Linear Prediction Method Research Articles

Genomic evaluation of residual feed intake in US Holstein cows: insights into lifetime feed efficiency

Residual feed intake (RFI) is an important trait of feed efficiency that has been increasingly considered in the breeding objectives for dairy cattle. The objectives of this study were to estimate the genetic parameters of RFI and its component traits, namely, dry-matter intake (DMI), body weight (BW), and energy-corrected milk (ECM), in lactating Holstein cows; we thus developed a system for genomic evaluation of RFI in lactating Holstein cows and explored the associations of the RFI of heifers and cows. The RFI values were calculated from 2,538 first (n = 2,118) and second (n = 420) lactation Holsteins cows between 2020 and 2024 as part of the STgenetics EcoFeed® program. Of the animals, 1,516 were heifers from the same research station with previously established RFI values . After quality control, 61,283 single-nucleotide polymorphisms were used for the analyses. Univariate analyses were performed to estimate the heritabilities of RFI and its components in lactating cows; bivariate analyses were then performed to estimate the genetic correlations between the RFI of heifers and lactating cows using the genomic best unbiased linear prediction method. Animals with phenotypes and genotypes were used as the training population, and animals with only genotypes were considered the prediction population. The reliability of breeding values was obtained by approximation based on partitioning a function of the accuracy of the training population’s genomic estimated breeding values (GEBVs) and magnitudes of genomic relationships between the individuals in the training and prediction populations. The heritability estimates (mean ± SE) of the RFI, DMI, ECM, and BW were 0.43 ± 0.07, 0.44 ± 0.04, 0.40 ± 0.05, and 0.46 ± 0.04, respectively. The average reliability of the GEBVs for RFI from the training and prediction populations were 44% and 30%, respectively. The genetic correlations for the RFI were 0.42 ± 0.08 between heifers and first lactation cows and 0.34 ± 0.06 between heifers and first and second lactation cows. Our results show that the genetic components of RFI are not fully carried over from heifers to cows and that there is re-ranking of the individuals at different life stages. Selection of animals for feed efficiency on a lifetime basis thus requires accounting for the efficiencies during animal growth and milk production as a lactating cow.

Methods of Calculating Prediction Error Variance and Prediction Accuracy for Restricted Best Linear Unbiased Prediction of Breeding Values.

Prediction error variance (PEV) and prediction accuracy (PA) of breeding values (BVs) are essential for formulating breeding plans and predicting response to selection. However, restricted best linear unbiased prediction method (RBLUP method) carries many unknowns: in particular, the formulas for calculating PEV and PA are not clear. New findings were obtained using the RBLUP method. The uniqueness of RBLUP of BVs was proven. The formulas of PEV and PA for the RBLUP of BVs were derived from restricted mixed model equations. A method was also devised for easily calculating the PEV and PA for the RBLUP of BVs. Finally, the relationship between the RBLUP and ordinary BLUP of BVs was derived. It has become easier to calculate the PEV and PA for the RBLUP of BVs. This method is particularly effective for calculating the PEV and PA when applying the RBLUP method to achieve relative desired changes in all traits. This has also made it possible to predict the response to selection using the RBLUP method.

Consumer Support for Climate Policies Driven by Political Ideologies

Consumer support for climate policies is essential for new sustainable consumption patterns, which may face challenges considering the left-right political spectrum. This study aims to understand how different types of climate policies receive different levels of support from Liberals (Left), Moderates (Center), and Conservatives (Right). We analyzed data from an online panel with 1000 Brazilians through linear (ANOVA, MANOVA, and Correspondence Analysis) and non-linear predictive (Artificial Neural Networks) methods. Although Liberals are more concerned about overall global warming and climate change than Conservatives, both groups are more prone to support than to oppose climate change public policies. Moreover, while Moderates and Conservatives are getting more concerned about climate change, Liberals are becoming more pessimistic about mitigation strategies. Policies based on opportunity-facilitating or constraining using regulatory or economic instruments are associated differently with Liberals, Moderates, and Conservatives, indicating specific preferences for each political ideology.

