A knowledge framework for computational molecular-disease relationships in cancer.

Michael N. Cantor, Yves A. Lussier

Research output: Contribution to journalArticlepeer-review

2 Scopus citations


Biomedical knowledge is growing at an exponential rate, with new discoveries being published across a range of information sources. A coded, fully-computable, and integrated approach to this information could increase the efficiency of its use, through improved retrieval as well as the eventual ability to apply decision support tools to the knowledge base. Though multiple knowledge bases (KBs) and databases (DBs) concerning gene-disease relationships exist, few present the information in a coded, easily computable form. Focusing on molecular-disease relationships in cancer (gene-disease and protein-disease), we evaluated articles in major biomedical journals, in order to develop both the framework for a knowledge model as well as evaluation criteria. We then used these criteria to evaluate major KBs, DBs, and terminologies. We discovered that although both the high-level as well as the specific molecular-disease relationships present in our test set were mapped in many of the databases, they generally were not applied together in a coded form. We propose a rationale behind a model mediated schema for the integration of these resources.

Original languageEnglish (US)
Pages (from-to)101-105
Number of pages5
JournalProceedings / AMIA ... Annual Symposium. AMIA Symposium
StatePublished - 2002

ASJC Scopus subject areas

  • General Medicine


Dive into the research topics of 'A knowledge framework for computational molecular-disease relationships in cancer.'. Together they form a unique fingerprint.

Cite this