Abstract
Machine learning is a powerful tool for simulating the quantitative structure activity relationship in drug discovery (QSAR). However, descriptor selection and model optimization remain two of most challenging tasks for domain experts to construct high-quality QSAR model. Therefore, we propose a QSAR-special automated machine learning method incorporating Automated Descriptor Selection with Automated Model Building (ADSMB) to efficiently and automatically build high-quality QSAR model. Automated Descriptor Selection provides a QSAR-special molecular descriptor selection mechanism to automatically obtain the descriptors without unique value, redundancy and low importance in QSAR dataset. Based on these QSAR-special descriptors, Automated Model Building constructs high-quality ensemble model of molecular descriptors and target activities under Bayesian optimization through Auto-Sklearn. Finally, we conduct experimental evaluation for our proposed method on Mutagenicity dataset. The results show ADSMB can obtain better and stable performance than the competing methods.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Peter, S.C., Dhanjal, J.K., Malik, V., et al.: Quantitative Structure-Activity Relationship (QSAR), Modeling Approaches to Biological Applications (2019)
Ma, J., Sheridan, R.P., Liaw, A., et al.: Deep neural nets as a method for quantitative structure-activity relationships. J. Chem. Inf. Model. 55(2), 263–274 (2015)
Zhang, L., Tan, J., Han, D., et al.: From machine learning to deep learning: progress in machine intelligence for rational drug discovery. Drug Discovery Today 22(11), 1680–1685 (2017)
Lavecchia, A.: Machine-learning approaches in drug discovery: methods and applications. Drug Discovery Today 20(3), 318–331 (2015)
Poorinmohammad, N., Mohabatkar, H., Behbahani, M., et al.: Computational prediction of anti HIV-1 peptides and in vitro evaluation of anti HIV-1 activity of HIV-1 P24-derived peptides. J. Pept. Sci. 21(1), 10–16 (2015)
Jain, N., Gupta, S., Sapre, N., et al.: In silico de novo design of novel NNRTIs: a bio-molecular modelling approach. RSC Adv. 5(19), 14814–14827 (2015)
Gupta, S., Basant, N., Singh, K.P.: Estimating sensory irritation potency of volatile organic chemicals using QSARs based on decision tree methods for regulatory purpose. Ecotoxicology 24(4), 873–886 (2015). https://doi.org/10.1007/s10646-015-1431-y
Kumari, P., Nath, A., Chaube, R.: Identification of human drug targets using machine-learning algorithms. Comput. Biol. Med. 56, 175–181 (2015)
Weidlich, I.E., Filippov, I.V., Brown, J., et al.: Inhibitors for the hepatitis C virus RNA polymerase explored by SAR with advanced machine learning methods. Bioorg. Med. Chem. 21(11), 3127–3 137 (2013)
Liu, Y., Yin, Y., Teng, Z., Wu, Q., Li, G.: Activities prediction of drug molecules by using the optimal ensemble based on uniform design. In: Huang, D.-S., Wunsch, D.C., Levine, D.S., Jo, K.-H. (eds.) ICIC 2008. LNCS, vol. 5226, pp. 106–113. Springer, Heidelberg (2008). https://doi.org/10.1007/978-3-540-87442-3_15
Yao, Q., Wang, M., Chen, Y., et al.: Taking human out of learning applications: a survey on automated machine learning. arXiv preprint arXiv:1810.13306 (2018)
Katz, G., Shin, E.C.R., Song, D.: ExploreKit: automatic descriptor generation and selection. In: 16th International Conference on Data Mining, pp. 979–984. IEEE (2016)
Klein, A., Falkner, S., Bartels, S., et al.: Fast Bayesian optimization of machine learning hyperparameters on large datasets. In: Artificial Intelligence and Statistics, pp. 528–536 (2017)
Feurer, M., Klein, A., Eggensperger, K., et al.: Efficient and robust automated machine learning. In: Advances in Neural Information Processing Systems, pp. 2962–2970 (2015)
Olson, R.S., Urbanowicz, R.J., Andrews, P.C., Lavender, N.A., Kidd, L.C., Moore, J.H.: Automating biomedical data science through tree-based pipeline optimization. In: Squillero, G., Burelli, P. (eds.) EvoApplications 2016, Part I. LNCS, vol. 9597, pp. 123–137. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-31204-0_9
Zoph, B., Le, Q.V.: Neural architecture search with reinforcement learning. arXiv preprint arXiv:1611.01578 (2016)
Liu, Y., Wu, J., Avdeev, M., Shi, S.: Multi-layer descriptor selection incorporating weighted score-based expert knowledge toward modelling materials with targeted properties. Adv. Theory Simul. 3(2), 1900215 (2020)
Acknowledgement
This work is supported by the National Key Research and Development Plan of China (Grant No.2016YFB1000600 and 2016YFB1000601) and the State Key Program of National Nature Science Foundation of China (Grant No. 61936001).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Liu, Y., Tian, W., Zhang, H. (2021). Activities Prediction of Drug Molecules by Using Automated Model Building with Descriptor Selection. In: Gao, W., et al. Intelligent Computing and Block Chain. FICC 2020. Communications in Computer and Information Science, vol 1385. Springer, Singapore. https://doi.org/10.1007/978-981-16-1160-5_7
Download citation
DOI: https://doi.org/10.1007/978-981-16-1160-5_7
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-1159-9
Online ISBN: 978-981-16-1160-5
eBook Packages: Computer ScienceComputer Science (R0)