Navegando por Autor "Silva, Gabi Nunes"

Agora exibindo 1 - 3 de 3

Artificial neural networks compared with Bayesian generalized linear regression for leaf rust resistance prediction in Arabica coffee
(Empresa Brasileira de Pesquisa Agropecuária - Embrapa, 2017-03) Silva, Gabi Nunes; Nascimento, Moysés; Sant’Anna, Isabela de Castro; Cruz, Cosme Damião; Caixeta, Eveline Teixeira; Carneiro, Pedro Crescêncio Souza; Rosado, Renato Domiciano Silva; Pestana, Kátia Nogueira; Almeida, Dênia Pires de; Oliveira, Marciane da Silva
The objective of this work was to evaluate the use of artificial neural networks in comparison with Bayesian generalized linear regression to predict leaf rust resistance in Arabica coffee (Coffea arabica). This study used 245 individuals of a F 2 population derived from the self-fertilization of the F 1 H511-1 hybrid, resulting from a crossing between the susceptible cultivar Catuaí Amarelo IAC 64 (UFV 2148-57) and the resistant parent Híbrido de Timor (UFV 443-03). The 245 individuals were genotyped with 137 markers. Artificial neural networks and Bayesian generalized linear regression analyses were performed. The artificial neural networks were able to identify four important markers belonging to linkage groups that have been recently mapped, while the Bayesian generalized model identified only two markers belonging to these groups. Lower prediction error rates (1.60%) were observed for predicting leaf rust resistance in Arabica coffee when artificial neural networks were used instead of Bayesian generalized linear regression (2.4%). The results showed that artificial neural networks are a promising approach for predicting leaf rust resistance in Arabica coffee.
Factor analysis for plant and production variables in Coffea canephorain the Western Amazon
(Universidade Federal de Lavras, 2022-06-09) Silva, Gabi Nunes; Barroso, Laís Mayara Azevedo; Cruz, Cosme Damião; Rocha, Rodrigo Barros; Ferreira, Fábio Medeiros
The evaluation of morphological characters related to the hulled coffee yield subsidizes the selection of Coffea canephora plants that combine a set of favorable traits. However, the greater the number of traits considered, the more difficult the selection process becomes. In this context, multivariate analyzes can be useful to overcome this problem. The aim of this study was to identify, in a set of agronomic traits of Coffea canephora, the determining factors of biological phenomena and use these factors to recognize patterns of diversity and similarity from biological complexes of interest to the breeder. To this, eleven morphological descriptors were evaluated of 130 clones of the botanical varieties Conilon and Robusta and intervarietal hybrids over two crop years in the experimental field of Embrapa, in the municipality of Ouro Preto do Oeste, state of Rondônia (RO). To group the traits, the multivariate technique of Factor Analysis was used. The effect of genotype x year interaction was significant for the eleven traits analyzed. Based on the scree plot, three factors were established. Factors were interpreted as architecture, vigor and grains with a satisfactory percentage of explained variability. The inter-pretation of the factors highlighted the importance of the Conilon variety to improve the architecture of the Robusta botanical variety. These results show that it is possible to use factor scores to identify varieties and traits that favor higher production of hulled coffee.
Genomic prediction of leaf rust resistance to Arabica coffee using machine learning algorithms
(Escola Superior de Agricultura "Luiz de Queiroz", 2021) Sousa, Ithalo Coelho de; Nascimento, Moysés; Silva, Gabi Nunes; Nascimento, Ana Carolina Campana; Cruz, Cosme Damião; Silva, Fabyano Fonseca e; Almeida, Dênia Pires de; Pestana, Kátia Nogueira; Azevedo, Camila Ferreira; Zambolim, Laércio; Caixeta, Eveline Teixeira
Genomic selection (GS) emphasizes the simultaneous prediction of the genetic effects of thousands of scattered markers over the genome. Several statistical methodologies have been used in GS for the prediction of genetic merit. In general, such methodologies require certain assumptions about the data, such as the normality of the distribution of phenotypic values. To circumvent the non-normality of phenotypic values, the literature suggests the use of Bayesian Generalized Linear Regression (GBLASSO). Another alternative is the models based on machine learning, represented by methodologies such as Artificial Neural Networks (ANN), Decision Trees (DT) and related possible refinements such as Bagging, Random Forest and Boosting. This study aimed to use DT and its refinements for predicting resistance to orange rust in Arabica coffee. Additionally, DT and its refinements were used to identify the importance of markers related to the characteristic of interest. The results were compared with those from GBLASSO and ANN. Data on coffee rust resistance of 245 Arabica coffee plants genotyped for 137 markers were used. The DT refinements presented equal or inferior values of Apparent Error Rate compared to those obtained by DT, GBLASSO, and ANN. Moreover, DT refinements were able to identify important markers for the characteristic of interest. Out of 14 of the most important markers analyzed in each methodology, 9.3 markers on average were in regions of quantitative trait loci (QTLs) related to resistance to disease listed in the literature.