Conserved network motifs allow protein-protein interaction prediction Export

@article{citeulike:63215, abstract = {Motivation: High-throughput protein interaction detection methods are strongly affected by false positive and false negative results. Focused experiments are needed to complement the large-scale methods by validating previously detected interactions but it is often difficult to decide which proteins to probe as interaction partners. Developing reliable computational methods assisting this decision process is a pressing need in bioinformatics. Results: We show that we can use the conserved properties of the protein network to identify and validate interaction candidates. We apply a number of machine learning algorithms to the protein connectivity information and achieve a surprisingly good overall performance in predicting interacting proteins. Using a leave-one-out' approach we find average success rates between 20 and 40\% for predicting the correct interaction partner of a protein. We demonstrate that the success of these methods is based on the presence of conserved interaction motifs within the network. Availability: A reference implementation and a table with candidate interacting partners for each yeast protein are available at http://www.protsuggest.org. 10.1093/bioinformatics/bth402}, author = {Albert, Istvan and Albert, Reka}, citeulike-article-id = {63215}, citeulike-linkout-0 = {http://dx.doi.org/10.1093/bioinformatics/bth402}, citeulike-linkout-1 = {http://bioinformatics.oxfordjournals.org/content/20/18/3346.abstract}, citeulike-linkout-2 = {http://bioinformatics.oxfordjournals.org/content/20/18/3346.full.pdf}, citeulike-linkout-3 = {http://bioinformatics.oxfordjournals.org/cgi/content/abstract/20/18/3346}, citeulike-linkout-4 = {http://www.ingentaconnect.com/content/oup/cabios/2004/00000020/00000018/art03346}, citeulike-linkout-5 = {http://view.ncbi.nlm.nih.gov/pubmed/15247093}, citeulike-linkout-6 = {http://www.hubmed.org/display.cgi?uids=15247093}, day = {12}, doi = {10.1093/bioinformatics/bth402}, issn = {1367-4803}, journal = {Bioinformatics}, keywords = {biology, dynamics, genetic, microbiology, motif, network, prediction}, month = {December}, number = {18}, pages = {3346--3352}, posted-at = {2009-11-02 21:55:18}, priority = {2}, publisher = {Oxford University Press}, title = {Conserved network motifs allow protein-protein interaction prediction}, url = {http://dx.doi.org/10.1093/bioinformatics/bth402}, volume = {20}, year = {2004} }

TY - JOUR ID - citeulike:63215 L3 - citeulike-article-id:63215 N2 - Motivation: High-throughput protein interaction detection methods are strongly affected by false positive and false negative results. Focused experiments are needed to complement the large-scale methods by validating previously detected interactions but it is often difficult to decide which proteins to probe as interaction partners. Developing reliable computational methods assisting this decision process is a pressing need in bioinformatics. Results: We show that we can use the conserved properties of the protein network to identify and validate interaction candidates. We apply a number of machine learning algorithms to the protein connectivity information and achieve a surprisingly good overall performance in predicting interacting proteins. Using a leave-one-out' approach we find average success rates between 20 and 40% for predicting the correct interaction partner of a protein. We demonstrate that the success of these methods is based on the presence of conserved interaction motifs within the network. Availability: A reference implementation and a table with candidate interacting partners for each yeast protein are available at http://www.protsuggest.org. 10.1093/bioinformatics/bth402 IS - 18 JF - Bioinformatics SN - 1367-4803 EP - 3352 TI - Conserved network motifs allow protein-protein interaction prediction PB - Oxford University Press VL - 20 SP - 3346 KW - biology KW - dynamics KW - genetic KW - microbiology KW - motif KW - network KW - prediction AU - Albert, Istvan AU - Albert, Reka PY - 2004/12/12/ UR - http://dx.doi.org/10.1093/bioinformatics/bth402 ER -