Knowledge discovery in a genetic database: the MINOS system

This paper concerns the management of genetic sequences in an object-oriented database and the extraction of knowledge from these sequences. In our case knowledge discovery consists in finding functions capable of predicting properties about genetic sequences. This problem is also known as functional inference. The paper is divided in two parts: the first one shows the interest of using an object-oriented query language to build and use prediction functions. In the second part, we propose to use prediction functions as descriptors of sequences in order to index them. The indexation is performed with concept lattices