Automatic Extraction of Protein Interaction in Literature

TL;DR

This paper presents an SVM-based method for extracting directional protein-protein interactions from biomedical literature, emphasizing the importance of dependency features and interaction words for accurate extraction and direction determination.

Contribution

It introduces a novel SVM-based approach utilizing dependency and interaction word features for extracting and determining the direction of protein-protein interactions from text.

Findings

Dependency features significantly improve extraction accuracy.

Interaction word features are effective for direction judgment.

Good results achieved on the LLL05 corpus.

Abstract

Protein-protein interaction extraction is the key precondition of the construction of protein knowledge network, and it is very important for the research in the biomedicine. This paper extracted directional protein-protein interaction from the biological text, using the SVM-based method. Experiments were evaluated on the LLL05 corpus with good results. The results show that dependency features are import for the protein-protein interaction extraction and features related to the interaction word are effective for the interaction direction judgment. At last, we analyzed the effects of different features and planed for the next step.