A new data mining approach for profiling and categorizing kinetic patterns of metabolic biomarkers after myocardial injury

MOTIVATION The discovery of new and unexpected biomarkers in cardiovascular disease is a highly data-driven process that requires the complementary power of modern metabolite profiling technologies, bioinformatics and biostatistics. Clinical biomarkers of early myocardial injury are lacking. A prospective biomarker cohort study was carried out to identify, categorize and profile kinetic patterns of early metabolic biomarkers of planned myocardial infarction (PMI) and spontaneous (SMI) myocardial infarction. We applied a targeted mass spectrometry (MS)-based metabolite profiling platform to serial blood samples drawn from carefully phenotyped patients undergoing alcohol septal ablation for hypertrophic obstructive cardiomyopathy serving as a human model of PMI. Patients with SMI and patients undergoing catheterization without induction of myocardial infarction served as positive and negative controls to assess generalizability of markers identified in PMI. RESULTS To identify metabolites of high predictive value in tandem mass spectrometry data, we introduced a new feature selection method for the categorization of metabolic signatures into three classes of weak, moderate and strong predictors, which can be easily applied to both paired and unpaired samples. Our paradigm outperformed standard null-hypothesis significance testing and other popular methods for feature selection in terms of the area under the receiver operating curve and the product of sensitivity and specificity. Our results emphasize that this new method was able to identify, classify and validate alterations of levels in multiple metabolites participating in pathways associated with myocardial injury as early as 10 min after PMI. AVAILABILITY The algorithm as well as supplementary material is available for download at: www.umit.at/page.cfm?vpath=departments/technik/iebe/tools/bi

[1]  R. Kloner,et al.  Inosine: A Protective Agent in an Organ Culture Model of Myocardial Ischemia , 1982, Circulation research.

[2]  K. Nithipatikom,et al.  Simultaneous determination of adenosine, inosine, hypoxanthine, xanthine, and uric acid in microdialysis samples using microbore column high-performance liquid chromatography with a diode array detector. , 1996, Analytical biochemistry.

[3]  Pedro Larrañaga,et al.  A review of feature selection techniques in bioinformatics , 2007, Bioinform..

[4]  Yvan Saeys,et al.  Robust Feature Selection Using Ensemble Feature Selection Techniques , 2008, ECML/PKDD.

[5]  F. Ginsberg.  Timing of Immunoreactive B-Type Natriuretic Peptide Levels and Treatment Delay in Acute Decompensated Heart Failure: An ADHERE (Acute Decompensated Heart Failure National Registry) Analysis , 2009 .

[6]  Bernhard Pfeifer,et al.  A new rule-based algorithm for identifying metabolic markers in prostate cancer using tandem mass spectrometry , 2008, Bioinform..

[7]  Nello Cristianini,et al.  An Introduction to Support Vector Machines and Other Kernel-based Learning Methods , 2000 .

[8]  J. Howie-Esquivel,et al.  Biomarkers in Acute Cardiovascular Disease , 2008, The Journal of cardiovascular nursing.

[9]  Frederick P Roth,et al.  Metabolomic Identification of Novel Biomarkers of Myocardial Ischemia , 2005, Circulation.

[10]  Thomas J. Wang,et al.  The search for new cardiovascular biomarkers , 2008, Nature.

[11]  Maguelonne Teisseire,et al.  Successes and New Directions in Data Mining , 2007 .

[12]  B. Hammock,et al.  Mass spectrometry-based metabolomics. , 2007, Mass spectrometry reviews.

[13]  Vladimir Shulaev,et al.  Metabolomics technology and bioinformatics , 2006, Briefings Bioinform..

[14]  D. Özmen,et al.  Urinary hypoxanthine and xanthine levels in acute coronary syndromes , 1999, International journal of clinical & laboratory research.

[15]  Christian Baumgartner,et al.  Biomarker Discovery, Disease Classification, and Similarity Query Processing on High-Throughput MS/MS Data of Inborn Errors of Metabolism , 2006, Journal of biomolecular screening.

[16]  John E Hale,et al.  The role of mass spectrometry in biomarker discovery and measurement. , 2006, Current drug metabolism.

[17]  Tobias Bäckström,et al.  Cardiac outflow of amino acids and purines during myocardial ischemia and reperfusion. , 2003, Journal of applied physiology.

[18]  P. Collinson,et al.  Biomarkers of cardiovascular damage and dysfunction--an overview. , 2007, Heart, lung & circulation.

[19]  M. Verani,et al.  Echocardiography-guided ethanol septal reduction for hypertrophic obstructive cardiomyopathy. , 1998, Circulation.

[20]  Geoff Holmes,et al.  Benchmarking Attribute Selection Techniques for Discrete Class Data Mining , 2003, IEEE Trans. Knowl. Data Eng..

[21]  J. Zimmerman,et al.  Diagnostic marker cooperative study for the diagnosis of myocardial infarction. , 1999, Circulation.

[22]  Christian Baumgartner,et al.  Data Mining and Knowledge Discovery in Metabolomics Armin , 2008 .

[23]  Marko Grobelnik,et al.  Proceedings of the European Conference on Machine Learning and Knowledge Discovery in Databases: Part II , 2009 .

[24]  Bernhard Pfeifer,et al.  A new ensemble-based algorithm for identifying breath gas marker candidates in liver disease using ion molecule reaction mass spectrometry , 2009, Bioinform..

[25]  Christian Baumgartner,et al.  Metabolite profiling of blood from individuals undergoing planned myocardial infarction reveals early markers of myocardial injury. , 2008, The Journal of clinical investigation.

[26]  David W. Hosmer,et al.  Applied Logistic Regression , 1991 .

[27]  R. Gerszten,et al.  Application of metabolomics to cardiovascular biomarker and pathway discovery. , 2008, Journal of the American College of Cardiology.

[28]  Yuan-Qing Xia,et al.  LC-MS Development strategies for quantitative bioanalysis. , 2006, Current drug metabolism.

[29]  Douglas B Kell,et al.  Metabolomic biomarkers: search, discovery and validation , 2007, Expert review of molecular diagnostics.

[30]  LarrañagaPedro,et al.  A review of feature selection techniques in bioinformatics , 2007 .

[31]  Tom Fawcett,et al.  An introduction to ROC analysis , 2006, Pattern Recognit. Lett..

[32]  Concha Bielza,et al.  Machine Learning in Bioinformatics , 2008, Encyclopedia of Database Systems.