%0 Journal Article %1 Netzer2012Networkbased %A Netzer, Michael %A Kugler, Karl G. %A Mueller, Laurin A. %A Weinberger, Klaus M. %A Graber, Armin %A Baumgartner, Christian %A Dehmer, Matthias %D 2012 %J Journal of theoretical biology %K bt3240 disease machine-learning metabolism networks %R 10.1016/j.jtbi.2012.06.003 %T A network-based feature selection approach to identify metabolic signatures in disease. %U http://dx.doi.org/10.1016/j.jtbi.2012.06.003 %X The identification and interpretation of metabolic biomarkers is a challenging task. In this context, network-based approaches have become increasingly a key technology in systems biology allowing to capture complex interactions in biological systems. In this work, we introduce a novel network-based method to identify highly predictive biomarker candidates for disease. First, we infer two different types of networks: (i) correlation networks, and (ii) a new type of network called ratio networks. Based on these networks, we introduce scores to prioritize features using topological descriptors of the vertices. To evaluate our method we use an example dataset where quantitative targeted MS/MS analysis was applied to a total of 52 blood samples from 22 persons with obesity (BMI >30) and 30 healthy controls. Using our network-based feature selection approach we identified highly discriminating metabolites for obesity (F-score >0.85, accuracy >85\%), some of which could be verified by literature. Copyright \copyright 2012 Elsevier Ltd. All rights reserved.

@article{Netzer2012Networkbased, abstract = { The identification and interpretation of metabolic biomarkers is a challenging task. In this context, network-based approaches have become increasingly a key technology in systems biology allowing to capture complex interactions in biological systems. In this work, we introduce a novel network-based method to identify highly predictive biomarker candidates for disease. First, we infer two different types of networks: (i) correlation networks, and (ii) a new type of network called ratio networks. Based on these networks, we introduce scores to prioritize features using topological descriptors of the vertices. To evaluate our method we use an example dataset where quantitative targeted {MS}/{MS} analysis was applied to a total of 52 blood samples from 22 persons with obesity ({BMI} >30) and 30 healthy controls. Using our network-based feature selection approach we identified highly discriminating metabolites for obesity (F-score >0.85, accuracy >85\%), some of which could be verified by literature. Copyright {\copyright} 2012 Elsevier Ltd. All rights reserved. }, added-at = {2018-12-02T16:09:07.000+0100}, author = {Netzer, Michael and Kugler, Karl G. and Mueller, Laurin A. and Weinberger, Klaus M. and Graber, Armin and Baumgartner, Christian and Dehmer, Matthias}, biburl = {https://www.bibsonomy.org/bibtex/2e26260c8261f3d9cb2be3ea4c670d894/karthikraman}, citeulike-article-id = {10881676}, citeulike-linkout-0 = {http://dx.doi.org/10.1016/j.jtbi.2012.06.003}, citeulike-linkout-1 = {http://view.ncbi.nlm.nih.gov/pubmed/22771628}, citeulike-linkout-2 = {http://www.hubmed.org/display.cgi?uids=22771628}, day = 3, doi = {10.1016/j.jtbi.2012.06.003}, interhash = {74d6a856f7d6a1389b1de9be256f8a4d}, intrahash = {e26260c8261f3d9cb2be3ea4c670d894}, issn = {1095-8541}, journal = {Journal of theoretical biology}, keywords = {bt3240 disease machine-learning metabolism networks}, month = jul, pmid = {22771628}, posted-at = {2012-07-13 13:44:55}, priority = {2}, timestamp = {2018-12-02T16:09:07.000+0100}, title = {A network-based feature selection approach to identify metabolic signatures in disease.}, url = {http://dx.doi.org/10.1016/j.jtbi.2012.06.003}, year = 2012 }