RÉSUMÉ
Introduction: Because Genomic selection (GS) is a predictive methodology, it needs to guarantee high-prediction accuracies for practical implementations. However, since many factors affect the prediction performance of this methodology, its practical implementation still needs to be improved in many breeding programs. For this reason, many strategies have been explored to improve the prediction performance of this methodology. Methods: When environmental covariates are incorporated as inputs in the genomic prediction models, this information only sometimes helps increase prediction performance. For this reason, this investigation explores the use of feature engineering on the environmental covariates to enhance the prediction performance of genomic prediction models. Results and discussion: We found that across data sets, feature engineering helps reduce prediction error regarding only the inclusion of the environmental covariates without feature engineering by 761.625% across predictors. These results are very promising regarding the potential of feature engineering to enhance prediction accuracy. However, since a significant gain in prediction accuracy was observed in only some data sets, further research is required to guarantee a robust feature engineering strategy to incorporate the environmental covariates.
RÉSUMÉ
OBJECTIVE: Neurosurgery has remained relatively homogeneous in terms of racial and gender diversity, trailing behind national demographics. Less than 5% of practicing neurosurgeons in the United States identify as Black/African American (AA). Research and academic productivity are highly emphasized within the field and are crucial for career advancement at academic institutions. They also serve as important avenues for mentorship and recruitment of diverse trainees and medical students. This study aimed to summarize the academic accomplishments of AA neurosurgeons by assessing publication quantity, h-index, and federal grant funding. METHODS: One hundred thirteen neurosurgery residency training programs accredited by the Accreditation Council for Graduate Medical Education in 2022 were included in this study. The American Society of Black Neurosurgeons registry was reviewed to analyze the academic metrics of self-identified Black or AA academic neurosurgeons. Data on the academic rank, leadership position, publication quantity, h-index, and race of neurosurgical faculty in the US were obtained from publicly available information and program websites. RESULTS: Fifty-five AA and 1393 non-AA neurosurgeons were identified. Sixty percent of AA neurosurgeons were fewer than 10 years out from residency training, compared to 37.4% of non-AA neurosurgeons (p = 0.001). AA neurosurgeons had a median 32 (IQR 9, 85) publications compared to 52 (IQR 22, 122) for non-AA neurosurgeons (p = 0.019). AA neurosurgeons had a median h-index of 12 (IQR 5, 24) compared to 16 (IQR 9, 31) for non-AA colleagues (p = 0.02). Following stratification by academic rank, these trends did not persist. No statistically significant differences in the median amounts of awarded National Institutes of Health funding (p = 0.194) or level of professorship attained (p = 0.07) were observed between the two cohorts. CONCLUSIONS: Racial disparities between AA and non-AA neurosurgeons exist in publication quantity and h-index overall but not when these groups are stratified by academic rank. Given that AA neurosurgeons comprise more junior faculty, it is expected that their academic accomplishments will increase as more enter academic practice and current neurosurgeons advance into more senior positions.
Sujet(s)
, Neurochirurgiens , Neurochirurgie , Humains , États-Unis , /statistiques et données numériques , Neurochirurgie/enseignement et éducation , Internat et résidence , Mâle , Femelle , Corps enseignant et administratif en médecine/statistiques et données numériques , Réussite universitaireRÉSUMÉ
The role of anti-Müllerian hormone (AMH), a potential marker of the hypothalamic-pituitary-ovarian axis, is not well established in adolescent females. Most studies use secondary sexual characteristics or chronological age as predictors for AMH. Skeletal maturity, an indicator of bone development, has not been examined to predict AMH. This study sought to examine patterns of change in AMH in relation to skeletal maturity. Demographics, anthropometry, hand-wrist radiographs, and cardiometabolic risk factors from 88 females (212 observations), between the ages of 8 to 18 years from the Fels Longitudinal Study were used in this study. AMH was analyzed using ELISA from stored frozen serum samples. Generalized linear mixed effect modeling was used. In the stepwise regression models, log-transformed AMH (AMHlog) was regressed on relative skeletal age as the skeletal maturity indicator (calculated as chronological age minus skeletal age) and adjusted for chronological age, adiposity, and cardiometabolic risk factors. Skeletal maturity significantly predicted lower AMHlog (ß= -0.073, SE=0.032, p=0.023). Glucose was significantly associated with decreases in AMHlog (ß= -0.008, SE=0.004, p=0.044). Chronological age modeled as a cubic function was not significant. AMH and skeletal maturity may provide correlated information on growth and pubertal status in adolescent females.
