Predicting environmental stressor levels with machine learning: a comparison between amplicon sequencing, metagenomics, and total RNA sequencing based on taxonomically assigned data.

Introduction: Microbes are increasingly (re)considered for environmental assessments because they are powerful indicators for the health of ecosystems. The complexity of microbial communities necessitates powerful novel tools to derive conclusions for environmental decision-makers, and machine learning is a promising option in that context. While amplicon sequencing is typically applied to assess microbial communities, metagenomics and total RNA sequencing (herein summarized as omics-based methods) can provide a more holistic picture of microbial biodiversity at sufficient sequencing depths. Despite this advantage, amplicon sequencing and omics-based methods have not yet been compared for taxonomy-based environmental assessments with machine learning. Methods: In this study, we applied 16S and ITS-2 sequencing, metagenomics, and total RNA sequencing to samples from a stream mesocosm experiment that investigated the impacts of two aquatic stressors, insecticide and increased fine sediment deposition, on stream biodiversity. We processed the data using similarity clustering and denoising (only applicable to amplicon sequencing) as well as multiple taxonomic levels, data types, feature selection, and machine learning algorithms and evaluated the stressor prediction performance of each generated model for a total of 1,536 evaluated combinations of taxonomic datasets and data-processing methods. Results: Sequencing and data-processing methods had a substantial impact on stressor prediction. While omics-based methods detected a higher diversity of taxa than amplicon sequencing, 16S sequencing outperformed all other sequencing methods in terms of stressor prediction based on the Matthews Correlation Coefficient. However, even the highest observed performance for 16S sequencing was still only moderate. Omics-based methods performed poorly overall, but this was likely due to insufficient sequencing depth. Data types had no impact on performance while feature selection significantly improved performance for omics-based methods but not for amplicon sequencing. Discussion: We conclude that amplicon sequencing might be a better candidate for machine-learning-based environmental stressor prediction than omics-based methods, but the latter require further research at higher sequencing depths to confirm this conclusion. More sampling could improve stressor prediction performance, and while this was not possible in the context of our study, thousands of sampling sites are monitored for routine environmental assessments, providing an ideal framework to further refine the approach for possible implementation in environmental diagnostics.

A computer vision image differential approach for automatic detection of aggressive behavior in pigs using deep learning.

Pig aggression is a major problem facing the industry as it negatively affects both the welfare and the productivity of group-housed pigs. This study aimed to use a supervised deep learning (DL) approach based on a convolutional neural network (CNN) and image differential to automatically detect aggressive behaviors in pairs of pigs. Different pairs of unfamiliar piglets (N = 32) were placed into one of the two observation pens for 3 d, where they were video recorded each day for 1 h following mixing, resulting in 16 h of video recordings of which 1.25 h were selected for modeling. Four different approaches based on the number of frames skipped (1, 5, or 10 for Diff1, Diff5, and Diff10, respectively) and the amalgamation of multiple image differences into one (blended) were used to create four different datasets. Two CNN models were tested, with architectures based on the Visual Geometry Group (VGG) VGG-16 model architecture, consisting of convolutional layers, max-pooling layers, dense layers, and dropout layers. While both models had similar architectures, the second CNN model included stacked convolutional layers. Nine different sigmoid activation function thresholds between 0.1 and 1.0 were evaluated and a 0.5 threshold was selected to be used for testing. The stacked CNN model correctly predicted aggressive behaviors with the highest testing accuracy (0.79), precision (0.81), recall (0.77), and area under the curve (0.86) values. When analyzing the model recall for behavior subtypes prediction, mounting and mobile non-aggressive behaviors were the hardest to classify (recall = 0.63 and 0.75), while head biting, immobile, and parallel pressing were easy to classify (recall = 0.95, 0.94, and 0.91). Runtimes were also analyzed with the blended dataset, taking four times less time to train and validate than the Diff1, Diff5, and Diff10 datasets. Preprocessing time was reduced by up to 2.3 times in the blended dataset compared to the other datasets and, when combined with testing runtimes, it satisfied the requirements for real-time systems capable of detecting aggressive behavior in pairs of pigs. Overall, these results show that using a CNN and image differential-based deep learning approach can be an effective and computationally efficient technique to automatically detect aggressive behaviors in pigs.

