One of the most important and challenging ``knowledge extraction' tasks in bioinformatics is the reverse engineering of gene regulatory networks (GRNs) from DNA microarray gene expression data. Indeed, as a result of the development of high-throughput data-collection techniques, biology is experiencing a data flood phenomenon that pushes biologists toward a new view of biology--systems biology--that aims at system-level understanding of biological systems.
Unfortunately, even for small model organisms such as the yeast Saccharomyces cerevisiae, the number p of genes is much larger than the number n of expression data samples. The dimensionality issue induced by this ``small n, large p' data setting renders standard statistical learning methods inadequate. Restricting the complexity of the models enables to deal with this serious impediment. Indeed, by introducing (a priori undesirable) bias in the model selection procedure, one reduces the variance of the selected model thereby increasing its accuracy.
Gaussian graphical models (GGMs) have proven to be a very powerful formalism to infer GRNs from expression data. Standard GGM selection techniques can unfortunately not be used in the ``small n, large p' data setting. One way to overcome this issue is to resort to regularization. In particular, shrinkage estimators of the covariance matrix--required to infer GGMs--have proven to be very effective. Our first contribution consists in a new shrinkage estimator that improves upon existing ones through the use of a Monte Carlo (parametric bootstrap) procedure.
Another approach to GGM selection in the ``small n, large p' data setting consists in reverse engineering limited-order partial correlation graphs (q-partial correlation graphs) to approximate GGMs. Our second contribution consists in an inference algorithm, the q-nested procedure, that builds a sequence of nested q-partial correlation graphs to take advantage of the smaller order graphs' topology to infer higher order graphs. This allows us to significantly speed up the inference of such graphs and to avoid problems related to multiple testing. Consequently, we are able to consider higher order graphs, thereby increasing the accuracy of the inferred graphs.
Another important challenge in bioinformatics is the prediction of gene function. An example of such a prediction task is the identification of genes that are targets of the nitrogen catabolite repression (NCR) selection mechanism in the yeast Saccharomyces cerevisiae. The study of model organisms such as Saccharomyces cerevisiae is indispensable for the understanding of more complex organisms. Our third contribution consists in extending the standard two-class classification approach by enriching the set of variables and comparing several feature selection techniques and classification algorithms.
Finally, our fourth contribution formulates the prediction of NCR target genes as a network inference task. We use GGM selection to infer multivariate dependencies between genes, and, starting from a set of genes known to be sensitive to NCR, we classify the remaining genes. We hence avoid problems related to the choice of a negative training set and take advantage of the robustness of GGM selection techniques in the ``small n, large p' data setting.
Identifer | oai:union.ndltd.org:BICfB/oai:ulb.ac.be:ETDULB:ULBetd-06302009-212720 |
Date | 02 July 2009 |
Creators | Kontos, Kevin |
Contributors | André, Bruno, Bersini, Hugues, Bontempi, Gianluca, Geurts, Pierre, Lenaerts, Tom, van Helden, Jacques |
Publisher | Universite Libre de Bruxelles |
Source Sets | Bibliothèque interuniversitaire de la Communauté française de Belgique |
Language | English |
Detected Language | English |
Type | text |
Format | application/pdf |
Source | http://theses.ulb.ac.be/ETD-db/collection/available/ULBetd-06302009-212720/ |
Rights | unrestricted, J'accepte que le texte de la thèse (ci-après l'oeuvre), sous réserve des parties couvertes par la confidentialité, soit publié dans le recueil électronique des thèses ULB. A cette fin, je donne licence à ULB : - le droit de fixer et de reproduire l'oeuvre sur support électronique : logiciel ETD/db - le droit de communiquer l'oeuvre au public Cette licence, gratuite et non exclusive, est valable pour toute la durée de la propriété littéraire et artistique, y compris ses éventuelles prolongations, et pour le monde entier. Je conserve tous les autres droits pour la reproduction et la communication de la thèse, ainsi que le droit de l'utiliser dans de futurs travaux. Je certifie avoir obtenu, conformément à la législation sur le droit d'auteur et aux exigences du droit à l'image, toutes les autorisations nécessaires à la reproduction dans ma thèse d'images, de textes, et/ou de toute oeuvre protégés par le droit d'auteur, et avoir obtenu les autorisations nécessaires à leur communication à des tiers. Au cas où un tiers est titulaire d'un droit de propriété intellectuelle sur tout ou partie de ma thèse, je certifie avoir obtenu son autorisation écrite pour l'exercice des droits mentionnés ci-dessus. |
Page generated in 0.0026 seconds