1 H NMR based metabolic profiling in Crohn’s disease by random forest methodology Fariba Fathi, a Laleh Majari-Kasmaee, a Ahmad Mani-Varnosfaderani, b Anahita Kyani, c† Mohammad Rostami-Nejad, d Kaveh Sohrabzadeh, e†† Nosratollah Naderi, d Mohammad Reza Zali, d Mostafa Rezaei-Tavirani, f††† Mohsen Tafazzoli a * and Afsaneh Arefi-Oskouie f * The present study was designed to search for metabolic biomarkers and their correlation with serum zinc in Crohn’s disease patients. Crohn’s disease (CD) is a form of inflammatory bowel disease that may affect any part of the gastrointestinal tract and can be difficult to diagnose using the clinical tests. Thus, introduction of a novel diagnostic method would be a major step towards CD treatment. Proton nuclear magnetic resonance spectroscopy ( 1 H NMR) was employed for metabolic profiling to find out which metab- olites in the serum have meaningful significance in the diagnosis of CD. CD and healthy subjects were correctly classified using random forest methodology. The classification model for the external test set showed a 94% correct classification of CD and healthy subjects. The present study suggests Valine and Isoleucine as differentiating metabolites for CD diagnosis. These metabolites can be used for screening of risky samples at the early stages of CD diagnoses. Moreover, a robust random forest regression model with good prediction outcomes was developed for correlating serum zinc level and metabolite concentrations. The regression model showed the correlation (R 2 ) and root mean square error values of 0.83 and 6.44, respectively. This model suggests valuable clues for understanding the mechanism of zinc deficiency in CD patients. Copyright © 2014 John Wiley & Sons, Ltd. Keywords: nuclear magnetic resonance spectroscopy; metabonomics; zinc; Crohn’s disease; random forest Introduction Crohn’s disease (CD) is one of the two major subtypes of inflam- matory bowel disease (IBD) that cause chronic inflammation of the intestinal tract. [1–3] While the pathophysiology of IBD is not fully understood, it has been widely accepted that multiple com- ponents, including environmental factors, diet, smoking habits, hormone levels, drug usage, and genetics contribute to the occurrence and perpetuation of this disease. Although the prevalence and incidence of IBD are stabilizing in high-incidence areas such as northern Europe and North America, in low-incidence areas such as southern Europe, Asia, and the developing world, they continue to rise. [4] Crohn’s disease often mimics other symptoms, hence correct identification of CD in some cases may be complicated. [5] To reach the correct diagnosis, clinical tests including endoscopic, histological, and radiologic techniques are applied. These methods can be time consuming and costly. With respect to these problems, metabonomics is an important technique for identification of biomarkers for early diseases detection. [6] Metabonomics is defined as ‘the quantitative measurement of the dynamic multi-parametric response of living systems to path- ophysiological stimuli or genetic modification’. [7] If biological variations in the target group are meaningfully different from those in the control group, quantitative analysis of metabolite can provide important results. [8] Proton nuclear magnetic resonance spectroscopy ( 1 H NMR) is one of the most commonly applied techniques to obtain vital information from complex and unprocessed biological samples. It provides quantitative and reproducible information with little * Correspondence to: Mohsen Tafazzoli, Department of Chemistry, Sharif University of Technology, P.O. Box 11155-9516, Tehran, Iran. E-mail: tafazzoli@sharif.edu ** Correspondence to: Afsaneh Arefi Oskouie, Department of Basic Science Faculty of Paramedical Sciences, Shahid Beheshti University of Medical Sciences, P.O. Box: 19395-4618.Tehran, Iran. E-mail: a_arefioskouie@yahoo.com † Present address: Department of Medicinal Chemistry, College of Pharmacy and Translational Oncology Program, University of Michigan, Ann Arbor, MI †† Present address: Department of Electrical Engineer, Payam Nonprofit Higher Education Institution, Golpayegan, Iran ††† Present address: Proteomics Research Center, Facultyof Paramedical Sciences, Shahid Beheshti University of Medical Sciences, Tehran, Iran a Department of Chemistry, Sharif University of Technology, Tehran, Iran b Department of Chemistry, Faculty of Sciences, Tarbiat Modares University, Tehran, Iran c Institute of Biochemistry and Biophysics, University of Tehran, Tehran, Iran d Gastroenterology and Liver Disease Research Center, Shahid Beheshti University of Medical Sciences, Tehran, Iran e Department of Electrical Engineer, Golpayegan Payam University, Tehran, Iran f Department of Basic Science Faculty of Paramedical, Shahid Beheshti University of Medical Sciences, Tehran, Iran Magn. Reson. Chem. 2014, 52, 370–376 Copyright © 2014 John Wiley & Sons, Ltd. Research article Received: 26 September 2013 Revised: 14 February 2014 Accepted: 20 March 2014 Published online in Wiley Online Library: 22 April 2014 (wileyonlinelibrary.com) DOI 10.1002/mrc.4074 370