Aggressive behavior in pigs is a major concern for the swine industry that negatively affects animal welfare. This study aims to provide an efficient automatic solution based on computer vision and supervised deep learning models able to distinguish between aggressive and non-aggressive behavior of pigs using video recordings.

Application of SVR-Mediated GWAS for Identification of Durable Genetic Regions Associated with Soybean Seed Quality Traits.

Soybean (Glycine max L.) is an important food-grade strategic crop worldwide because of its high seed protein and oil contents. Due to the negative correlation between seed protein and oil percentage, there is a dire need to detect reliable quantitative trait loci (QTL) underlying these traits in order to be used in marker-assisted selection (MAS) programs. Genome-wide association study (GWAS) is one of the most common genetic approaches that is regularly used for detecting QTL associated with quantitative traits. However, the current approaches are mainly focused on estimating the main effects of QTL, and, therefore, a substantial statistical improvement in GWAS is required to detect associated QTL considering their interactions with other QTL as well. This study aimed to compare the support vector regression (SVR) algorithm as a common machine learning method to fixed and random model circulating probability unification (FarmCPU), a common conventional GWAS method in detecting relevant QTL associated with soybean seed quality traits such as protein, oil, and 100-seed weight using 227 soybean genotypes. The results showed a significant negative correlation between soybean seed protein and oil concentrations, with heritability values of 0.69 and 0.67, respectively. In addition, SVR-mediated GWAS was able to identify more relevant QTL underlying the target traits than the FarmCPU method. Our findings demonstrate the potential use of machine learning algorithms in GWAS to detect durable QTL associated with soybean seed quality traits suitable for genomic-based breeding approaches. This study provides new insights into improving the accuracy and efficiency of GWAS and highlights the significance of using advanced computational methods in crop breeding research.

Does wing use and disuse cause behavioural and musculoskeletal changes in domestic fowl (Gallus gallus domesticus)?

Domestic chickens may live in environments which restrict wing muscle usage. Notably, reduced wing activity and accompanying muscle weakness are hypothesized risk factors for keel bone fractures and deviations. We used radio-frequency identification (RFID) to measure duration spent at elevated resources (feeders, nest-boxes), ultrasonography to measure muscle thickness (breast and lower leg) changes, radiography and palpation to determine fractures and deviations, respectively, following no, partial (one-sided wing sling) and full (cage) immobilization in white- and brown-feathered birds. We hypothesized partially immobilized hens would reduce elevated resource usage and that both immobilization groups would show decreased pectoralis thickness (disuse) and increased prevalence of fractures and deviations. Elevated nest-box usage was 42% lower following five weeks of partial immobilization for brown-feathered hens but no change in resource usage in white-feathered birds was observed. Fully immobilized, white-feathered hens showed a 17% reduction in pectoralis thickness, while the brown-feathered counterparts showed no change. Lastly, fractures and deviations were not affected in either strain or form of wing immobilization; however, overall low numbers of birds presented with these issues. Altogether, this study shows a profound difference between white- and brown-feathered hens in response to wing immobilization and associated muscle physiology.

Unravelling the genetics of non-random fertilization associated with gametic incompatibility.

In the dairy industry, mate allocation is dependent on the producer's breeding goals and the parents' breeding values. The probability of pregnancy differs among sire-dam combinations, and the compatibility of a pair may vary due to the combination of gametic haplotypes. Under the hypothesis that incomplete incompatibility would reduce the odds of fertilization, and complete incompatibility would lead to a non-fertilizing or lethal combination, deviation from Mendelian inheritance expectations would be observed for incompatible pairs. By adding an interaction to a transmission ratio distortion (TRD) model, which detects departure from the Mendelian expectations, genomic regions linked to gametic incompatibility can be identified. This study aimed to determine the genetic background of gametic incompatibility in Holstein cattle. A total of 283,817 genotyped Holstein trios were used in a TRD analysis, resulting in 422 significant regions, which contained 2075 positional genes further investigated for network, overrepresentation, and guilt-by-association analyses. The identified biological pathways were associated with immunology and cellular communication and a total of 16 functional candidate genes were identified. Further investigation of gametic incompatibility will provide opportunities to improve mate allocation for the dairy cattle industry.

Predicting dry matter intake in Canadian Holstein dairy cattle using milk mid-infrared reflectance spectroscopy and other commonly available predictors via artificial neural networks.

