Virtual screening has become an essential step in the early drug discovery process. Generally speaking, it consists in using computational techniques for selecting compounds from chemical libraries in order to identify drug-like molecules acting on a biological target of therapeutic interest. In the present study we consider virtual screening as a particular form of the KDD (Knowledge Discovery from Databases) approach. The knowledge to be discovered concerns the way a compound can be considered as a consistent ligand for a given target. The data from which this knowledge has to be discovered derive from diverse sources such as chemical, structural, and biological data related to ligands and their cognate targets. More precisely, we aim to extract filters from chemical libraries and protein-ligand interactions. In this context, the three basic steps of a KDD process have to be implemented. Firstly, a model-driven data integration step is applied to appropriate heterogeneous data found in public databases. This facilitates subsequent extraction of various datasets for mining. In particular and for specific ligand descriptors, it allows transforming a multiple-instance problem into a single-instance one. In a second step, mining algorithms are applied to the datasets and finally the most accurate knowledge units are eventually proposed as new filters. We report here this KDD approach and the experimental results we obtained with a set of ligands of the hormone receptor LXR.