Email updates

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

This article is part of the supplement: Workshop on Advances in Bio Text Mining

Open Access Poster presentation

A fast and effective dependency graph kernel for PPI relation extraction

Domonkos Tikk12*, Peter Palaga1 and Ulf Leser1

Author Affiliations

1 Knowledge Management in Bioinformatics, Institute for Computer Science, Humboldt-Universität zu Berlin, Unter den Linden 6, 10099 Berlin, Germany

2 Department of Telecommunications and Media Informatics, Budapest University of Technology and Economics, H-1117 Budapest, Magyar Tudósok krt 2., Hungary

For all author emails, please log on.

BMC Bioinformatics 2010, 11(Suppl 5):P8  doi:10.1186/1471-2105-11-S5-P8


The electronic version of this article is the complete one and can be found online at: http://www.biomedcentral.com/1471-2105/11/S5/P8


Published:6 October 2010

© 2010 Tikk et al; licensee BioMed Central Ltd.

Background

Extraction of protein-protein interactions (PPIs) reported in scientific publications is a core topic of biomedical text mining. The ultimate goal is to devise a PPI extraction method that performs well on large amount of unseen text independently from the training corpus. One popular, machine-learning based approach to PPI extraction builds on the convolution kernels, i.e., similarity functions defined on the parse-based representation of sentences and interactions. Kernel functions differ in (1) the underlying sentence representation (bag-of-words, syntax tree parse, dependency graphs), (2) the substructures retrieved from the sentence representation to define interactions, and (3) calculation of the similarity function.

Method

We present a novel kernel method called k-band shortest path spectrum kernel (kBSPS), an extension of the spectrum tree kernel (SpT) [1]. It combines three ideas: First, interactions are represented as vertex-walks as in SpT but adapted to dependency graphs. The kBSPS kernel includes also edge labels into vertex-walks, thus also exploiting the dependency type of a relationship. Second, it uses a novel similarity function on vertex-walks permitting certain mismatches, thus allowing for linguistic variations. The tolerant matching distinguishes three types of nodes: dependency types (D), candidate entities (E), and other surface tokens (L). Mismatches / matches are scored differently depending on the type of nodes. Third, apart from the shortest path between the proteins of the candidate interaction, kBSPS also adds all nodes within distance k from this path to the vertex-walk representation.

Results

We evaluated kBSPS kernel on the 5 standard PPI benchmark corpora (AIMed, BioInfer, HPRD50, IEPA, LLL) using document-level 10-fold cross-validation (CV) and cross-learning (CL; 4-vs-1) evaluation. CV evaluation is somewhat biased, because the training and the test data have very similar corpus characteristics and machine learners tend to learn that, therefore CL evaluation, where the training and test data sets are drawn from different distributions, provides a more unbiased picture. Our results are compared with three state-of-the-art kernel approaches to PPI extraction (see Table 1).

Table 1. Comparison of kBSPS in terms of AUC, F1-measure and classification time with other state-of-the-art kernels using the CV and CL evaluation scenarios

Conclusion

We have shown that kBSPS kernel is on par with state-of-the-art kernels at the more general CL evaluation. Furthermore, its performance is more stable (drops the least from CV) than other methods. Notably, kBSPS is also much faster than any other kernel, making it applicable to very large corpora.

Acknowledgements

Domonkos Tikk was supported by the Alexander-von-Humboldt Foundation.

References

  1. Kuboyama T, Hirata K, Kashima H, Aoki-Kinoshita KF, Yasuda H: A spectrum tree kernel.

    Information and Media Technologies 2007, 2:292-299. OpenURL

  2. Giuliano C, Lavelli A, Romano L: Exploiting shallow linguistic information for relation extraction from biomedical literature. [http://acl.ldc.upenn.edu/E/E06/E06-1051.pdf] webcite

    Proc. of the 11st Conf. of the European Chapter of the Association for Computational Linguistics (EACL'06) Trento, Italy: The Association for Computer Linguistics; 2006, 401-408. OpenURL

  3. Airola A, Pyysalo S, Björne J, Pahikkala T, Ginter F, et al.: All-paths graph kernel for protein-protein interaction extraction with evaluation of cross-corpus learning.

    BMC Bioinformatics 2008, 9(Suppl 11):S2. PubMed Abstract | BioMed Central Full Text | PubMed Central Full Text OpenURL