4%) and Gentamicin (37.8% vs 23.2%) were more resistance towards CNS whereas Enrofloxacin (41.1% vs 25.2%) and Tetracycline (36.8% vs 15.1%) were more resistant towards S. aureus. Older aged, multiparous and late lactating animals had the highest prevalence of staphylococcal SCM i.e., 58.1%, 56% and 52.6%, respectively. The study concludes that there is a high prevalence of Staphylococcal SCM in Western Chitwan, Nepal. CNS is the most common mastitis pathogen. Increased antimicrobial resistance to S. aureus and CNS could be the result of the indiscriminate use of antibiotic drugs without an antibiotic susceptibility test (AST). This study emphasizes the importance of ongoing antibiotic surveillance, excellent farm and animal hygiene, and suitable housing and feeding management.

Relationship Between Somatic Cell Counts and Mammary Gland Parenchyma Ultrasonography in Buffaloes

The aim of the present study was to determine whether the echotextural features of the mammary gland parenchyma in buffaloes during lactation at different somatic cell levels could be used to diagnose mastitis. This study was divided into two parts. In the first experiment, experimental buffaloes (n = 65) with somatic cell counts (SCC) tests (n = 94) in different seasons, including spring (n = 22), summer (n = 24), autumn (n = 37), and winter (n = 11), were used to obtain ultrasonic variables for each quarter of mammary gland that could best explain the corresponding somatic cell level. In the second part of the study, the first part's experimental results were verified by subjecting at least one-quarter udder of eight buffaloes to ultrasonography seven times during mid-July to mid-August for obtaining ultrasonic values at different somatic cell levels. The echo textural characteristics [mean numerical pixel values (NPVs) and pixel heterogeneity (pixel standard deviation, PSD)] were evaluated using 16 ultrasonographic images of each buffalo with Image ProPlus software. The effects of SCC, days in milk (DIM), scanning order (SO), season, as well as the scanning plane and udder quarter (SP + UQ) on both the PSD and NPVs of the mammary gland were significant (p < 0.05). The correlation coefficient between pre-milking sagittal PSD and somatic cell score (SCS) was the highest (r = 0.4224, p < 0.0001) with fitted linear model: y = 0.19445x (dependent variable: SCS, independent variables: pre-milking sagittal PSD; R² = 0.84, p < 0.0001). In addition, SCC and ultrasonic of udder quarter were followed for 1 month, confirming that pre-milking sagittal PSD of mammary gland value could explain the SCC variation in milk. The current study demonstrated that the ultrasonographic examination of the udder could be one of the complementary tools for diagnosing subclinical mastitis in buffaloes.

Bidimensional and Tridimensional Poincaré Maps in Cardiology: A Multiclass Machine Learning Study

Heart rate is a nonstationary signal and its variation may contain indicators of current disease or warnings about impending cardiac diseases. Hence, heart rate variation analysis has become a noninvasive tool to further study the activities of the autonomic nervous system. In this scenario, the Poincaré plot analysis has proven to be a valuable tool to support cardiac diseases diagnosis. The study’s aim is a preliminary exploration of the feasibility of machine learning to classify subjects belonging to five cardiac states (healthy, hypertension, myocardial infarction, congestive heart failure and heart transplanted) using ten unconventional quantitative parameters extracted from bidimensional and three-dimensional Poincaré maps. Knime Analytic Platform was used to implement several machine learning algorithms: Gradient Boosting, Adaptive Boosting, k-Nearest Neighbor and Naïve Bayes. Accuracy, sensitivity and specificity were computed to assess the performances of the predictive models using the leave-one-out cross-validation. The Synthetic Minority Oversampling technique was previously performed for data augmentation considering the small size of the dataset and the number of features. A feature importance, ranked on the basis of the Information Gain values, was computed. Preliminarily, a univariate statistical analysis was performed through one-way Kruskal Wallis plus post-hoc for all the features. Machine learning analysis achieved interesting results in terms of evaluation metrics, such as demonstrated by Adaptive Boosting and k-Nearest Neighbor (accuracies greater than 90%). Gradient Boosting and k-Nearest Neighbor reached even 100% score in sensitivity and specificity, respectively. The most important features according to information gain are in line with the results obtained from the statistical analysis confirming their predictive power. The study shows the proposed combination of unconventional features extracted from Poincaré maps and well-known machine learning algorithms represents a valuable approach to automatically classify patients with different cardiac diseases. Future investigations on enriched datasets will further confirm the potential application of this methodology in diagnostic.

