Back to Search Start Over

Artificial neural networks compared with Bayesian generalized linear regression for leaf rust resistance prediction in Arabica coffee

Authors :
Gabi Nunes Silva
Moysés Nascimento
Isabela de Castro Sant’Anna
Cosme Damião Cruz
Eveline Teixeira Caixeta
Pedro Crescêncio Souza Carneiro
Renato Domiciano Silva Rosado
Kátia Nogueira Pestana
Dênia Pires de Almeida
Marciane da Silva Oliveira
Source :
Pesquisa Agropecuária Brasileira, Vol 52, Iss 3, Pp 186-193 (2017)
Publication Year :
2017
Publisher :
Embrapa Informação Tecnológica, 2017.

Abstract

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.

Details

Language :
English, Spanish; Castilian, Portuguese
ISSN :
16783921 and 0100204x
Volume :
52
Issue :
3
Database :
Directory of Open Access Journals
Journal :
Pesquisa Agropecuária Brasileira
Publication Type :
Academic Journal
Accession number :
edsdoj.6e4a39e66d3f453ea08547554608f9bf
Document Type :
article
Full Text :
https://doi.org/10.1590/s0100-204x2017000300009