One of the steps in any information extraction task is to identify the proper nouns. In the context of genomics, these nouns are the names of the biological entities involved in the facts to be extracted, such as genes, proteins or species.

The HELIX group, XRCE and two INRA labs (in Versailles and Ghent, in Belgium) have been involved in the BioMiRe project supported by the « Ministère chargé de la Recherche ». The objective of the BioMiRe project was to developp a software module dedicated to this identification task.