Systems Biology–Derived Genetic Signatures of Mastitis in Dairy Cattle: A New Avenue for Drug Repurposing

Simple Summary

Therapeutic success of bovine mastitis depends mainly on accurately diagnosing the type of pathogen involved. Despite the development prospects for bovine mastitis diagnosis, including new biomarker discovery to target specific pathogens with high sensitivity and specificity, treatment studies have shown controversial results, and the most efficient, safe, and economical treatments for mastitis are still topics of scientific debate. The goal of this research is the integration of different levels of systems biology data to predict candidate drugs for the control and management of E. coli mastitis. We propose that the novel drugs could be used by pharmaceutical scientists or veterinarians to find commercially efficacious medicines.

Abstract

Mastitis, a disease with high incidence worldwide, is the most prevalent and costly disease in the dairy industry. Gram-negative bacteria such as Escherichia coli (E. coli) are assumed to be among the leading agents causing acute severe infection with clinical signs. E. Coli, environmental mastitis pathogens, are the primary etiological agents of bovine mastitis in well-managed dairy farms. Response to E. Coli infection has a complex pattern affected by genetic and environmental parameters. On the other hand, the efficacy of antibiotics and/or anti-inflammatory treatment in E. coli mastitis is still a topic of scientific debate, and studies on the treatment of clinical cases show conflicting results. Unraveling the bio-signature of mastitis in dairy cattle can open new avenues for drug repurposing. In the current research, a novel, semi-supervised heterogeneous label propagation algorithm named Heter-LP, which applies both local and global network features for data integration, was used to potentially identify novel therapeutic avenues for the treatment of E. coli mastitis. Online data repositories relevant to known diseases, drugs, and gene targets, along with other specialized biological information for E. coli mastitis, including critical genes with robust bio-signatures, drugs, and related disorders, were used as input data for analysis with the Heter-LP algorithm. Our research identified novel drugs such as Glibenclamide, Ipratropium, Salbutamol, and Carbidopa as possible therapeutics that could be used against E. coli mastitis. Predicted relationships can be used by pharmaceutical scientists or veterinarians to find commercially efficacious medicines or a combination of two or more active compounds to treat this infectious disease.

Milk Somatic Cell Count and Polymorphonuclear Cells in Healthy Quarters of Cows That Underwent Blanket and Selective Dry Therapy: An Italian Case Study

The incidence of mastitis increases with parity in dairy cattle and multiparous cows are often treated at drying off to limit the risk of udder health issues and support mammary gland tissues recovery. Milk somatic cells count (SCC, cells/mL) comprises different white blood cells fractions and is worldwide used to monitor and genetically improve udder health. Nevertheless, only certain SCC fractions increase when an udder inflammation occurs. Considering that antibiotic use for preventive purposes will be forbidden in 2022, we compared two different dry therapy protocols, blanket (BDCT) and selective (SDCT), on different SCC fractions in healthy quarters milk. Multiparous Holstein cows were enrolled in a randomized controlled trial and SCC, neutrophils, macrophages, lymphocytes, polymorphonuclear cells (PMN) and differential somatic cell count (DSCC) recorded after the experimental drying off were available. Significant differences were observed between the two protocols, with more favorable parameters in BDCT than SDCT cows. Results showed that moving from BDCT to SDCT is expected to significantly increase some SCC fractions, such as PMN, in healthy quarters. The baseline SCC level at the onset of lactation was greater in cows under SDCT than BDCT. Although not significant, clinical mastitis prevalence was numerically lower in BDCT (7.32%) than SDCT (8.62%). In this study we referred to a limited number of cows, but still findings will be useful to improve the knowledge on the impact of SDCT on milk SCC fractions in healthy quarters.

