Genetic programming for the identification of interactions between genes and diseases in texts

• Grant number: 15/21467-0
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: January 01, 2016
• End date: December 31, 2016
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
• Principal Investigator: Renato Tinós
• Grantee: Carla Antonieta da Silva Santos Chibante
• Host Institution: Faculdade de Filosofia, Ciências e Letras de Ribeirão Preto (FFCLRP). Universidade de São Paulo (USP). Ribeirão Preto , SP, Brazil

Abstract

Like in other areas of scientific knowledge, researchers in Molecular Biology have reported their findings mainly through scientific papers. As a result, the number of published papers describing the relationship between genes and diseases has grown exponentially in recent years. The main objective of this project is investigating the use of Genetic Programming (PG), an Evolutionary Computation technique used to optimize symbolic structures, to extract relationships between genes and diseases in scientific papers. The PG should generate new syntactic rules to be used in the identification of relationships in papers of a corpus in the area of Medicine. The PG should be able to change the structure of the syntactic rules through the optimization process. Each individual of the PG should encode a set of rules. To validate the proposed methodology, the PG will be evaluated in a corpus in which words and relationships are already identified. (AU)