The foresight methodology for transitional shale gas reservoirs prediction based on a knowledge graph

The sedimentary environment in the eastern Ordos area of China is complex and contains a large number of transitional facies environments. Yet, there are many characteristics such as large vertical lithology changes, complex lateral sedimentary environment changes, small monolith thickness and large organic matter content changes, which lead to large uncertainty in the prediction of favorable areas for transitional shale gas. As the intricate reservoirs continue to unfold, the conventional linear prediction methods find themselves facing an arduous path to meet the demands of development. The ever-evolving complexity of these reservoirs has outpaced the capabilities of these traditional approaches. It becomes apparent that a more comprehensive and adaptable approach is necessary to navigate the intricacies of these reservoirs and unlock their hidden potential. Therefore, we put forward a method of introducing knowledge graph into transitional shale gas reservoir prediction in the eastern Ordos region by using big data technology. Because artificial intelligence big data relies heavily on data tags, it is particularly important for the construction of tags. Firstly, a top-down knowledge graph in the field of reservoir prediction is constructed to determine the key parameters used in prediction, namely porosity, total organic carbon and brittleness index. Secondly, the decision tree knowledge graph optimization label is constructed in a bottom-up way. The key parameter of this prediction is the knowledge graph obtained according to the professional knowledge of reservoir prediction, so as to optimize the school label of U-net and reduce the workload of artificial judgment. The results of the combination of the two methods are applied to 11 wells in Daji area of Ordos, and the experimental results are consistent with the actual situation of the reservoir. Based on the foundation of theoretical knowledge, this method enhances the efficiency and accuracy of interpretation and evaluation. It provides fundamental and technical support for the selection of favorable areas in shale gas exploration and the evaluation of exploration and development prospects, particularly in transitional shale gas areas, which is innovative and advanced in the field.

Application of model predictive control scheme for piezoelectric ceramic micro-displacement

Abstract Currently, in the domain of micro-control technology, many operations need to meet the standard of nanometer-level positioning. As a high-precision micro-displacement element, piezoelectric ceramics are widely used in the field of micro-control due to their characteristics such as no need for transmission devices, high resolution, large output force, small size, and fast response speed. However, the inherent hysteresis nonlinearity of piezoelectric ceramics can lead to decreased displacement accuracy, oscillation, and even system instability. Therefore, eliminating the influence of nonlinear characteristics and improving displacement accuracy possess significant practical importance. In this paper, a model predictive control scheme is designed, which achieves faster response speed and higher accuracy compared to traditional control methods such as Proportional Integral Derivative control. Relevant simulations and tests have been conducted. In this scheme, hysteresis nonlinearity is first modeled and then compensated through feedforward, thereby simplifying the displacement control of piezoelectric ceramics into a more manageable linear problem. Subsequently, a linear model predictive control method is adopted to control the entire system. Both simulation and experimental results have verified the effectiveness of this control method.

Analysis of Tianjin real estate market: multiple linear regression prediction method

In this paper, the price prediction of Tianjin real estate market is studied, and the key factors affecting housing prices are systematically analyzed by using the method of multiple linear regression prediction. The research data comes from the real estate transaction data of Tianjin from 2018 to 2022, covering independent variable information such as housing area, housing age, geographical location and supporting facilities. By constructing multiple linear regression model, it is found that housing area and supporting facilities have a significant positive impact on housing prices, while housing age and distance from the city center have a significant negative impact on housing prices. Specifically, for every 1 square meter increase in housing area, house prices are expected to rise by 450 yuan; Every year the age of the house increases, the house price is expected to drop by 200 yuan; Every kilometer away from the city center, house prices are expected to drop in 800 yuan; Every time the score of supporting facilities is increased by 1 point, the house price is expected to increase by 1200 yuan. The goodness-of-fit test of the model shows that the R value is 0.85, which shows that the model has strong explanatory power. In addition, through the correlation analysis of independent variables, it is found that there is a positive correlation between housing area and supporting facilities, but the correlation with other variables is weak. This study not only enriches the theoretical research of the real estate market, but also provides valuable decision-making reference for the government, enterprises and consumers, and helps the healthy and stable development of the real estate market in Tianjin.

