%0 Journal Article %1 rlims-p.2005 %A Hu, Z. Z. %A Narayanaswamy, M. %A Ravikumar, K. E. %A Vijay-Shanker, K. %A Wu, C. H. %D 2005 %J Bioinformatics %K CAT CAT-DBS-phophorylation CAT-REL-NLP CAT-REL-RULE RLIMS-P proteins rule-based %P 2759-2765 %T Literature mining and database annotation of protein phosphorylation using a rule-based system %U http://bioinformatics.oxfordjournals.org/cgi/content/full/21/11/2759?view=long&pmid=15814565 %V 21 %X Motivation: A large volume of experimental data on protein phosphorylation is buried in the fast-growing PubMed literature. While of great value, such information is limited in databases owing to the laborious process of literature-based curation. Computational literature mining holds promise to facilitate database curation. Results: A rule-based system, RLIMS-P (Rule-based LIterature Mining System for Protein Phosphorylation), was used to extract protein phosphorylation information from MEDLINE abstracts. An annotation-tagged literature corpus developed at PIR was used to evaluate the system for finding phosphorylation papers and extracting phosphorylation objects (kinases, substrates and sites) from abstracts. RLIMS-P achieved a precision and recall of 91.4 and 96.4% for paper retrieval, and of 97.9 and 88.0% for extraction of substrates and sites. Coupling the high recall for paper retrieval and high precision for information extraction, RLIMS-P facilitates literature mining and database annotation of protein phosphorylation. Availability: The program is available on request from the authors. The phosphorylation patterns and datasets used in this study are available at http://pir.georgetown.edu/iprolink/

@article{rlims-p.2005, abstract = {Motivation: A large volume of experimental data on protein phosphorylation is buried in the fast-growing PubMed literature. While of great value, such information is limited in databases owing to the laborious process of literature-based curation. Computational literature mining holds promise to facilitate database curation. Results: A rule-based system, RLIMS-P (Rule-based LIterature Mining System for Protein Phosphorylation), was used to extract protein phosphorylation information from MEDLINE abstracts. An annotation-tagged literature corpus developed at PIR was used to evaluate the system for finding phosphorylation papers and extracting phosphorylation objects (kinases, substrates and sites) from abstracts. RLIMS-P achieved a precision and recall of 91.4 and 96.4% for paper retrieval, and of 97.9 and 88.0% for extraction of substrates and sites. Coupling the high recall for paper retrieval and high precision for information extraction, RLIMS-P facilitates literature mining and database annotation of protein phosphorylation. Availability: The program is available on request from the authors. The phosphorylation patterns and datasets used in this study are available at http://pir.georgetown.edu/iprolink/}, added-at = {2010-09-20T08:30:58.000+0200}, author = {Hu, Z. Z. and Narayanaswamy, M. and Ravikumar, K. E. and Vijay-Shanker, K. and Wu, C. H.}, biburl = {https://www.bibsonomy.org/bibtex/27f10d97763f333b7f0f9e8e6b8df994e/huiyangsfsu}, interhash = {fcfaa6b25bb6c4520f92b1db0838f525}, intrahash = {7f10d97763f333b7f0f9e8e6b8df994e}, journal = {Bioinformatics }, keywords = {CAT CAT-DBS-phophorylation CAT-REL-NLP CAT-REL-RULE RLIMS-P proteins rule-based}, pages = {2759-2765}, timestamp = {2010-11-12T00:56:08.000+0100}, title = {Literature mining and database annotation of protein phosphorylation using a rule-based system}, url = {http://bioinformatics.oxfordjournals.org/cgi/content/full/21/11/2759?view=long&pmid=15814565}, volume = 21, year = 2005 }