MILK LIPIDS AND SUBCLINICAL MASTITIS

This article deals with the process of obtaining quality raw milk by analyzing its lipid composition. The lipid composition of raw milk depends on many factors, among which, first of all, is the species, the composition of the diet and the physiological state of the breast. In recent years, a large amount of data has accumulated on the fluctuations of certain lipid parameters of milk depending on the type, age, lactation, diet, time of year, exercise, animal husbandry technology, physiological state of the lactating organism in general and breast status in particular. Factors of regulation of fatty acid composition of raw milk: genetically determined parameters of quality and safety; fatty acid composition of the diet; synthesis of fatty acids by microorganisms of the digestive tract; synthesis of fatty acids in the breast; physiological state of the breast. The milk of each species of productive animals has its own specific lipid profile and is used in the formulation of certain dairy products to obtain the planned technological and nutritional parameters. Diagnosis of productive animals for subclinical mastitis involves the use of auxiliary (thermometry, thermography, electrical conductivity) and laboratory research methods: counting the number of somatic cells; use of specialized tests; microbiological studies of milk; biochemical studies of milk. The biochemical component in the diagnosis of subclinical forms of mastitis is underestimated. An increase in body temperature implies an increase in the intensity of heat release during the oxidation of substrates, sometimes due to a decrease in the intensity of synthesis of energy-intensive compounds. There are simply no other sources of energy in the body. The situation is the same with certain parts of the metabolism, which are aimed at the development of protective reactions to the etiological factor aimed at the defeat of the breast. That is why the biochemical composition of breast secretions in the absence of clinical signs of mastitis undergoes biochemical changes and the task of scientists is to develop mechanisms for clear tracking of such changes, identification of animals with subclinical forms of mastitis and effective treatment.

Comparison of machine learning methods to predict udder health status based on somatic cell counts in dairy cows

Bovine mastitis is one of the most important economic and health issues in dairy farms. Data collection during routine recording procedures and access to large datasets have shed the light on the possibility to use trained machine learning algorithms to predict the udder health status of cows. In this study, we compared eight different machine learning methods (Linear Discriminant Analysis, Generalized Linear Model with logit link function, Naïve Bayes, Classification and Regression Trees, k-Nearest Neighbors, Support Vector Machines, Random Forest and Neural Network) to predict udder health status of cows based on somatic cell counts. Prediction accuracies of all methods were above 75%. According to different metrics, Neural Network, Random Forest and linear methods had the best performance in predicting udder health classes at a given test-day (healthy or mastitic according to somatic cell count below or above a predefined threshold of 200,000 cells/mL) based on the cow’s milk traits recorded at previous test-day. Our findings suggest machine learning algorithms as a promising tool to improve decision making for farmers. Machine learning analysis would improve the surveillance methods and help farmers to identify in advance those cows that would possibly have high somatic cell count in the subsequent test-day.

Rule Discovery in Milk Content towards Mastitis Diagnosis: Dealing with Farm Heterogeneity over Multiple Years through Classification Based on Associations

Simple Summary

Invisible (subclinical) mastitis decreases milk quality and production. Invisible mastitis is linked to an increased use of antimicrobials. The risk of the emergence of antimicrobial-resistant bacteria is a major public health concern worldwide. Therefore, early detection of infected cows is of great importance. Machine learning has opened a new avenue for early mastitis prediction based on simple and accessible milking parameters, such as milk volume, fat, protein, lactose, electrical conductivity (EC), milking time, and milking peak flow. However, farm heterogeneity is a major challenge where multiple patterns can predict mastitis. Here, we employed a classification based on associations and scaling approach for multiple pattern discovery over multiple years. The approach we have developed helps to address farm heterogeneity and generalise machine learning-based diagnosis of mastitis worldwide.

