Development of machine learning approaches based on biological networks for predic...
| Grant number: | 12/00741-8 |
| Support type: | Scholarships in Brazil - Doctorate |
| Effective date (Start): | April 01, 2012 |
| Effective date (End): | January 31, 2015 |
| Field of knowledge: | Biological Sciences - Biophysics |
| Principal Investigator: | Ney Lemke |
| Grantee: | Esther Camilo dos Reis |
| Home Institution: | Instituto de Biociências (IBB). Universidade Estadual Paulista (UNESP). Campus de Botucatu. Botucatu , SP, Brazil |
| Associated scholarship(s): | 12/22395-4 - Visualization of forests of trees, BE.EP.DR |
Abstract Cell differentiation, carcinogenesis, and gene essentiality are some examples of biological processes that can not be fully explained through the study of individual genes. There is now a concern of researchers in understanding how the various entities of a system interact and produce certain phenotypes using the techniques of systems biology. However, few of these approaches are genome scaled and consider the effects of environment on these networks. In this context, this project aims to predict the phenotypes of the bacterium Escherichia coli, that is, the evaluation of its growth profile in different conditions by metabolic flux balance analysis (FBA) and machine learning. The representation of the system is done by using graph where the interacting elements are represented by nodes and interactions by edges that connect pairs of nodes. From the network it will be extracted centralities data which together with the results of the FBA calculations will be used as attributes of training for the learning algorithm. | |