Supervised reconstruction of biological networks with local models Export

@article{citeulike:1485841, abstract = {Motivation: Inference and reconstruction of biological networks from heterogeneous data is currently an active research subject with several important applications in systems biology. The problem has been attacked from many different points of view with varying degrees of success. In particular, predicting new edges with a reasonable false discovery rate is highly demanded for practical applications, but remains extremely challenging due to the sparsity of the networks of interest. Results: While most previous approaches based on the partial knowledge of the network to be inferred build global models to predict new edges over the network, we introduce here a novel method which predicts whether there is an edge from a newly added vertex to each of the vertices of a known network using local models. This involves learning individually a certain subnetwork associated with each vertex of the known network, then using the discovered classification rule associated with only that vertex to predict the edge to the new vertex. Excellent experimental results are shown in the case of metabolic and protein-protein interaction network reconstruction from a variety of genomic data. Availability: An implementation of the proposed algorithm is available upon request from the authors. Contact: Jean-Philippe.Vert@ensmp.fr 10.1093/bioinformatics/btm204}, address = {Institut de Math\'{e}matiques et de Mod\'{e}lisation de Montpellier, UMR CNRS 5149, Equipe de Probabilit\'{e}s et Statistique, Universit\'{e} Montpellier II, CC 051, Place Eug\`{e}ne Bataillon, 34095 Montpellier Cedex 5 and Centre for Computational Biology, Ecole des Mines de Paris, 35 rue Saint-Honore, 77305 Fontainebleau Cedex, France.}, author = {Bleakley, Kevin and Biau, Gerard and Vert, Jean-Philippe}, citeulike-article-id = {1485841}, citeulike-linkout-0 = {http://dx.doi.org/10.1093/bioinformatics/btm204}, citeulike-linkout-1 = {http://bioinformatics.oxfordjournals.org/content/23/13/i57.abstract}, citeulike-linkout-2 = {http://bioinformatics.oxfordjournals.org/content/23/13/i57.full.pdf}, citeulike-linkout-3 = {http://view.ncbi.nlm.nih.gov/pubmed/17646345}, citeulike-linkout-4 = {http://www.hubmed.org/display.cgi?uids=17646345}, day = {1}, doi = {10.1093/bioinformatics/btm204}, issn = {1460-2059}, journal = {Bioinformatics}, keywords = {graph, machine-learning, reconstruction, supervised-machine-learning, svm, vert}, month = {July}, number = {13}, pages = {i57--65}, posted-at = {2009-11-07 22:17:42}, priority = {2}, title = {Supervised reconstruction of biological networks with local models}, url = {http://dx.doi.org/10.1093/bioinformatics/btm204}, volume = {23}, year = {2007} }

TY - JOUR ID - citeulike:1485841 L3 - citeulike-article-id:1485841 N2 - Motivation: Inference and reconstruction of biological networks from heterogeneous data is currently an active research subject with several important applications in systems biology. The problem has been attacked from many different points of view with varying degrees of success. In particular, predicting new edges with a reasonable false discovery rate is highly demanded for practical applications, but remains extremely challenging due to the sparsity of the networks of interest. Results: While most previous approaches based on the partial knowledge of the network to be inferred build global models to predict new edges over the network, we introduce here a novel method which predicts whether there is an edge from a newly added vertex to each of the vertices of a known network using local models. This involves learning individually a certain subnetwork associated with each vertex of the known network, then using the discovered classification rule associated with only that vertex to predict the edge to the new vertex. Excellent experimental results are shown in the case of metabolic and protein-protein interaction network reconstruction from a variety of genomic data. Availability: An implementation of the proposed algorithm is available upon request from the authors. Contact: Jean-Philippe.Vert@ensmp.fr 10.1093/bioinformatics/btm204 IS - 13 JF - Bioinformatics SN - 1460-2059 AD - Institut de Mathématiques et de Modélisation de Montpellier, UMR CNRS 5149, Equipe de Probabilités et Statistique, Université Montpellier II, CC 051, Place Eugène Bataillon, 34095 Montpellier Cedex 5 and Centre for Computational Biology, Ecole des Mines de Paris, 35 rue Saint-Honore, 77305 Fontainebleau Cedex, France. EP - 65 TI - Supervised reconstruction of biological networks with local models VL - 23 SP - i57 KW - graph KW - machine-learning KW - reconstruction KW - supervised-machine-learning KW - svm KW - vert AU - Bleakley, Kevin AU - Biau, Gerard AU - Vert, Jean-Philippe PY - 2007/07/01/ UR - http://dx.doi.org/10.1093/bioinformatics/btm204 ER -