Dry matter intake (DMI) is a fundamental component of the animal's feed efficiency, but measuring DMI of individual cows is expensive. Mid-infrared reflectance spectroscopy (MIRS) on milk samples could be an inexpensive alternative to predict DMI. The objectives of this study were (1) to assess if milk MIRS data could improve DMI predictions of Canadian Holstein cows using artificial neural networks (ANN); (2) to investigate the ability of different ANN architectures to predict unobserved DMI; and (3) to validate the robustness of developed prediction models. A total of 7,398 milk samples from 509 dairy cows distributed over Canada, Denmark, and the United States were analyzed. Data from Denmark and the United States were used to increase the training data size and variability to improve the generalization of the prediction models over the lactation. For each milk spectra record, the corresponding weekly average DMI (kg/d), test-day milk yield (MY, kg/d), fat yield (FY, g/d), and protein yield (PY, g/d), metabolic body weight (MBW), age at calving, year of calving, season of calving, days in milk, lactation number, country, and herd were available. The weekly average DMI was predicted with various ANN architectures using 7 predictor sets, which were created by different combinations MY, FY, PY, MBW, and MIRS data. All predictor sets also included age of calving and days in milk. In addition, the classification effects of season of calving, country, and lactation number were included in all models. The explored ANN architectures consisted of 3 training algorithms (Bayesian regularization, Levenberg-Marquardt, and scaled conjugate gradient), 2 types of activation functions (hyperbolic tangent and linear), and from 1 to 10 neurons in hidden layers). In addition, partial least squares regression was also applied to predict the DMI. Models were compared using cross-validation based on leaving out 10% of records (validation A) and leaving out 10% of cows (validation B). Superior fitting statistics of models comprising MIRS information compared with the models fitting milk, fat and protein yields suggest that other unknown milk components may help explain variation in weekly average DMI. For instance, using MY, FY, PY, and MBW as predictor variables produced a predictive accuracy (r) ranging from 0.510 to 0.652 across ANN models and validation sets. Using MIRS together with MY, FY, PY, and MBW as predictors resulted in improved fitting (r = 0.679-0.777). Including MIRS data improved the weekly average DMI prediction of Canadian Holstein cows, but it seems that MIRS predicts DMI mostly through its association with milk production traits and its utility to estimate a measure of feed efficiency that accounts for the level of production, such as residual feed intake, might be limited and needs further investigation. The better predictive ability of nonlinear ANN compared with linear ANN and partial least squares regression indicated possible nonlinear relationships between weekly average DMI and the predictor variables. In general, ANN using Bayesian regularization and scaled conjugate gradient training algorithms yielded slightly better weekly average DMI predictions compared with ANN using the Levenberg-Marquardt training algorithm.

Predicting methane emission in Canadian Holstein dairy cattle using milk mid-infrared reflectance spectroscopy and other commonly available predictors via artificial neural networks.

Interest in reducing eructed CH4 is growing, but measuring CH4 emissions is expensive and difficult in large populations. In this study, we investigated the effectiveness of milk mid-infrared spectroscopy (MIRS) data to predict CH4 emission in lactating Canadian Holstein cows. A total of 181 weekly average CH4 records from 158 Canadian cows and 217 records from 44 Danish cows were used. For each milk spectra record, the corresponding weekly average CH4 emission (g/d), test-day milk yield (MY, kg/d), fat yield (FY, g/d), and protein yield (PY, g/d) were available. The weekly average CH4 emission was predicted using various artificial neural networks (ANN), partial least squares regression, and different sets of predictors. The ANN architectures consisted of 3 training algorithms, 1 to 10 neurons with hyperbolic tangent activation function in the hidden layer, and 1 neuron with linear (purine) activation function in the hidden layer. Random cross-validation was used to compared the predictor sets: MY (set 1); FY (set 2); PY (set 3); MY and FY (set 4); MY and PY (set 5); MY, FY, and PY (set 6); MIRS (set 7); and MY, FY, PY, and MIRS (set 8). All predictor sets also included age at calving and days in milk, in addition to country, season of calving, and lactation number as categorical effects. Using only MY (set 1), the predictive accuracy (r) ranged from 0.245 to 0.457 and the root mean square error (RMSE) ranged from 87.28 to 99.39 across all prediction models and validation sets. Replacing MY with FY (set 2; r = 0.288-0.491; RMSE = 85.94-98.04) improved the predictive accuracy, but using PY (set 3; r = 0.260-0.468; RMSE = 86.95-98.47) did not. Adding FY to MY (set 4; r = 0.272-0.469; RMSE = 87.21-100.76) led to a negligible improvement compared with sets 1 and 3, but it slightly decreased accuracy compared with set 2. Adding PY to MY (set 5; r = 0.250-0.451; RMSE = 87.66-100.94) did not improve prediction ability. Combining MY, FY, and PY (set 6; r = 0.252-0.455; RMSE = 87.74-101.93) yielded accuracy slightly lower than sets 2 and 3. Using only MIRS data (set 7; r = 0.586-0.717; RMSE = 69.09-96.20) resulted in superior accuracy compared with all previous sets. Finally, the combination of MIRS data with MY, FY, and PY (set 8; r = 0.590-0.727; RMSE = 68.02-87.78) yielded similar accuracy to set 7. Overall, sets including the MIRS data yielded significantly better predictions than the other sets. To assess the predictive ability in a new unseen herd, a limited block cross-validation was performed using 20 cows in the same Canadian herd, which yielded r = 0.229 and RMSE = 154.44, which were clearly much worse than the average r = 0.704 and RMSE = 70.83 when predictions were made by random cross-validation. These results warrant further investigation when more data become available to allow for a more comprehensive block cross-validation before applying the calibrated models for large-scale prediction of CH4 emissions.

