Title |
Performance Evaluation of Algorithms for the Classification of Metabolic 1H NMR Fingerprints
|
---|---|
Published in |
Journal of Proteome Research, November 2012
|
DOI | 10.1021/pr3009034 |
Pubmed ID | |
Authors |
Jochen Hochrein, Matthias S. Klein, Helena U. Zacharias, Juan Li, Gene Wijffels, Horst Joachim Schirra, Rainer Spang, Peter J. Oefner, Wolfram Gronwald |
Abstract |
Nontargeted metabolite fingerprinting is increasingly applied to biomedical classification. The choice of classification algorithm may have a considerable impact on outcome. In this study, employing nested cross-validation for assessing predictive performance, six binary classification algorithms in combination with different strategies for data-driven feature selection were systematically compared on five data sets of urine, serum, plasma, and milk one-dimensional fingerprints obtained by proton nuclear magnetic resonance (NMR) spectroscopy. Support Vector Machines and Random Forests combined with t-score-based feature filtering performed well on most data sets, whereas the performance of the other tested methods varied between data sets. |
X Demographics
Geographical breakdown
Country | Count | As % |
---|---|---|
United States | 1 | 100% |
Demographic breakdown
Type | Count | As % |
---|---|---|
Scientists | 1 | 100% |
Mendeley readers
Geographical breakdown
Country | Count | As % |
---|---|---|
Cuba | 1 | 2% |
Colombia | 1 | 2% |
Germany | 1 | 2% |
Unknown | 48 | 94% |
Demographic breakdown
Readers by professional status | Count | As % |
---|---|---|
Researcher | 15 | 29% |
Student > Ph. D. Student | 8 | 16% |
Student > Master | 5 | 10% |
Student > Doctoral Student | 5 | 10% |
Student > Postgraduate | 4 | 8% |
Other | 8 | 16% |
Unknown | 6 | 12% |
Readers by discipline | Count | As % |
---|---|---|
Chemistry | 14 | 27% |
Medicine and Dentistry | 9 | 18% |
Agricultural and Biological Sciences | 8 | 16% |
Biochemistry, Genetics and Molecular Biology | 4 | 8% |
Computer Science | 3 | 6% |
Other | 7 | 14% |
Unknown | 6 | 12% |