Effects of lameness of dairy cows

Lameness is one of the most important welfare problems in dairy cattle. Most studies on lameness have focused on wide ranging surveys to identify causal factors, but few have considered the welfare implications of this disorder. In this study, we compared the social and individual behavior of 10 lame cows and 10 nonlame cows. The 20 Holstein-Friesian cows calved in the summer and spent the autumn and winter together with another 36 nonlame cows in a Newton Rigg cubicle house building. The cubicle to cow ratio was 1:1, and wheat straw bedding was provided every day. The investigators fed the cows ad lib a silage-based diet and milked them twice a day, at which time they received adjusted amounts of concentrate. The investigators observed the 2 groups of cows a total of 32 hr to obtain information on social and individual behaviors through scan and behavior sampling. Although lame cows were less likely to start an aggressive interaction, there were no differences in times receiving aggression. No differences were found in the times licking other cows; however, the frequency of times being licked was higher in the lame cows. The lame cows spent more time lying out of the cubicles, had longer total lying times, and spent less time feeding. The behavioral differences seen show that lame cows do not cope as successfully with their environment as do nonlame cows. Also, these results provide useful information on how licking in dairy cows may play a role in alleviating discomfort of other herd members who are in pain or who are sick.     

Machine learning approaches for prediction of linear B-cell epitopes on proteins

Identification and characterization of antigenic determinants on proteins has received considerable attention utilizing both, experimental as well as computational methods. For computational routines mostly structural as well as physicochemical parameters have been utilized for predicting the antigenic propensity of protein sites. However, the performance of computational routines has been low when compared to experimental alternatives. Here we describe the construction of machine learning based classifiers to enhance the prediction quality for identifying linear B-cell epitopes on proteins. Our approach combines several parameters previously associated with antigenicity, and includes novel parameters based on frequencies of amino acids and amino acid neighborhood propensities. We utilized machine learning algorithms for deriving antigenicity classification functions assigning antigenic propensities to each amino acid of a given protein sequence. We compared the prediction quality of the novel classifiers with respect to established routines for epitope scoring, and tested prediction accuracy on experimental data available for HIV proteins. The major finding is that machine learning classifiers clearly outperform the reference classification systems on the HIV epitope validation set.     

Machine learning approaches for the prediction of signal peptides and other protein sorting signals

Prediction of protein sorting signals from the sequence of amino acids has great importance in the field of proteomics today. Recently, the growth of protein databases, combined with machine learning approaches, such as neural networks and hidden Markov models, have made it possible to achieve a level of reliability where practical use in, for example automatic database annotation is feasible. In this review, we concentrate on the present status and future perspectives of SignalP, our neural network-based method for prediction of the most well-known sorting signal: the secretory signal peptide. We discuss the problems associated with the use of SignalP on genomic sequences, showing that signal peptide prediction will improve further if integrated with predictions of start codons and transmembrane helices. As a step towards this goal, a hidden Markov model version of SignalP has been developed, making it possible to discriminate between cleaved signal peptides and uncleaved signal anchors. Furthermore, we show how SignalP can be used to characterize putative signal peptides from an archaeon, Methanococcus jannaschii. Finally, we briefly review a few methods for predicting other protein sorting signals and discuss the future of protein sorting prediction in general.     

Machine learning approaches to lung cancer prediction from mass spectra

We addressed the problem of discriminating between 24 diseased and 17 healthy specimens on the basis of protein mass spectra. To prepare the data, we performed mass to charge ratio (m/z) normalization, baseline elimination, and conversion of absolute peak height measures to height ratios. After preprocessing, the major difficulty encountered was the extremely large number of variables (1676 m/z values) versus the number of examples (41). Dimensionality reduction was treated as an integral part of the classification process; variable selection was coupled with model construction in a single ten-fold cross-validation loop. We explored different experimental setups involving two peak height representations, two variable selection methods, and six induction algorithms, all on both the original 1676-mass data set and on a prescreened 124-mass data set. Highest predictive accuracies (1-2 off-sample misclassifications) were achieved by a multilayer perceptron and Na?ve Bayes, with the latter displaying more consistent performance (hence greater reliability) over varying experimental conditions. We attempted to identify the most discriminant peaks (proteins) on the basis of scores assigned by the two variable selection methods and by neural network based sensitivity analysis. These three scoring schemes consistently ranked four peaks as the most relevant discriminators: 11683, 1403, 17350 and 66107.     

