Abstract
Virtual screening (VS) is widely used during computational drug discovery to reduce costs. Chemogenomics-based virtual screening (CGBVS) can be used to predict new compound-protein interactions (CPIs) from known CPI network data using several methods, including machine learning and data mining. Although CGBVS facilitates highly efficient and accurate CPI prediction, it has poor performance for prediction of new compounds for which CPIs are unknown. The pairwise kernel method (PKM) is a state-of-the-art CGBVS method and shows high accuracy for prediction of new compounds. In this study, on the basis of link mining, we improved the PKM by combining link indicator kernel (LIK) and chemical similarity and evaluated the accuracy of these methods. The proposed method obtained an average area under the precision-recall curve (AUPR) value of 0.562, which was higher than that achieved by the conventional Gaussian interaction profile (GIP) method (0.425), and the calculation time was only increased by a few percent.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
Let \( k:X \times X \to {\mathbb{R}} \) be a positive definite kernel and \( f:X \to {\mathbb{R}} \) be an arbitrary function. Then, the kernel \( k^{{\prime }} ({\mathbf{x}},{\mathbf{y}}) = f({\mathbf{x}})k({\mathbf{x}},{\mathbf{y}})f({\mathbf{y}})\;\;({\mathbf{x}},{\mathbf{y}} \in X) \) is also positive definite.
References
Lavecchia, A.: Machine-learning approaches in drug discovery: methods and applications. Drug Discov. Today. 20, 318–331 (2015)
Drwal, M.N., Griffith, R.: Combination of ligand- and structure-based methods in virtual screening. Drug Discov. Today Technol. 10, e395–e401 (2013)
Ding, H., Takigawa, I., Mamitsuka, H., Zhu, S.: Similarity-based machine learning methods for predicting drug-target interactions: a brief review. Brief. Bioinform. 15, 734–747 (2014)
Yamanishi, Y., Araki, M., Gutteridge, A., Honda, W., Kanehisa, M.: Prediction of drug-target interaction networks from the integration of chemical and genomic spaces. Bioinformatics 24, i232–i240 (2008)
van Laarhoven, T., Nabuurs, S.B., Marchiori, E.: Gaussian interaction profile kernels for predicting drug-target interaction. Bioinformatics 27, 3036–3043 (2011)
van Laarhoven, T., Marchiori, E.: Predicting drug-target interactions for new drug compounds using a weighted nearest neighbor profile. PLoS ONE 8, e66952 (2013)
Jacob, L., Vert, J.P.: Protein-ligand interaction prediction: an improved chemogenomics approach. Bioinformatics 24, 2149–2156 (2008)
Daminelli, S., Thomas, J.M., Duran, C., Cannistraci, C.V.: Common neighbours and the local-community-paradigm for topological link prediction in bipartite net-works. New J. Phys. 17, 113037 (2015)
Duran, C., Daminelli, S., Thomas, J.M., Haupt, V.J., Schroeder, M., Cannistraci, C.V.: Pioneering topological methods for network-based drug-target prediction by exploiting a brain-network self-organization theory. Brief Bioinform. (2017) [Epub ahead of print]
Rogers, D., Hahn, M.: Extended-connectivity fingerprints. J. Chem. Inf. Model. 50, 742–754 (2010)
Smith, T.F., Waterman, M.S.: Identification of common molecular subsequences. J. Mol. Biol. 147, 195–197 (1981)
Hattori, M., Okuno, Y., Goto, S., Kanehisa, M.: Development of a chemical structure comparison method for integrated analysis of chemical and genomic information in the metabolic pathways. J. Am. Chem. Soc. 125, 11853–11865 (2003)
Bouchard, M., Jousselme, A.-L., Doré, P.-E.: A proof for the positive definiteness of the Jaccard index matrix. Int. J. Approx. Reason. 54, 615–626 (2013)
scikit-learn: machine learning in Python. http://scikit-learn.org/stable/. Accessed 27 March 2017
Chang, C.-C., Lin, C.: LIBSVM: A library for support vector machines. ACM Trans. Intell. Syst. Technol. 2, 1–27 (2011)
NetworkX-High-productivity software for complex networks. https://networkx.github.io/. Accessed 27 March 2017
Gonen, M.: Predicting drug-target interactions from chemical and genomic kernels using Bayesian matrix factorization. Bioinformatics 28, 2304–2310 (2012)
Nascimento, A.C.A., Prudêncio, R.B.C., Costa, I.G.: A multiple kernel learning algorithm for drug-target interaction prediction. BMC Bioinformatics 17, 46 (2016)
Liu, Y., Wu, M., Miao, C., Zhao, P., Li, X.L.: Neighborhood regularized logistic matrix factorization for drug-target interaction prediction. PLoS Comput. Biol. 12, e1004760 (2016)
Acknowledgments
This work was partially supported by the Japan Society for the Promotion of Science (JSPS) KAKENHI (grant numbers 24240044 and 15K16081), and Core Research for Evolutional Science and Technology (CREST) “Extreme Big Data” (grant number JPMJCR1303) from the Japan Science and Technology Agency (JST).
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Ohue, M., Yamazaki, T., Ban, T., Akiyama, Y. (2017). Link Mining for Kernel-Based Compound-Protein Interaction Predictions Using a Chemogenomics Approach. In: Huang, DS., Jo, KH., Figueroa-García, J. (eds) Intelligent Computing Theories and Application. ICIC 2017. Lecture Notes in Computer Science(), vol 10362. Springer, Cham. https://doi.org/10.1007/978-3-319-63312-1_48
Download citation
DOI: https://doi.org/10.1007/978-3-319-63312-1_48
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-63311-4
Online ISBN: 978-3-319-63312-1
eBook Packages: Computer ScienceComputer Science (R0)