Small Area Estimation of Maluku and Papua Island Child Poverty Levels in 2023

Child welfare issues such as child poverty pose a challenge for Indonesia. The provinces in Maluku and Papua have the highest rates of child poverty. Data on child poverty at regencies/municipalities level is needed to address this issue through targeted policies. The direct estimations have a Relative Standard Error (RSE) value of more than 25 percent, necessitating the use of an indirect method, Small Area Estimation (SAE). This study aims to compare the results of indirect estimates of the percentage of children aged 0-17 living in poverty at the regencies/municipalities level in Maluku and Papua using SAE Empirical Best Linear Unbiased Prediction (EBLUP) and Hierarchical Bayes Beta (HB Beta) methods. Susenas KOR March 2023 data is used to produce direct estimates, while Podes 2021 data is used to form auxiliary variables. The results indicate that the SAE HB Beta method provides estimates with better RSE compared to SAE EBLUP. All regencies/municipalities in the Maluku and Papua have a fairly good level of accuracy.

Economic Evaluation of Conservation through Use of an Araucaria angustifolia Provenance and Progeny Test.

Araucaria angustifolia is a species known for its valuable wood and nuts, but it is threatened with extinction. The plantation of forests for genetic resource conservation is a complementary strategy designed to reduce the species' genetic variability loss. This study aimed to evaluate the technical and economic viability of A. angustifolia for genetic conservation through use. The analyzed provenance and progeny trial was established in 1982 in Itapeva, Brazil. It was structured using a compact family blocks design with 110 open-pollinated progenies from five natural populations, three replicates, ten plants per subplot, and 3.0 m × 2.0 m spacing. After 33 years, the trial was evaluated for total height, diameter at breast height, wood volume, and survival. The variance components and genetic parameter estimates were performed using Restricted Maximum Likelihood/Best Linear Unbiased Prediction methods (REML/BLUP) methods with the Selegen software (version 2014). The production and management scenarios were obtained using the SisAraucaria software (version 2003). Sensitivity analysis and economic parameter estimates were obtained through various economic evaluation methods using the Planin software (version 1995). In general, the genetic parameters indicated that the population has enough variability for both conservation and breeding purposes, suggesting technical viability for the establishment of a seed orchard. The economic parameters indicated that the commercialization of wood and araucaria nuts proved to be more profitable than wood production by itself. In conclusion, araucaria genetic conservation through use is a technically and economically viable ex situ conservation strategy.

Evaluating the strength of subgrade soil for pavement design: an analysis using support vector regression model optimized by bayesian algorithm

Determining the strength of subgrade soil, crucial for flexible pavement design, traditionally relies on time-consuming and labour-intensive California Bearing Ratio (CBR) tests. The limitations of linear and non-linear regression-based prediction methods have led to an increased importance of soft computing techniques in providing flexible and consistent CBR predictions for practical engineering. This paper proposes a hybrid model that combines the Bayesian Optimization algorithm (BOA) with support vector regression (SVR) to predict CBR for subgrade soil in pavement design. A database of 238 soil test datasets from northern Algeria was utilised to develop the BOA-SVR model. Using the BOA technique to optimize hyperparameters can improve the model’s performance. The developed hybrid model closely matched experimental results, with a coefficient of determination of 89% and a mean squared error of 5.77, indicating high predictive accuracy. Comparative analysis shows that the BOA-SVR model performs better than conventional and other machine learning models in predicting CBR in tested subgrade soils, in terms of accuracy and robustness. Finally, the optimal subset of features from the initial dataset combined with the BOA-SVR model is determined using an exhaustive feature selection method that includes cross-validation. The results of the experiment indicate that the accuracy of the hybrid model that has been developed is improved by a subset of only seven features from the twelve initial features, this allows for the reduction of computing time and storage space.

