Superiority of artificial neural networks for a genetic classification procedure

Machine Learning-Assisted Approaches in Modernized Plant Breeding Programs

In the face of a growing global population, plant breeding is being used as a sustainable tool for increasing food security. A wide range of high-throughput omics technologies have been developed and used in plant breeding to accelerate crop improvement and develop new varieties with higher yield performance and greater resilience to climate changes, pests, and diseases. With the use of these new advanced technologies, large amounts of data have been generated on the genetic architecture of plants, which can be exploited for manipulating the key characteristics of plants that are important for crop improvement. Therefore, plant breeders have relied on high-performance computing, bioinformatics tools, and artificial intelligence (AI), such as machine-learning (ML) methods, to efficiently analyze this vast amount of complex data. The use of bigdata coupled with ML in plant breeding has the potential to revolutionize the field and increase food security. In this review, some of the challenges of this method along with some of the opportunities it can create will be discussed. In particular, we provide information about the basis of bigdata, AI, ML, and their related sub-groups. In addition, the bases and functions of some learning algorithms that are commonly used in plant breeding, three common data integration strategies for the better integration of different breeding datasets using appropriate learning algorithms, and future prospects for the application of novel algorithms in plant breeding will be discussed. The use of ML algorithms in plant breeding will equip breeders with efficient and effective tools to accelerate the development of new plant varieties and improve the efficiency of the breeding process, which are important for tackling some of the challenges facing agriculture in the era of climate change.

Genomic prediction through machine learning and neural networks for traits with epistasis

•

Performance of machine learning and neural netowrks in Genomic analysis.

•

Heritability and QTL number impacts on performance machine learning methods.

•

Machine learning models in genomic analyses.

•

Neural networks can present better performance for complex quantitative traits.

Genomic wide selection (GWS) is one contributions of molecular genetics to breeding. Machine learning (ML) and artificial neural networks (ANN) methods are non-parameterized and can develop more accurate and parsimonious models for GWS analysis. Multivariate Adaptive Regression Splines (MARS) is considered one of the most flexible ML methods, automatically modeling nonlinearities and interactions of the predictor variables. This study aimed to evaluate and compare methods based on ANN, ML, including MARS, and G-BLUP through GWS. An F2 population formed by 1000 individuals and genotyped for 4010 SNP markers and twelve traits from a model considering epistatic effect, with QTL numbers ranging from eight to 480 and heritability (h2) of 0.3, 0.5 or 0.8 were simulated. Variation in heritability and number of QTL impacts the performance of methods. About quantitative traits (40, 80, 120, 240, and 480 QTLs) was observed highest R2 to Radial Base Network (RBF) and G-BLUP, followed by Random Forest (RF), Bagging (BA), and Boosting (BO). RF and BA also showed better results for traits to h2 of 0.3 with R2 values 16.51% and 16.30%, respectively, while MARS methods showed better results for oligogenic traits with R2 values ranging from 39,12 % to 43,20 % in h2 of 0.5 and from 59.92% to 78,56% in h2 of 0.8. Non-additive MARS methods also showed high R2 for traits with high heritability and 240 QTLs or more. ANN and ML methods are powerful tools to predict genetic values in traits with epistatic effect, for different degrees of heritability and QTL numbers.

Prediction of the importance of auxiliary traits using computational intelligence and machine learning: A simulation study

The present study evaluated the importance of auxiliary traits of a principal trait based on phenotypic information and previously known genetic structure using computational intelligence and machine learning to develop predictive tools for plant breeding. Data of an F₂ population represented by 500 individuals, obtained from a cross between contrasting homozygous parents, were simulated. Phenotypic traits were simulated based on previously established means and heritability estimates (30%, 50%, and 80%); traits were distributed in a genome with 10 linkage groups, considering two alleles per marker. Four different scenarios were considered. For the principal trait, heritability was 50%, and 40 control loci were distributed in five linkage groups. Another phenotypic control trait with the same complexity as the principal trait but without any genetic relationship with it and without pleiotropy or a factorial link between the control loci for both traits was simulated. These traits shared a large number of control loci with the principal trait, but could be distinguished by the differential action of the environment on them, as reflected in heritability estimates (30%, 50%, and 80%). The coefficient of determination were considered to evaluate the proposed methodologies. Multiple regression, computational intelligence, and machine learning were used to predict the importance of the tested traits. Computational intelligence and machine learning were superior in extracting nonlinear information from model inputs and quantifying the relative contributions of phenotypic traits. The R² values ranged from 44.0% - 83.0% and 79.0% - 94.0%, for computational intelligence and machine learning, respectively. In conclusion, the relative contributions of auxiliary traits in different scenarios in plant breeding programs can be efficiently predicted using computational intelligence and machine learning.

