Ontologies and Biomedical Language Processing

Lawrence Hunter, University of Colorado, Denver

The University of Colorado collaborative R01 is a focused effort to explore both the potential for, and obstacles to, the application of biomedical language processing to analyze bodies of biomedical data, and implementing tools for maintaining quality measurement and qualitycontrol of ontologies.

These explorations are grouped into two specific aims:
(1) Develop methods and tools for analysis of biomedical corpora that can be used to evaluate the congruence between ontologies and the concepts expressed in peer-reviewed publications, including using the literature to assess the completeness of an ontology, suggest missing concepts, and provide relevant literature examples for curators.
(2) Evaluate the utility of biomedical language processing tools and techniques when applied to terms and definitions of biomedical ontologies, both to enrich and interconnect orthogonal ontologies, and to provide quality assurance and quality control mechanisms.

Particularly, we propose to develop and evaluate methods for connecting terms within and across ontologies, and for implementing automated measures of ontology quality.

BioNLP is an initiative by the Center for Computational Pharmacology at the University of Colorado Denver Health Sciences Center associated with this R01. Its purpose is to create and distribute code, software, and data for applying natural language processing techniques to biomedical texts in order to analyze and maintain the quality of biomedical ontologies.