Education, Science, Technology, Innovation and Life
Open Access
Sign In

Polarized Surface Area and Oil-Water Partition Coefficient Predicted through the Machine Learning Based on Deepchem

Download as PDF

DOI: 10.23977/acss.2021.050204 | Downloads: 9 | Views: 197

Author(s)

Jin Li 1

Affiliation(s)

1 Sichuan Normal University, Chengdu, Sichuan 610101, China

Corresponding Author

Jin Li

ABSTRACT

Accurate prediction of the chemical information of compounds played a vital role in the discovery of drug-like properties. The Polarized surface area (PSA) and oil-water partition coefficient (AlogP) of drug-like compounds properties were predicted based on DeepChem. By comparing the four models (Random Forest, Deep Neural Network, Convolutional Neural Network, Graphic Convolution), it is shown that CNN has 94% accuracy in PSA, DNN has 81% accuracy in AlogP. DeepChem can easily build a platform for molecular machine learning to predict specific characteristic attributes by selecting data sets, which may provide the possibility for drug prediction.

KEYWORDS

Machine learning, Polarized surface area, Oil-water partition coefficient, Deepchem, Drug-like

CITE THIS PAPER

Jin Li, Polarized Surface Area and Oil-Water Partition Coefficient Predicted through the Machine Learning Based on Deepchem. Advances in Computer, Signals and Systems (2021) Vol. 5: 14-21. DOI: http://dx.doi.org/10.23977/acss.2021.050204.

REFERENCES

[1] Deep-learning models for Drug Discovery and Quantum Chemistry. https://github. com/deepchem/deepchem, 2018 (accessed July 25, 2018).
[2] Bengio, Y., A. Courville, and P. Vincent, Representation learning: A review and new perspectives. IEEE transactions on pattern analysis and machine intelligence, 2013. 35(8): pp. 1798-1828.
[3] Gómez-Bombarelli, R., et al., Automatic chemical design using a data-driven continuous representation of molecules (2016). arXiv preprint arXiv:1610.02415.
[4] Rogers, D. and M. Hahn, Extended-connectivity fingerprints. Journal of chemical information and modeling, 2010. 50(5): pp. 742-754.
[5] Breiman, L., Random forests. Machine learning, 2001. 45(1): pp. 5-32.
[6] LeCun, Y., et al., Gradient-based learning applied to document recognition. Proceedings of the IEEE, 1998. 86(11): pp. 2278-2324.
[7] Duvenaud, D.K., et al. Convolutional networks on graphs for learning molecular fingerprints. in Advances in neural information processing systems. 2015.
[8] Ghose, A.K., V.N. Viswanadhan, and J.J. Wendoloski, A Knowledge-Based Approach in Designing Combinatorial or Medicinal Chemistry Libraries for Drug Discovery. 1. A Qualitative and Quantitative Characterization of Known Drug Databases. Journal of Combinatorial Chemistry, 1999. 1(1): pp. 55-68.
[9] Clark, D.E., Rapid calculation of polar molecular surface area and its application to the prediction of transport phenomena. 1. Prediction of intestinal absorption. Journal of pharmaceutical sciences, 1999. 88(8):pp. 807-814.
[10] Veber, D.F., et al., Molecular properties that influence the oral bioavailability of drug candidates. Journal of medicinal chemistry, 2002. 45(12): pp. 2615-2623.
[11] Martin, Y.C., A bioavailability score. Journal of medicinal chemistry, 2005. 48(9): pp. 3164-3170.

Downloads: 1359
Visits: 71175

Sponsors, Associates, and Links


All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.