ABSTRACT: The biotrophic fungus Hemileia vastatrix causes coffee leaf rust (CLR), one of the most devastating diseases in Coffea arabica . Coffee, like other plants, has developed effective mechanisms to recognize and respond to infections caused by pathogens. Plant resistance gene analogs (RGAs) have been identified in certain plants as candidates for resistance ( R ) genes or membrane receptors that activate the R genes. The RGAs identified in different plants possess conserved domains that play specific roles in the fight against pathogens. Despite the importance of RGAs, in coffee plants these genes and other molecular mechanisms of disease resistance are still unknown. This study aimed to sequence and characterize candidate genes from coffee plants with the potential for involvement in resistance to H. vastatrix . Sequencing was performed based on a library of bacterial artificial chromosomes (BAC) of the coffee clone ‘Híbrido de Timor’ (HdT) CIFC 832/2 and screened using a functional marker. Two RGAs, HdT_LRR_RLK1 and HdT_LRR_RLK2, containing the motif of leucine-rich repeat-like kinase (LRR-RLK) were identified. Based on the presence or absence of the HdT_LRR_RLK2 RGA in a number of differential coffee clones containing different combinations of the rust resistance gene, these RGAs did not correspond to any resistance gene already characterized (SH1-9). These genes were also analyzed using qPCR and demonstrated a major expression peak at 24 h after inoculation in both the compatible and incompatible interactions between coffee and H. vastatrix . These results are valuable information for breeding programs aimed at developing CLR-resistant cultivars, in addition to enabling a better understanding of the interactions between coffee and H. vastatrix .

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.

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.