ABSTRACT 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.

ABSTRACT. Modifications were made in the PCR conditions aiming to overcome the problem of non-amplification of the Xanthomonas phaseoli pv. manihotis (Xpm) fragment, using the primer pair XV / XK described in the literature. The objective of this study was to propose changes in the primers already described (XV / XK_MOD) and validate the use of these new primers in identifying Xpm. The validation procedure was carried out with the primer pair XV and XK_MOD, using different strains of Xpm, other plant pathogenic and endophytic bacteria genera and one isolate of X. phaseoli pv. passiflorae. As a control, additional reactions were conducted in multiplex with the universal primers for the 16S rRNA gene of the bacteria together with XV / XK and XV / XK_MOD. Using the forward primer (XV) described in the literature together with the modified reverse primer (XK_MOD), it was possible to achieve amplification from DNA extracted from in vitro cultures and from infected tissue, but no amplification was noticed for the primer pair described in the literature, confirming the effectiveness of the proposed modification.

Resumo: O objetivo deste trabalho foi avaliar o uso de redes neurais artificiais em comparação à modelagem por meio de modelos lineares generalizados na predição de resistência à ferrugem em café arábica (Coffea arabica). Foram utilizados 245 indivíduos provenientes de uma população F2, oriundos da autofecundação do híbrido F1 H511-1, resultante do cruzamento da cultivar suscetível Catuaí Amarelo IAC 64 (UFV 2148-57) e do genitor resistente Híbrido de Timor (UFV 443-03). Os 245 indivíduos foram genotipados com 137 marcadores. Realizaram-se análises com redes neurais artificiais e com modelos lineares generalizados sob o enfoque bayesiano. As redes neurais identificaram quatro marcadores importantes pertencentes a grupos de ligação que foram recentemente mapeados, enquanto o modelo generalizado bayesiano identificou somente dois marcadores pertencentes a esses grupos. Foram observadas taxas de erro de predição inferiores (1,60%) para predizer a resistência à ferrugem em café arábica, quando foram utilizadas as redes neurais artificiais em vez de modelos lineares generalizados sob o enfoque bayesiano (2,4%). Os resultados mostraram que as redes neurais artificiais são uma abordagem promissora para predizer a resistência à ferrugem em café arábica.

Abstract: 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 F2 population derived from the self-fertilization of the F1 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.

O objetivo deste trabalho foi quantificar a variabilidade genética entre e dentro de populações de caroá (Neoglaziovia variegata), por meio de marcadores "random amplified polymorphic DNA" (RAPD). Foram analisados 180 genótipos de caroá, provenientes dos municípios de Guanambi, Juazeiro e Valente, no Estado da Bahia. Foi observado elevado polimorfismo entre as populações de caroá. As dissimilaridades genéticas entre os genótipos variaram de 0,08 a 0,95, com média de 0,44.Avariância molecular mostrou que 56% da variação total foi explicada pelas diferenças entre indivíduos dentro de locais. As diferenças entre municípios explicaram 17% da variação total, enquanto as diferenças entre locais dentro dos municípios explicaram 26% da variação.

The objective of this work was to quantify the genetic variability within and among populations of caroá (Neoglaziovia variegata) using random amplified polymorphic DNA(RAPD) markers. One hundred eighty caroá genotypes from Guanambi, Juazeiro and Valente counties in the state of Bahia, Brazil, were analyzed. A high polymorphism was observed among the caroá populations. The genetic dissimilarities among all genotypes ranged from 0.08 to 0.95 with an average of 0.44. The molecular variance showed that 56% of the total variation was explained by the differences among individuals with in locations.The differences among counties explained 17% of the total variation, while the differences among places within counties explained 26% of the variation.

Este trabalho teve como objetivo caracterizar molecularmente genótipos elite, e recomendados, de bananeira, por meio de marcadores RAPD e microssatélites. Foram utilizados 47 primers de RAPD e 34 primers de microssatélites. Foi também conduzido um ensaio de contaminação, utilizando-se o primer AGMI 24-25, cuja variedade Tropical foi considerada a amostra-padrão, e as cultivares Caipira e Prata Graúda como contaminantes. Os marcadores permitiram separar as cultivares de acordo com a origem e a constituição genômica e definiram padrões moleculares para algumas cultivares avaliadas. As cultivares Garantida, Preciosa e Pacovan Ken apresentaram alta similaridade genética com ambos marcadores. O primer AGMI 24-25 demonstrou alta capacidade discriminatória de genótipos em ensaios de contaminação.

The objective of this work was to characaterize elite banana genotypes, and those recommended, using RAPD and microsatellites. Forty-seven RAPD primers and 34 microsatellites primers were used. A contamination essay using the AGMI 24-25 primer was also carried out. Tropical variety was considered the standard sample and the Caipira and Prata Graúda, contaminants. Markers were able to separate the cultivars according to their origin and genomic constitution as well as defined molecular profiles for some of the cultivars evaluated. Garantida, Preciosa and Pacovan Ken cultivars presented genetic similarity with both markers. The AGMI 24-25 primer demonstrated high capacity to discriminate the genotypes in the contamination essay.