Abstract

Subclinical mastitis, an economically challenging disease of dairy cattle, is associated with an increased use of antimicrobials which reduces milk quantity and quality. It is more common than clinical mastitis and far more difficult to detect. Recently, much attention has been paid to the development of machine-learning expert systems for early detection of subclinical mastitis from milking features. However, differences between animals within a farm as well as between farms, particularly across multiple years, are major obstacles to the generalisation of machine learning models. Here, for the first time, we integrated scaling by quartiling with classification based on associations in a multi-year study to deal with farm heterogeneity by discovery of multiple patterns towards mastitis. The data were obtained from one farm comprising Holstein Friesian cows in Ongaonga, New Zealand, using an electronic automated monitoring system. The data collection was repeated annually over 3 consecutive years. Some discovered rules, such as when the milking peak flow is low, electrical conductivity (EC) of milk is low, milk lactose is low, milk fat is high, and milk volume is low, the cow has subclinical mastitis, reached high confidence (>70%) in multiple years. On averages, over 3 years, low level of milk lactose and high value of milk EC were part of 93% and 83.8% of all subclinical mastitis detecting rules, offering a reproducible pattern of subclinical mastitis detection. The scaled year-independent combinational rules provide an easy-to-apply and cost-effective machine-learning expert system for early detection of hidden mastitis using milking parameters.

Dairy Cows' Health during Alpine Summer Grazing as Assessed by Milk Traits, Including Differential Somatic Cell Count: A Case Study from Italy

Simple Summary

Dairy herds in alpine areas usually adopt summer grazing, mainly to reduce feeding costs. This practice is related to the maintenance of local traditions and to the manufacturing of niche dairy products. However, it is important to assess the impact of this practice on cattle health. This case study investigated how milk-related health traits vary across extensive grazing during the summer period, using data collected in a dairy herd whose cows were repeatedly controlled for individual milk samples. Although the transition from barn farming to pasture led to a reduction in milk production, proper grazing management can make dairy cows more resilient in terms of udder health and metabolic efficiency. Findings of the present research report suggested that pasture can be adopted to maintain dairy herd sustainability without impairing animal health.

Abstract

Extensive summer grazing is a dairy herd management practice frequently adopted in mountainous areas. Nowadays, this activity is threatened by its high labour demand, but it is fundamental for environmental, touristic and economic implications, as well as for the preservation of social and cultural traditions. Scarce information on the effects of such low-input farming systems on cattle health is available. Therefore, the present case study aimed at investigating how grazing may affect the health status of dairy cows by using milk traits routinely available from the national milk recording scheme. The research involved a dairy herd of 52 Simmental and 19 Holstein × Simmental crossbred cows. The herd had access to the pasture according to a rotational grazing scheme from late spring up to the end of summer. A total of 616 test day records collected immediately before and during the grazing season were used. Individual milk yield was registered during the milking procedure. Milk samples were analysed for composition (fat, protein, casein and lactose contents) and health-related milk indicators (electrical conductivity, urea and β-hydroxybutyrate) using mid-infrared spectroscopy. Somatic cell count (SCC) and differential SCC were also determined. Data were analysed with a linear mixed model, which included the fixed effects of the period of sampling, cow breed, stage of lactation and parity, and the random effects of cow nested within breed and the residual. The transition from barn farming to pasture had a negative effect on milk yield, together with a small deterioration of fat and protein percentages. Health-related milk indicators showed a minor deterioration of the fat to protein ratio, differential SCC and electrical conductivity, particularly towards the end of the grazing season, whereas the somatic cell score and β-hydroxybutyrate were relatively constant. Overall, the study showed that, when properly managed, pasture grazing does not have detrimental effects on dairy cows in terms of udder health and efficiency. Therefore, the proper management of cows on pasture can be a valuable solution to preserve the economic, social and environmental sustainability of small dairy farms in the alpine regions, without impairing cows’ health.

