
Comprehensive and empirical evaluation of machine learning algorithms for small molecule LC retention time prediction
- Author
- Robbin Bouwmeester (UGent) , Lennart Martens (UGent) and Sven Degroeve (UGent)
- Organization
- Abstract
- Liquid chromatography is a core component of almost all mass spectrometric analyses of (bio)molecules. Because of the high-throughput nature of mass spectrometric analyses, the interpretation of these chromatographic data increasingly relies on informatics solutions that attempt to predict an analyte's retention time. The key components of such predictive algorithms are the features these are supplies with, and the actual machine learning algorithm used to fit the model parameters. Therefore, we have evaluated the performance of seven machine learning algorithms on 36 distinct metabolomics data sets, using two distinct feature sets. Interestingly, the results show that no single learning algorithm performs optimally for all data sets, with different types of algorithms achieving top performance for different types of analytes or different protocols. Our results thus show that an evaluation of machine learning algorithms for retention time prediction is needed to find a suitable algorithm for specific analytes or protocols. Importantly, however, our results also show that blending different types of models together decreases the error on outliers, indicating that the combination of several approaches holds substantial promise for the development of more generic, high-performing algorithms.
- Keywords
- Analytical Chemistry
Downloads
-
(...).pdf
- full text (Published version)
- |
- UGent only
- |
- |
- 2.69 MB
-
259168.full.pdf
- full text (Author's original)
- |
- open access
- |
- |
- 546.03 KB
Citation
Please use this url to cite or link to this publication: http://hdl.handle.net/1854/LU-8598878
- MLA
- Bouwmeester, Robbin, et al. “Comprehensive and Empirical Evaluation of Machine Learning Algorithms for Small Molecule LC Retention Time Prediction.” ANALYTICAL CHEMISTRY, vol. 91, no. 5, 2019, pp. 6394–3703.
- APA
- Bouwmeester, R., Martens, L., & Degroeve, S. (2019). Comprehensive and empirical evaluation of machine learning algorithms for small molecule LC retention time prediction. ANALYTICAL CHEMISTRY, 91(5), 6394–3703.
- Chicago author-date
- Bouwmeester, Robbin, Lennart Martens, and Sven Degroeve. 2019. “Comprehensive and Empirical Evaluation of Machine Learning Algorithms for Small Molecule LC Retention Time Prediction.” ANALYTICAL CHEMISTRY 91 (5): 6394–3703.
- Chicago author-date (all authors)
- Bouwmeester, Robbin, Lennart Martens, and Sven Degroeve. 2019. “Comprehensive and Empirical Evaluation of Machine Learning Algorithms for Small Molecule LC Retention Time Prediction.” ANALYTICAL CHEMISTRY 91 (5): 6394–3703.
- Vancouver
- 1.Bouwmeester R, Martens L, Degroeve S. Comprehensive and empirical evaluation of machine learning algorithms for small molecule LC retention time prediction. ANALYTICAL CHEMISTRY. 2019;91(5):6394–3703.
- IEEE
- [1]R. Bouwmeester, L. Martens, and S. Degroeve, “Comprehensive and empirical evaluation of machine learning algorithms for small molecule LC retention time prediction,” ANALYTICAL CHEMISTRY, vol. 91, no. 5, pp. 6394–3703, 2019.
@article{8598878, abstract = {Liquid chromatography is a core component of almost all mass spectrometric analyses of (bio)molecules. Because of the high-throughput nature of mass spectrometric analyses, the interpretation of these chromatographic data increasingly relies on informatics solutions that attempt to predict an analyte's retention time. The key components of such predictive algorithms are the features these are supplies with, and the actual machine learning algorithm used to fit the model parameters. Therefore, we have evaluated the performance of seven machine learning algorithms on 36 distinct metabolomics data sets, using two distinct feature sets. Interestingly, the results show that no single learning algorithm performs optimally for all data sets, with different types of algorithms achieving top performance for different types of analytes or different protocols. Our results thus show that an evaluation of machine learning algorithms for retention time prediction is needed to find a suitable algorithm for specific analytes or protocols. Importantly, however, our results also show that blending different types of models together decreases the error on outliers, indicating that the combination of several approaches holds substantial promise for the development of more generic, high-performing algorithms.}, author = {Bouwmeester, Robbin and Martens, Lennart and Degroeve, Sven}, issn = {0003-2700}, journal = {ANALYTICAL CHEMISTRY}, keywords = {Analytical Chemistry}, language = {eng}, number = {5}, pages = {6394--3703}, title = {Comprehensive and empirical evaluation of machine learning algorithms for small molecule LC retention time prediction}, url = {http://dx.doi.org/10.1021/acs.analchem.8b05820}, volume = {91}, year = {2019}, }
- Altmetric
- View in Altmetric
- Web of Science
- Times cited: