Issue No. 03 - July-September (2010 vol. 7)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/TCBB.2010.51
Jörg Hakenberg , Arizona State University, Tempe, AZ
Robert Leaman , Arizona State University, Phoenix, AZ
Nguyen Ha Vo , Arizona State University, Tempe, AZ
Siddhartha Jonnalagadda , Arizona State University, Phoenix, AZ
Ryan Sullivan , Arizona State University, Phoenix, AZ
Christopher Miller , Arizona State University, Phoenix, AZ
Luis Tari , Hoffmann-La Roche Inc., Nutley, NJ
Chitta Baral , Arizona State University, Tempe, AZ
Graciela Gonzalez , Arizona State University, Phoenix, AZ
Proteins and their interactions govern virtually all cellular processes, such as regulation, signaling, metabolism, and structure. Most experimental findings pertaining to such interactions are discussed in research papers, which, in turn, get curated by protein interaction databases. Authors, editors, and publishers benefit from efforts to alleviate the tasks of searching for relevant papers, evidence for physical interactions, and proper identifiers for each protein involved. The BioCreative II.5 community challenge addressed these tasks in a competition-style assessment to evaluate and compare different methodologies, to make aware of the increasing accuracy of automated methods, and to guide future implementations. In this paper, we present our approaches for protein-named entity recognition, including normalization, and for extraction of protein-protein interactions from full text. Our overall goal is to identify efficient individual components, and we compare various compositions to handle a single full-text article in between 10 seconds and 2 minutes. We propose strategies to transfer document-level annotations to the sentence-level, which allows for the creation of a more fine-grained training corpus; we use this corpus to automatically derive around 5,000 patterns. We rank sentences by relevance to the task of finding novel interactions with physical evidence, using a sentence classifier built from this training corpus. Heuristics for paraphrasing sentences help to further remove unnecessary information that might interfere with patterns, such as additional adjectives, clauses, or bracketed expressions. In BioCreative II.5, we achieved an f-score of 22 percent for finding protein interactions, and 43 percent for mapping proteins to UniProt IDs; disregarding species, f-scores are 30 percent and 55 percent, respectively. On average, our best-performing setup required around 2 minutes per full text. All data and pattern sets as well as Java classes that extend third-party software are available as supplementary information (see Appendix).
Biology and genetics, text analysis, bioinformatics (genome or protein) databases.
Jörg Hakenberg, Robert Leaman, Nguyen Ha Vo, Siddhartha Jonnalagadda, Ryan Sullivan, Christopher Miller, Luis Tari, Chitta Baral, Graciela Gonzalez, "Efficient Extraction of Protein-Protein Interactions from Full-Text Articles", IEEE/ACM Transactions on Computational Biology and Bioinformatics, vol. 7, no. , pp. 481-494, July-September 2010, doi:10.1109/TCBB.2010.51