%0 Journal Article %1 citeulike:3367555 %A Krallinger, Martin %A Valencia, Alfonso %A Hirschman, Lynette %D 2008 %J Genome biology %K CAT CAT-REV-IE CAT-REV-IR CAT-REV-TM genes literature mining %N Suppl 2 %P S8+ %R 10.1186/gb-2008-9-s2-s8 %T Linking genes to literature: text mining, information extraction, and retrieval applications for biology. %U http://dx.doi.org/10.1186/gb-2008-9-s2-s8 %V 9 Suppl 2 %X Efficient access to information contained in online scientific literature collections is essential for life science research, playing a crucial role from the initial stage of experiment planning to the final interpretation and communication of the results. The biological literature also constitutes the main information source for manual literature curation used by expert-curated databases. Following the increasing popularity of web-based applications for analyzing biological data, new text-mining and information extraction strategies are being implemented. These systems exploit existing regularities in natural language to extract biologically relevant information from electronic texts automatically. The aim of the BioCreative challenge is to promote the development of such tools and to provide insight into their performance. This review presents a general introduction to the main characteristics and applications of currently available text-mining systems for life sciences in terms of the following: the type of biological information demands being addressed; the level of information granularity of both user queries and results; and the features and methods commonly exploited by these applications. The current trend in biomedical text mining points toward an increasing diversification in terms of application types and techniques, together with integration of domain-specific resources such as ontologies. Additional descriptions of some of the systems discussed here are available on the internet http://zope.bioinfo.cnio.es/bionlp\_tools/.

@article{citeulike:3367555, abstract = {Efficient access to information contained in online scientific literature collections is essential for life science research, playing a crucial role from the initial stage of experiment planning to the final interpretation and communication of the results. The biological literature also constitutes the main information source for manual literature curation used by expert-curated databases. Following the increasing popularity of web-based applications for analyzing biological data, new text-mining and information extraction strategies are being implemented. These systems exploit existing regularities in natural language to extract biologically relevant information from electronic texts automatically. The aim of the BioCreative challenge is to promote the development of such tools and to provide insight into their performance. This review presents a general introduction to the main characteristics and applications of currently available text-mining systems for life sciences in terms of the following: the type of biological information demands being addressed; the level of information granularity of both user queries and results; and the features and methods commonly exploited by these applications. The current trend in biomedical text mining points toward an increasing diversification in terms of application types and techniques, together with integration of domain-specific resources such as ontologies. Additional descriptions of some of the systems discussed here are available on the internet http://zope.bioinfo.cnio.es/bionlp\_tools/.}, added-at = {2010-06-16T08:03:34.000+0200}, author = {Krallinger, Martin and Valencia, Alfonso and Hirschman, Lynette}, biburl = {https://www.bibsonomy.org/bibtex/2bc5d8d6901d934648f38e7daad35a0ac/huiyangsfsu}, citeulike-article-id = {3367555}, citeulike-linkout-0 = {http://dx.doi.org/10.1186/gb-2008-9-s2-s8}, citeulike-linkout-1 = {http://view.ncbi.nlm.nih.gov/pubmed/18834499}, citeulike-linkout-2 = {http://www.hubmed.org/display.cgi?uids=18834499}, doi = {10.1186/gb-2008-9-s2-s8}, interhash = {58be5d360e77c9b382f02a074e0acb37}, intrahash = {bc5d8d6901d934648f38e7daad35a0ac}, issn = {1465-6914}, journal = {Genome biology}, keywords = {CAT CAT-REV-IE CAT-REV-IR CAT-REV-TM genes literature mining}, number = {Suppl 2}, pages = {S8+}, posted-at = {2010-04-23 05:34:09}, priority = {2}, timestamp = {2010-11-12T04:42:30.000+0100}, title = {Linking genes to literature: text mining, information extraction, and retrieval applications for biology.}, url = {http://dx.doi.org/10.1186/gb-2008-9-s2-s8}, volume = {9 Suppl 2}, year = 2008 }