Predicting the Associations between Meridians and Chinese Traditional Medicine Using a Cost-Sensitive Graph Convolutional Neural Network
Abstract
:1. Introduction
2. Materials and Methods
2.1. Graph Convolutional Neural Network (GCN)
2.2. Cost-Sensitive GCN with Focal Loss Function for Imbalanced Dataset
2.3. Splitting Strategies and Evaluation Metric
3. Experiments and Results
3.1. Herb Information
3.2. The Prediction Performance Using Machine Learning and Deep Learning Approaches
3.3. The Performance of Split Methods
4. Discussion
4.1. The Effects of the Hyperparameters in the Cost-Sensitive GCN Model
4.2. The Performance of Our Approach Compared with State-of-the-Art Methods
4.3. Vascular Disease as a Case Study
5. Conclusions
Author Contributions
Funding
Acknowledgments
Conflicts of Interest
References
- Cheng, J.T. Chinese Herbal Medicine: Perspectives. In Herbal Medicines; Springer: Berlin/Heidelberg, Germany, 2016; Volume 604, pp. 225–235. [Google Scholar]
- Wang, G.J.; Ayati, M.H.; Zhang, W.B. Meridian studies in China: A systematic review. J. Acupunct. Meridian Stud. 2010, 3, 1–9. [Google Scholar] [CrossRef] [Green Version]
- Brower, V. Back to nature: Extinction of medicinal plants threatens drug discovery. J. Natl. Cancer Inst. 2008, 100, 838–839. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Longhurst, J.C. Defining Meridians: A modern basis of understanding. J. Acupunct. Meridian Stud. 2010, 3, 67–74. [Google Scholar] [CrossRef] [Green Version]
- Chon, T.Y.; Lee, M.C. Acupuncture. Mayo Clinic Proc. 2013, 88, 1141–1146. [Google Scholar] [CrossRef] [Green Version]
- Zhao, X.; Zheng, X.; Fan, T.P.; Li, Z.; Zhang, Y.; Zheng, J. A novel drug discovery strategy inspired by traditional medicine philosophies. Science 2015, 347, S38–S40. [Google Scholar]
- Gu, S.; Pei, J. Innovating Chinese Herbal Medicine: From Traditional Health Practice to Scientific Drug Discovery. Front. Pharmacol. 2017, 8, 381. [Google Scholar] [CrossRef] [Green Version]
- De Luca, V.; Salim, V.; Atsumi, S.M.; Yu, F. Mining the biodiversity of plants: A revolution in the making. Science 2012, 336, 1658–1661. [Google Scholar] [CrossRef]
- Normile, D. The new face of traditional Chinese medicine. Science 2003, 299, 188–190. [Google Scholar] [CrossRef]
- Liu, Z.L.; Zhu, W.R.; Zhou, W.C.; Ying, H.F.; Zheng, L.; Guo, Y.B.; Chen, J.X.; Shen, X.H. Traditional Chinese medicinal herbs combined with epidermal growth factor receptor tyrosine kinase inhibitor for advanced non-small cell lung cancer: A systematic review and meta-analysis. J. Integr. Med. 2014, 12, 346–358. [Google Scholar] [CrossRef]
- Heyadri, M.; Hashempur, M.H.; Ayati, M.H.; Quintern, D.; Nimrouzi, M.; Mosavat, S.H. The use of Chinese herbal drugs in Islamic medicine. J. Integr. Med. 2015, 13, 363–367. [Google Scholar] [CrossRef]
- Jiang, W.Y. Therapeutic wisdom in traditional Chinese medicine: A perspective from modern science. Trends Pharmacol. Sci. 2005, 26, 558–563. [Google Scholar] [CrossRef]
- Lukman, S.; He, Y.; Hui, S.C. Computational methods for traditional Chinese medicine: A survey. Comput. Methods Programs Biomed. 2007, 88, 283–294. [Google Scholar] [CrossRef]
- Gawehn, E.; Hiss, J.A.; Schneider, G. Deep learning in drug discovery. Mol. Inform. 2016, 35, 3–14. [Google Scholar] [CrossRef] [PubMed]
- Wang, Y.; Jafari, M.; Tang, Y.; Tang, J. Predicting Meridian in Chinese traditional medicine using machine learning approaches. PLoS Comput. Biol. 2019, 15, e1007249. [Google Scholar] [CrossRef] [Green Version]
- Zhang, W.; Huai, Y.; Miao, Z.; Qian, A.; Wang, Y. Systems Pharmacology for Investigation of the Mechanisms of Action of Traditional Chinese Medicine in Drug Discovery. Front. Pharmacol. 2019, 10, 743. [Google Scholar] [CrossRef]