RÉSUMÉ
Introduction: Genomic selection (GS) has gained global importance due to its potential to accelerate genetic progress and improve the efficiency of breeding programs. Objectives of the research: In this research we proposed a method to improve the prediction accuracy of tested lines in new (untested) environments. Method-1: The new method trained the model with a modified response variable (a difference of response variables) that decreases the lack of a non-stationary distribution between the training and testing and improved the prediction accuracy. Comparing new and conventional method: We compared the prediction accuracy of the conventional genomic best linear unbiased prediction (GBLUP) model (M1) including (or not) genotype × environment interaction (GE) (M1_GE; M1_NO_GE) versus the proposed method (M2) on several data sets. Results and discussion: The gain in prediction accuracy of M2, versus M1_GE, M1_NO_GE in terms of Pearson´s correlation was of at least 4.3%, while in terms of percentage of top-yielding lines captured when was selected the 10% (Best10) and 20% (Best20) of lines was at least of 19.5%, while in terms of Normalized Root Mean Squared Error (NRMSE) was of at least of 42.29%.
RÉSUMÉ
Phosphate ester hydrolysis is an important reaction that plays a major role in both enzymatic and non-enzymatic processes, including DNA and pesticide breaking. Although it is a widely studied reaction, the precise mechanistic details, especially for copper complexes, remain under discussion. To contribute to the debate, we present the catalyzed hydrolysis of phosphomono-, di- and tri-esters mediated by the [Cu(II)(1,10-phenanthroline)] complex. The reaction coordinates for several substrates were explored through the metadynamics formalism. Thus, we found that for mono- and di-substituted ester phosphates a concerted mechanism is observed, where a coordinated hydroxyl group attacks the phosphorus atom at the same side as the leaving group, along with a proton transfer. In contrast, tri-substituted phosphate remains coordinated with the metal, and the nucleophile acts independently following an addition-elimination process. That is, the metallic complex achieves a specific nucleophile-phosphate interaction that produces a concerted transition state in the phosphoester hydrolysis process.
RÉSUMÉ
Genomic selection (GS) is revolutionizing plant breeding. However, because it is a predictive methodology, a basic understanding of statistical machine-learning methods is necessary for its successful implementation. This methodology uses a reference population that contains both the phenotypic and genotypic information of genotypes to train a statistical machine-learning method. After optimization, this method is used to make predictions of candidate lines for which only genotypic information is available. However, due to a lack of time and appropriate training, it is difficult for breeders and scientists of related fields to learn all the fundamentals of prediction algorithms. With smart or highly automated software, it is possible for these professionals to appropriately implement any state-of-the-art statistical machine-learning method for its collected data without the need for an exhaustive understanding of statistical machine-learning methods and programing. For this reason, we introduce state-of-the-art statistical machine-learning methods using the Sparse Kernel Methods (SKM) R library, with complete guidelines on how to implement seven statistical machine-learning methods that are available in this library for genomic prediction (random forest, Bayesian models, support vector machine, gradient boosted machine, generalized linear models, partial least squares, feed-forward artificial neural networks). This guide includes details of the functions required to implement each of the methods, as well as others for easily implementing different tuning strategies, cross-validation strategies, and metrics to evaluate the prediction performance and different summary functions that compute it. A toy dataset illustrates how to implement statistical machine-learning methods and facilitate their use by professionals who do not possess a strong background in machine learning and programing.
Sujet(s)
Amélioration des plantes , Logiciel , Théorème de Bayes , Génomique/méthodes , Apprentissage machineRÉSUMÉ
While sparse testing methods have been proposed by researchers to improve the efficiency of genomic selection (GS) in breeding programs, there are several factors that can hinder this. In this research, we evaluated four methods (M1-M4) for sparse testing allocation of lines to environments under multi-environmental trails for genomic prediction of unobserved lines. The sparse testing methods described in this study are applied in a two-stage analysis to build the genomic training and testing sets in a strategy that allows each location or environment to evaluate only a subset of all genotypes rather than all of them. To ensure a valid implementation, the sparse testing methods presented here require BLUEs (or BLUPs) of the lines to be computed at the first stage using an appropriate experimental design and statistical analyses in each location (or environment). The evaluation of the four cultivar allocation methods to environments of the second stage was done with four data sets (two large and two small) under a multi-trait and uni-trait framework. We found that the multi-trait model produced better genomic prediction (GP) accuracy than the uni-trait model and that methods M3 and M4 were slightly better than methods M1 and M2 for the allocation of lines to environments. Some of the most important findings, however, were that even under a scenario where we used a training-testing relation of 15-85%, the prediction accuracy of the four methods barely decreased. This indicates that genomic sparse testing methods for data sets under these scenarios can save considerable operational and financial resources with only a small loss in precision, which can be shown in our cost-benefit analysis.
