Section: Application Domains

Biology and Chemistry

Participants : Mehwish Alam, Aleksey Buzmakov, Adrien Coulet, Nicolas Jay, Amedeo Napoli, Mohsen Sayed, Malika Smaïl-Tabbone, Yannick Toussaint.

Keywords:

knowledge discovery in life sciences, bioinformatics, biology, chemistry, genomics

One major application domain which is currently investigated by the Orpailleur team is related to life sciences, with particular emphasis on biology, medicine, and chemistry. The understanding of biological systems provides complex problems for computer scientists, and the developed solutions bring new research ideas or possibilities for biologists and for computer scientists as well. Accordingly, the Orpailleur team includes biologists, chemists, and a physician, making Orpailleur a very original EPI at Inria. Indeed, the interactions between researchers in biology and researchers in computer science improve not only knowledge about systems in biology, chemistry, and medicine, but knowledge about computer science as well.

Knowledge discovery is gaining more and more interest and importance in life sciences for mining either homogeneous databases such as protein sequences and structures, or heterogeneous databases for discovering interactions between genes and environment, or between genetic and phenotypic data, especially for public health and pharmacogenomics domains. The latter case appears to be one main challenge in knowledge discovery in biology and involves knowledge discovery from complex data depending on domain knowledge.

On the same line as biological data, chemical data are presenting important challenges w.r.t. knowledge discovery, for example for mining collections of molecular structures and collections of chemical reactions in organic chemistry. The mining of such collections is an important task for various reasons among which the challenge of graph mining and the industrial needs (especially in drug design, pharmacology and toxicology). Molecules and chemical reactions are complex data that can be modeled as undirected labeled graphs. One objective for guiding computer-based synthesis in organic chemistry is to discover general synthesis methods (i.e. kinds of “meta-reactions”) from currently available chemical reaction databases for designing generic and reusable synthesis plans.

Graph mining methods may play an important role in this framework and Formal Concept Analysis can also be used in an efficient and well-founded way [34] . Combining supervised methods –with a training set where objects are tagged– and unsupervised methods, “jumping emerging patterns” can be detected that characterize classes of interest, e.g. toxic molecules or inhibitors. Then, a hybrid classification method based on FCA can be used for building a concept lattice where some of the concepts can be used as reference classes for classifying unknown objects, for recognition and prediction tasks. Graph mining in the framework of FCA is a very important task on which we are actively working, whose results can be transferred to text mining as well.