Application domains investigated by the Orpailleur team are mainly related to life sciences, e.g. agronomy, biology, chemistry, cooking and medicine. The understanding of life science systems provides complex problems for computer scientists, and the developed solutions bring new research directions for biologists and for computer scientists as well. Accordingly interactions between researchers in life sciences and researchers in computer science may improve not only knowledge about systems in biology, chemistry, and medicine, but knowledge about computer science as well.
Nowadays, knowledge discovery is used for mining databases including protein sequences and structures, gene interactions, pharmacogenomics, metabolomic data, and health data. On the same line, chemical data provide challenges for mining collections of molecular structures and collections of chemical reactions in organic chemistry. In particular, this calls for efficient graph mining techniques related to industrial needs (drug design).
In medicine, some applications are related to the analysis of patient trajectories which are considered as sequences. Methods for mining sequences should be adapted for addressing the complex nature of medical events. In such a context, knowledge management and decision making (e.g. in the treatment of cancer) are also tasks of interest. Moreover, sequence mining may also be used for analyzing visitor trajectories in museums and touristic sites. In this way, we are also investigating biclustering techniques for recommendation purposes.
Finally, we are also working in agronomy, mainly on decision making, on the mining of spatio-temporal data, on the understanding of culture rotations and on landscape evolution w.r.t. agricultural activities.