Leonardo Ornella

Genomic prediction in CIMMYT maize and wheat breeding programs.

Genomic selection (GS) has been implemented in animal and plant species, and is regarded as a useful tool for accelerating genetic gains. Varying levels of genomic prediction accuracy have been obtained in plants, depending on the prediction problem assessed and on several other factors, such as trait heritability, the relationship between the individuals to be predicted and those used to train the models for prediction, number of markers, sample size and genotype × environment interaction (GE). The main objective of this article is to describe the results of genomic prediction in International Maize and Wheat Improvement Center’s (CIMMYT’s) maize and wheat breeding programs, from the initial assessment of the predictive ability of different models using pedigree and marker information to the present, when methods for implementing GS in practical global maize and wheat breeding programs are being studied and investigated. Results show that pedigree (population structure) accounts for a sizeable proportion of the prediction accuracy when a global population is the prediction problem to be assessed. However, when the prediction uses unrelated populations to train the prediction equations, prediction accuracy becomes negligible. When genomic prediction includes modeling GE, an increase in prediction accuracy can be achieved by borrowing information from correlated environments. Several questions on how to incorporate GS into CIMMYT’s maize and wheat programs remain unanswered and subject to further investigation, for example, prediction within and between related bi-parental crosses. Further research on the quantification of breeding value components for GS in plant breeding populations is required.

Reference genes for real-time PCR quantification of microRNAs and messenger RNAs in rat models of hepatotoxicity.

Hepatotoxicity is associated with major changes in liver gene expression induced by xenobiotic exposure. Understanding the underlying mechanisms is critical for its clinical diagnosis and treatment. MicroRNAs are key regulators of gene expression that control mRNA stability and translation, during normal development and pathology. The canonical technique to measure gene transcript levels is Real-Time qPCR, which has been successfully modified to determine the levels of microRNAs as well. However, in order to obtain accurate data in a multi-step method like RT-qPCR, the normalization with endogenous, stably expressed reference genes is mandatory. Since the expression stability of candidate reference genes varies greatly depending on experimental factors, the aim of our study was to identify a combination of genes for optimal normalization of microRNA and mRNA qPCR expression data in experimental models of acute hepatotoxicity. Rats were treated with four traditional hepatotoxins: acetaminophen, carbon tetrachloride, D-galactosamine and thioacetamide, and the liver expression levels of two groups of candidate reference genes, one for microRNA and the other for mRNA normalization, were determined by RT-qPCR in compliance with the MIQE guidelines. In the present study, we report that traditional reference genes such as U6 spliceosomal RNA, Beta Actin and Glyceraldehyde-3P-dehydrogenase altered their expression in response to classic hepatotoxins and therefore cannot be used as reference genes in hepatotoxicity studies. Stability rankings of candidate reference genes, considering only those that did not alter their expression, were determined using geNorm, NormFinder and BestKeeper software packages. The potential candidates whose measurements were stable were further tested in different combinations to find the optimal set of reference genes that accurately determine mRNA and miRNA levels. Finally, the combination of MicroRNA-16/5S Ribosomal RNA and Beta 2 Microglobulin/18S Ribosomal RNA were validated as optimal reference genes for microRNA and mRNA quantification, respectively, in rat models of acute hepatotoxicity.

Genomic prediction of genetic values for resistance to wheat rusts

Durable resistance to the rust diseases of wheat (Triticum aestivum L.) can be achieved by developing lines that have race‐nonspecific adult plant resistance conferred by multiple minor slow‐rusting genes. Genomic selection (GS) is a promising tool for accumulating favorable alleles of slow‐rusting genes. In this study, five CIMMYT wheat populations evaluated for resistance were used to predict resistance to stem rust (Puccinia graminis) and yellow rust (Puccinia striiformis) using Bayesian least absolute shrinkage and selection operator (LASSO) (BL), ridge regression (RR), and support vector regression with linear or radial basis function kernel models. All parents and populations were genotyped using 1400 Diversity Arrays Technology markers and different prediction problems were assessed. Results show that prediction ability for yellow rust was lower than for stem rust, probably due to differences in the conditions of infection of both diseases. For within population and environment, the correlation between predicted and observed values (Pearsons correlation [ρ]) was greater than 0.50 in 90% of the evaluations whereas for yellow rust, ρ ranged from 0.0637 to 0.6253. The BL and RR models have similar prediction ability, with a slight superiority of the BL confirming reports about the additive nature of rust resistance. When making predictions between environments and/or between populations, including information from another environment or environments or another population or populations improved prediction.

Genomic-enabled prediction with classification algorithms.

