Identification of functionally related enzymes by learning-to-rank methods
- Author
- Michiel Stock (UGent) , Thomas Fober, Eyke Hüllermeier, Serghei Glinca, Gerhard Klebe, Tapio Pahikkala, Antti Airola, Bernard De Baets (UGent) and Willem Waegeman (UGent)
- Organization
- Abstract
- Enzyme sequences and structures are routinely used in the biological sciences as queries to search for functionally related enzymes in online databases. To this end, one usually departs from some notion of similarity, comparing two enzymes by looking for correspondences in their sequences, structures or surfaces. For a given query, the search operation results in a ranking of the enzymes in the database, from very similar to dissimilar enzymes, while information about the biological function of annotated database enzymes is ignored. In this work, we show that rankings of that kind can be substantially improved by applying kernel-based learning algorithms. This approach enables the detection of statistical dependencies between similarities of the active cleft and the biological function of annotated enzymes. This is in contrast to search-based approaches, which do not take annotated training data into account. Similarity measures based on the active cleft are known to outperform sequence-based or structure-based measures under certain conditions. We consider the Enzyme Commission (EC) classification hierarchy for obtaining annotated enzymes during the training phase. The results of a set of sizeable experiments indicate a consistent and significant improvement for a set of similarity measures that exploit information about small cavities in the surface of enzymes.
- Keywords
- machine learning, proteins, Bioinformatics, biochemistry, PROTEIN FUNCTION PREDICTION, SUPPORT VECTOR MACHINES, STRUCTURAL-ANALYSIS, GRAPH KERNELS, BINDING, ALIGNMENT, CLASSIFICATION, RECOGNITION, NETWORK, SITES
Downloads
-
(...).pdf
- full text
- |
- UGent only
- |
- |
- 731.25 KB
Citation
Please use this url to cite or link to this publication: http://hdl.handle.net/1854/LU-5946211
- MLA
- Stock, Michiel, et al. “Identification of Functionally Related Enzymes by Learning-to-Rank Methods.” IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS, vol. 11, no. 6, 2014, pp. 1157–69, doi:10.1109/TCBB.2014.2338308.
- APA
- Stock, M., Fober, T., Hüllermeier, E., Glinca, S., Klebe, G., Pahikkala, T., … Waegeman, W. (2014). Identification of functionally related enzymes by learning-to-rank methods. IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS, 11(6), 1157–1169. https://doi.org/10.1109/TCBB.2014.2338308
- Chicago author-date
- Stock, Michiel, Thomas Fober, Eyke Hüllermeier, Serghei Glinca, Gerhard Klebe, Tapio Pahikkala, Antti Airola, Bernard De Baets, and Willem Waegeman. 2014. “Identification of Functionally Related Enzymes by Learning-to-Rank Methods.” IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS 11 (6): 1157–69. https://doi.org/10.1109/TCBB.2014.2338308.
- Chicago author-date (all authors)
- Stock, Michiel, Thomas Fober, Eyke Hüllermeier, Serghei Glinca, Gerhard Klebe, Tapio Pahikkala, Antti Airola, Bernard De Baets, and Willem Waegeman. 2014. “Identification of Functionally Related Enzymes by Learning-to-Rank Methods.” IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS 11 (6): 1157–1169. doi:10.1109/TCBB.2014.2338308.
- Vancouver
- 1.Stock M, Fober T, Hüllermeier E, Glinca S, Klebe G, Pahikkala T, et al. Identification of functionally related enzymes by learning-to-rank methods. IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS. 2014;11(6):1157–69.
- IEEE
- [1]M. Stock et al., “Identification of functionally related enzymes by learning-to-rank methods,” IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS, vol. 11, no. 6, pp. 1157–1169, 2014.
@article{5946211,
abstract = {{Enzyme sequences and structures are routinely used in the biological sciences as queries to search for functionally related enzymes in online databases. To this end, one usually departs from some notion of similarity, comparing two enzymes by looking for correspondences in their sequences, structures or surfaces. For a given query, the search operation results in a ranking of the enzymes in the database, from very similar to dissimilar enzymes, while information about the biological function of annotated database enzymes is ignored. In this work, we show that rankings of that kind can be substantially improved by applying kernel-based learning algorithms. This approach enables the detection of statistical dependencies between similarities of the active cleft and the biological function of annotated enzymes. This is in contrast to search-based approaches, which do not take annotated training data into account. Similarity measures based on the active cleft are known to outperform sequence-based or structure-based measures under certain conditions. We consider the Enzyme Commission (EC) classification hierarchy for obtaining annotated enzymes during the training phase. The results of a set of sizeable experiments indicate a consistent and significant improvement for a set of similarity measures that exploit information about small cavities in the surface of enzymes.}},
author = {{Stock, Michiel and Fober, Thomas and Hüllermeier, Eyke and Glinca, Serghei and Klebe, Gerhard and Pahikkala, Tapio and Airola, Antti and De Baets, Bernard and Waegeman, Willem}},
issn = {{1545-5963}},
journal = {{IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS}},
keywords = {{machine learning,proteins,Bioinformatics,biochemistry,PROTEIN FUNCTION PREDICTION,SUPPORT VECTOR MACHINES,STRUCTURAL-ANALYSIS,GRAPH KERNELS,BINDING,ALIGNMENT,CLASSIFICATION,RECOGNITION,NETWORK,SITES}},
language = {{eng}},
number = {{6}},
pages = {{1157--1169}},
title = {{Identification of functionally related enzymes by learning-to-rank methods}},
url = {{http://dx.doi.org/10.1109/TCBB.2014.2338308}},
volume = {{11}},
year = {{2014}},
}
- Altmetric
- View in Altmetric
- Web of Science
- Times cited: