? Since the introduction of the Mycin system more than 25 years ago, it has widely been hypothesized that extensive, well-represented computer knowledge-bases will facilitate a wide variety of scientific and clinical tasks. Driven by growing knowledge-management challenges arising from the proliferation of high throughput instrumentation, recently created knowledge-bases in areas related to genomics and related aspects of contemporary biology, such as the Gene Ontology, EcoCyc and PharmGKB, have begun to become integrated into the laboratory practices of a growing number of molecular biologists. However, these successful molecular biology knowledge-bases (MBKBs) have two drawbacks which impede their more general application: each has been narrowed to a particular special purpose, either in its domain of applicability or in the scope of knowledge represented, and each of these knowledge-bases was constructed largely on the basis of enormous human effort. Given the current state of molecular biology data and recent advances in database integration and information extraction technology, we proposed to test the following hypothesis: Current computational technology and existing human-curated knowledge resources are sufficient to build an extensive, high-quality computational knowledge-base of molecular biology. To test this hypothesis we propose to first create tools which can (a) automatically link incommensurate knowledge sources using semantic linking, and (b) use natural language processing techniques to extract new information from NCBrs GeneRIFs and from the GO definitions fields; and second, to evaluate the results of these methods by carefully quantifying the degree to which the induced linkages and extracted assertions are complete, consistent and correct. Although we propose to construct a broad and rich knowledge-base in order to develop and test the adequacy of largely automated methods to leverage existing human-curated collections, we do not propose to build a comprehensive MBKB. ? ? ?

Agency
National Institute of Health (NIH)
Institute
National Library of Medicine (NLM)
Type
Research Project (R01)
Project #
5R01LM008111-03
Application #
7123058
Study Section
Biomedical Library and Informatics Review Committee (BLR)
Program Officer
Ye, Jane
Project Start
2004-09-30
Project End
2008-08-05
Budget Start
2006-09-28
Budget End
2008-08-05
Support Year
3
Fiscal Year
2006
Total Cost
$611,872
Indirect Cost
Name
University of Colorado Denver
Department
Pharmacology
Type
Schools of Medicine
DUNS #
041096314
City
Aurora
State
CO
Country
United States
Zip Code
80045
Boguslav, Mayla; Cohen, K Bretonnel; Baumgartner, William A et al. (2018) Improving precision in concept normalization. Pac Symp Biocomput 23:566-577
Cohen, K Bretonnel; Xia, Jingbo; Zweigenbaum, Pierre et al. (2018) Three Dimensions of Reproducibility in Natural Language Processing. LREC Int Conf Lang Resour Eval 2018:156-165
Callahan, Tiffany J; Baumgartner, William A; Bada, Michael et al. (2018) OWL-NETS: Transforming OWL Representations for Improved Network Inference. Pac Symp Biocomput 23:133-144
Cohen, K Bretonnel; Lanfranchi, Arrick; Choi, Miji Joo-Young et al. (2017) Coreference annotation and resolution in the Colorado Richly Annotated Full Text (CRAFT) corpus of biomedical journal articles. BMC Bioinformatics 18:372
Kao, David P; Stevens, Laura M; Hinterberg, Michael A et al. (2017) Phenotype-Specific Association of Single-Nucleotide Polymorphisms with Heart Failure and Preserved Ejection Fraction: a Genome-Wide Association Analysis of the Cardiovascular Health Study. J Cardiovasc Transl Res 10:285-294
Hunter, Lawrence E (2017) Knowledge-based biomedical Data Science. EPJ Data Sci 1:19-25
Greene, Casey S; Garmire, Lana X; Gilbert, Jack A et al. (2017) Celebrating parasites. Nat Genet 49:483-484
Hooper, Joan E; Feng, Weiguo; Li, Hong et al. (2017) Systems biology of facial development: contributions of ectoderm and mesenchyme. Dev Biol 426:97-114
Oellrich, Anika; Collier, Nigel; Groza, Tudor et al. (2016) The digital revolution in phenotyping. Brief Bioinform 17:819-30
Cohen, K Bretonnel; Fort, Karën; Adda, Gilles et al. (2016) Ethical Issues in Corpus Linguistics And Annotation: Pay Per Hit Does Not Affect Effective Hourly Rate For Linguistic Resource Development On Amazon Mechanical Turk. LREC Int Conf Lang Resour Eval 2016:8-12

Showing the most recent 10 out of 91 publications