Machine-Learning-Based Genome-Wide Association Studies for Uncovering QTL Underlying Soybean Yield and Its Components.

A genome-wide association study (GWAS) is currently one of the most recommended approaches for discovering marker-trait associations (MTAs) for complex traits in plant species. Insufficient statistical power is a limiting factor, especially in narrow genetic basis species, that conventional GWAS methods are suffering from. Using sophisticated mathematical methods such as machine learning (ML) algorithms may address this issue and advance the implication of this valuable genetic method in applied plant-breeding programs. In this study, we evaluated the potential use of two ML algorithms, support-vector machine (SVR) and random forest (RF), in a GWAS and compared them with two conventional methods of mixed linear models (MLM) and fixed and random model circulating probability unification (FarmCPU), for identifying MTAs for soybean-yield components. In this study, important soybean-yield component traits, including the number of reproductive nodes (RNP), non-reproductive nodes (NRNP), total nodes (NP), and total pods (PP) per plant along with yield and maturity, were assessed using a panel of 227 soybean genotypes evaluated at two locations over two years (four environments). Using the SVR-mediated GWAS method, we were able to discover MTAs colocalized with previously reported quantitative trait loci (QTL) with potential causal effects on the target traits, supported by the functional annotation of candidate gene analyses. This study demonstrated the potential benefit of using sophisticated mathematical approaches, such as SVR, in a GWAS to complement conventional GWAS methods for identifying MTAs that can improve the efficiency of genomic-based soybean-breeding programs.

Effects of clipping of flight feathers on resource use in Gallus gallus domesticus.

Ground-dwelling species of birds, such as domestic chickens (Gallus gallus domesticus), experience difficulties sustaining flight due to high wing loading. This limited flight ability may be exacerbated by loss of flight feathers that is prevalent among egg-laying chickens. Despite this, chickens housed in aviary style systems need to use flight to access essential resources stacked in vertical tiers. To understand the impact of flight feather loss on chickens' ability to access elevated resources, we clipped primary and secondary flight feathers for two hen strains (brown-feathered and white-feathered, n = 120), and recorded the time hens spent at elevated resources (feeders, nest-boxes). Results showed that flight feather clipping significantly reduced the percentage of time that hens spent at elevated resources compared to ground resources. When clipping both primary and secondary flight feathers, all hens exhibited greater than or equal to 38% reduction in time spent at elevated resources. When clipping only primary flight feathers, brown-feathered hens saw a greater than 50% reduction in time spent at elevated nest-boxes. Additionally, brown-feathered hens scarcely used the elevated feeder regardless of treatment. Clipping of flight feathers altered the amount of time hens spent at elevated resources, highlighting that distribution and accessibility of resources is an important consideration in commercial housing.

Genome-Wide Association Studies of Soybean Yield-Related Hyperspectral Reflectance Bands Using Machine Learning-Mediated Data Integration Methods.

