Skip to Main content Skip to Navigation

Variable selection for data aggregated from different sources with group of variable structure

Abstract : During the last decades, the amount of available genetic data on populations has growndrastically. From one side, a refinement of chemical technologies have made possible theextraction of the human genome of individuals at an accessible cost. From the other side,consortia of institutions and laboratories around the world have permitted the collectionof data on a variety of individuals and population. This amount of data raised hope onour ability to understand the deepest mechanisms involved in the functioning of our cells.Notably, genetic epidemiology is a field that studies the relation between the geneticfeatures and the onset of a disease. Specific statistical methods have been necessary forthose analyses, especially due to the dimensions of available data: in genetics, informationis contained in a high number of variables compared to the number of observations.In this dissertation, two contributions are presented. The first project called PIGE (Pathway-Interaction Gene Environment) deals with gene-environment interaction assessments.The second one aims at developing variable selection methods for data which has groupstructures in both the variables and the observations.The document is divided into six chapters. The first chapter sets the background of this work,where both biological and mathematical notations and concepts are presented and gives ahistory of the motivation behind genetics and genetic epidemiology. The second chapterpresent an overview of the statistical methods currently in use for genetic epidemiology.The third chapter deals with the identification of gene-environment interactions. It includesa presentation of existing approaches for this problem and a contribution of the thesis. Thefourth chapter brings off the problem of meta-analysis. A definition of the problem and anoverview of the existing approaches are presented. Then, a new approach is introduced.The fifth chapter explains the pleiotropy studies and how the method presented in theprevious chapter is suited for this kind of analysis. The last chapter compiles conclusionsand research lines for the future.
Document type :
Complete list of metadatas

Cited literature [216 references]  Display  Hide  Download
Contributor : Abes Star :  Contact
Submitted on : Thursday, September 10, 2020 - 1:01:40 AM
Last modification on : Thursday, September 10, 2020 - 3:25:33 AM


Version validated by the jury (STAR)


  • HAL Id : tel-02935022, version 1



Camilo Broc. Variable selection for data aggregated from different sources with group of variable structure. Functional Analysis [math.FA]. Université de Pau et des Pays de l'Adour; Universidad del País Vasco. Facultad de ciencias, 2019. English. ⟨NNT : 2019PAUU3048⟩. ⟨tel-02935022⟩



Record views


Files downloads