Extracting interactions between proteins from the literature

Abstract

During the last decade, biomedicine has witnessed a tremendous development. Large amounts of experimental and computational biomedical data have been generated along with new discoveries, which are accompanied by an exponential increase in the number of biomedical publications describing these discoveries. In the meantime, there has been a great interest with scientific communities in text mining tools to find knowledge such as protein-protein interactions, which is most relevant and useful for specific analysis tasks. This paper provides a outline of the various information extraction methods in biomedical domain, especially for discovery of protein-protein interactions. It surveys methodologies involved in plain texts analyzing and processing, categorizes current work in biomedical information extraction, and provides examples of these methods. Challenges in the field are also presented and possible solutions are discussed.

Combining syntactic information and domain-specific lexical patterns to extract drug-drug interactions from biomedical texts

“…Therefore, it is risky to draw conclusions on the performance of the different techniques. In general terms, the linguistic-based approaches perform well for capturing relatively simple binary relationships between entities in a sentence, but fail to extract more complex relationships expressed in various coordinate and relational clauses [30]. We believe that the performance of linguisticbased approaches is strongly influenced by the shortage of biomedical parsers.…”

“…Linguistic phenomena including negation, modality and mood, which can alter or even reverse the meaning of the sentence, have hardly ever been studied by the pattern-based approaches. Thus, pattern-based approaches are not able to correctly process anything other than short and straightforward sentences [30], which, on the other hand, are quite rare in biomedical texts.…”

SOA-Based Integration of Text Mining Services

“…The most important tasks that need to be solved are (a) recognition of gene and protein names (named entity recognition, NER), (b) recognition of functional information, and (c) recognition of the relationship between biological entities (such as protein-protein interaction or gene-gene regulation) [7]. For each of these steps, various algorithms have been proposed and implemented (see [14] or [18] for surveys). Their performance differs largely depending on the particular task at hand.…”

AutoBind: automatic extraction of protein–ligand-binding affinity data from biological literature

“…For example, 'activate' and 'interact' are two common relation terms that connect molecule entities. This technique has been applied to protein-protein interactions (Blaschke et al, 1999;Koike and Takagi , 2005;Zhou and He, 2008), pathway networks (McDonald et al, 2004) and drug interactions (Tari et al, 2010).…”