- Willett, P.; Barnard, J.M.; Downs, G.M. Chemical similarity searching. J. Chem. Inf. Comput. Sci. 1998, 38, 983–996. [Google Scholar] [CrossRef] [Green Version]
- Fu, X.; Mervin, L.H.; Li, X.; Yu, H.; Li, J.; Mohamad Zobir, S.Z.; Zoufir, A.; Zhou, Y.; Song, Y.; Wang, Z.; et al. Toward understanding the cold, hot, and neutral nature of Chinese Medicines using in silico mode-of-action analysis. J. Chem. Inf. Model. 2017, 57, 468–483. [Google Scholar] [CrossRef]
- Wang, M.; Li, L.; Yu, C.; Yan, A.; Zhao, Z.; Zhang, G.; Jiang, M.; Lu, A.; Gasteiger, J. Classification of Mixtures of Chinese Herbal Medicines Based on a Self-Organizing Map (SOM). Mol. Inform. 2016, 35, 109–115. [Google Scholar] [CrossRef]
- Krizhevsky, A.; Sutskever, I.; Hinton, G.E. Imagenet classification with deep convolutional neural networks. Adv. Neural Inf. Process. Syst. 2012, 25, 1097–1105. [Google Scholar] [CrossRef]
- Dahl, G.E.; Jaitly, N.; Salakhutdinov, R. Multi-task neural networks for qsar predictions. arXiv 2014, arXiv:1406.1231. [Google Scholar]
- Lusci, A.; Pollastri, G.; Baldi, P. Deep architectures and deep learning in chemoinformatics: The prediction of aqueous solubility for drug-like molecules. J. Chem. Inf. Model. 2013, 53, 1563–1575. [Google Scholar] [CrossRef] [Green Version]
- Duvenaud, D.; Maclaurin, D.; Aguilera-Iparraguirre, J.; Gómez-Bombarell, R.; Hirzel, T.; Aspuru-Guzik, A.; Adams, R.P. Convolutional networks on graphs for learning molecular fingerprints. In Proceedings of the Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems, Montreal, QC, CA, 7–12 December 2015; pp. 2224–2232. [Google Scholar]
- Wu, Z.; Ramsundar, B.; Feinberg, E.N.; Gomes, J.; Geniesse, C.; Pappu, A.S.; Leswing, K.; Pande, V. Moleculenet: A benchmark for molecular machine learning. arXiv 2017, arXiv:1703.00564. [Google Scholar]
- Cao, S.; Lu, W.; Xu, Q. Deep neural networks for learning graph representations. In Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence (AAAI-16), Phoenix, AZ, USA, 12–17 February 2016; pp. 1145–1152. [Google Scholar]
- Defferrard, M.; Bresson, X.; Vandergheynst, P. Convolutional neural networks on graphs with fast localized spectral filtering. In Proceedings of the Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems, Barcelona, Spain, 5–10 December 2016; pp. 3844–3852. [Google Scholar]
- Zhang, R.Z.; Yu, S.J.; Bai, H.; Ning, K. TCM-Mesh: The database and analytical system for network pharmacology analysis for TCM preparations. Sci. Rep. 2017, 7, 2821. [Google Scholar] [CrossRef] [Green Version]
- Rogers, D.; Hahn, M. Extended-connectivity fingerprints. J. Chem. Inf. Model. 2010, 50, 742–754. [Google Scholar] [CrossRef]
- Kearnes, S.; McCloskey, K.; Berndl, M.; Pande, V.; Riley, P. Molecular graph convolutions: Moving beyond fingerprints. J. Comput. Aided Mol. Des. 2016, 30, 595–608. [Google Scholar] [CrossRef] [Green Version]
- Li, J.; Cai, D.; He, X. Learning Graph-Level Representation for Drug Discovery. arXiv 2017, arXiv:1709.03741. [Google Scholar]
- Ioffe, S.; Szegedy, C. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In Proceedings of the 32nd International Conference on Machine Learning (ICML), Lille, France, 6–11 July 2015; pp. 448–456. [Google Scholar]
- Ramsundar, B.; Kearnes, S.; Riley, P.; Webster, D.; Konerding, D.; Pande, V. Massively multitask networks for drug discovery. arXiv 2015, arXiv:1502.02072. [Google Scholar]
- Japkowicz, N.; Stephen, S. The Class Imbalance Problem: A Systematic Study. Intell. Data Anal. 2002, 6, 429–449. [Google Scholar] [CrossRef]
- Lin, T.Y.; Goyal, P.; Girshick, R.; He, K.; Dollár, P. Focal loss for dense object detection. arXiv 2017, arXiv:1708.02002. [Google Scholar]