Machine learning and statistics to qualify environments through multi-traits in Coffea arabica

Several factors such as genotype, environment, and post-harvest processing can affect the responses of important traits in the coffee production chain. Determining the influence of these factors is of great relevance, as they can be indicators of the characteristics of the coffee produced. The most efficient models choice to be applied should take into account the variety of information and the particularities of each biological material. This study was developed to evaluate statistical and machine learning models that would better discriminate environments through multi-traits of coffee genotypes and identify the main agronomic and beverage quality traits responsible for the variation of the environments. For that, 31 morpho-agronomic and post-harvest traits were evaluated, from field experiments installed in three municipalities in the Matas de Minas region, in the State of Minas Gerais, Brazil. Two types of post-harvest processing were evaluated: natural and pulped. The apparent error rate was estimated for each method. The Multilayer Perceptron and Radial Basis Function networks were able to discriminate the coffee samples in multi-environment more efficiently than the other methods, identifying differences in multi-traits responses according to the production sites and type of post-harvest processing. The local factors did not present specific traits that favored the severity of diseases and differentiated vegetative vigor. Sensory traits acidity and fragrance/aroma score also made little contribution to the discrimination process, indicating that acidity and fragrance/aroma are characteristic of coffee produced and all coffee samples evaluated are of the special type in the Mata of Minas region. The main traits responsible for the differentiation of production sites are plant height, fruit size, and bean production. The sensory trait "Body" is the main one to discriminate the form of post-harvest processing.

Genome-enabled prediction using probabilistic neural network classifiers

BACKGROUND

Multi-layer perceptron (MLP) and radial basis function neural networks (RBFNN) have been shown to be effective in genome-enabled prediction. Here, we evaluated and compared the classification performance of an MLP classifier versus that of a probabilistic neural network (PNN), to predict the probability of membership of one individual in a phenotypic class of interest, using genomic and phenotypic data as input variables. We used 16 maize and 17 wheat genomic and phenotypic datasets with different trait-environment combinations (sample sizes ranged from 290 to 300 individuals) with 1.4 k and 55 k SNP chips. Classifiers were tested using continuous traits that were categorized into three classes (upper, middle and lower) based on the empirical distribution of each trait, constructed on the basis of two percentiles (15-85 % and 30-70 %). We focused on the 15 and 30 % percentiles for the upper and lower classes for selecting the best individuals, as commonly done in genomic selection. Wheat datasets were also used with two classes. The criteria for assessing the predictive accuracy of the two classifiers were the area under the receiver operating characteristic curve (AUC) and the area under the precision-recall curve (AUCpr). Parameters of both classifiers were estimated by optimizing the AUC for a specific class of interest.

RESULTS

The AUC and AUCpr criteria provided enough evidence to conclude that PNN was more accurate than MLP for assigning maize and wheat lines to the correct upper, middle or lower class for the complex traits analyzed. Results for the wheat datasets with continuous traits split into two and three classes showed that the performance of PNN with three classes was higher than with two classes when classifying individuals into the upper and lower (15 or 30 %) categories.

CONCLUSIONS

The PNN classifier outperformed the MLP classifier in all 33 (maize and wheat) datasets when using AUC and AUCpr for selecting individuals of a specific class. Use of PNN with Gaussian radial basis functions seems promising in genomic selection for identifying the best individuals. Categorizing continuous traits into three classes generally provided better classification than when using two classes, because classification accuracy improved when classes were balanced.