Helicobacter Pylori and Interleukin-17: a Possible predictive approach to Gastric Cancer using Artificial Intelligence

• Grant number: 24/21796-2
• Support Opportunities: Scholarships in Brazil - Doctorate
• Start date: August 01, 2025
• End date: February 28, 2029
• Field of knowledge: Biological Sciences - Microbiology - Applied Microbiology
• Principal Investigator: José Celso Rocha
• Grantee: Bruno Mari Fredi
• Host Institution: Faculdade de Ciências e Letras (FCL-ASSIS). Universidade Estadual Paulista (UNESP). Campus de Assis. Assis , SP, Brazil

Abstract

Gastric Cancer (GC) is a multifactorial disease influenced by an individual's genetic factors and Helicobacter pylori (H. pylori) infections. The extent of this infection is due to the presence of H. pylori virulence factors that contribute to chronic inflammation and tissue damage. Interleukins (ILs) are cytokines of the immune system produced in response to infections. IL-17 is a key element in this inflammatory response, and several Single Nucleotide Polymorphisms (SNPs) of IL-17 may contribute to GC. Investigating the relationship between IL-17 SNPs and the presence of H. pylori will help elucidate the predisposition, prognosis, and evolutionary processes of gastric diseases and GC. Artificial Intelligence (AI) has been widely employed in the diagnosis, prediction, and molecular characterization of diseases, contributing significantly to the advancement of precision medicine. The development of predictive models using Artificial Neural Networks, Genetic Algorithms, Random Forest, and Categorical Boost represents a promising tool in predicting the risk of GC development, based on the individual's genetic variables and the presence of the Helicobacter pylori bacterium. Thus, the objective of this project is to develop a computational algorithm using AI techniques to identify susceptibility factors and predict the risk of GC. For this purpose, based on 300 gastric biopsy samples divided into three groups (Control, Gastritis, and Cancer), using qPCR, the following will be conducted: (I) Diagnosis of the presence of H. pylori and the virulence markers: cagA, cagE, cagG, cagM, cagT, dupA, oipA, vacA, virb11;(II) Detection of clinically relevant SNPs in the IL-17 genes; and (III) Using AI techniques, such as Artificial Neural Networks, Genetic Algorithms, Random Forest, and Categorical Boost, develop on the Matlab and/or Python platform a predictive model capable of identifying and classifying the studied groups, thus characterizing the susceptibility factors for GC. (AU)