Biobibliometrics: information retrieval and visualization from co-occurrences of gene names in Medline abstracts. Export

@article{citeulike:2937823, abstract = {Successful information retrieval from biomedical literature databases is becoming increasingly difficult. We have developed a prototype system for retrieving and visualizing information from literature and genomic databases using gene names. The premise of our work is that, if two genes have a related biological function, the co-occurrence of two gene names (or aliases of those genes) within the biomedical literature is more likely. From a collection of Medline documents, we have extracted the number of co-occurrences of every pair of Saccharomyces cerevisiae genes. The query is automatically conflated to include gene aliases as well. In addition, the retrieved document set can be filtered by the user with a MeSH term. From this co-occurrence data we construct a matrix that contains dissimilarity measurements of every pair of genes, based on their joint and individual occurrence statistics. A graph is generated from this matrix, with node and edge inclusion being determined by a user-defined threshold. Nodes of the graph represent genes, while edge lengths are a function of the occurrence of the two genes within the literature. Nodes can be hypertext-linked to sequence databases, while edges are linked to those Medline documents that generated them. The system is a tool for efficiently exploring the biomedical information landscape and may act as a inference network.}, address = {Kentucky Center for Structural Biology, University of Kentucky, Lexington 40536-0298, USA.}, author = {Stapley, B. J. and Benoit, G.}, citeulike-article-id = {2937823}, citeulike-linkout-0 = {http://view.ncbi.nlm.nih.gov/pubmed/10902200}, citeulike-linkout-1 = {http://www.hubmed.org/display.cgi?uids=10902200}, issn = {1793-5091}, journal = {Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing}, keywords = {co-occurnace, information, information-extraction, information-retrieval, medline, pubmed, text-mining}, pages = {529--540}, posted-at = {2008-10-09 15:50:55}, priority = {2}, title = {Biobibliometrics: information retrieval and visualization from co-occurrences of gene names in Medline abstracts.}, url = {http://view.ncbi.nlm.nih.gov/pubmed/10902200}, year = {2000} }

TY - JOUR ID - citeulike:2937823 L3 - citeulike-article-id:2937823 N2 - Successful information retrieval from biomedical literature databases is becoming increasingly difficult. We have developed a prototype system for retrieving and visualizing information from literature and genomic databases using gene names. The premise of our work is that, if two genes have a related biological function, the co-occurrence of two gene names (or aliases of those genes) within the biomedical literature is more likely. From a collection of Medline documents, we have extracted the number of co-occurrences of every pair of Saccharomyces cerevisiae genes. The query is automatically conflated to include gene aliases as well. In addition, the retrieved document set can be filtered by the user with a MeSH term. From this co-occurrence data we construct a matrix that contains dissimilarity measurements of every pair of genes, based on their joint and individual occurrence statistics. A graph is generated from this matrix, with node and edge inclusion being determined by a user-defined threshold. Nodes of the graph represent genes, while edge lengths are a function of the occurrence of the two genes within the literature. Nodes can be hypertext-linked to sequence databases, while edges are linked to those Medline documents that generated them. The system is a tool for efficiently exploring the biomedical information landscape and may act as a inference network. JF - Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing SN - 1793-5091 AD - Kentucky Center for Structural Biology, University of Kentucky, Lexington 40536-0298, USA. EP - 540 TI - Biobibliometrics: information retrieval and visualization from co-occurrences of gene names in Medline abstracts. SP - 529 KW - co-occurnace KW - information KW - information-extraction KW - information-retrieval KW - medline KW - pubmed KW - text-mining AU - Stapley, BJ AU - Benoit, G PY - 2000/// UR - http://view.ncbi.nlm.nih.gov/pubmed/10902200 ER -