- Svetnik, V.; Liaw, A.; Tong, C.; Culberson, J.C.; Sheridan, R.P.; Feuston, B.P. Random forest: A classification and regression tool for compound classification and QSAR modeling. J. Chem. Inf. Comput. Sci. 2003, 43, 1947–1958. [Google Scholar] [CrossRef]
- Baskin, I.I.; Palyulin, V.A.; Zefirov, N.S. Neural networks in building QSAR models. Methods Mol. Biol. 2008, 458, 133–154. [Google Scholar]
- Ribeiro, M.T.; Singh, S.; Guestrin, C. Why Should I Trust You? Explaining the Predictions of Any Classifier. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA, 13–17 August 2016; pp. 1135–1144. [Google Scholar]
- Ashish, K.; Bandyopadhyay, D.; Mondal, S.; Ghosh, R.K. Colchicine in coronary artery disease: Role of anti-inflammatory medications redefined. Int. J. Cardiol. 2018, 254, 51. [Google Scholar] [CrossRef]
- Papageorgiou, N.; Briasoulis, A.; Lazaros, G.; Imazio, M.; Tousoulis, D. Colchicine for prevention and treatment of cardiac diseases: A meta-analysis. Cardiovasc. Ther. 2017, 35, 10–18. [Google Scholar] [CrossRef]
- Hussein, G.; Sankawa, U.; Goto, H.; Matsumoto, K.; Watanabe, H. Astaxanthin, a carotenoid with potential in human health and nutrition. J. Nat. Prod. 2006, 69, 443–449. [Google Scholar] [CrossRef]
- Liu, Z.W.; Shu, J.; Tu, J.Y.; Zhang, C.H.; Hong, J. Liver in the Chinese and Western Medicine. Integr. Med. Int. 2017, 4, 39–45. [Google Scholar] [CrossRef] [Green Version]
- Chao, C.T.; Liu, Y.P.; Su, S.F.; Yeh, H.Y.; Chen, H.Y.; Lee, P.J.; Chen, W.J.; Lee, Y.M.; Huang, J.W.; Chiang, C.K.; et al. Circulating microRNA-125b predicts the presence and progression of uremic vascular calcification. Arterioscler. Thromb. Vasc. Biol. 2017, 37, 1402–1414. [Google Scholar] [CrossRef] [Green Version]
- Chao, C.T.; Yeh, H.Y.; Yuan, T.H.; Chiang, C.K.; Chen, H.W. MicroRNA-125b in vascular diseases: An updated systematic review of pathogenetic implications and clinical applications. J. Cell. Mol. Med. 2019, 23, 5884–5894. [Google Scholar] [CrossRef]
Features | Methods | ROC-AUC |
---|---|---|
ECFP4 | Logistic regression | 0.66 |
ECFP4 | Random forest | 0.67 |
ECFP4 | AdaBoost | 0.65 |
ECFP4 | NN | 0.68 |
Neural fingerprint | Cost-sensitive GCN | 0.82 |
Meridian | Train | Validate | Test |
---|---|---|---|
Bladder | 0.89 | 0.86 | 0.85 |
Cardiovascular | 0.97 | 0.94 | 0.94 |
Gallbladder | 0.91 | 0.87 | 0.87 |
Heart | 0.82 | 0.80 | 0.79 |
Kidney | 0.81 | 0.78 | 0.78 |
Large intestine | 0.88 | 0.84 | 0.84 |
Liver | 0.79 | 0.75 | 0.77 |
Lung | 0.79 | 0.77 | 0.75 |
Small intestine | 0.97 | 0.94 | 0.93 |
Spleen | 0.80 | 0.78 | 0.78 |
Stomach | 0.78 | 0.74 | 0.75 |
Three end | 0.99 | 0.94 | 0.95 |
Split Methods | ROC-AUC |
---|---|
Index | 0.60 |
Random | 0.67 |
Scaffold | 0.63 |
Random stratified | 0.82 |
© 2020 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
Share and Cite
Yeh, H.-Y.; Chao, C.-T.; Lai, Y.-P.; Chen, H.-W. Predicting the Associations between Meridians and Chinese Traditional Medicine Using a Cost-Sensitive Graph Convolutional Neural Network. Int. J. Environ. Res. Public Health 2020, 17, 740. https://0-doi-org.brum.beds.ac.uk/10.3390/ijerph17030740
Yeh H-Y, Chao C-T, Lai Y-P, Chen H-W. Predicting the Associations between Meridians and Chinese Traditional Medicine Using a Cost-Sensitive Graph Convolutional Neural Network. International Journal of Environmental Research and Public Health. 2020; 17(3):740. https://0-doi-org.brum.beds.ac.uk/10.3390/ijerph17030740
Chicago/Turabian StyleYeh, Hsiang-Yuan, Chia-Ter Chao, Yi-Pei Lai, and Huei-Wen Chen. 2020. "Predicting the Associations between Meridians and Chinese Traditional Medicine Using a Cost-Sensitive Graph Convolutional Neural Network" International Journal of Environmental Research and Public Health 17, no. 3: 740. https://0-doi-org.brum.beds.ac.uk/10.3390/ijerph17030740