Fast school closures correspond with a lower rate of COVID-19 incidence and deaths in most countries

School closures have been used as one of the main nonpharmaceutical interventions to overcome the spread of SARS-CoV-2. Different countries use this intervention with a wide range of time intervals from the date of the first confirmed case or death. This study aimed to investigate whether fast or late school closures affect the cumulative number of COVID-19 cases or deaths. A worldwide population-based observational study has been conducted and a range of attributes were weighted using 10 attribute weighting models against the normalized number of infected cases or death in the form of numeric, binominal and polynomial labels. Statistical analysis was performed for the most weighted and the most common attributes of all types of labels. By the end of March 2021, the school closure data of 198 countries with at least one COVID-19 case were available. The days before the first school closure were one of the most weighted factors in relation to the normalized number of infected cases and deaths in numeric, binomial, and quartile forms. The average of days before the first school closure in the lowest quartile to highest quartile of infected cases (Q1, Q2, Q3 and Q4) was -6.10 [95% CI, -26.5 to 14.2], 9.35 [95% CI, 2.16 to 16.53], 17.55 [95% CI, 5.95 to 29.15], and 16.00 [95% CI, 11.69 to 20.31], respectively. In addition, 188 countries reported at least one death from COVID-19. The average of the days before the first school closure in the lowest quartile of death to highest quartile (Q1, Q2, Q3 and Q4) was -49.4 [95% CI, -76.5 to -22.3], -10.34 [95% CI, -30.12 to 9.44], -18.74 [95% CI, -32.72 to -4.77], and -12.89 [95% CI, -27.84 to 2.06], respectively. Countries that closed schools faster, especially before the detection of any confirmed case or death, had fewer COVID-19 cases or deaths per million of the population on total days of involvement. It can be concluded that rapid prevention policies are the main determinants of the countries' success.

Application of machine learning to improve dairy farm management: A systematic literature review

In recent years, several researchers and practitioners applied machine learning algorithms in the dairy farm context and discussed several solutions to predict various variables of interest, most of which were related to incipient diseases. The objective of this article is to identify, assess, and synthesize the papers that discuss the application of machine learning in the dairy farm management context. Using a systematic literature review (SLR) protocol, we retrieved 427 papers, of which 38 papers were determined as primary studies and thus were analysed in detail. More than half of the papers (55 %) addressed disease detection. The other two categories of problems addressed were milk production and milk quality. Seventy-one independent variables were identified and grouped into seven categories. The two prominent categories that were used in more than half of the papers were milking parameters and milk properties. The other categories of independent variables were milk content, pregnancy/calving information, cow characteristics, lactation, and farm characteristics. Twenty-three algorithms were identified, which we grouped into four categories. Decision tree-based algorithms are by far the most used followed by artificial neural network-based algorithms. Regression-based algorithms and other algorithms that do not belong to the previous categories were used in 13 papers. Twenty-three evaluation parameters were identified of which 7 were used 3 or more times. The three evaluation parameters that were used by more than half of the papers are sensitivity, specificity, RMSE. The challenges most encountered were feature selection and unbalanced data and together with problem size, overfitting/estimating, and parameter tuning account for three-quarters of the challenges identified. To the best of our knowledge, this is the first SLR study on the use of machine learning to improve dairy farm management, and to this end, this study will be valuable not only for researchers but also practitioners in dairy farms.

Association of GH, STAT5A, MYF5 gene polymorphisms with milk somatic cell count, EC and pH levels of Holstein dairy cattle

This study was conducted to ivnestigate the associations of GH-AluI, STAT5A-AvaI and MYF5-TaqI gene polymorphisms with milk somatic cell count (SCC), electrical conductivity (EC) and pH levels in Holstein dairy cows. For this purpose, 167 blood and 1670 milk samples of 167 Holstein cows in their 2nd lactation were used. There were significant relationships between GH-AluI genotypes and milk EC (p < 0.001) and between STAT5A-AvaI genotypes and milk EC (p = 0.007), but there were not any significant relationships between MYF5 gene polymorphism and the investigated traits (p > 0.05). The greatest EC values were observed in GH-AluI-LV and STAT5A-AvaI-TT-genotyped individuals. Just because of association of EC with mastitis, it was concluded that present GH-AluI and STAT5A-AvaI polymorphisms could be used in further studies to be conducted to improve mastitis resistance and milk quality traits of Holstein dairy cows.