In conjunction with big data analysis methods, plant omics technologies have provided scientists with cost-effective and promising tools for discovering genetic architectures of complex agronomic traits using large breeding populations. In recent years, there has been significant progress in plant phenomics and genomics approaches for generating reliable large datasets. However, selecting an appropriate data integration and analysis method to improve the efficiency of phenome-phenome and phenome-genome association studies is still a bottleneck. This study proposes a hyperspectral wide association study (HypWAS) approach as a phenome-phenome association analysis through a hierarchical data integration strategy to estimate the prediction power of hyperspectral reflectance bands in predicting soybean seed yield. Using HypWAS, five important hyperspectral reflectance bands in visible, red-edge, and near-infrared regions were identified significantly associated with seed yield. The phenome-genome association analysis of each tested hyperspectral reflectance band was performed using two conventional genome-wide association studies (GWAS) methods and a machine learning mediated GWAS based on the support vector regression (SVR) method. Using SVR-mediated GWAS, more relevant QTL with the physiological background of the tested hyperspectral reflectance bands were detected, supported by the functional annotation of candidate gene analyses. The results of this study have indicated the advantages of using hierarchical data integration strategy and advanced mathematical methods coupled with phenome-phenome and phenome-genome association analyses for a better understanding of the biology and genetic backgrounds of hyperspectral reflectance bands affecting soybean yield formation. The identified yield-related hyperspectral reflectance bands using HypWAS can be used as indirect selection criteria for selecting superior genotypes with improved yield genetic gains in large breeding populations.

Application of machine learning and genetic optimization algorithms for modeling and optimizing soybean yield using its component traits.

Improving genetic yield potential in major food grade crops such as soybean (Glycine max L.) is the most sustainable way to address the growing global food demand and its security concerns. Yield is a complex trait and reliant on various related variables called yield components. In this study, the five most important yield component traits in soybean were measured using a panel of 250 genotypes grown in four environments. These traits were the number of nodes per plant (NP), number of non-reproductive nodes per plant (NRNP), number of reproductive nodes per plant (RNP), number of pods per plant (PP), and the ratio of number of pods to number of nodes per plant (P/N). These data were used for predicting the total soybean seed yield using the Multilayer Perceptron (MLP), Radial Basis Function (RBF), and Random Forest (RF), machine learning (ML) algorithms, individually and collectively through an ensemble method based on bagging strategy (E-B). The RBF algorithm with highest Coefficient of Determination (R2) value of 0.81 and the lowest Mean Absolute Errors (MAE) and Root Mean Square Error (RMSE) values of 148.61 kg.ha-1, and 185.31 kg.ha-1, respectively, was the most accurate algorithm and, therefore, selected as the metaClassifier for the E-B algorithm. Using the E-B algorithm, we were able to increase the prediction accuracy by improving the values of R2, MAE, and RMSE by 0.1, 0.24 kg.ha-1, and 0.96 kg.ha-1, respectively. Furthermore, for the first time in this study, we allied the E-B with the genetic algorithm (GA) to model the optimum values of yield components in an ideotype genotype in which the yield is maximized. The results revealed a better understanding of the relationships between soybean yield and its components, which can be used for selecting parental lines and designing promising crosses for developing cultivars with improved genetic yield potential.

ASAS-NANP SYMPOSIUM: Applications of machine learning for livestock body weight prediction from digital images.

Monitoring, recording, and predicting livestock body weight (BW) allows for timely intervention in diets and health, greater efficiency in genetic selection, and identification of optimal times to market animals because animals that have already reached the point of slaughter represent a burden for the feedlot. There are currently two main approaches (direct and indirect) to measure the BW in livestock. Direct approaches include partial-weight or full-weight industrial scales placed in designated locations on large farms that measure passively or dynamically the weight of livestock. While these devices are very accurate, their acquisition, intended purpose and operation size, repeated calibration and maintenance costs associated with their placement in high-temperature variability, and corrosive environments are significant and beyond the affordability and sustainability limits of small and medium size farms and even of commercial operators. As a more affordable alternative to direct weighing approaches, indirect approaches have been developed based on observed or inferred relationships between biometric and morphometric measurements of livestock and their BW. Initial indirect approaches involved manual measurements of animals using measuring tapes and tubes and the use of regression equations able to correlate such measurements with BW. While such approaches have good BW prediction accuracies, they are time consuming, require trained and skilled farm laborers, and can be stressful for both animals and handlers especially when repeated daily. With the concomitant advancement of contactless electro-optical sensors (e.g., 2D, 3D, infrared cameras), computer vision (CV) technologies, and artificial intelligence fields such as machine learning (ML) and deep learning (DL), 2D and 3D images have started to be used as biometric and morphometric proxies for BW estimations. This manuscript provides a review of CV-based and ML/DL-based BW prediction methods and discusses their strengths, weaknesses, and industry applicability potential.

