Abstract:
In the field of maize cultivation, plant breeding is undergoing a transformation driven by genomic selection, which necessitates the utilization of machine learning models to validate common traits such as taste, nutritional content, and disease resistance. To enhance the development of efficient molecular markers for common traits, Single Nucleotide Polymorphisms (SNPs) in maize are mapped. By utilizing these molecular markers, Marker-Assisted Selection (MAS) has emerged as a promising approach to rapidly improve common traits in maize. This study focuses on validating common traits in maize using a machine learning algorithm with SNPs as markers. Logistic regression and feedforward neural network models were evaluated to determine the most effective computational approach for validating traits in maize. The results showed that logistic regression achieved higher accuracy in validating SNP markers compared to the feedforward neural network. The logistic regression model accurately identified SNP markers associated with common traits, achieving a 99% accuracy rate, while the feedforward neural network achieved 97% accuracy. These findings demonstrate the potential of machine learning techniques in validating SNP markers within maize breeding programs. They highlight the importance of selecting the appropriate machine learning algorithm to ensure optimal marker validation and enable the development of improved maize varieties with common traits such as enhanced taste, nutritional value, and resistance to diseases.
Page(s):
88-88
DOI:
DOI not available
Published:
Journal: Abstract Book on International Conference on Food and Applied Sciences (ICFAS-23) 3-5 August 23, Volume: 0, Issue: 0, Year: 2023