The MEDLINE Mining Projects

DOWNLOAD MEDLINE MINING PROJECTS

The MEDLINE Mining Projects are a group of relations extracted automatically from Medline. The information extraction systems used to mine the relations are MutationFinder and OpenDMAP. Both applications are part of the parent project BioNLP. More information about both systems is available on thier SourceForge websites by clicking their names.

The projects available now include:

Expression in Cell Instances¹
Protein-Protein Interaction Instances^1>
Point Mutation Instances²
Transport Instances¹

¹ Please cite the following paper for use of the data:: Hunter, L, Z Lu, J Firby, WA Baumgartner, Jr., HL Johnson, PV Ogren, KB Cohen. (submitted) OpenDMAP: An open-source, ontology-driven concept analysis engine, with applications to capturing knowledge regarding protein transport, protein interactions and cell-type-specific gene expression. [pdf coming soon] <bibtex>
² Please cite the following paper for use of the data:: J. Gregory Caporaso, William A. Baumgartner Jr., David A. Randolph, K. Bretonnel Cohen, and Lawrence Hunter. (2007) MutationFinder: A high-performance system for extracting point mutation mentions from text. Bioinformatics. doi: 10.1093/bioinformatics/btm235 <pdf> <bibtex>

Check back regularly for new projects.

We are interested in your feedback about these datasets. Please direct all bug reports and comments about the contents of the corpora to BioNLP-Corpora Bug Tracker. Be sure to choose the appropriate Medline Project dataset (e.g. "Medline: Expression") from the dropdown options in the "Category" field.

Maintained by Helen L. Johnson.
This file last modified Monday, 04-May-2009 18:13:12 UTC