This article is part of the supplement: Proceedings of the Second International Symposium on Languages in Biology and Medicine (LBM) 2007
Gene Ontology density estimation and discourse analysis for automatic GeneRiF extraction
1 University and Hospitals of Geneva, Geneva, Switzerland
2 Swiss-Prot Research Group, Swiss Institute of Bioinformatics, Geneva, Switzerland
BMC Bioinformatics 2008, 9(Suppl 3):S9 doi:10.1186/1471-2105-9-S3-S9Published: 11 April 2008
This paper describes and evaluates a sentence selection engine that extracts a GeneRiF (Gene Reference into Functions) as defined in ENTREZ-Gene based on a MEDLINE record. Inputs for this task include both a gene and a pointer to a MEDLINE reference. In the suggested approach we merge two independent sentence extraction strategies. The first proposed strategy (LASt) uses argumentative features, inspired by discourse-analysis models. The second extraction scheme (GOEx) uses an automatic text categorizer to estimate the density of Gene Ontology categories in every sentence; thus providing a full ranking of all possible candidate GeneRiFs. A combination of the two approaches is proposed, which also aims at reducing the size of the selected segment by filtering out non-content bearing rhetorical phrases.
Based on the TREC-2003 Genomics collection for GeneRiF identification, the LASt extraction strategy is already competitive (52.78%). When used in a combined approach, the extraction task clearly shows improvement, achieving a Dice score of over 57% (+10%).
Argumentative representation levels and conceptual density estimation using Gene Ontology contents appear complementary for functional annotation in proteomics.