Maged Nasser
Naomie Salim
ABSTRACT
Molecular 2D similarity searching is one of the most widely used techniques for ligand-based virtual screening (LBVS). This study has used the concepts of deep learning by adapted deep belief networks (DBN) and data fusion concept with DBN to enhance the molecular similarity searching of chemical compounds in LBVS. The MDDR Datasets represented by different descriptors to convert the molecule shape to numerical values and each descriptor has different important features rather than the others. The DBN with data fusion is adapted to obtain a lower detection error probability and a higher reliability by using data from multiple distributed descriptors and analyzing the performance of combination and individual descriptors target by target and showed that the combination descriptor did better than both original descriptors. The overall results of this research showed that the use of DBN with data fusion in similarity-based is found to significantly outperform the conventional, industry-standard Tanimoto-based similarity search systems and some others benchmarks witch have been adapted by others researchers, with 1 % and 5% performance improvement in the average recall rates.
- Rollinger, J.M., H. Stuppner, and T. Langer, Virtual screening for the discovery of bioactive natural products, in Natural Compounds as Drugs Volume I. 2008, Springer. p. 211--249.Google Scholar
- Sirci, F., et al., Ligand-, structure-and pharmacophore-based molecular fingerprints: a case study on adenosine A1, A2A, A2B, and A3 receptor antagonists. Journal of computer-aided molecular design, 2012. 26(11): p. 1247--1266.Google Scholar
- Walters, W.P., M.T. Stahl, and M.A. Murcko, Virtual screening---an overview. Drug Discovery Today, 1998. 3(4): p. 160--178.Google Scholar
- Chen, C., et al., Combining structure-based pharmacophore modeling, virtual screening, and in silico ADMET analysis to discover novel tetrahydro-quinoline based pyruvate kinase isozyme M2 activators with antitumor activity. Drug design, development and therapy, 2014. 8: p. 1195.Google Scholar
- Drwal, M.N. and R. Griffith, Combination of ligand-and structure-based methods in virtual screening. Drug Discovery Today: Technologies, 2013. 10(3): p. e395-e401.Google Scholar
- Willett, P., Combination of similarity rankings using data fusion. Journal of chemical information and modeling, 2013. 53(1): p. 1--10.Google Scholar
- Klon, A.E., et al., Finding more needles in the haystack: A simple and efficient method for improving high-throughput docking results. Journal of medicinal chemistry, 2004. 47(11): p. 2743--2749.Google Scholar
- Chen, X. and C.H. Reynolds, Performance of similarity measures in 2D fragment-based similarity searching: comparison of structural descriptors and similarity coefficients. J Chem Inf Comput Sci, 2002. 42.Google Scholar
- Sakkiah, S., et al., Theoretical approaches to identify the potent scaffold for human sirtuin1 activator: Bayesian modeling and density functional theory. Medicinal Chemistry Research, 2014. 23(9): p. 3998--4010.Google Scholar
- Hall, D.L. and S.A. McMullen, Mathematical techniques in multisensor data fusion. 2004: Artech House.Google Scholar
- Liggins II, M., D. Hall, and J. Llinas, Handbook of multisensor data fusion: theory and practice. 2017: CRC press.Google Scholar
- Brey, R.L., et al., Neuropsychiatric syndromes in lupus: prevalence using standardized definitions. Neurology, 2002. 58(8): p. 1214--1220.Google Scholar
- LeCun, Y., Y. Bengio, and G. Hinton, Deep learning. Nature, 2015. 521(7553): p. 436--444.Google Scholar
- Maharani, D., H. Murfi, and Y. Satria, Performance of Deep Neural Network for Tabular Data A Case Study of Loss Cost Prediction in Fire Insurance. International Journal of Machine Learning and Computing, 2019. 9(6).Google ScholarCross Ref
- Ngiam, J., et al. Multimodal deep learning. in Proceedings of the 28th international conference on machine learning (ICML-11). 2011.Google ScholarDigital Library
- Glorot, X. and Y. Bengio. Understanding the difficulty of training deep feedforward neural networks. in Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics. 2010.Google Scholar
- Erhan, D., et al., Why does unsupervised pre-training help deep learning? Journal of Machine Learning Research, 2010. 11(Feb): p. 625--660.Google Scholar
