gProt: Annotating Protein Interactions Using Google and Gene Ontology Export

@incollection{citeulike:2409499, abstract = {With the increasing amount of biomedical literature, there is a need for automatic extraction of information to support biomedical researchers. Due to incomplete biomedical information databases, the extraction cannot be done straightforward using dictionaries, so several approaches using contextual rules and machine learning have previously been proposed. Our work is inspired by the previous approaches, but is novel in the sense that it combines Google and Gene Ontology for annotating protein interactions. We got promising empirical results - 57.5\% terms as valid GO annotations, and 16.9\% protein names in the answers provided by our system gProt. The total error-rate was 25.6\% consisting mainly of overly general answers and syntactic errors, but also including semantic errors, other biological entities (than proteins and GO-terms) and false information sources. Keywords: Biomedical Literature Data Mining, Gene Ontology, Google API}, author = {S{\ae}tre, Rune and Tveit, Amund and Ranang, Martin T. and Steigedal, Tonje S. and Thommesen, Liv and Stunes, Kamilla and L{\ae}greid, Astrid}, citeulike-article-id = {2409499}, citeulike-linkout-0 = {http://dx.doi.org/10.1007/11553939_166}, doi = {10.1007/11553939_166}, journal = {Knowledge-Based Intelligent Information and Engineering Systems}, keywords = {bioinformatics, google, ie, relationextraction, textmining}, pages = {1195--1203}, posted-at = {2008-02-21 22:10:46}, priority = {2}, title = {gProt: Annotating Protein Interactions Using Google and Gene Ontology}, url = {http://dx.doi.org/10.1007/11553939_166}, year = {2005} }

TY - CHAP ID - citeulike:2409499 L3 - citeulike-article-id:2409499 N2 - With the increasing amount of biomedical literature, there is a need for automatic extraction of information to support biomedical researchers. Due to incomplete biomedical information databases, the extraction cannot be done straightforward using dictionaries, so several approaches using contextual rules and machine learning have previously been proposed. Our work is inspired by the previous approaches, but is novel in the sense that it combines Google and Gene Ontology for annotating protein interactions. We got promising empirical results - 57.5% terms as valid GO annotations, and 16.9% protein names in the answers provided by our system gProt. The total error-rate was 25.6% consisting mainly of overly general answers and syntactic errors, but also including semantic errors, other biological entities (than proteins and GO-terms) and false information sources. Keywords: Biomedical Literature Data Mining, Gene Ontology, Google API JF - Knowledge-Based Intelligent Information and Engineering Systems EP - 1203 TI - gProt: Annotating Protein Interactions Using Google and Gene Ontology SP - 1195 KW - bioinformatics KW - google KW - ie KW - relationextraction KW - textmining AU - Sætre, Rune AU - Tveit, Amund AU - Ranang, Martin AU - Steigedal, Tonje AU - Thommesen, Liv AU - Stunes, Kamilla AU - Lægreid, Astrid PY - 2005/// UR - http://dx.doi.org/10.1007/11553939_166 ER -