[In silico drug discovery based on the integration of bioinformatics and chemoinformatics]

With the near completion of the human genome sequencing, bioinformatics and chemoinformatics are expected as promising tools in genome-based drug discovery. The emerging field of chemical genomics is accumulating large-scale assay data on compound-protein interactions. We are now developing new mining methods for the chemical genomics data based on the integration of bioinformatics and chemoinformatics. Here we present a GPCR-ligand database (GLIDA) and a novel in silico screening method, which we have developed. GLIDA is a novel public GPCR-related chemical genomics database that is primarily focused on the correlation of information between GPCRs and their ligands. Our in silico screening method is based on statistical machine learning of the conserved patterns of molecular recognition extracted from comprehensive compound-protein interaction data. These are promising approaches to accelerating drug discovery processes.