Predicting protein--protein interactions from primary structure.

@article{citeulike:616663, abstract = {MOTIVATION: An ambitious goal of proteomics is to elucidate the structure, interactions and functions of all proteins within cells and organisms. The expectation is that this will provide a fuller appreciation of cellular processes and networks at the protein level, ultimately leading to a better understanding of disease mechanisms and suggesting new means for intervention. This paper addresses the question: can protein-protein interactions be predicted directly from primary structure and associated data? Using a diverse database of known protein interactions, a Support Vector Machine (SVM) learning system was trained to recognize and predict interactions based solely on primary structure and associated physicochemical properties. RESULTS: Inductive accuracy of the trained system, defined here as the percentage of correct protein interaction predictions for previously unseen test sets, averaged 80\% for the ensemble of statistical experiments. Future proteomics studies may benefit from this research by proceeding directly from the automated identification of a cell's gene products to prediction of protein interaction pairs.}, address = {Department of Bioengineering, 9500 Gilman Drive, University of California, San Diego, La Jolla, CA 92093-0412, USA.}, author = {Bock, J. R. and Gough, D. A. }, citeulike-article-id = {616663}, doi = {http://dx.doi.org/10.1093/bioinformatics/17.5.455}, issn = {1367-4803}, journal = {Bioinformatics}, keywords = {ppi, prediction}, month = {May}, number = {5}, pages = {455--460}, posted-at = {2007-10-16 09:22:52}, priority = {5}, title = {Predicting protein--protein interactions from primary structure.}, url = {http://dx.doi.org/10.1093/bioinformatics/17.5.455}, volume = {17}, year = {2001} }

TY - JOUR ID - citeulike:616663 L3 - citeulike-article-id:616663 TI - Predicting protein--protein interactions from primary structure. JF - Bioinformatics VL - 17 IS - 5 SP - 455 EP - 460 AD - Department of Bioengineering, 9500 Gilman Drive, University of California, San Diego, La Jolla, CA 92093-0412, USA. SN - 1367-4803 N2 - MOTIVATION: An ambitious goal of proteomics is to elucidate the structure, interactions and functions of all proteins within cells and organisms. The expectation is that this will provide a fuller appreciation of cellular processes and networks at the protein level, ultimately leading to a better understanding of disease mechanisms and suggesting new means for intervention. This paper addresses the question: can protein-protein interactions be predicted directly from primary structure and associated data? Using a diverse database of known protein interactions, a Support Vector Machine (SVM) learning system was trained to recognize and predict interactions based solely on primary structure and associated physicochemical properties. RESULTS: Inductive accuracy of the trained system, defined here as the percentage of correct protein interaction predictions for previously unseen test sets, averaged 80% for the ensemble of statistical experiments. Future proteomics studies may benefit from this research by proceeding directly from the automated identification of a cell's gene products to prediction of protein interaction pairs. KW - ppi KW - prediction AU - Bock, JR AU - Gough, DA PY - 2001/05// UR - http://dx.doi.org/10.1093/bioinformatics/17.5.455 ER -