Assessment of approximate string matching in a biomedical text retrieval problem. Export

@article{citeulike:445579, abstract = {Text-based search is widely used for biomedical data mining and knowledge discovery. Character errors in literatures affect the accuracy of data mining. Methods for solving this problem are being explored. This work tests the usefulness of the Smith-Waterman algorithm with affine gap penalty as a method for biomedical literature retrieval. Names of medicinal herbs collected from herbal medicine literatures are matched with those from medicinal chemistry literatures by using this algorithm at different string identity levels (80-100\%). The optimum performance is at string identity of 88\%, at which the recall and precision are 96.9\% and 97.3\%, respectively. Our study suggests that the Smith-Waterman algorithm is useful for improving the success rate of biomedical text retrieval.}, address = {Department of Computational Science, National University of Singapore, Blk SOC1, Level 7, 3 Science Drive 2, Singapore 117543, Singapore.}, author = {Wang, J. F. and Li, Z. R. and Cai, C. Z. and Chen, Y. Z.}, citeulike-article-id = {445579}, citeulike-linkout-0 = {http://dx.doi.org/10.1016/j.compbiomed.2004.06.002}, citeulike-linkout-1 = {http://view.ncbi.nlm.nih.gov/pubmed/16124992}, citeulike-linkout-2 = {http://www.hubmed.org/display.cgi?uids=16124992}, doi = {10.1016/j.compbiomed.2004.06.002}, issn = {0010-4825}, journal = {Comput Biol Med}, keywords = {algorithmes, string-matching}, month = {October}, number = {8}, pages = {717--724}, posted-at = {2006-07-20 10:27:15}, priority = {2}, title = {Assessment of approximate string matching in a biomedical text retrieval problem.}, url = {http://dx.doi.org/10.1016/j.compbiomed.2004.06.002}, volume = {35}, year = {2005} }

TY - JOUR ID - citeulike:445579 L3 - citeulike-article-id:445579 N2 - Text-based search is widely used for biomedical data mining and knowledge discovery. Character errors in literatures affect the accuracy of data mining. Methods for solving this problem are being explored. This work tests the usefulness of the Smith-Waterman algorithm with affine gap penalty as a method for biomedical literature retrieval. Names of medicinal herbs collected from herbal medicine literatures are matched with those from medicinal chemistry literatures by using this algorithm at different string identity levels (80-100%). The optimum performance is at string identity of 88%, at which the recall and precision are 96.9% and 97.3%, respectively. Our study suggests that the Smith-Waterman algorithm is useful for improving the success rate of biomedical text retrieval. IS - 8 JF - Comput Biol Med SN - 0010-4825 AD - Department of Computational Science, National University of Singapore, Blk SOC1, Level 7, 3 Science Drive 2, Singapore 117543, Singapore. EP - 724 TI - Assessment of approximate string matching in a biomedical text retrieval problem. VL - 35 SP - 717 KW - algorithmes KW - string-matching AU - Wang, JF AU - Li, ZR AU - Cai, CZ AU - Chen, YZ PY - 2005/10// UR - http://dx.doi.org/10.1016/j.compbiomed.2004.06.002 ER -