Machine learning for profile prediction in genomics

A recent deluge of publicly available multi-omics data has fueled the development of machine learning methods aimed at investigating important questions in genomics. Although the motivations for these methods vary, a task that is commonly adopted is that of profile prediction, where predictions are made for one or more forms of biochemical activity along the genome, for example, histone modification, chromatin accessibility, or protein binding. In this review, we give an overview of the research works performing profile prediction, define two broad categories of profile prediction tasks, and discuss the types of scientific questions that can be answered in each.     

A note on possible link between behaviour and the occurrence of lameness in dairy cows

Lameness in cattle is a major welfare problem and has important economic implications. It is known that lameness has a multifactorial causation; however, it is still not clear why some individuals are more susceptible than others to present foot lesions under the same environment. Social and individual behaviour is thought to play an important role. The aim of this study was to assess the possible relationships between social behaviour, individual time budgets, and the incidence of lameness in 40 dairy cows. The incidence of lameness in the group of cows observed was 42%. There were no differences in the mean time standing between low-, middle- and high-ranking cows. Low-ranking cows spent more time standing still in passageways and standing half in the cubicles than middle- and high-ranking cows. No differences were found in the mean time standing between cows that got lame and cows that did not get lame. However, cows that got clinically lame spent longer standing half in the cubicles and had a significantly lower index of displacements than those cows that did not get lame. This study may offer a starting point to better understand the relationships between behaviour and the occurrence of lameness in dairy cows.     

The association between lameness,ovarian cysts and fertility in lactating dairy cows

The objective of this observational study was to evaluate the association between lameness, ovarian cysts, and fertility in lactating dairy cows. Data analysis of historical records from a 3000 Holstein farm was conducted. Sixty-five cows that became lame within 30 days postpartum were used as cases, and 130 nonlame cows served as controls. The outcome variables were incidence of ovarian cysts (OC, %), conception rate at first service (CRFS, %), overall pregnancy rate (PR, %), and calving to first service interval (CFSI, day), Incidence of OC and CRFS were analyzed by logistic regression, PR by survival analysis and CFSI by ANOVA. Lame cows had a lower CRFS (17.5% versus 42.6%) and higher incidence of OC (25.0% versus 11.1%) than controls (P0.05). There was a multicollinearity relationship between lameness and ovarian cysts. The results show that cows that became lame within the first 30 days postpartum were associated with a higher incidence of ovarian cysts, a lower likelihood of pregnancy, and lower fertility than control cows. Because this is an observational study it is not possible to conclude a cause-effect relationship.     

Machine learning techniques for protein function prediction

Proteins play important roles in living organisms, and their function is directly linked with their structure. Due to the growing gap between the number of proteins being discovered and their functional characterization (in particular as a result of experimental limitations), reliable prediction of protein function through computational means has become crucial. This paper reviews the machine learning techniques used in the literature, following their evolution from simple algorithms such as logistic regression to more advanced methods like support vector machines and modern deep neural networks. Hyperparameter optimization methods adopted to boost prediction performance are presented. In parallel, the metamorphosis in the features used by these algorithms from classical physicochemical properties and amino acid composition, up to text-derived features from biomedical literature and learned feature representations using autoencoders, together with feature selection and dimensionality reduction techniques, are also reviewed. The success stories in the application of these techniques to both general and specific protein function prediction are discussed.     

Effect of feeding yeast culture on reproduction and lameness in dairy cows under heat stress

Multiparous Holstein cows (n=717) from two dairy farms were blocked at calving by parity and previous lactation milk yield and, within each block, randomly assigned to one of two treatments: a diet containing no yeast culture (Control; n=359) or 30 g/d of a culture of Saccharomyces cerevisiae (YC; n=358) from 20 to 140 d postpartum. Only cows calving during months of heat stress, May-August were enrolled. Lameness score (1-5 scale) was evaluated at study enrollment and again at 100 d postpartum. The body condition score (BCS, 1-5 scale) was evaluated at calving, 28, 58 and 140 d postpartum. Cows received two injections of PGF(2alpha) at 37 and 51 d postpartum, and those observed in estrus were inseminated. Cows not in estrus were enrolled in a timed AI protocol at 65 d postpartum and inseminated at 75 d postpartum. Ovaries were examined by ultrasonography at 37 and 51 d postpartum to determine whether estrous cycling had been initiated by the presence of a corpus lutem (CL) in at least one of the two examinations. Pregnancy was diagnosed at 31, 38 and 66 d after the first AI and at 38 and 66 d after the second and third AI. Diet did not affect time of onset of estrous cycles postpartum, and 8.2% of the cows were anovular. Detection of estrus in the 7d after the second injection of PGF(2alpha) was similar for control and YC. For control and YC, conception rates 38 d after AI at first (30.8% and 31.4%), second (39.3% and 35.1%) and third (25.8% and 30.6%) inseminations, and pregnancy losses did not differ, which resulted in similar median days to pregnancy and proportion of pregnant cows at 140 d postpartum. Yeast culture did not affect incidence of lameness, but tended to reduce lameness score. Lame cows and anovular cows had lesser conception rates at first AI, and extended interval from calving to conception. A THI of 71 was identified as the critical point in which fertility was reduced in lactating dairy cows, although the sensitivity and specificity were minimal. Cows exposed to a THI>71 on the day of first AI had a 33% reduction in the rate of pregnancy resulting in extended interval to pregnancy. Feeding a yeast culture of S. cerevisiae had minor effects on lameness score, but no impact on reproduction of multiparous cows under heat stress.     

