These pages describe briefly Penn's
BioTagger software suite. Currently the tagger supports three types
of entities: gene entities, genomic variations entities and malignancy
Please read the README file to learn about usage and input/output
The core of the tagger is derived from the machine learning package
These taggers are based on the work published in:
Automated recognition of malignancy mentions in biomedical literature.
Y. Jin, R. T. McDonald, K. Lerman, M. A. Mandel, S. Carroll, M. Y. Liberman, F. C. Pereira, R. S. Winters, and P. S. White
Identifying Gene and Protein Mentions in Text Using Conditional Random Fields
R. McDonald and F. Pereira
An entity tagger for recognizing acquired genomic variations in cancer literature
R. T. McDonald, R. S. Winters, M. Mandel, Y. Jin, P. S. White, and F. Pereira
3249 - 3251
Programming: Kevin Lerman, Yang Jin, Eric Pancoast and Ryan McDonald.
Research supported in part by the National Science Foundation under grant
EIA-0205448 (Mining the Bibliome).