Sujet(s)
Modèles génétiques , Amélioration des plantes , Amélioration des plantes/méthodes , Génome végétal/génétique , Phénotype , Génomique , Produits agricoles/génétiqueRÉSUMÉ
Sparse testing is essential to increase the efficiency of the genomic selection methodology, as the same efficiency (in this case prediction power) can be obtained while using less genotypes evaluated in the fields. For this reason, it is important to evaluate the existing methods for performing the allocation of lines to environments. With this goal, four methods (M1-M4) to allocate lines to environments were evaluated under the context of a multi-trait genomic prediction problem: M1 denotes the allocation of a fraction (subset) of lines in all locations, M2 denotes the allocation of a fraction of lines with some shared lines in locations but not arranged based on the balanced incomplete block design (BIBD) principle, M3 denotes the random allocation of a subset of lines to locations, and M4 denotes the allocation of a subset of lines to locations using the BIBD principle. The evaluation was done using seven real multi-environment data sets common in plant breeding programs. We found that the best method was M4 and the worst was M1, while no important differences were found between M3 and M4. We concluded that M4 and M3 are efficient in the context of sparse testing for multi-trait prediction.
Sujet(s)
Génome végétal , Amélioration des plantes , Phénotype , Génotype , GénomiqueRÉSUMÉ
The genomic selection (GS) methodology proposed over 20 years ago by Meuwissen et al. (Genetics, 2001) has revolutionized plant breeding. A predictive methodology that trains statistical machine learning algorithms with phenotypic and genotypic data of a reference population and makes predictions for genotyped candidate lines, GS saves significant resources in the selection of candidate individuals. However, its practical implementation is still challenging when the plant breeder is interested in the prediction of future seasons or new locations and/or environments, which is called the "leave one environment out" issue. Furthermore, because the distributions of the training and testing set do not match, most statistical machine learning methods struggle to produce moderate or reasonable prediction accuracies. For this reason, the main objective of this study was to explore the use of the multi-trait partial least square (MT-PLS) regression methodology for this specific task, benchmarking its performance with the Bayesian Multi-trait Genomic Best Linear Unbiased Predictor (MT-GBLUP) method. The benchmarking process was performed with five actual data sets. We found that in all data sets the MT-PLS method outperformed the popular MT-GBLUP method by 349.8% (under predictor E + G), 484.4% (under predictor E + G + GE; where E denotes environments, G genotypes and GE the genotype by environment interaction) and 15.9% (under predictor G + GE) across traits. Our results provide empirical evidence of the power of the MT-PLS methodology for the prediction of future seasons or new environments. Furthermore, the comparison between single univariate-trait (UT) versus MT for GBLUP and PLS gave an increase in prediction accuracy of MT-GBLUP versus UT-GBLUP, but not for MT-PLS versus UT-PLS.
RÉSUMÉ
The adoption of machine learning frameworks in areas beyond computer science have been facilitated by the development of user-friendly software tools that do not require an advanced understanding of computer programming. In this paper, we present a new package (sparse kernel methods, SKM) software developed in R language for implementing six (generalized boosted machines, generalized linear models, support vector machines, random forest, Bayesian regression models and deep neural networks) of the most popular supervised machine learning algorithms with the optional use of sparse kernels. The SKM focuses on user simplicity, as it does not try to include all the available machine learning algorithms, but rather the most important aspects of these six algorithms in an easy-to-understand format. Another relevant contribution of this package is a function for the computation of seven different kernels. These are Linear, Polynomial, Sigmoid, Gaussian, Exponential, Arc-Cosine 1 and Arc-Cosine L (with L = 2, 3, ) and their sparse versions, which allow users to create kernel machines without modifying the statistical machine learning algorithm. It is important to point out that the main contribution of our package resides in the functionality for the computation of the sparse version of seven basic kernels, which is indispensable for reducing computational resources to implement kernel machine learning methods without a significant loss in prediction performance. Performance of the SKM is evaluated in a genome-based prediction framework using both a maize and wheat data set. As such, the use of this package is not restricted to genome prediction problems, and can be used in many different applications.
RÉSUMÉ
Genomic enabled prediction is playing a key role for the success of genomic selection (GS). However, according to the No Free Lunch Theorem, there is not a universal model that performs well for all data sets. Due to this, many statistical and machine learning models are available for genomic prediction. When multitrait data is available, models that are able to account for correlations between phenotypic traits are preferred, since these models help increase the prediction accuracy when the degree of correlation is moderate to large. For this reason, in this chapter we review multitrait models for genome-enabled prediction and we illustrate the power of this model with real examples. In addition, we provide details of the software (R code) available for its application to help users implement these models with its own data. The multitrait models were implemented under conventional Bayesian Ridge regression and best linear unbiased predictor, but also under a deep learning framework. The multitrait deep learning framework helps implement prediction models with mixed outcomes (continuous, binary, ordinal, and count, measured on different scales), which is not easy in conventional statistical models. The illustrative examples are very detailed in order to make the implementation of multitrait models in plant and animal breeding friendlier for breeders and scientists.
