Abstract
Background: Identifying and validating biomarkers' scores of polymorphic bands are important for studies related to the molecular diversity of pathogens. Although these validations provide more relevant results, the experiments are very complex and time-consuming. Besides rapid identification of plant pathogens causing disease, assessing genetic diversity and pathotype formation using automated soft computing methods are advantageous in terms of following genetic variation of pathogens on plants. In the present study, artificial neural network (ANN) as a soft computing method was applied to classify plant pathogen types and fungicide susceptibilities using the presence/absence of certain sequence markers as predictive features.
Results: A plant pathogen, causing downy mildew disease on cucurbits was considered as a model microorganism. Significant accuracy was achieved with particle swarm optimization (PSO) trained ANNs.
Conclusions: This pioneer study for estimation of pathogen properties using molecular markers demonstrates that neural networks achieve good performance for the proposed application.
Upon acceptance of an article by the journal, authors will be asked to transfer the copyright to Electronic Journal of Biotechnology, which is committed to maintain the electronic access to the journal and to administer a policy of fair control and ensure the widest possible dissemination of the information. The author can use the article for academic purposes, stating clearly the following: "Published in Electronic Journal of Biotechnology at DOI:10.2225/volXX-issueX-fulltext-XX".
The Copyright Transfer Agreement must be submitted as a signed scanned copy to biotec@ucv.cl. All authors must send a copy of this document.