In pursuit of a better broiler: growth, efficiency, and mortality of 16 strains of broiler chickens.

To meet the growing consumer demand for chicken meat, the poultry industry has selected broiler chickens for increasing efficiency and breast yield. While this high productivity means affordable and consistent product, it has come at a cost to broiler welfare. There has been increasing advocacy and consumer pressure on primary breeders, producers, processors, and retailers to improve the welfare of the billions of chickens processed annually. Several small-scale studies have reported better welfare outcomes for slower-growing strains compared to fast-growing, conventional strains. However, these studies often housed birds with range access or used strains with vastly different growth rates. Additionally, there may be traits other than growth, such as body conformation, that influence welfare. As the global poultry industries consider the implications of using slower growing strains, there was a need for a comprehensive, multidisciplinary examination of broiler chickens with a wide range of genotypes differing in growth rate and other phenotypic traits. To meet this need, our team designed a study to benchmark data on conventional and slower-growing strains of broiler chickens reared in standardized laboratory conditions. Over a 2-year period, we studied 7,528 broilers from 16 different genetic strains. In this paper, we compare the growth, efficiency, and mortality of broilers to one of two target weights (TW): 2.1 kg (TW1) and 3.2 kg (TW2). We categorized strains by their growth rate to TW2 as conventional (CONV), fastest-slow strains (FAST), moderate-slow strains (MOD), and slowest-slow strains (SLOW). When incubated, hatched, housed, managed, and fed the same, the categories of strains differed in body weights, growth rates, feed intake, and feed efficiency. At 48 d of age, strains in the CONV category were 835 to 1,264 g heavier than strains in the other categories. By TW2, differences in body weights and feed intake resulted in a 22 to 43-point difference in feed conversion ratios. Categories of strains did not differ in their overall mortality rates.

The relationship of pork carcass weight and leanness parameters in the Ontario commercial pork industry.

This study aimed to examine the correlation of carcass weight, fat depth, muscle depth, and predicted lean yield in commercial pigs. Data were collected on 850,819 pork carcasses from the same pork processing facility between October 2017 and September 2018. Hot carcass weight was reported following slaughter as a head-on weight; while fat and muscle depth were measured with a Destron PG-100 probe and used for the calculation of predicted lean yield based on the Canadian Lean Yield (CLY) equation [CLY (%) = 68.1863 - (0.7833 × fat depth) + (0.0689 × muscle depth) + (0.0080 × fat depth2) - (0.0002 × muscle depth2) + (0.0006 × fat depth × muscle depth)]. Descriptive statistics, regression equations including coefficients of determination, and Pearson product moment correlation coefficients (when assumptions for linearity were met) and Spearman's rank-order correlation coefficients (when assumptions for linearity were not met) were calculated for attributes using SigmaPlot, version 11 (Systat Software, Inc., San Jose, CA). Weak positive correlation was observed between hot carcass weight and fat depth (r = 0.289; P < 0.0001), and between hot carcass weight and muscle depth (r = 0.176; P < 0.0001). Weak negative correlations were observed between hot carcass weight and predicted lean yield (r = -0.235; P < 0.0001), and between fat depth and muscle depth (r = -0.148; P < 0.0001). Upon investigation of relationships between fat depth and predicted lean yield, and between muscle depth and predicted lean yield using scatter plots, it was determined that these relationships were not linear and therefore the assumptions of Pearson product moment correlation were not met. Thus, these relationships were expressed as nonlinear functions and Spearman's rank-order correlation coefficients were used. A strong negative correlation was observed between fat depth and predicted lean yield (r = -0.960; P < 0.0001), and a moderate positive correlation was observed between muscle depth and predicted lean yield (r = 0.406; P < 0.0001). Results from this dataset revealed that hot carcass weight was generally weakly correlated (r < |0.35|) with fat depth, muscle depth, and predicted lean yield. Therefore, it was concluded that there were no consistent weight thresholds where pigs were fatter or heavier muscled.

Application of Machine Learning Algorithms in Plant Breeding: Predicting Yield From Hyperspectral Reflectance in Soybean.