Machine learning methods for metabolic pathway prediction

Background  

A key challenge in systems biology is the reconstruction of an organism's metabolic network from its genome sequence. One strategy for addressing this problem is to predict which metabolic pathways, from a reference database of known pathways, are present in the organism, based on the annotated genome of the organism.     

Machine learning in protein structure prediction

Prediction of protein structure from sequence has been intensely studied for many decades, owing to the problem's importance and its uniquely well-defined physical and computational bases. While progress has historically ebbed and flowed, the past two years saw dramatic advances driven by the increasing “neuralization” of structure prediction pipelines, whereby computations previously based on energy models and sampling procedures are replaced by neural networks. The extraction of physical contacts from the evolutionary record; the distillation of sequence–structure patterns from known structures; the incorporation of templates from homologs in the Protein Databank; and the refinement of coarsely predicted structures into finely resolved ones have all been reformulated using neural networks. Cumulatively, this transformation has resulted in algorithms that can now predict single protein domains with a median accuracy of 2.1 Å, setting the stage for a foundational reconfiguration of the role of biomolecular modeling within the life sciences.     

Individualised automated lameness detection in dairy cows and the impact of historical window length on algorithm performance

Lameness is an important economic problem in the dairy sector, resulting in production loss and reduced welfare of dairy cows. Given the modern-day expansion of dairy herds, a tool to automatically detect lameness in real-time can therefore create added value for the farmer. The challenge in developing camera-based tools is that one system has to work for all the animals on the farm despite each animal having its own individual lameness response. Individualising these systems based on animal-level historical data is a way to achieve accurate monitoring on farm scale. The goal of this study is to optimise a lameness monitoring algorithm based on back posture values derived from a camera for individual cows by tuning the deviation thresholds and the quantity of the historical data being used. Back posture values from a sample of 209 Holstein Friesian cows in a large herd of over 2000 cows were collected during 15 months on a commercial dairy farm in Sweden. A historical data set of back posture values was generated for each cow to calculate an individual healthy reference per cow. For a gold standard reference, manual scoring of lameness based on the Sprecher scale was carried out weekly by a single skilled observer during the final 6 weeks of data collection. Using an individual threshold, deviations from the healthy reference were identified with a specificity of 82.3%, a sensitivity of 79%, an accuracy of 82%, and a precision of 36.1% when the length of the healthy reference window was not limited. When the length of the healthy reference window was varied between 30 and 250 days, it was observed that algorithm performance was maximised with a reference window of 200 days. This paper presents a high-performing lameness detection system and demonstrates the importance of the historical window length for healthy reference calculation in order to ensure the use of meaningful historical data in deviation detection algorithms.     

Biosensors in the livestock industry: an automated ovulation prediction system for dairy cows

Biosensor technology can offer the livestock industry new types of monitoring and measuring devices of which the specificity, sensitivity, reproducibility, speed and ease of use exceed the current technology. Biosensors can be applied to the detection and identification of infectious diseases in livestock, contaminants and toxins in feed, therapeutic drug residues in animal husbandry and oestrus detection. Our team is applying biosensor technology to the livestock industry by developing a fully automated ovulation prediction system for dairy cows. The results from field-tests show that the progesterone biosensor can characterize the ovulation cycles of cows and detect pregnancy.     

Machine learning approach for the prediction of protein secondary structure

PROMIS (protein machine induction system), a program for machine learning, was used to generalize rules that characterize the relationship between primary and secondary structure in globular proteins. These rules can be used to predict an unknown secondary structure from a known primary structure. The symbolic induction method used by PROMIS was specifically designed to produce rules that are meaningful in terms of chemical properties of the residues. The rules found were compared with existing knowledge of protein structure: some features of the rules were already recognized (e.g. amphipathic nature of alpha-helices). Other features are not understood, and are under investigation. The rules produced a prediction accuracy for three states (alpha-helix, beta-strand and coil) of 60% for all proteins, 73% for proteins of known alpha domain type, 62% for proteins of known beta domain type and 59% for proteins of known alpha/beta domain type. We conclude that machine learning is a useful tool in the examination of the large databases generated in molecular biology.     

