Métodos estatísticos aplicados à análise da expressão gênica

• Ano de defesa: 2006
• Autor(a) principal: Saraiva, Erlandson Ferreira
• Orientador(a): Milan, Luis Aparecido
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: por
• Instituição de defesa: Universidade Federal de São Carlos
• Programa de Pós-Graduação: Programa de Pós-Graduação em Estatística - PPGEs
• País: BR
• Palavras-chave em Português: Estatística matemática; Expressão gênica; Inferência bayesiana; Seleção de modelos; Processos de Dirichlet; Arranjos de DNA; Teste t; Modelo com mistura de distribuições; Inferência bayesiana não paramétrica
• Área do conhecimento CNPq: CIENCIAS EXATAS E DA TERRA::PROBABILIDADE E ESTATISTICA::ESTATISTICA
• Link de acesso: https://repositorio.ufscar.br/handle/20.500.14289/4596

The technology of the DNA-Arrays is a tool used to identify and to compare levels of expression of a great number of genes or fragments of genes, in di¤erent conditions. With this comparison, it is possible to identify genes possibly causing illnesses of genetic origin (cancer for example). Great amounts of numerical data (related the measures of levels of expression of the genes) are generated and statistical methods are important for analysis of this data with objective to identify the genes that present evidences for di¤erent levels of expression. The objective of our research is to develop and to describe methods statistical, capable of identifing genes that present evidences for di¤erent levels of expression. We describe the test t, considered for Baldi and Long (2001) and consider three others methods. The first method considered is based on the use of parametric Bayes inference and the methods for selection of models, Bayes factor and DIC; the second method is based an semi-parametric bayesian inference, model of mixtures of Dirichlet processes. The third method is based on the use of a model with infinite mixtures of distributions that applied the analysis of the genica expression determines groups of similar levels of expression.