Milk somatic cell count and its relationship with milk yield and quality traits in Italian water buffaloes

In Southern Italy, buffalo (Bubalus bubalis) milk is mostly intended for the manufacture of Mozzarella di Bufala Campana Protected Denomination of Origin (PDO) cheese. Despite the economic boost of the last 2 decades, the buffalo farming system should be improved to maximize the efficiency of the dairy industry, improve yield and quality of milk and cheese, and work toward better animal welfare. Milk somatic cell count (SCC) is used worldwide as an indicator of udder health in individual milk and is useful for monitoring farm hygiene in bulk milk. Mastitis data are currently not available on a large scale in Italy; thus, SCC is essential for identifying animals with suspected udder infection and inflammation. Moreover, high milk SCC is associated with altered composition and acidity, and poor technological properties of milk. However, payment systems of the PDO area are based simply on the delivered volume of milk rather than on quality characteristics. Hence, currently there are no penalties for elevated SCC in bulk milk in the Italian buffalo dairy industry. In addition, SCC for buffalo milk is not mentioned by either the European Community regulations or the PDO protocol, evidencing a lack of rules for the maximum SCC limit. To provide a phenotypic characterization of SCC at the population level and to improve knowledge on buffalo milk quality, 876,299 test-day records of 70,156 buffaloes reared in the PDO area were analyzed. Data revealed that around 11% of herd-test-dates (≥5 animals sampled each) showed average milk SCC ≥400,000 cells/mL (i.e., above the threshold fixed by the European Community for bovine milk). This suggests that there is room to improve SCC at both the farm and individual level. Within first parity, more than 28 and 15% of lactations had average SCC ≥200,000 and ≥300,000 cells/mL, respectively. Both percentages increased with parity and were 39 and 25% in sixth parity, respectively. Supporting this, the proportion of lactations with average SCC ≥500,000 cells/mL increased from 6% in first parity to 12% in sixth parity. Milk yield and SCC were negatively correlated with each other, especially when SCC level was high. An ANOVA was carried out on test-day record milk yield and composition traits, with fixed effects of parity, lactation stage, class of somatic cell score (n = 6), month of calving, and their interactions; buffalo, herd-test-date, and residual were considered random effects. Significantly lower milk yield and lactose percentage were estimated in progressively higher classes of somatic cell score, whereas no significant differences were observed for fat and protein percentages. This is the first attempt to investigate milk SCC in a large data set of Italian dairy buffaloes. These findings may be helpful for defining reliable and effective SCC thresholds to be adopted whenever specific penalties for high SCC are included in milk payment systems. Finally, these results could be used in mastitis monitoring plans aiming to reduce SCC and udder issues at both the individual and farm levels in the Italian buffalo population.

Automated prediction of mastitis infection patterns in dairy herds using machine learning

Mastitis in dairy cattle is extremely costly both in economic and welfare terms and is one of the most significant drivers of antimicrobial usage in dairy cattle. A critical step in the prevention of mastitis is the diagnosis of the predominant route of transmission of pathogens into either contagious (CONT) or environmental (ENV), with environmental being further subdivided as transmission during either the nonlactating “dry” period (EDP) or lactating period (EL). Using data from 1000 farms, random forest algorithms were able to replicate the complex herd level diagnoses made by specialist veterinary clinicians with a high degree of accuracy. An accuracy of 98%, positive predictive value (PPV) of 86% and negative predictive value (NPV) of 99% was achieved for the diagnosis of CONT vs ENV (with CONT as a “positive” diagnosis), and an accuracy of 78%, PPV of 76% and NPV of 81% for the diagnosis of EDP vs EL (with EDP as a “positive” diagnosis). An accurate, automated mastitis diagnosis tool has great potential to aid non-specialist veterinary clinicians to make a rapid herd level diagnosis and promptly implement appropriate control measures for an extremely damaging disease in terms of animal health, productivity, welfare and antimicrobial use.