An optimal midcourse guidance method for dual pulse air-to-air missiles using linear Gauss pseudospectral model predictive control method

This paper proposes an optimal midcourse guidance method for dual pulse air-to-air missiles, which is based on the framework of the linear Gauss pseudospectral model predictive control method. Firstly, a multistage optimal control problem with unspecified terminal time is formulated. Secondly, the control and terminal time update formulas are derived analytically. In contrast to previous work, the derivation process fully considers the Hamiltonian function corresponding to the unspecified terminal time, which is coupled with control, state, and costate. On the assumption of small perturbation, a special algebraic equation is provided to represent the equivalent optimal condition for the terminal time. Also, using Gauss pseudospectral collocation, error propagation dynamical equations involving the first-order correction term of the terminal time are transformed into a set of algebraic equations. Furthermore, analytical modification formulas can be derived by associating those equations and optimal conditions to eliminate terminal error and approach nonlinear optimal control. Even with their mathematical complexity, these formulas produce more accurate control and terminal time corrections and remove reliance on task-related parameters. Finally, several numerical simulations, comparisons with typical methods, and Monte Carlo simulations have been done to verify its optimality, high convergence rate, great stability and robustness.

Investigating the genomic background of calving-related traits in Canadian Jersey cattle

Traits related to calving have a significant impact on animal welfare and farm profitability in dairy production systems. Identifying genomic regions associated with calving traits could contribute to refining dairy cattle breeding programs and management practices in the dairy industry. Therefore, the primary objectives of this study were to estimate genetic parameters and perform genome-wide association studies (GWAS) and functional enrichment analyses for stillbirth, gestation length, calf size, and calving ease traits in North American Jersey cattle. A total of 40,503 animals with phenotypic records and 5,398 animals genotyped for 45,101 single nucleotide polymorphisms (SNPs) were included in the analyses. Genetic parameters were estimated based on animal models and Bayesian methods. The effects of SNPs were estimated using the Single-step Genomic Best Linear Unbiased Prediction (ssGBLUP) method. The heritability (standard error) estimates ranged from 0.01 (0.01) for stillbirths (SB) in heifers to 0.11 (0.01) for gestation length (GL) in cows. The genetic correlations ranged from -0.58 (0.11) between calving ease (CE) and SB in heifers to 0.44 (0.14) between calving ease and calf size (CZ) in cows. CE showed the highest genetic correlation between heifers and cows, 0.8 (0.22) respectively. The candidate genes identified, including MTHFR, SERPINA5, IGFBP3, and ZRANB1, are involved in key biological processes and metabolic pathways related to the studied traits. Reducing environmental variation and identifying novel indicators of reproduction traits in the Jersey breed are needed given the low heritability estimates for most traits evaluated in this study. In conclusion, this study provides a characterization of the genetic background of calving-related traits in Jersey cattle. The estimates obtained can be used to improve or build selection indexes in Jersey cattle breeding programs in North America.

Enhancing deep neural network training efficiency and performance through linear prediction

Deep neural networks have achieved remarkable success in various fields. However, training an effective deep neural network still poses challenges. This paper aims to propose a method to optimize the training effectiveness of deep neural networks, with the goal of improving their performance. Firstly, based on the observation that parameters (weights and bias) of deep neural network change in certain rules during training process, the potential of parameters prediction for improving training efficiency is discovered. Secondly, the potential of parameters prediction to improve the performance of deep neural network by noise injection introduced by prediction errors is revealed. And then, considering the limitations comprehensively, a deep neural network Parameters Linear Prediction method is exploit. Finally, performance and hyperparameter sensitivity validations are carried out on some representative backbones. Experimental results show that by employing proposed Parameters Linear Prediction method, as opposed to SGD, has led to an approximate 1% increase in accuracy for optimal model, along with a reduction of about 0.01 in top-1/top-5 error. Moreover, it also exhibits stable performance under various hyperparameter settings, shown the effectiveness of the proposed method and validated its capacity in enhancing network’s training efficiency and performance.

Genomic Selection for Weaning Weight in Alpine Merino Sheep Based on GWAS Prior Marker Information.

