Research article
Extraction of semantic biomedical relations from text using conditional random fields
-
* Corresponding author: Mathaeus Dejori mathaeus.dejori@siemens.com
1 Institute for Computer Science, Ludwig-Maximilians-University Munich, Oettingenstr. 67, 80538 Munich, Germany
2 Siemens AG, Corporate Technology, Information and Communications, Otto-Hahn-Ring 6, 81739 Munich, Germany
3 Integrated Data Systems Department, Siemens Corporate Research, 755 College Road East, Princeton, New Jersey 08540, USA
BMC Bioinformatics 2008, 9:207 doi:10.1186/1471-2105-9-207
Published: 23 April 2008Additional files
Additional file 1:
Entrez Gene identifiers used in the gene-disease data set. This files contains a list of the 453 randomly selected Entrez Gene database entries for the creation of the gene-disease data set.
Format: CSV Size: 3KB Download file
Additional file 2:
Gene-disease data set description. This file provides further details about the gene-disease data set, its creation and the labeling procedure including annotation guidelines and inter-annotator agreement.
Format: PDF Size: 42KB Download file
This file can be viewed with: Adobe Acrobat Reader
Additional file 3:
GeneRIF gene-disease graph. The gene-disease network extracted from the latest GeneRIF version with a total of 34758 semantic associations between 4939 unique genes and 1745 unique disease entities provided as a resource description framework (RDF) graph.
Format: ZIP Size: 2.2MB Download file
Additional file 4:
Keywords of the relation specific dictionary for the gene-disease data set. List of keywords used in the relation specific dictionaries for the gene-disease data set.
Format: CSV Size: 3KB Download file
Additional file 5:
Keywords of the relation specific dictionary for the disease-treatment data set. List of keywords used in the relation specific dictionaries for the disease-treatment data set.
Format: CSV Size: 1KB Download file