Pearson’s correlation coefficient (ρ) is the most commonly reported metric of the success of prediction in genomic selection (GS). However, in real breeding ρ may not be very useful for assessing the quality of the regression in the tails of the distribution, where individuals are chosen for selection. This research used 14 maize and 16 wheat data sets with different trait–environment combinations. Six different models were evaluated by means of a cross-validation scheme (50 random partitions each, with 90% of the individuals in the training set and 10% in the testing set). The predictive accuracy of these algorithms for selecting individuals belonging to the best α=10, 15, 20, 25, 30, 35, 40% of the distribution was estimated using Cohen’s kappa coefficient (κ) and an ad hoc measure, which we call relative efficiency (RE), which indicates the expected genetic gain due to selection when individuals are selected based on GS exclusively. We put special emphasis on the analysis for α=15%, because it is a percentile commonly used in plant breeding programmes (for example, at CIMMYT). We also used ρ as a criterion for overall success. The algorithms used were: Bayesian LASSO (BL), Ridge Regression (RR), Reproducing Kernel Hilbert Spaces (RHKS), Random Forest Regression (RFR), and Support Vector Regression (SVR) with linear (lin) and Gaussian kernels (rbf). The performance of regression methods for selecting the best individuals was compared with that of three supervised classification algorithms: Random Forest Classification (RFC) and Support Vector Classification (SVC) with linear (lin) and Gaussian (rbf) kernels. Classification methods were evaluated using the same cross-validation scheme but with the response vector of the original training sets dichotomised using a given threshold. For α=15%, SVC-lin presented the highest κ coefficients in 13 of the 14 maize data sets, with best values ranging from 0.131 to 0.722 (statistically significant in 9 data sets) and the best RE in the same 13 data sets, with values ranging from 0.393 to 0.948 (statistically significant in 12 data sets). RR produced the best mean for both κ and RE in one data set (0.148 and 0.381, respectively). Regarding the wheat data sets, SVC-lin presented the best κ in 12 of the 16 data sets, with outcomes ranging from 0.280 to 0.580 (statistically significant in 4 data sets) and the best RE in 9 data sets ranging from 0.484 to 0.821 (statistically significant in 5 data sets). SVC-rbf (0.235), RR (0.265) and RHKS (0.422) gave the best κ in one data set each, while RHKS and BL tied for the last one (0.234). Finally, BL presented the best RE in two data sets (0.738 and 0.750), RFR (0.636) and SVC-rbf (0.617) in one and RHKS in the remaining three (0.502, 0.458 and 0.586). The difference between the performance of SVC-lin and that of the rest of the models was not so pronounced at higher percentiles of the distribution. The behaviour of regression and classification algorithms varied markedly when selection was done at different thresholds, that is, κ and RE for each algorithm depended strongly on the selection percentile. Based on the results, we propose classification method as a promising alternative for GS in plant breeding.

Multiclass classification of microarray data samples with a reduced number of genes

BackgroundMulticlass classification of microarray data samples with a reduced number of genes is a rich and challenging problem in Bioinformatics research. The problem gets harder as the number of classes is increased. In addition, the performance of most classifiers is tightly linked to the effectiveness of mandatory gene selection methods. Critical to gene selection is the availability of estimates about the maximum number of genes that can be handled by any classification algorithm. Lack of such estimates may lead to either computationally demanding explorations of a search space with thousands of dimensions or classification models based on gene sets of unrestricted size. In the former case, unbiased but possibly overfitted classification models may arise. In the latter case, biased classification models unable to support statistically significant findings may be obtained.ResultsA novel bound on the maximum number of genes that can be handled by binary classifiers in binary mediated multiclass classification algorithms of microarray data samples is presented. The bound suggests that high-dimensional binary output domains might favor the existence of accurate and sparse binary mediated multiclass classifiers for microarray data samples.ConclusionsA comprehensive experimental work shows that the bound is indeed useful to induce accurate and sparse multiclass classifiers for microarray data samples.

Applications of Machine Learning in Breeding for Stress Tolerance in Maize

Corn is one of the world’s most important cereals and a major source of calories for humanity, along with rice and wheat. Climate change and the use of marginal land for crop production require the development of genotypes adapted to stressful environments, particularly drought tolerant plants. Among the new technologies currently available for accelerate the releasing of new genotypes there is an emerging discipline called Machine Learning (ML). A primary goal of ML algorithms is to automatically learn to recognize complex patterns and make intelligent decisions based on data. This work reviews several strategic applications of ML in maize breeding. Quantitative trait loci mapping, heterotic group assignment and the popular genome-wide selection are some of the key areas currently addressed by the literature. Results are encouraging and propose ML algorithms as a valuable alternative to traditional statistical techniques applied in maize, even the more recently introduced linear mixed models.

Applications of Machine Learning Methods to Genomic Selection in Breeding Wheat for Rust Resistance

Genomic‐enabled prediction Machine learning Wheat breeding Rust resistance