This study aims to compare the accuracy of genomic estimated breeding values (GEBV) estimated using a genomic best linear unbiased prediction (GBLUP) method and GEBV estimates incorporating prior marker information from a genome-wide association study (GWAS) for the weaning weight trait in highland Merino sheep. The objective is to provide theoretical and technical support for improving the accuracy of genomic selection. The study used a population of 1007 highland Merino ewes, with the weaning weight at 3 months as the target trait. The population was randomly divided into two groups. The first group was used for GWAS analysis to identify significant markers, and the top 5%, top 10%, top 15%, and top 20% markers were selected as prior marker information. The second group was used to estimate genetic parameters and compare the accuracy of GEBV predictions using different prior marker information. The accuracy was obtained using a five-fold cross-validation. Finally, both groups were subjected to cross-validation. The study's findings revealed that the heritability of the weaning weight trait, as calculated using the GBLUP model, ranged from 0.122 to 0.394, with corresponding prediction accuracies falling between 0.075 and 0.228. By incorporating prior marker information from GWAS, the heritability was enhanced to a range of 0.125 to 0.407. The inclusion of the top 5% to top 20% significant SNPs from GWAS results as prior information into GS showed potential for improving the accuracy of predicting genomic breeding value.

Spectrum estimation for voiced speech using average weighted linear prediction

In many different areas, such as neurophysics, geophysics, and communication, it is vital to effectively handle signals when there is unwanted disturbance. Linear prediction (LP) methods provide precise modeling capabilities for various parametric models and are used in a wide range of fields such as predicting future data, compressing speech, analyzing spectra, filling in missing signals, and decreasing noise. LP is especially beneficial in speech processing systems. Speech analysis and synthesis greatly relies on spectral envelopes, which are closely connected to models of speech production and perception. However, the performance of the LP method may decline when limited information is involved in pitch synchronous analysis. In order to overcome this constraint, we developed the implementation of the Average Weighted Linear Prediction (AWLP) technique, which does not require the use of a window. The AWLP utilizes a signal of weighted prediction error acquired from the autocorrelation process of LP. By performing this action, it provides a more precise estimation of the power spectrum and coefficients used for vocal tract parametric models. Importantly, the effectiveness of the AWLP can be seen in both pitch synchronous and asynchronous analyses, which means it is appropriate for situations where segments are chosen randomly. We confirm the effectiveness of the AWLP technique by employing it on both synthetic voice and real speech. Additionally, we assess its effectiveness by comparing it to the direct autocorrelation technique and a modified autocorrelation (MA) approach. To sum up, the AWLP method presents a hopeful solution for reliable spectral analysis that addresses the divide between pitch synchronous and asynchronous situations.

The best linear unbiased prediction (BLUP) method as a tool to estimate the lifetime risk of pancreatic ductal adenocarcinoma in high-risk individuals with no known pathogenic germline variants

Pancreatic ductal adenocarcinoma (PDAC) is the fourth leading cause of cancer-related death in the Western world. The number of diagnosed cases and the mortality rate are almost equal as the majority of patients present with advanced disease at diagnosis. Between 4 and 10% of pancreatic cancer cases have an apparent hereditary background, known as hereditary pancreatic cancer (HPC) and familial pancreatic cancer (FPC), when the genetic basis is unknown. Surveillance of high-risk individuals (HRI) from these families by imaging aims to detect PDAC at an early stage to improve prognosis. However, the genetic basis is unknown in the majority of HRIs, with only around 10–13% of families carrying known pathogenic germline mutations. The aim of this study was to assess an individual’s genetic cancer risk based on sex and personal and family history of cancer. The Best Linear Unbiased Prediction (BLUP) methodology was used to estimate an individual’s predicted risk of developing cancer during their lifetime. The model uses different demographic factors in order to estimate heritability. A reliable estimation of heritability for pancreatic cancer of 0.27 on the liability scale, and 0.07 at the observed data scale as obtained, which is different from zero, indicating a polygenic inheritance pattern of PDAC. BLUP was able to correctly discriminate PDAC cases from healthy individuals and those with other cancer types. Thus, providing an additional tool to assess PDAC risk HRI with an assumed genetic predisposition in the absence of known pathogenic germline mutations.