Comprehensive analysis of machine learning models for prediction of sub-clinical mastitis: Deep Learning and Gradient-Boosted Trees outperform other models

Sub-clinical bovine mastitis decreases milk quality and production. Moreover, sub-clinical mastitis leads to the use of antibiotics with consequent increased risk of the emergence of antibiotic-resistant bacteria. Therefore, early detection of infected cows is of great importance. The Somatic Cell Count (SCC) day-test used for mastitis surveillance, gives data that fluctuate widely between days, creating questions about its reliability and early prediction power. The recent identification of risk parameters of sub-clinical mastitis based on milking parameters by machine learning models is emerging as a promising new tool to enhance early prediction of mastitis occurrence. To develop the optimal approach for early sub-clinical mastitis prediction, we implemented 2 steps: (1) Finding the best statistical models to accurately link patterns of risk factors to sub-clinical mastitis, and (2) Extending this application from the farms tested to new farms (method generalization). Herein, we applied various machine learning-based prediction systems on a big milking dataset to uncover the best predictive models of sub-clinical mastitis. Data from 364,249 milking instances were collected by an electronic automated in-line monitoring system where milk volume, lactose concentration, electrical conductivity (EC), protein concentration, peak flow and milking time for each sample were measured. To provide a platform for the application of the models developed to other farms, the Z transformation approach was employed. Following this, various prediction systems [Deep Learning (DL), Naïve Bayes, Generalized Liner Model, Logistic Regression, Decision Tree, Gradient-Boosted Tree (GBT) and Random Forest] were applied to the non-transformed milking dataset and to a Z-standardized dataset. ROC (Receiver Operating Characteristics Curve), AUC (Area Under The Curve), and high accuracy demonstrated the high sensitivity of GBT and DL in detecting sub-clinical mastitis. GBT was the most accurate model (accuracy of 84.9%) in prediction of sub-clinical bovine mastitis. These data demonstrate how these models could be applied for prediction of sub-clinical mastitis in multiple bovine herds regardless of the size and sampling techniques.

On the genomic regions associated with milk lactose in Fleckvieh cattle

Lactose is a sugar uniquely found in mammals' milk and it is the major milk solid in bovines. Lactose yield (LY, kg/d) is responsible for milk volume, whereas lactose percentage (LP) is thought to be more related to epithelial integrity and thus to udder health. There is a paucity of studies that have investigated lactose at the genomic level in dairy cows. This paper aimed to improve our knowledge on LP and LY, providing new insights into the significant genomic regions affecting these traits. A genome-wide association study for LP and LY was carried out in Fleckvieh cattle by using bulls' deregressed estimated breeding values of first lactation as pseudo-phenotypes. Heritabilities of first-lactation test-day LP and LY estimated using linear animal models were 0.38 and 0.25, respectively. A total of 2,854 bulls genotyped with a 54K SNP chip were available for the genome-wide association study; a linear mixed model approach was adopted for the analysis. The significant SNP of LP were scattered across the whole genome, with signals on chromosomes 1, 2, 3, 7, 12, 16, 18, 19, 20, 28, and 29; the top 4 significant SNP explained 4.90% of the LP genetic variance. The signals were mostly in regions or genes with involvement in molecular intra- or extracellular transport; for example, CDH5, RASGEF1C, ABCA6, and SLC35F3. A significant region within chromosome 20 was previously shown to affect mastitis or somatic cell score in cattle. As regards LY, the significant SNP were concentrated in fewer regions (chromosomes 6 and 14), related to mastitis/somatic cell score, immune response, and transport mechanisms. The 5 most significant SNP for LY explained 8.45% of genetic variance and more than one-quarter of this value has to be attributed to the variant within ADGRB1. Significant peaks in target regions remained even after adjustment for the 2 most significant variants previously detected on BTA6 and BTA14. The present study is a prelude for deeper investigations into the biological role of lactose for milk secretion and volume determination, stressing the connection with genes regulating intra- or extracellular trafficking and immune and inflammatory responses in dairy cows. Also, these results improve the knowledge on the relationship between lactose and udder health; they support the idea that LP and its derived traits are potential candidates as indicators of udder health in breeding programs aimed to enhance cows' resistance to mastitis.

