Text mining and protein annotations: the construction and use of protein description sentences. Export

@article{citeulike:1325327, abstract = {Existing biological knowledge stored as structured database records has been extracted manually by database curators analyzing the scientific literature. Most of this information was derived from sentences which describe biologically relevant aspects of genes and gene products. We introduce the Protein description sentence (Prodisen) corpus, a useful resource for the automatic identification and construction of text-based protein and gene description records using information extraction and text classification techniques. Basic guidelines and criteria relevant for the construction of a text corpus of functional descriptions of genes and proteins are proposed. The steps used for the corpus construction and its features are presented. Moreover, some of the potential applications of the Prodisen corpus for biomedical text mining purposes are explored and the obtained results are presented.}, address = {Dep. Struct. Comp. Biology Spanish National Cancer Centre (CNIO), Melchor Fern\'{a}ndez Almagro, 3, E-28029 Madrid, Spain. mkrallinger@cnio.es}, author = {Krallinger, M. and Malik, R. and Valencia, A.}, citeulike-article-id = {1325327}, citeulike-linkout-0 = {http://view.ncbi.nlm.nih.gov/pubmed/17503385}, citeulike-linkout-1 = {http://www.hubmed.org/display.cgi?uids=17503385}, issn = {0919-9454}, journal = {Genome Inform}, keywords = {protein-function, text-mining}, number = {2}, pages = {121--130}, posted-at = {2007-05-24 16:53:30}, priority = {2}, title = {Text mining and protein annotations: the construction and use of protein description sentences.}, url = {http://view.ncbi.nlm.nih.gov/pubmed/17503385}, volume = {17}, year = {2006} }

TY - JOUR ID - citeulike:1325327 L3 - citeulike-article-id:1325327 N2 - Existing biological knowledge stored as structured database records has been extracted manually by database curators analyzing the scientific literature. Most of this information was derived from sentences which describe biologically relevant aspects of genes and gene products. We introduce the Protein description sentence (Prodisen) corpus, a useful resource for the automatic identification and construction of text-based protein and gene description records using information extraction and text classification techniques. Basic guidelines and criteria relevant for the construction of a text corpus of functional descriptions of genes and proteins are proposed. The steps used for the corpus construction and its features are presented. Moreover, some of the potential applications of the Prodisen corpus for biomedical text mining purposes are explored and the obtained results are presented. IS - 2 JF - Genome Inform SN - 0919-9454 AD - Dep. Struct. Comp. Biology Spanish National Cancer Centre (CNIO), Melchor Fernández Almagro, 3, E-28029 Madrid, Spain. mkrallinger@cnio.es EP - 130 TI - Text mining and protein annotations: the construction and use of protein description sentences. VL - 17 SP - 121 KW - protein-function KW - text-mining AU - Krallinger, M AU - Malik, R AU - Valencia, A PY - 2006/// UR - http://view.ncbi.nlm.nih.gov/pubmed/17503385 ER -