Sujet(s)
Génome , Génomique , Animaux , Théorème de Bayes , Génotype , Apprentissage machine , Modèles génétiques , PhénotypeRÉSUMÉ
In genomic selection choosing the statistical machine learning model is of paramount importance. In this paper, we present an application of a zero altered random forest model with two versions (ZAP_RF and ZAPC_RF) to deal with excess zeros in count response variables. The proposed model was compared with the conventional random forest (RF) model and with the conventional Generalized Poisson Ridge regression (GPR) using two real datasets, and we found that, in terms of prediction performance, the proposed zero inflated random forest model outperformed the conventional RF and GPR models.
Sujet(s)
Génome , Modèles statistiques , GénomiqueRÉSUMÉ
Genomic selection (GS) has the potential to revolutionize predictive plant breeding. A reference population is phenotyped and genotyped to train a statistical model that is used to perform genome-enabled predictions of new individuals that were only genotyped. In this vein, deep neural networks, are a type of machine learning model and have been widely adopted for use in GS studies, as they are not parametric methods, making them more adept at capturing nonlinear patterns. However, the training process for deep neural networks is very challenging due to the numerous hyper-parameters that need to be tuned, especially when imperfect tuning can result in biased predictions. In this paper we propose a simple method for calibrating (adjusting) the prediction of continuous response variables resulting from deep learning applications. We evaluated the proposed deep learning calibration method (DL_M2) using four crop breeding data sets and its performance was compared with the standard deep learning method (DL_M1), as well as the standard genomic Best Linear Unbiased Predictor (GBLUP). While the GBLUP was the most accurate model overall, the proposed deep learning calibration method (DL_M2) helped increase the genome-enabled prediction performance in all data sets when compared with the traditional DL method (DL_M1). Taken together, we provide evidence for extending the use of the proposed calibration method to evaluate its potential and consistency for predicting performance in the context of GS applied to plant breeding.
RÉSUMÉ
The molecular alumosilicates AlL{OSi(OtBu)2O}[OSi{(µ3-O)(MR2)2(µ-OtBu)}(OtBu)] (L = HC[CMeNAr]2-, where M = Al, R = Me (2), Et (3), and iBu (4) and M = Ga, R = Me (5)) were obtained from the reaction of AlL{OSi(OtBu)2(OH)}2 (1) with 1 or 2 equiv of the respective organometallic precursor. These compounds have a central bicyclic inorganic core formed by a six-membered AlSi2O3 alumosilicate ring with a Si-O-Si unit connected via a Si-O bond to a four-membered Al2O2 alumoxane ring. These compounds are formed even though 1 is specifically designed to yield 4R alumosilicate rings that would obey the Löweinstein's and Dempsey's rules about concatenation between silicon and aluminum tetrahedra in alumosilicates. We propose a mechanism for this rearrangement, based on the experimental evidence and density functional theory calculations, that involves a κ3µ2 coordination of a silicate unit to two AlMe2 groups, which weakens one Si-O bond and explains how aluminum atoms can cleave Si-O bonds. Furthermore, formation of the products experimentally confirms the theory that Al-O-Al groups can exist in alumosilicates if the oxygen atom belongs to an OH moiety.
RÉSUMÉ
PURPOSE: Results examining associations between metabolic syndrome (MetS) and depression, as well as on quality of life (QoL), are inconsistent. We aimed to determine whether individuals with MetS had decreased mental health-related QoL (MH-QoL) and higher frequency of depressive symptoms. METHODS: Data from 1,015 participants from the Fels Longitudinal Study were analyzed (mean age ± SD: 49.6 ± 18.7 years, 29.3% MetS, 51% females). MetS was determined using American Heart Association/National Heart, Lung, and Blood Institute criteria. Depressive symptoms (yes vs. no) were assessed with The Patient Health Questionnaire-9 (PHQ-9). MH-QoL (low (≤ 42) vs. high) was assessed with The Medical Outcomes 36-Item Short Form Survey (SF-36). Sex- and age-stratified mixed effects logistic regressions were used to examine the longitudinal relationship between MetS and MH-QoL while adjusting for covariates such as age, smoking status, and drinking status. RESULTS: In cross-sectional analysis, MetS was significantly associated with elevated depressive symptoms in women (OR 2.14, 95% CI 1.22-3.78, p < 0.01), but not in men. In the longitudinal analysis, MetS was observed to have a protective effect among men in the older age group as it approached significance (OR 0.34, 95% CI 0.11-1.05, p = 0.06). CONCLUSION: MetS was adversely associated with depressive symptoms and poor MH-QoL. Our cross-sectional results suggest that depressive symptoms are higher among women with MetS. Interestingly, our longitudinal results suggest that MH-QoL in men with MetS may improve with age.