E M Marcotte1, I Xenarios, D Eisenberg. 1. Molecular Biology Institute, UCLA-DOE Laboratory of Structural Biology & Molecular Medicine, University of California at Los Angeles, PO Box 951570, Los Angeles, CA 90095-1570, USA.
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, approximately 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.
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, approximately 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.
Authors: I Xenarios; E Fernandez; L Salwinski; X J Duan; M J Thompson; E M Marcotte; D Eisenberg Journal: Nucleic Acids Res Date: 2001-01-01 Impact factor: 16.971
Authors: Joseph C Mellor; Itai Yanai; Karl H Clodfelter; Julian Mintseris; Charles DeLisi Journal: Nucleic Acids Res Date: 2002-01-01 Impact factor: 16.971
Authors: Ulas Karaoz; T M Murali; Stan Letovsky; Yu Zheng; Chunming Ding; Charles R Cantor; Simon Kasif Journal: Proc Natl Acad Sci U S A Date: 2004-02-23 Impact factor: 11.205