TOPICAL CLUSTERING OF BIOMEDICAL ABSTRACT by SELF ORGANIZING MAPS Fattore

One of the major challenges in the post-genomic era is the speed up of the process of identification of molecules involved in a specific disease (molecular targets). Even if the experimental procedure have greatly enhanced the analytical capability, the textual data analysis still play a central role in the experimental activity design or in the data collection. The extraction of useful information from published papers is still strongly dependent by the human expertise in the selection and retrieval of relevant papers. The search of abstract in MEDLINE or PubMed databases, is a common activity for researcher. Often the navigation in textual databases is not simple and in many case the user can retrieve only list of abstracts without any kind of additional information about the relatedness of the abstract content with the submitted query.. In the last decade the applications without any kind of additional information about the relatedness of the abstract content with the submitted query.. In the last decade the application of Natural language processing tools has acquired some relevance in bioinformatic field. The possibility to retrieve and organize the textual information, according specific topics, allows the user to select and analyse only a reduced set of papers. In our work we present the a application of document clustering system, founded on Self-Organizing Maps, to reorganize in a hierarchical way the cluster of abstracts retrieved by PubMed query. The system is available at the following site http://www.biocomp.ge.ismac.cnr.it.