Machine learning application to identify genomic regions associated with resistance to grasshoppers (Notozulia entreriana Berg) in Urochloa decumbens

• Grant number: 21/01801-3
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Effective date (Start): May 01, 2021
• Effective date (End): December 31, 2021
• Field of knowledge: Agronomical Sciences - Agronomy - Crop Science
• Principal Investigator: Anete Pereira de Souza
• Grantee: Isabella Cotta Galvão
• Host Institution: Centro de Biologia Molecular e Engenharia Genética (CBMEG). Universidade Estadual de Campinas (UNICAMP). Campinas , SP, Brazil

Abstract

Urochloa decumbens is one of the main forages used in pastures in tropical and subtropical regions, standing out for its good adaptation to acid and poor soils, easy multiplication by seeds, and good animal performance. However, the susceptibility to attack by the insect spittlebug (Notozulia entreriana Berg) compromises the carrying capacity of the pastures, as well as the production of biomass. One of the main objectives of breeding programs is to launch cultivars resistant to this insect pest, but so far, studies to understand the genetic mechanisms involved in the resistance response are limited, mainly due to the high genomic complexity of U. decumbens. In this context, this project aims to apply machine learning algorithms and attribute selection to elucidate new genetic associations related to resistance to spittlebug in U. decumbens. The computational intelligence-based approach is expected to make it possible to identify genomic regions of U. decumbens associated with resistance to spittlebugs, with potential applications in breeding programs, to reduce the vulnerability of Brazilian pastures. (AU)