Next Article in Journal
Amino Acid Biosynthesis Pathways in Diatoms
Next Article in Special Issue
A Novel Methodology to Estimate Metabolic Flux Distributions in Constraint-Based Models
Previous Article in Journal
Getting Your Peaks in Line: A Review of Alignment Methods for NMR Spectral Data
Previous Article in Special Issue
Knowledge Discovery in Spectral Data by Means of Complex Networks
Open AccessArticle

Peak Detection Method Evaluation for Ion Mobility Spectrometry by Using Machine Learning Approaches

Computational Systems Biology Group, Max Planck Institute for Informatics, Saarbrücken, Germany
Cluster of Excellence for Multimodal Computing and Interaction. Saarland University,Saarbrücken, Germany
Computer Science XI and Collaborative Research Center SFB 876, TU Dortmund, Germany
Analytik, BioMedizinZentrum Dortmund, Germany
Genome Informatics, Human Genetics, Faculty of Medicine, University of Duisburg-Essen,Essen, Germany
Computational Biology Group, Department of Mathematics and Computer Science, University of Southern Denmark, Odense, Denmark
Author to whom correspondence should be addressed.
Metabolites 2013, 3(2), 277-293;
Received: 25 January 2013 / Revised: 15 March 2013 / Accepted: 9 April 2013 / Published: 16 April 2013
(This article belongs to the Special Issue Data Processing in Metabolomics)
Ion mobility spectrometry with pre-separation by multi-capillary columns (MCC/IMS) has become an established inexpensive, non-invasive bioanalytics technology for detecting volatile organic compounds (VOCs) with various metabolomics applications in medical research. To pave the way for this technology towards daily usage in medical practice, different steps still have to be taken. With respect to modern biomarker research, one of the most important tasks is the automatic classification of patient-specific data sets into different groups, healthy or not, for instance. Although sophisticated machine learning methods exist, an inevitable preprocessing step is reliable and robust peak detection without manual intervention. In this work we evaluate four state-of-the-art approaches for automated IMS-based peak detection: local maxima search, watershed transformation with IPHEx, region-merging with VisualNow, and peak model estimation (PME).We manually generated Metabolites 2013, 3 278 a gold standard with the aid of a domain expert (manual) and compare the performance of the four peak calling methods with respect to two distinct criteria. We first utilize established machine learning methods and systematically study their classification performance based on the four peak detectors’ results. Second, we investigate the classification variance and robustness regarding perturbation and overfitting. Our main finding is that the power of the classification accuracy is almost equally good for all methods, the manually created gold standard as well as the four automatic peak finding methods. In addition, we note that all tools, manual and automatic, are similarly robust against perturbations. However, the classification performance is more robust against overfitting when using the PME as peak calling preprocessor. In summary, we conclude that all methods, though small differences exist, are largely reliable and enable a wide spectrum of real-world biomedical applications. View Full-Text
Keywords: mcc/ims; peak detection; machine learning; ion mobility spectrometry; spectrum analysis mcc/ims; peak detection; machine learning; ion mobility spectrometry; spectrum analysis
Show Figures

Figure 1

MDPI and ACS Style

Hauschild, A.-C.; Kopczynski, D.; D'Addario, M.; Baumbach, J.I.; Rahmann, S.; Baumbach, J. Peak Detection Method Evaluation for Ion Mobility Spectrometry by Using Machine Learning Approaches. Metabolites 2013, 3, 277-293.

Show more citation formats Show less citations formats

Article Access Map by Country/Region

Only visits after 24 November 2015 are recorded.
Search more from Scilit
Back to TopTop