Teses e Dissertações
URI permanente desta comunidadehttps://thoth.dti.ufv.br/handle/123456789/2
Navegar
1 resultados
Resultados da Pesquisa
Item Computational intelligence and statistical learning applied to Coffea canephora(Universidade Federal de Viçosa, 2022-05-02) Sousa, Ithalo Coelho de; Nascimento, Moysés; Sant’anna, Isabela de Castro; Cruz, Cosme Damião; Azevedo, Camila Ferreira; Nascimento, Ana Carolina CampanaGenomic prediction in Coffee breeding has shown good potential in predictive ability (PA), genetic gains and reduction of the selection cycle time. Many methodologies are used to predict the genetic merit, but some of them require priori assumptions that may increase the complexity of the model. Artificial neural network (ANN) has advantage to not require priori assumptions about the relationships between inputs and the output allowing great flexibility to handle different types of complex non-additive effects, such as dominance and epistasis. Despite this advantage, the biological interpretability of ANNs is still limited. In the elaboration of this research project, two basic questions were formulated. The first question, is it possible to estimate genetic parameters using ANNs? The second, is it possible to reduce the panel marker size with no penalty in predictive ability? For this, the analyzes were divided into two articles. In the first article, the aim was to estimate the heritability and markers effects for two traits in Coffea canephora using an additive-dominance architecture ANN and to compare it with genomic best linear unbiased prediction (GBLUP). In the second article, the aim was to evaluate the trade-off between density marker panels size and the PA for eight agronomic traits in Coffea canephora using machine learning (bagging and random forest) algorithms and comparing them with BLASSO (Bayesian Least Absolute Shrinkage and Selection Operator) method. For both article, the data set consisted of 165 genotypes of Coffea canephora genotyped for 14,387 snp markers, after quality control analysis. For the first article the phenotypic data used was rust (Rus) and yield (Y). For the second article the phenotypic data is composed by vegetative vigor (Vig), rust (Rus) and cercosporiose incidence (Cer), fruit maturation time (Mat), fruit size (FS), plant height (PH), diameter of the canopy projection (DC) and yield (Y). In the first article we reduced the dimensionality of the data using bagging decision tree and then run 64,000 neural networks for each trait selecting the best architecture based on predictive ability for estimating the heritability, obtained results compatibles with those in literature. In the second article, 12 different density market panels were used to evaluate the effect of dimensionality reduction in PA. The common trend observed in the analysis shows an increase of the PA as the number of markers decreases, having a peak in most of the cases when used between 500 and 1,000 markers. In general, the worst results were obtained when used the full SNP panel density. The results of the second article indicate that the reduction of the number of markers can improve the selection of individuals at a lower cost. Computational Intelligence methods prove to be powerful tools for predicting genetic values, to estimate genetic parameters and to select markers. Keywords: GBLUP. BLASSO. BAGGING. Random forest. GEBV. Marker effect. Heritability.