面向蛋白质功能位点识别的机器学习平台构建

有关蛋白质功能的研究是解析生命奥秘的基础,机器学习技术在该领域已有广泛应用。利用支持向量机(support vectormachine,SVM)方法,构建一个预测蛋白质功能位点的通用平台。该平台先提取非同源蛋白质序列,再对这些序列进行特征编码(包括序列的基本信息、物化特征、结构信息及序列保守性特征等),以编码好的样本作为训练数据,利用SVM进行训练,得到敏感性、特异性、Matthew相关系数、准确率及ROC曲线等评价指标,反复测试,得到评价指标最优的SVM模型后,便可以用来预测蛋白质序列上的功能位点。该平台除了应用在预测蛋白质功能位点之外,还可以应用于疾病相关单核苷酸多态性(SNP)预测分析、预测蛋白质结构域分析、生物分子间的相互作用等。     

Machine learning approaches in MALDI-MSI: clinical applications

Introduction: Despite the unquestionable advantages of Matrix-Assisted Laser Desorption/Ionization Mass Spectrometry Imaging in visualizing the spatial distribution and the relative abundance of biomolecules directly on-tissue, the yielded data is complex and high dimensional. Therefore, analysis and interpretation of this huge amount of information is mathematically, statistically and computationally challenging.

Areas covered: This article reviews some of the challenges in data elaboration with particular emphasis on machine learning techniques employed in clinical applications, and can be useful in general as an entry point for those who want to study the computational aspects. Several characteristics of data processing are described, enlightening advantages and disadvantages. Different approaches for data elaboration focused on clinical applications are also provided. Practical tutorial based upon Orange Canvas and Weka software is included, helping familiarization with the data processing.

Expert commentary: Recently, MALDI-MSI has gained considerable attention and has been employed for research and diagnostic purposes, with successful results. Data dimensionality constitutes an important issue and statistical methods for information-preserving data reduction represent one of the most challenging aspects. The most common data reduction methods are characterized by collecting independent observations into a single table. However, the incorporation of relational information can improve the discriminatory capability of the data.     

Machine learning approaches applied in spinal pain research

The purpose of this narrative review is to provide a critical reflection of how analytical machine learning approaches could provide the platform to harness variability of patient presentation to enhance clinical prediction. The review includes a summary of current knowledge on the physiological adaptations present in people with spinal pain. We discuss how contemporary evidence highlights the importance of not relying on single features when characterizing patients given the variability of physiological adaptations present in people with spinal pain. The advantages and disadvantages of current analytical strategies in contemporary basic science and epidemiological research are reviewed and we consider how analytical machine learning approaches could provide the platform to harness the variability of patient presentations to enhance clinical prediction of pain persistence or recurrence. We propose that machine learning techniques can be leveraged to translate a potentially heterogeneous set of variables into clinically useful information with the potential to enhance patient management.     

Evaluation of enteric methane prediction equations for dairy cows used in whole farm models

The importance of evaluating greenhouse gas (GHG) emissions from dairy cows within the whole farm setting is being realized as more important than evaluating these emissions in isolation. Current whole farm models aimed at evaluating GHG emissions make use of simple regression equations to predict enteric methane (CH₄) production. The objective of the current paper is to evaluate the performance of nine CH₄ prediction equations that are currently being used in whole farm GHG models. Data used to evaluate the prediction equations came from a collection of individual (IND) and treatment averaged (TRT) data. Equations were compared based on mean square prediction error (MSPE) and concordance correlation coefficient (CCC) analysis. In general, predictions were poor, with root MSPE (as a percentage of observed mean) values ranging from 20.2 to 52.5 for the IND database and from 24.0 to 38.2 for the TRT database and CCC values ranging from 0.009 to 0.493 for the IND database and from 0.000 to 0.271 for the TRT database. Overall, the equations of Moe & Tyrrell and IPCC Tier II performed best on the IND dataset, and the equations of Moe & Tyrrell and Kirchgeßner et al., performed best on the TRT dataset. Results show that the simple more generalized equations performed worse than those that attempted to represent important aspects of diet composition, but in general significant amounts of bias and deviation of the regression slope from unity existed for all equations. The low prediction accuracy of CH₄ equations in whole farm models may introduce substantial error into inventories of GHG emissions and lead to incorrect mitigation recommendations.