PolySearch: a web-based text mining system for extracting relationships between human diseases, genes, mutations, drugs and metabolites

@article{citeulike:2805405, abstract = {A particular challenge in biomedical text mining is to find ways of handling comprehensive' or associative' queries such as Find all genes associated with breast cancer'. Given that many queries in genomics, proteomics or metabolomics involve these kind of comprehensive searches we believe that a web-based tool that could support these searches would be quite useful. In response to this need, we have developed the PolySearch web server. PolySearch supports >50 different classes of queries against nearly a dozen different types of text, scientific abstract or bioinformatic databases. The typical query supported by PolySearch is Given X, find all Y's' where X or Y can be diseases, tissues, cell compartments, gene/protein names, SNPs, mutations, drugs and metabolites. PolySearch also exploits a variety of techniques in text mining and information retrieval to identify, highlight and rank informative abstracts, paragraphs or sentences. PolySearch's performance has been assessed in tasks such as gene synonym identification, protein-protein interaction identification and disease gene identification using a variety of manually assembled gold standard' text corpuses. Its f-measure on these tasks is 88, 81 and 79\%, respectively. These values are between 5 and 50\% better than other published tools. The server is freely available at http://wishart.biology.ualberta.ca/polysearch 10.1093/nar/gkn296}, author = {Cheng, Dean and Knox, Craig and Young, Nelson and Stothard, Paul and Damaraju, Sambasivarao and Wishart, David S. }, citeulike-article-id = {2805405}, doi = {10.1093/nar/gkn296}, journal = {Nucl. Acids Res.}, keywords = {pubmed, text\_mining}, month = {May}, pages = {gkn296+}, posted-at = {2008-05-16 15:44:44}, priority = {2}, title = {PolySearch: a web-based text mining system for extracting relationships between human diseases, genes, mutations, drugs and metabolites}, url = {http://dx.doi.org/10.1093/nar/gkn296}, year = {2008} }

TY - JOUR ID - citeulike:2805405 L3 - citeulike-article-id:2805405 TI - PolySearch: a web-based text mining system for extracting relationships between human diseases, genes, mutations, drugs and metabolites JF - Nucl. Acids Res. SP - gkn296 N2 - A particular challenge in biomedical text mining is to find ways of handling comprehensive' or associative' queries such as Find all genes associated with breast cancer'. Given that many queries in genomics, proteomics or metabolomics involve these kind of comprehensive searches we believe that a web-based tool that could support these searches would be quite useful. In response to this need, we have developed the PolySearch web server. PolySearch supports >50 different classes of queries against nearly a dozen different types of text, scientific abstract or bioinformatic databases. The typical query supported by PolySearch is Given X, find all Y's' where X or Y can be diseases, tissues, cell compartments, gene/protein names, SNPs, mutations, drugs and metabolites. PolySearch also exploits a variety of techniques in text mining and information retrieval to identify, highlight and rank informative abstracts, paragraphs or sentences. PolySearch's performance has been assessed in tasks such as gene synonym identification, protein-protein interaction identification and disease gene identification using a variety of manually assembled gold standard' text corpuses. Its f-measure on these tasks is 88, 81 and 79%, respectively. These values are between 5 and 50% better than other published tools. The server is freely available at http://wishart.biology.ualberta.ca/polysearch 10.1093/nar/gkn296 KW - pubmed KW - text_mining AU - Cheng, Dean AU - Knox, Craig AU - Young, Nelson AU - Stothard, Paul AU - Damaraju, Sambasivarao AU - Wishart, David PY - 2008/05/16/ UR - http://dx.doi.org/10.1093/nar/gkn296 ER -