Send to

Choose Destination
Methods Mol Biol. 2014;1159:135-45. doi: 10.1007/978-1-4939-0709-0_8.

Mining biological networks from full-text articles.

Author information

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


The study of biological networks is playing an increasingly important role in the life sciences. Many different kinds of biological system can be modelled as networks; perhaps the most important examples are protein-protein interaction (PPI) networks, metabolic pathways, gene regulatory networks, and signalling networks. Although much useful information is easily accessible in publicly databases, a lot of extra relevant data lies scattered in numerous published papers. Hence there is a pressing need for automated text-mining methods capable of extracting such information from full-text articles. Here we present practical guidelines for constructing a text-mining pipeline from existing code and software components capable of extracting PPI networks from full-text articles. This approach can be adapted to tackle other types of biological network.

[Indexed for MEDLINE]

Supplemental Content

Full text links

Icon for Springer
Loading ...
Support Center