Mining literature for protein-protein interactions

@article{citeulike:771672, abstract = {Motivation: A central problem in bioinformatics is how to capture information from the vast current scientific literature in a form suitable for analysis by computer. We address the special case of information on protein-protein interactions, and show that the frequencies of words in Medline abstracts can be used to determine whether or not a given paper discusses protein-protein interactions. For those papers determined to discuss this topic, the relevant information can be captured for the Database of Interacting Proteins. Furthermore, suitable gene annotations can also be captured. Results: Our Bayesian approach scores Medline abstracts for probability of discussing the topic of interest according to the frequencies of discriminating words found in the abstract. More than 80 discriminating words (e.g. complex, interaction, two-hybrid) were determined from a training set of 260 Medline abstracts corresponding to previously validated entries in the Database of Interacting Proteins. Using these words and a log likelihood scoring function, [IMG]f1.gif" BORDER="0">2000 Medline abstracts were identified as describing interactions between yeast proteins. This approach now forms the basis for the rapid expansion of the Database of Interacting Proteins. Contact: marcotte@icmb.utexas.edu; ixenario@mbi.ucla.edu; david@mbi.ucla.edu 10.1093/bioinformatics/17.4.359}, author = {Marcotte, Edward M. and Xenarios, Ioannis and Eisenberg, David }, citeulike-article-id = {771672}, doi = {10.1093/bioinformatics/17.4.359}, journal = {Bioinformatics}, keywords = {text-mining}, month = {April}, number = {4}, pages = {359--363}, posted-at = {2008-03-19 02:53:56}, priority = {2}, title = {Mining literature for protein-protein interactions}, url = {http://dx.doi.org/10.1093/bioinformatics/17.4.359}, volume = {17}, year = {2001} }

TY - JOUR ID - citeulike:771672 L3 - citeulike-article-id:771672 TI - Mining literature for protein-protein interactions JF - Bioinformatics VL - 17 IS - 4 SP - 359 EP - 363 N2 - Motivation: A central problem in bioinformatics is how to capture information from the vast current scientific literature in a form suitable for analysis by computer. We address the special case of information on protein-protein interactions, and show that the frequencies of words in Medline abstracts can be used to determine whether or not a given paper discusses protein-protein interactions. For those papers determined to discuss this topic, the relevant information can be captured for the Database of Interacting Proteins. Furthermore, suitable gene annotations can also be captured. Results: Our Bayesian approach scores Medline abstracts for probability of discussing the topic of interest according to the frequencies of discriminating words found in the abstract. More than 80 discriminating words (e.g. complex, interaction, two-hybrid) were determined from a training set of 260 Medline abstracts corresponding to previously validated entries in the Database of Interacting Proteins. Using these words and a log likelihood scoring function, [IMG]f1.gif" BORDER="0">2000 Medline abstracts were identified as describing interactions between yeast proteins. This approach now forms the basis for the rapid expansion of the Database of Interacting Proteins. Contact: marcotte@icmb.utexas.edu; ixenario@mbi.ucla.edu; david@mbi.ucla.edu 10.1093/bioinformatics/17.4.359 KW - text-mining AU - Marcotte, Edward AU - Xenarios, Ioannis AU - Eisenberg, David PY - 2001/04/01/ UR - http://dx.doi.org/10.1093/bioinformatics/17.4.359 ER -