Genomic prediction model optimization for growth traits of olive flounder (Paralichthys olivaceus)

Genomic prediction (GP) has emerged an effective tool for addressing the many shortcomings of traditional selective breeding, thereby enhancing the selection process. In this study, we optimized GP methods using 5-fold cross-validation to estimate genome-estimated breeding values for the weight traits of olive flounder (Paralichthys olivaceus). To accomplish our goal, we determined the parentage of the target broodstock and the ability of 11 prediction models to predict the weight traits of 1.8-year-old olive flounders, which were genotyped using a 70 K single nucleotide polymorphism (SNP) array. Moreover, our optimization efforts toward the predictive ability of genomic best linear unbiased prediction (GBLUP), Bayesian B (BB), and random forest (RF) methods encompassed changes in various aspects such as fixed effects, SNP quantity, population size, and phenotypic data collected at different fish ages. Additionally, we assessed the predictive ability for the total length and body depth of fish using GBLUP, BB, and RF. Among the 11 prediction methods used in this study, the BB (0.675), Elastic Net (0.679), and RF (0.698) methods exhibited the highest predictive abilities, whereas the GBLUP (0.637) method demonstrated the lowest. Incorporating information regarding fish sex as a fixed effect substantially improved the predictive ability of GBLUP and BB. For mean models, utilizing 3000–5000 random SNP markers resulted in a higher predictive ability, similar to that obtained using 50,000 SNPs. Increasing the population size reduced the standard deviation of the predictive ability. Notably, phenotypic records from 1.8-year-old fish exhibited a significantly higher predictive ability than those from the other age groups. Furthermore, GBLUP, BB, and RF provided higher predictive abilities for length (0.655–0.852) and body depth (0.665–0.861). These findings may significantly shape future olive flounder genomic selection programs and offer valuable insights into GP in aquaculture.

Accurate and robust linear representation for containership stability conditions with ballast water

Stowage planning involves optimizing the placement of cargo on a ship while ensuring the ship's stability conditions are met. This optimization problem is typically formulated as a mixed-integer linear programming problem. However, a challenge arises in representing stability conditions as linear constraints since these conditions have non-linear relationships to the decision variables. Although there are methods for linearizing these stability conditions, they lack a systematic modeling approach and numerical verification of accuracy and reliability. In particular, the complex and diverse nature of ballast water contributes to significant non-linearity, posing a considerable challenge in developing an accurate linear approximation. This study proposes linear prediction methods that incorporate ballast water to address major stability conditions such as trim, drafts, shear force, bending moment, torsion, and transverse metacentric height. We introduce a comprehensive training and testing methodology for prediction, and validate the proposed method by comparing it with true values on two ships of different capacities, demonstrating its accuracy and scalability.

Effect of genetic and sex effect on genomic prediction for horn development in Nellore cattle

This study aimed to evaluate the influence of phenotypic classification of horn development, animal sex effect, and non-autosomal SNP (single nucleotide polymorphism) markers on the genetic parameters and genomic prediction ability for horn development in Nellore cattle using the single-step genomic best linear unbiased prediction method. The polled phenotype was evaluated in two (presence and absence of horns), three (scurs and polled offspring from a horned parent, and the polled and horned animals), and four (absence of horn, polled born to a parent with horn, scurs, and presence of horn) phenotypic categories. A total of 12 statistical models were evaluated. The variance components were estimated using the THRGIBBS1F90 software, and a threshold animal model was used for genomic prediction analyses with the single-step genomic BLUP (ssGBLUP) procedure. Accuracy, bias, and dispersion parameters were evaluated based on the linear regression (LR) method. The highest heritability (0.84) was obtained when the polled character was evaluated as a binary trait. The lowest heritability estimates (0.44 to 0.45) for horn development were obtained when the phenotype was classified into three categories. For the same horn development classification method, the heritability estimates were similar regardless of the genomic evaluated models and fixed effects included in the model. For models considering four and three phenotypic categories for horn development, the inclusion of the sex effect as a fixed effect within the CG did not improve the accuracy, bias, and dispersion of genomic predictions for horn development. Analyzing the trait with binary expression, the highest prediction accuracy was observed when the effect of sex was not included in the CG and without the SNPs in the sex chromosomes. These models displayed the highest dispersion, pointing out the low robustness of genomic prediction. In addition, models that use less than four categories to classify the horn development phenotype, with no discrimination between polled and homozygous polled displayed lower prediction ability. The inclusion of non-autosomal SNPs in the analyses for the models considering four phenotypic categories leads to an improvement in prediction accuracy in 5,26 %, bias, and dispersion reduction, 37 % and 4,55 %, respectively, compared with models that only considered autosomal SNPs. The selection using genomic information for the polled trait is feasible, and it is an alternative to obtaining polled Nellore animals. The binary coding of horn development is an unsuitable oversimplification of polled phenotype, and probably, the genetic background of horn development is more complex than previously proposed. The most adequate prediction model to evaluate the horn development in Nellore cattle was considering four phenotypic categories and including non-autosomal SNP in the analyses for genomic prediction purposes of naturally genetically polled animals. Genetic dehorning can be adopted on a large scale as a low-cost and non-invasive approach to increase the frequency of hornless animals using genomic information and mating strategies.

