Learning stories: computational learning to classify metabolic stories

• Grant number: 17/04250-2
• Support type: Scholarships in Brazil - Scientific Initiation
• Effective date (Start): May 01, 2017
• Effective date (End): December 31, 2017
• Field of knowledge: Physical Sciences and Mathematics - Computer Science
• Principal researcher: Roberto Marcondes Cesar Junior
• Grantee: Larissa de Oliveira Penteado
• Home Institution: Instituto de Matemática e Estatística (IME). Universidade de São Paulo (USP). São Paulo , SP, Brazil

Abstract

Along with the technological advances, the access to larger and larger quantities of data about the organisms' metabolome is available. The analysis and comprehension of this information is extremely important, because through this we can have a better understanding of how the response mechanisms of the organisms work, when they are exposed to different physiological conditions and stresses. To accomplish this task, in the area of Bioinformatics, some methods stand out, they search for metabolic pathways, that explain such metabolite concentration variances, from metabolic networks that represent the reactions that can occur in an organism. Because the number of pathways obtained by these methods is very large and difficult to analyze, it is interesting to apply Machine Learning techniques in order to categorize the pathways obtained and understand them more significantly. This Scientific Initiation project is about this theme. (AU)