Recent substantial advances in high-throughput field phenotyping have provided plant breeders with affordable and efficient tools for evaluating a large number of genotypes for important agronomic traits at early growth stages. Nevertheless, the implementation of large datasets generated by high-throughput phenotyping tools such as hyperspectral reflectance in cultivar development programs is still challenging due to the essential need for intensive knowledge in computational and statistical analyses. In this study, the robustness of three common machine learning (ML) algorithms, multilayer perceptron (MLP), support vector machine (SVM), and random forest (RF), were evaluated for predicting soybean (Glycine max) seed yield using hyperspectral reflectance. For this aim, the hyperspectral reflectance data for the whole spectra ranged from 395 to 1005 nm, which were collected at the R4 and R5 growth stages on 250 soybean genotypes grown in four environments. The recursive feature elimination (RFE) approach was performed to reduce the dimensionality of the hyperspectral reflectance data and select variables with the largest importance values. The results indicated that R5 is more informative stage for measuring hyperspectral reflectance to predict seed yields. The 395 nm reflectance band was also identified as the high ranked band in predicting the soybean seed yield. By considering either full or selected variables as the input variables, the ML algorithms were evaluated individually and combined-version using the ensemble-stacking (E-S) method to predict the soybean yield. The RF algorithm had the highest performance with a value of 84% yield classification accuracy among all the individual tested algorithms. Therefore, by selecting RF as the metaClassifier for E-S method, the prediction accuracy increased to 0.93, using all variables, and 0.87, using selected variables showing the success of using E-S as one of the ensemble techniques. This study demonstrated that soybean breeders could implement E-S algorithm using either the full or selected spectra reflectance to select the high-yielding soybean genotypes, among a large number of genotypes, at early growth stages.

Pairwise visual comparison of small RNA secondary structures with base pair probabilities.

BACKGROUND: Predicted RNA secondary structures are typically visualized using dot-plots for base pair binding probabilities and planar graphs for unique structures, such as the minimum free energy structure. These are however difficult to analyze simultaneously. RESULTS: This work introduces a compact unified view of the most stable conformation of an RNA secondary structure and its base pair probabilities, which is called the Circular Secondary Structure Base Pairs Probabilities Plot (CS2BP2-Plot). Along with our design we provide access to a web server implementation of our solution that facilitates pairwise comparison of short RNA (and DNA) sequences up to 200 base pairs. The web server first calculates the minimum free energy secondary structure and the base pair probabilities for up to 10 RNA or DNA sequences using RNAfold and then provides a two panel comparative view that includes CS2BP2-Plots along with the traditional graph, planar and circular diagrams obtained with VARNA. The CS2BP2-Plots include highlighting of the nucleotide differences between two selected sequences using ClustalW local alignments. We also provide descriptive statistics, dot-bracket secondary structure representations and ClustalW local alignments for compared sequences. CONCLUSIONS: Using circular diagrams and colour and weight-coded arcs, we demonstrate how a single image can replace the state-of-the-art dual representations (dot-plots and minimum free energy structures) for base-pair probabilities of RNA secondary structures while allowing efficient exploration and comparison of different RNA conformations via a web server front end. With that, we provide the community, especially the biologically oriented, with an intuitive tool for ncRNA visualization. Web-server: https://nrcmonsrv01.nrc.ca/cs2bp2plot.

A review of traditional and machine learning methods applied to animal breeding.

The current livestock management landscape is transitioning to a high-throughput digital era where large amounts of information captured by systems of electro-optical, acoustical, mechanical, and biosensors is stored and analyzed on a daily and hourly basis, and actionable decisions are made based on quantitative and qualitative analytic results. While traditional animal breeding prediction methods have been used with great success until recently, the deluge of information starts to create a computational and storage bottleneck that could lead to negative long-term impacts on herd management strategies if not handled properly. A plethora of machine learning approaches, successfully used in various industrial and scientific applications, made their way in the mainstream approaches for livestock breeding techniques, and current results show that such methods have the potential to match or surpass the traditional approaches, while most of the time they are more scalable from a computational and storage perspective. This article provides a succinct view on what traditional and novel prediction methods are currently used in the livestock breeding field, how successful they are, and how the future of the field looks in the new digital agriculture era.

Analysis of MAPK and MAPKK gene families in wheat and related Triticeae species.

