Email updates

Keep up to date with the latest news and content from BMC Bioinformatics and BioMed Central.

Open Access Highly Accessed Methodology article

A text-mining system for extracting metabolic reactions from full-text articles

Jan Czarnecki1, Irene Nobeli1, Adrian M Smith2 and Adrian J Shepherd1*

Author Affiliations

1 Department of Biological Sciences and Institute of Molecular and Structural Biology, Birkbeck, University of London, Malet Street, London, WC1E 7HX, UK

2 Unilever R&D, Colworth Science Park, Sharnbrook, Bedfordshire, MK44 1LG, UK

For all author emails, please log on.

BMC Bioinformatics 2012, 13:172  doi:10.1186/1471-2105-13-172

Published: 23 July 2012

Additional files

Additional file 1:

ReactionExtractor. An example Java program, provided as a runnable .jar file, implementing the algorithm described in the paper. The program takes a plain text file as input and outputs all predicted reactions from the input text. Running instructions are included in the archive. The open source tools described in the paper (BANNER, OSCAR3 and OpenNLP) are all included in the archive.

Format: ZIP Size: 11.9MB Download file

Open Data

Additional file 2:

SupplementaryMaterial. An archive containing a detailed, worked example of the algorithm and the reconstructions of the tetrahydrofolate biosynthesis pathway and the fatty acid β-oxidation I pathway, together with a set of example sentences annotated with the putative entities and relationships extracted by our system.

Format: ZIP Size: 524KB Download file

Open Data