Invited review: Milk lactose-Current status and future challenges in dairy cattle

Lactose is the main carbohydrate in mammals' milk, and it is responsible for the osmotic equilibrium between blood and alveolar lumen in the mammary gland. It is the major bovine milk solid, and its synthesis and concentration in milk are affected mainly by udder health and the cow's energy balance and metabolism. Because this milk compound is related to several biological and physiological factors, information on milk lactose in the literature varies from chemical properties to heritability and genetic associations with health traits that may be exploited for breeding purposes. Moreover, lactose contributes to the energy value of milk and is an important ingredient for the food and pharmaceutical industries. Despite this, lactose has seldom been included in milk payment systems, and it has never been used as an indicator trait in selection indices. The interest in lactose has increased in recent years, and a summary of existing information about lactose in the dairy sector would be beneficial for the scientific community and the dairy industry. The present review collects and summarizes knowledge about lactose by covering and linking several aspects of this trait in bovine milk. Finally, perspectives on the use of milk lactose in dairy cattle, especially for selection purposes, are outlined.

Unified Transcriptomic Signature of Arbuscular Mycorrhiza Colonization in Roots of Medicago truncatula by Integration of Machine Learning, Promoter Analysis, and Direct Merging Meta-Analysis

Plant root symbiosis with Arbuscular mycorrhizal (AM) fungi improves uptake of water and mineral nutrients, improving plant development under stressful conditions. Unraveling the unified transcriptomic signature of a successful colonization provides a better understanding of symbiosis. We developed a framework for finding the transcriptomic signature of Arbuscular mycorrhiza colonization and its regulating transcription factors in roots of Medicago truncatula. Expression profiles of roots in response to AM species were collected from four separate studies and were combined by direct merging meta-analysis. Batch effect, the major concern in expression meta-analysis, was reduced by three normalization steps: Robust Multi-array Average algorithm, Z-standardization, and quartiling normalization. Then, expression profile of 33685 genes in 18 root samples of Medicago as numerical features, as well as study ID and Arbuscular mycorrhiza type as categorical features, were mined by seven models: RELIEF, UNCERTAINTY, GINI INDEX, Chi Squared, RULE, INFO GAIN, and INFO GAIN RATIO. In total, 73 genes selected by machine learning models were up-regulated in response to AM (Z-value difference > 0.5). Feature weighting models also documented that this signature is independent from study (batch) effect. The AM inoculation signature obtained was able to differentiate efficiently between AM inoculated and non-inoculated samples. The AP2 domain class transcription factor, GRAS family transcription factors, and cyclin-dependent kinase were among the highly expressed meta-genes identified in the signature. We found high correspondence between the AM colonization signature obtained in this study and independent RNA-seq experiments on AM colonization, validating the repeatability of the colonization signature. Promoter analysis of upregulated genes in the transcriptomic signature led to the key regulators of AM colonization, including the essential transcription factors for endosymbiosis establishment and development such as NF-YA factors. The approach developed in this study offers three distinct novel features: (I) it improves direct merging meta-analysis by integrating supervised machine learning models and normalization steps to reduce study-specific batch effects; (II) seven attribute weighting models assessed the suitability of each gene for the transcriptomic signature which contributes to robustness of the signature (III) the approach is justifiable, easy to apply, and useful in practice. Our integrative framework of meta-analysis, promoter analysis, and machine learning provides a foundation to reveal the transcriptomic signature and regulatory circuits governing Arbuscular mycorrhizal symbiosis and is transferable to the other biological settings.