A two-year post-doctoral position in Computer Science and chemoinformatics was open at the GREYC laboratory (CNRS UMR 6072) at University of Caen.
Working context: the position has been accepted by the Emergence call for proposals funded by the Region Basse-Normandie. The work is partially linked to some activities of the project Bingo2.
Location: Caen, Normandy, France
Topic: Designing classifiers by using graph structures to predict toxicological properties of chemical compounds
The European Union has recently adopted a new regulation (the REACH regulation) about the production and commercialization of chemicals. The REACH regulation enables us to use alternate methods (typically in silico methods) in order to define the physicochemical profile of molecules. A lot of research is devoted to the creation of classification rules to predict the activity of a molecule according to its structure. This post-doctorate position focuses on the processing of chemical information: its purpose is to contribute to the development of reliable decision rules and classifiers to assess the toxicity of a chemical compound according to its structure. In this context, this research includes an analysis of the relevance of two families of descriptors:
- The largest common subgraph. Molecular structures are modelized by graphs, hence the largest common subgraph to two graphs induces a notion of intersection between the molecular structures. However, there are several notions of largest common subgraph and there is a need to compare their relative interest of in the context of structure activity relationship.
- Kernel similarities. These methods are applied to graphs for few years. In spite of their implementation may be expensive, their performances are promising. We need to assess the relevance of kernel similarities in the prediction of chemical activity.
As molecular structures are graphs, combinatorial algorithms are required to compute such descriptors and similarities. One of the goals of this work is to assess the interest of these descriptors and then to design prediction rules and classifiers. Such classifiers will be applied to a large spectrum of molecules. The chemical databases are provided by the CERMN (research center on drugs and medicines) associated to this project. These bases cover the whole spectrum of compounds manufactured or marketed within the European Union.
ProfileWe are looking for a PhD computer scientist with strong knowledge in at least one the following fields: combinatorial algorithms, data mining or automatic learning. Besides a sound experience of programming will be appreciated.
Place, duration and remuneration
- 24 months contract, starting from early 2009
- net salary: 2,030 euros per month (gross salary: 2,487 euros per month)
- the position requires working at GREYC laboratory
How to apply
Please send your application (PDF format) as soon as possible. Screening of applications starts immediately and continues until the position is filled.
Send CV and cover letter, including names of at least two references, to the following emails:
Bertrand Cuissart +33 2 31 56 73 72 Bertrand.Cuissart@info.unicaen.fr
Bruno Crémilleux +33 2 31 56 74 35 Bruno.Cremilleux@info.unicaen.fr
GREYC - CNRS UMR 6072, Université de Caen, Campus Côte de Nacre F-14032 Caen Cedex - France