- Le Roux, N. and Y. Bengio, Representational power of restricted Boltzmann machines and deep belief networks. Neural computation, 2008. 20(6): p. 1631--1649.Google Scholar
- Bengio, Y., Learning deep architectures for AI. Foundations and trends® in Machine Learning, 2009. 2(1): p. 1--127.Google Scholar
- Salido, J.A.A. and C. Ruiz, Using deep learning for melanoma detection in dermoscopy images. International Journal of Machine Learning and Computing, 2018. 8(1): p. 61--68.Google Scholar
- Hinton, G.E., S. Osindero, and Y.-W. Teh, A fast learning algorithm for deep belief nets. Neural computation, 2006. 18(7): p. 1527--1554.Google Scholar
- Rumelhart, D., McClelland. Parallel distributed processing. 1986, Cambridge, MA: MIT Press.Google Scholar
- Klinger, S. and J. Austin, Weighted superstructures for chemical similarity searching, in Proceedings of the 9th Joint Conference on Information Sciences. 2006.Google Scholar
- Arif, S.M., J.D. Holliday, and P. Willett. The Use of Weighted 2D Fingerprints in Similarity-Based Virtual Screening. in Elsevier Inc. 2016.Google Scholar
- Abdo, A. and N. Salim, New fragment weighting scheme for the bayesian inference network in ligand-based virtual screening. Journal of chemical information and modeling, 2010. 51(1): p. 25--32.Google Scholar
- Ahmed, A., A. Abdo, and N. Salim, Ligand-based Virtual screening using Bayesian inference network and reweighted fragments. The Scientific World Journal, 2012.Google Scholar
- Vogt, M., A.M. Wassermann, and J. Bajorath, Application of information---Theoretic concepts in chemoinformatics. Information, 2010. 1(2): p. 60--73.Google Scholar
- Unity. Tripos Inc.Google Scholar
- Matter, H. and T. Pötter, Comparing 3D pharmacophore triplets and 2D fingerprints for selecting diverse compound subsets. Journal of chemical information and computer sciences, 1999. 39(6): p. 1211--1225.Google Scholar
- James, C., D. Weininger, and J. Delany, Daylight theory manual. Daylight Chemical Information Systems. Inc., Irvine, CA, 1995.Google Scholar
- Xue, L., et al., Mini-fingerprints detect similar activity of receptor ligands previously recognized only by three-dimensional pharmacophore-based methods. Journal of chemical information and computer sciences, 2001. 41(2): p. 394--401.Google Scholar
- Xue, L., et al., Profile scaling increases the similarity search performance of molecular fingerprints containing numerical descriptors and structural keys. Journal of chemical information and computer sciences, 2003. 43(4): p. 1218--1225.Google Scholar
- Peng, Z., et al., Deep Boosting: Joint feature selection and analysis dictionary learning in hierarchy. Neurocomputing, 2016. 178: p. 36--45.Google Scholar
- Semwal, V.B., K. Mondal, and G.C. Nandi, Robust and accurate feature selection for humanoid push recovery and classification: deep learning approach. Neural Computing and Applications, 2017. 28(3): p. 565--574.Google Scholar
- Suk, H.-I., et al., Deep sparse multi-task learning for feature selection in Alzheimer's disease diagnosis. Brain Structure and Function, 2016. 221(5): p. 2569--2587.Google Scholar
- Zou, Q., et al., Deep learning based feature selection for remote sensing scene classification. IEEE Geoscience and Remote Sensing Letters, 2015. 12(11): p. 2321--2325.Google Scholar
- Ibrahim, R., et al. Multi-level gene/MiRNA feature selection using deep belief nets and active learning. in 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. 2014. IEEE.Google ScholarCross Ref
- Dahl, G.E., N. Jaitly, and R. Salakhutdinov, Multi-task neural networks for QSAR predictions. arXiv preprint arXiv:1406.1231, 2014.Google Scholar
- Hamza, H., et al. Bioactivity Prediction Using Convolutional Neural Network. in International Conference of Reliable Information and Communication Technology. 2019. Springer.Google Scholar
- Unterthiner, T., et al. Deep learning as an opportunity in virtual screening. in Proceedings of the Deep Learning Workshop at NIPS. 2014.Google Scholar
- Unterthiner, T., et al., Toxicity prediction using deep learning. arXiv preprint arXiv:1503.01445, 2015.Google Scholar
- Ramsundar, B., et al., Massively multitask networks for drug discovery. arXiv preprint arXiv:1502.02072, 2015.Google Scholar
