ISIthalo Coelho de Sousa

Ithalo Coelho de Sousa

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Ithalo Coelho de Sousa has a total of 29 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Marker pre-selection as a strategy to enhance genomic prediction with machine learning: Exploring the influence of trait-specific genomic structures

    by Wagner Faria Barbosa, Antônio Carlos da Silva Júnior, Ithalo Coelho de Sousa, Francyse Edite de Oliveira Chagas de Moraes, Michele Jorge Silva Siqueira, Leonardo Lopes Bhering, Moysés Nascimento, Cosme Damião Cruz

    This study focused on incorporating dimensionality reduction based on marker significance to better harness the potential of machine learning for genomic prediction in different trait-genomic structures. The aim was to show that outcomes achieved with reduced data would improve predictive accuracy ( ) and precision (root-mean-square error: RMSE) while reducing computational time. Distinct subsets of markers, in simulated data, were chosen by prioritizing importance via the Bagging technique. Predictive modelling was subsequently conducted using both Bagging and the diverse architectures of a Multilayer Perceptron (MLP) neural network. This study was carried out with six traits of an F2 simulated population (derived from contrasting homozygotes) with 1,000 individuals. Three traits had three different heritabilities (0.4, 0.6, and 0.8) and were controlled by a set of 40 quantitative trait loci (QTLs). Additionally, four QTLs with more pronounced heritability effects (set at unity) were introduced in three other traits while preserving the same genetic control structure as the earlier traits. In our investigation, as the number of markers increased, both techniques gradually increased training time; however, the time needed for computation notably extended beyond the threshold of 100 markers for Bagging. In comparison to the MLP model, the Bagging model generally obtained better accuracy (higher ) and precision (lower RMSE) values regardless of heritability and added QTLs. Most importantly, results highlight that for traits subject to robust genetic control of additional QTLs, MLP networks experienced a decline in prediction performance from a few markers (~10). In contrast, Bagging kept constant or subtly improved predication performance. Finally, the dimensionality reduction procedure effectively improves genomic prediction, and Bagging captures complex genetic control structures for prediction better than MLP networks.

  • The trade-off between density marker panels size and predictive ability of genomic prediction for agronomic traits in Coffea canephora

    by Ithalo Coelho de Sousa, Cynthia Aparecida Valiati Barreto, Eveline Teixeira Caixeta, Ana Carolina Campana Nascimento, Camila Ferreira Azevedo, Emilly Ruas Alkimim, Moysés Nascimento


  • Open Access

    Classification of soybean cultivars by means of artificial neural networks

    by João Victor Costa Carneiro Paixão, Éder Matsuo, Ithalo Coelho de Sousa, Moysés Nascimento, Igor Silva Oliveira, Adalberto Filipe Macedo, Gustavo Martins Santana

    The cultivation of soy has an economic importance for the Brazilian agricultural scenario. The aim of this study was to establish a network architecture for the classification of soybean genotypes, by means of morphological characters measured in the juvenile phase of the plant, and finally to compare the results obtained through Artificial Neural Network (ANN) and Anderson Discriminant Analysis. The study analyzed plants of 10 conventional cultivars in the initial stages of development (V1, V2 and V3 stages). The experiment was carried out in a randomized block design with 5 replications, and the experimental unit was represented by 9 plants. The data were submitted to the Anderson Discriminant Analysis and multilayer Perceptron ANN, with 1 or 2 hidden layers. To analyze the homogeneity of the variance and covariance matrix, the Box’s M-Test was adopted in the Program R, at 5% significance level. An input layer, one or two hidden layers, and an output layer formed the ANN architecture. The 5-fold cross validation was used to verify the efficiency of the discriminant functions and also in the ANN analysis. Subsequently, the apparent error rate (AER) was obtained. Box’s M-Test indicated inhomogeneity in the variance and covariance matrices, which indicated the need to perform Anderson's Quadratic Discriminant Analysis. The ANNs presented lower apparent error rate when compared to the Anderson's Quadratic Discriminant Analysis and the artificial neural network with 1 hidden layer was sufficient to perform the classification of soybean cultivars.


  • Open Access

    Marker effects and heritability estimates using additive-dominance genomic architectures via artificial neural networks in Coffea canephora

    by Ithalo Coelho de Sousa, Moysés Nascimento, Isabela de Castro Sant’anna, Eveline Teixeira Caixeta, Camila Ferreira Azevedo, Cosme Damião Cruz, Felipe Lopes da Silva, Emilly Ruas Alkimim, Ana Carolina Campana Nascimento, Nick Vergara Lopes Serão

    Many methodologies are used to predict the genetic merit in animals and plants, 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. The aim of this research was to estimate the heritability and markers effects for two traits inCoffea canephorausing an additive-dominance architecture ANN and to compare it with genomic best linear unbiased prediction (GBLUP). The data used consists of 51 clones ofC.canephoravarietal Conilon, 32 of varietal group Robusta and 82 intervarietal hybrids. From this, 165 phenotyped individuals were genotyped for 14,387 SNPs. Due to the high computational cost of ANNs, we used Bagging decision tree to reduce the dimensionality of the data, selecting the markers that accumulated 70% of the total importance. An ANN with three hidden layers was run, each varying from 1 to 40 neurons summing 64,000 neural networks. The network architectures with the best predictive ability were selected. The best architectures were composed by 4, 15, and 33 neurons in the first, second and third hidden layers, respectively, for yield, and by 13, 20, and 24 neurons, respectively for rust resistance. The predictive ability was greater when using ANN with three hidden layers than using one hidden layer and GBLUP, with 0.72 and 0.88 for yield and coffee leaf rust resistance, respectively. The concordance rate (CR) of the 10% larger markers effects among the methods varied between 10% and 13.8%, for additive effects and between 5.4% and 11.9% for dominance effects. The narrow-sense ( ha2 ) and dominance-only ( hd2 ) heritability estimates were 0.25 and 0.06, respectively, for yield, and 0.67 and 0.03, respectively for rust resistance. The ANN was able to estimate the heritabilities from an additive-dominance genomic architectures and the ANN with three hidden layers obtained best predictive ability when compared with those obtained from GBLUP and ANN with one hidden layer.


  • Open Access

    Genomic prediction of leaf rust resistance to Arabica coffee using machine learning algorithms

    by Ithalo Coelho de Sousa, Moysés Nascimento, Gabi Nunes Silva, Ana Carolina Campana Nascimento, Cosme Damião Cruz, Fabyano Fonseca e Silva, Dênia Pires de Almeida, Kátia Nogueira Pestana, Camila Ferreira Azevedo, Laércio Zambolim, et al.

    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.