ED Droit
Alternative methods of dispute resolution with the administration
by Aaron AMESSAN (INSTITUT LÉON DUGUIT)
The defense will take place at 14h00 - Salle des thèses FACULTÉ DROIT ET SCIENCE POLITIQUE Avenue Léon Duguit 33608 Pessac
in front of the jury composed of
- Jean-François BRISSON - Professeur des universités - Université de Bordeaux - Directeur de these
- Antoine CLAEYS - Professeur des universités - Université de Poitiers - Rapporteur
- Sébastien SAUNIER - Professeur des universités - Université Toulouse I Capitole - Rapporteur
- Jean GOURDOU - Professeur des universités - Université de Pau et des Pays de l'Adour (UPPA) - Examinateur
- Jean-Philippe FERREIRA - Professeur des universités - Université de Bordeaux - Examinateur
The search for alternative solutions to legal proceedings and decisions is no longer an epiphenomenon in public law. Although, despite their age-old nature, mechanisms for settling disputes with the authorities in a different way have been generally unsuccessful, the resurgence of certain cyclical and structural factors linked both to the objective of the proper administration of justice and to improving relations between the public and the authorities has led the standard-setting authorities to see alternative dispute resolution (ADR) as a pragmatic response to the challenges of justice in the 21st century. The combined efforts of the public authorities have made it possible, in particular with the J21 Act of 2016 and its aftermath, to give concrete form to the policy of promoting ADR by establishing a simplified legal framework conducive to the general immersion of ADR in most areas of administrative litigation. Although practice seems to confirm, albeit in a variable and measured way, this favour for ADR, the perfectible nature of the current legal regime for ADR calls for caution on the part of those involved in the justice system in their implementation, as it tends to complicate the quest for a balance between making ADR commonplace and preserving the imperative rules of public law.
ED Sociétés, Politique, Santé Publique
Computational approach for drug repositioning: towards an holistic perspective with knowledge graphs(OREGANO).
by Marina BOUDIN (Bordeaux Population Health Research Center)
The defense will take place at 11h00 - Amphi Louis Centre de recherche Bordeaux Population Health - 146 rue Léo Saignat 33076 Bordeaux Cedex
in front of the jury composed of
- Gayo DIALLO - Professeur - Université de Bordeaux - Directeur de these
- Adrien COULET - Chargé de recherche - INRIA - Rapporteur
- Lina SOUALMIA - Professeure - Université de Rouen - Rapporteur
- Patricia THéBAULT - Professeur - LaBRI - Examinateur
- Fleur MOUGIN - Professeur - Centre de recherche Bordeaux Population Health - CoDirecteur de these
- Richard CHBEIR - Professeur - IUT de Bayonne et du Pays Basque - Examinateur
Drug discovery is a long and costly process. Drug repositioning is a promising alternative: finding new indications for existing drugs. By comparing large quantities of information on drugs that have failed in the final phases of clinical trials, or that have been granted marketing authorization and thus marketed, it is possible to find candidate drugs for repositioning that are capable of treating a condition for which they were not initially developed. To compare all these drugs, computational methods based on large databases are favored for their efficiency, speed and ability to analyse large quantities of information. Knowledge graphs are ideal structures for integrating this heterogeneous information. A knowledge graph organizes this information into triples consisting of a subject, an object and a predicate explaining the relationship between the subject and the object. This graph, combined with embedding techniques (machine learning), can be used to predict new relationships between subjects and objects (which are nodes in the graph). It is therefore possible to transform the problem of repositioning into a problem of discovering new links in a graph. This thesis addresses these issues within the framework of the OREGANO project, which aims to build a large knowledge graph on drugs and apply node plunging techniques for drug repositioning. These techniques “project” the graph into a vector space where each entity is represented by a vector. One of the innovations brought by OREGANO is also to include data on natural compounds whose medicinal properties are exploited in many countries and whose repositioning potential has been little explored. First, we present the way in which we designed the OREGANO knowledge graph, considering two distinct integration approaches. We then describe the evolutions that have been made to the graph over the years. Thirdly, we demonstrate the ability of the OREGANO knowledge graph to predict new links using embedding techniques. Predictions are evaluated with standard metrics and empirically in the context of drug repositioning. The OREGANO graph, as well as the algorithm and code developments, are available to the scientific community at https://gitub.u-bordeaux.fr/erias/oregano.