iProLINK: an integrated protein resource for literature mining. Export

@article{citeulike:563697, abstract = {The exponential growth of large-scale molecular sequence data and of the PubMed scientific literature has prompted active research in biological literature mining and information extraction to facilitate genome/proteome annotation and improve the quality of biological databases. Motivated by the promise of text mining methodologies, but at the same time, the lack of adequate curated data for training and benchmarking, the Protein Information Resource (PIR) has developed a resource for protein literature mining--iProLINK (integrated Protein Literature INformation and Knowledge). As PIR focuses its effort on the curation of the UniProt protein sequence database, the goal of iProLINK is to provide curated data sources that can be utilized for text mining research in the areas of bibliography mapping, annotation extraction, protein named entity recognition, and protein ontology development. The data sources for bibliography mapping and annotation extraction include mapped citations (PubMed ID to protein entry and feature line mapping) and annotation-tagged literature corpora. The latter includes several hundred abstracts and full-text articles tagged with experimentally validated post-translational modifications (PTMs) annotated in the PIR protein sequence database. The data sources for entity recognition and ontology development include a protein name dictionary, word token dictionaries, protein name-tagged literature corpora along with tagging guidelines, as well as a protein ontology based on PIRSF protein family names. iProLINK is freely accessible at http://pir.georgetown.edu/iprolink, with hypertext links for all downloadable files.}, address = {Georgetown University Medical Center, 3900 Reservoir Road, NW, Washington, DC 20057, USA.}, author = {Hu, Z. Z. and Mani, I. and Hermoso, V. and Liu, H. and Wu, C. H.}, citeulike-article-id = {563697}, citeulike-linkout-0 = {http://dx.doi.org/10.1016/j.compbiolchem.2004.09.010}, citeulike-linkout-1 = {http://view.ncbi.nlm.nih.gov/pubmed/15556482}, citeulike-linkout-2 = {http://www.hubmed.org/display.cgi?uids=15556482}, doi = {10.1016/j.compbiolchem.2004.09.010}, issn = {1476-9271}, journal = {Comput Biol Chem}, keywords = {database}, month = {December}, number = {5-6}, pages = {409--416}, posted-at = {2007-12-28 19:10:40}, priority = {0}, title = {iProLINK: an integrated protein resource for literature mining.}, url = {http://dx.doi.org/10.1016/j.compbiolchem.2004.09.010}, volume = {28}, year = {2004} }

TY - JOUR ID - citeulike:563697 L3 - citeulike-article-id:563697 N2 - The exponential growth of large-scale molecular sequence data and of the PubMed scientific literature has prompted active research in biological literature mining and information extraction to facilitate genome/proteome annotation and improve the quality of biological databases. Motivated by the promise of text mining methodologies, but at the same time, the lack of adequate curated data for training and benchmarking, the Protein Information Resource (PIR) has developed a resource for protein literature mining--iProLINK (integrated Protein Literature INformation and Knowledge). As PIR focuses its effort on the curation of the UniProt protein sequence database, the goal of iProLINK is to provide curated data sources that can be utilized for text mining research in the areas of bibliography mapping, annotation extraction, protein named entity recognition, and protein ontology development. The data sources for bibliography mapping and annotation extraction include mapped citations (PubMed ID to protein entry and feature line mapping) and annotation-tagged literature corpora. The latter includes several hundred abstracts and full-text articles tagged with experimentally validated post-translational modifications (PTMs) annotated in the PIR protein sequence database. The data sources for entity recognition and ontology development include a protein name dictionary, word token dictionaries, protein name-tagged literature corpora along with tagging guidelines, as well as a protein ontology based on PIRSF protein family names. iProLINK is freely accessible at http://pir.georgetown.edu/iprolink, with hypertext links for all downloadable files. IS - 5-6 JF - Comput Biol Chem SN - 1476-9271 AD - Georgetown University Medical Center, 3900 Reservoir Road, NW, Washington, DC 20057, USA. EP - 416 TI - iProLINK: an integrated protein resource for literature mining. VL - 28 SP - 409 KW - database AU - Hu, ZZ AU - Mani, I AU - Hermoso, V AU - Liu, H AU - Wu, CH PY - 2004/12// UR - http://dx.doi.org/10.1016/j.compbiolchem.2004.09.010 ER -