BACKGROUND: The mitogen-activated protein kinase (MAPK) family is involved in signal transduction networks that underpin many different biological processes in plants, ranging from development to biotic and abiotic stress responses. To date this class of enzymes has received little attention in Triticeae species, which include important cereal crops (wheat, barley, rye and triticale) that represent over 20% of the total protein food-source worldwide. RESULTS: The work presented here focuses on two subfamilies of Triticeae MAPKs, the MAP kinases (MPKs), and the MAPK kinases (MKKs) whose members phosphorylate the MPKs. In silico analysis of multiple Triticeae sequence databases led to the identification of 152 MAPKs belonging to these two sub-families. Some previously identified MAPKs were renamed to reflect the literature consensus on MAPK nomenclature. Two novel MPKs, MPK24 and MPK25, have been identified, including the first example of a plant MPK carrying the TGY activation loop sequence common to mammalian p38 MPKs. An EF-hand calcium-binding domain was found in members of the Triticeae MPK17 clade, a feature that appears to be specific to Triticeae species. New insights into the novel MEY activation loop identified in MPK11s are offered. When the exon-intron patterns for some MPKs and MKKs of wheat, barley and ancestors of wheat were assembled based on transcript data in GenBank, they showed deviations from the same sequence predicted in Ensembl. The functional relevance of MAPKs as derived from patterns of gene expression, MPK activation and MKK-MPK interaction is discussed. CONCLUSIONS: A comprehensive resource of accurately annotated and curated Triticeae MPK and MKK sequences has been created for wheat, barley, rye, triticale, and two ancestral wheat species, goat grass and red wild einkorn. The work we present here offers a central information resource that will resolve existing confusion in the literature and sustain expansion of MAPK research in the crucial Triticeae grains.

Temporal ordering of substitutions in RNA evolution: Uncovering the structural evolution of the Human Accelerated Region 1.

The Human Accelerated Region 1 (HAR1) is the most rapidly evolving region in the human genome. It is part of two overlapping long non-coding RNAs, has a length of only 118 nucleotides and features 18 human specific changes compared to an ancestral sequence that is extremely well conserved across non-human primates. The human HAR1 forms a stable secondary structure that is strikingly different from the one in chimpanzee as well as other closely related species, again emphasizing its human-specific evolutionary history. This suggests that positive selection has acted to stabilize human-specific features in the ensemble of HAR1 secondary structures. To investigate the evolutionary history of the human HAR1 structure, we developed a computational model that evaluates the relative likelihood of evolutionary trajectories as a probabilistic version of a Hamiltonian path problem. The model predicts that the most likely last step in turning the ancestral primate HAR1 into the human HAR1 was exactly the substitution that distinguishes the modern human HAR1 sequence from that of Denisovan, an archaic human, providing independent support for our model. The MutationOrder software is available for download and can be applied to other instances of RNA structure evolution.

The Plant Orthology Browser: An Orthology and Gene-Order Visualizer for Plant Comparative Genomics.

Worldwide genome sequencing efforts for plants with medium and large genomes require identification and visualization of orthologous genes, while their syntenic conservation becomes the pinnacle of any comparative and functional genomics study. Using gene models for 20 fully sequenced plant genomes, including model organisms and staple crops such as Coss., (L.) Heynh., (L.) Beauv., turnip ( L.), barley ( L.), rice ( L.), sorghum [ (L.) Moench], wheat ( L.), red wild einkorn ( Tumanian ex Gandilyan), and maize ( L.), we computationally predicted 1,021,611 orthologs using stringent sequence similarity criteria. For each pair of plant species, we determined sets of conserved synteny blocks using strand orientation and physical mapping. Gene ontology (GO) annotations are added for each gene. Plant Orthology Browser (POB) includes three interconnected modules: (i) a gene-order visualization module implementing an interactive environment for exploration of gene order between any pair of chromosomes in two plant species, (ii) a synteny visualization module providing unique interactive dot plot representations of orthologous genes between a pair of chromosomes in two distinct plant species, and (iii) a search module that interconnects all modules via free-text search capability with online as-you-type suggestions and highlighting that allows exploration of the underlining information without constraint of interface-dependent search fields. The POB is a web-based orthology and annotation visualization tool, which currently supports 20 completely sequenced plant species with considerably large genomes and offers intuitive and highly interactive pairwise comparison and visualization of genomic traits via gene orthology.