This article is part of the supplement: Selected proceedings of the Fifth International Workshop on Data Integration in the Life Sciences 2008 .

Proceedings

Integrating protein-protein interactions and text mining for protein function prediction

Samira Jaeger^1,2 , Sylvain Gaudan² , Ulf Leser¹ and Dietrich Rebholz-Schuhmann²

¹  Knowledge Management in Bioinformatics, Humboldt-University Berlin, Unter den Linden 6, 10099 Berlin, Germany

²  European Bioinformatics Institute, Wellcome Trust Genome Campus, Hinxton, Cambridge, CB10 1SD, UK

author email corresponding author email

BMC Bioinformatics 2008, 9(Suppl 8):S2doi:10.1186/1471-2105-9-S8-S2

Published:	22 July 2008

Abstract

Background

Functional annotation of proteins remains a challenging task. Currently the scientific literature serves as the main source for yet uncurated functional annotations, but curation work is slow and expensive. Automatic techniques that support this work are still lacking reliability. We developed a method to identify conserved protein interaction graphs and to predict missing protein functions from orthologs in these graphs. To enhance the precision of the results, we furthermore implemented a procedure that validates all predictions based on findings reported in the literature.

Results

Using this procedure, more than 80% of the GO annotations for proteins with highly conserved orthologs that are available in UniProtKb/Swiss-Prot could be verified automatically. For a subset of proteins we predicted new GO annotations that were not available in UniProtKb/Swiss-Prot. All predictions were correct (100% precision) according to the verifications from a trained curator.

Conclusion

Our method of integrating CCSs and literature mining is thus a highly reliable approach to predict GO annotations for weakly characterized proteins with orthologs.