Heritability and predictive ability for the heterobothriosis resistance and growth performance in the tiger pufferfish Takifugu rubripes fed standard or low fishmeal diets

Heterobothriosis resistance and high growth performance are major concerns in the tiger pufferfish (Takifugu rubripes) farming. Our previous small-scale study suggested the feasibility of genomic selection (GS) for these traits but also identified an undesired genetic correlation between them, which could hamper simultaneous genetic improvement. Here, we sought to validate these initial findings through larger samples and crosses and also explore the potential of GS for the individuals fed a normal fishmeal diet and a low fishmeal (LFM) diet. We produced three populations: one was fed a normal diet (PopFM: 1100 individuals) and two were fed an LFM diet (PopLFM1: 993 individuals; PopLFM2: 1017 individuals); all three populations were artificially infected with Heterobothrium okamotoi, a monogenean parasite causing heterobothriosis. We recorded standard lengths of the fish after artificial infection (SLEAI) and the number of parasites on the gill cavity wall (HC) and genotyped genome-wide single nucleotide polymorphisms (SNPs) using genotyping by random amplicon sequencing, direct (GRAS-Di) technology for each sample: PopFM, 12 K SNPs; PopLFM1, 19 K SNPs; PopLFM2, 21 K SNPs. Heritability and prediction ability for each trait were estimated for each population using genomic best linear unbiased prediction (GBLUP), Bayes C, and Bayesian ridge regression methods. SNP effects on each trait were estimated by Bayes C, Bayesian ridge regression, and genome-wide association analyses (GWAS) using the same data sets. We observed moderate to high levels of heritability for HC (0.16–0.57) and SLEAI (0.50–0.77), with predictive ability of 0.25–0.55 for HC and of 0.51–0.73 for SLEAI. These values were slightly larger in LFM diet groups. As reported previously, a weak undesired genetic correlation was observed between the traits, and the correlation was more pronounced in the LFM groups. In conclusion, our results indicate that genetic gain in growth and parasite resistance traits can be expected for the tiger pufferfish through GS, especially for individuals reared on an LFM diet. However, close attention should be paid to the extent of the undesirable genetic correlation between the two traits that may be amplified in the populations fed an LFM diet.

Selection of informative markers using machine learning approaches and genome-wide association studies to improve genomic prediction in Hanwoo cattle: a simulation study

The present study deploys a comparison of Gradient Boosting Machine (GBM), Extreme Gradient Boosting (XGBoost), and Genome Wide Association Studies (GWAS) in selecting optimum subsets of single nucleotide polymorphisms (SNPs) to be used in genomic prediction in cattle. The data simulation was carried out for 6,000 animals and 47,841 SNPs which include 43,633 polygenic markers and 4208 quantitative trait loci (QTL) using QMSim software. The genomic prediction was conducted with the best linear unbiased prediction (BLUP) method using the BLUPF90 program. The accuracy of prediction was computed in three different types, namely, Empirical all SNPs, Empirical QTL, and theoretical accuracy, Accuracy PEV . Among the three models, the highest Empirical all SNPs accuracy 0.79 was derived for GBM followed by 0.77 for XGBoost and 0.76 for GWAS. The Empirical QTL accuracy was almost equal for all three models. The maximum theoretical accuracy was obtained for GWAS which was 0.93, whereas GBM and XGBoost obtained 0.86 and 0.85 accuracy levels respectively. Our results indicate that all three models comparably performed in genomic predictions; however, subsets selected by both GBM and GWAS reported higher prediction accuracies compared to the whole SNP set. The number of QTL selected as a proportion of the total number of SNPs was superior in GWAS. These observations can be validated using real data which could enable further optimization of the analysis process.