- Lusci, A., G. Pollastri, and P. Baldi, Deep architectures and deep learning in chemoinformatics: the prediction of aqueous solubility for drug-like molecules. Journal of chemical information and modeling, 2013. 53(7): p. 1563--1575.Google Scholar
- Duvenaud, D.K., et al. Convolutional networks on graphs for learning molecular fingerprints. in Advances in neural information processing systems. 2015.Google Scholar
- Nasser, M., et al. Deep Belief Network for Molecular Feature Selection in Ligand-Based Virtual Screening. in International Conference of Reliable Information and Communication Technology. 2018. Springer.Google Scholar
- Turtle, H. and W.B. Croft, Evaluation of an inference network-based retrieval model. ACM Transactions on Information Systems (TOIS), 1991. 9(3): p. 187--222.Google ScholarDigital Library
- Bartell, B.T., G.W. Cottrell, and R.K. Belew. Automatic combination of multiple ranked retrieval systems. in SIGIR'94. 1994. Springer.Google Scholar
- Belkin, H.E., C.R. Kilburn, and B. De Vivo, Chemistry of the lavas and tephra from the recent (AD 1631-1944) Vesuvius (Italy) volcanic activity. 1993: US Department of the Interior, US Geological Survey.Google Scholar
- Hull, D.A., J.O. Pedersen, and H. Schütze. Method combination for document filtering. in Proceedings of the 19th annual international ACM SIGIR conference on Research and development in information retrieval. 1996. Citeseer.Google ScholarDigital Library
- Ginn, C.M., P. Willett, and J. Bradshaw, Combination of molecular similarity measures using data fusion, in Virtual Screening: An Alternative or Complement to High Throughput Screening? 2000, Springer. p. 1--16.Google Scholar
- Croft, W.B., H.R. Turtle, and D.D. Lewis. The use of phrases and structured queries in information retrieval. in Proceedings of the 14th annual international ACM SIGIR conference on Research and development in information retrieval. 1991. ACM.Google ScholarDigital Library
- Rajashekar, T. and W.B. Croft, Combining automatic and manual index representations in probabilistic retrieval. Journal of the American society for information science, 1995. 46(4): p. 272--283.Google Scholar
- Al-Dabbagh, M.M., et al., A quantum-based similarity method in virtual screening. Molecules, 2015. 20(10): p. 18107--18127.Google ScholarCross Ref
- Himmat, M., et al., Adapting document similarity measures for ligand-based virtual screening. Molecules, 2016. 21(4): p. 476.Google ScholarCross Ref
- Pipeline Pilot Software: SciTegic Accelrys Inc. http://www.accelrys.com/. San Diego Accelrys Inc; 2008.Google Scholar
- Semwal, V.B., K. Mondal, and G. Nandi, Robust and accurate feature selection for humanoid push recovery and classification: deep learning approach. Neural Computing and Applications, 2015: p. 1--10.Google Scholar
- Hinton, G., A practical guide to training restricted Boltzmann machines. Momentum, 2010. 9(1): p. 926.Google Scholar
- Yuan, C., X. Sun, and R. Lv, Fingerprint liveness detection based on multi-scale LPQ and PCA. China Communications, 2016. 13(7): p. 60--65.Google Scholar
Index Terms
- Molecular Similarity Searching Based on Deep Belief Networks with Different Molecular Descriptors
Recommendations
Similarity searching in ligand-based virtual screening using different fingerprints and different similarity coefficients
Similarity searching plays an increasingly important role in virtual screening. It is a screening technique that works by comparing the features of the target compound with the features of each compound in the database of compounds. This comparison can be ...
Convolutional Neural Networks for Predicting Molecular Binding Affinity to HIV-1 Proteins
BCB '18: Proceedings of the 2018 ACM International Conference on Bioinformatics, Computational Biology, and Health InformaticsComputational techniques for binding-affinity prediction and molecular docking have long been considered in terms of their utility for drug discovery. With the advent of deep learning, new supervised learning techniques have emerged which can utilize the ...
An investigation of molecular dynamics simulation and molecular docking: Interaction of citrus flavonoids and bovine β-lactoglobulin in focus
Citrus flavonoids are natural compounds with important health benefits. The study of their interaction with a transport protein, such as bovine @b-lactoglobulin (BLG), at the atomic level could be a valuable factor to control their transport to ...
Comments