Text Mining of Biological Resources
Hypothesis generation and exploration from biological resources; Knowledge discovery from biological resources; Literature-based discovery from biological resources
Text mining is about automatically or semiautomatically exploring hypotheses or new ideas from a set of resources. The mined hypotheses require further tests with methods native to the discipline, in this case with scientific methods in biomedicine. An overall goal in text mining is to support the intellectual activities of biomedical scientists as they explore new ideas using a collection of resources. Text mining is similar to data mining. But instead of mining a collection of well-structured data, text mining operates off semi-structured text collections. Current text mining efforts in biomedicine increasingly involve more structured data sources such as the Entrez Gene database maintained by the National Library of Medicine (NLM).
There is some diversity of opinion on the kindsof research that fall...
- 2.Database of Interacting Proteins: http://dip.doe-mbi.ucla.edu/
- 3.Entrez Gene: http://www.ncbi.nlm.nih.gov/sites/entrez?db=gene
- 4.Gene Ontology: http://www.geneontology.org/
- 9.Seki K, Mostafa J. Discovering implicit associations between genes and hereditary diseases. In: Proceedings of the 12th Pacific Symposium on Bio-computing; 2007. p. 316–27.Google Scholar