Design of Potential Drugs and Vaccines for COVID 19 by the Application of Machine Learning and Artificial Intelligence

ABSTRACT

Computational methods like neural network and genetic algorithm can be used to speed up the drug discovery process. Machine learning method like artificial neural networks is widely used in pharmaceutical industry. ANNs have some advantages over classical statistical methods because they can investigate complex, nonlinear relationships. sequence alignment, variable selection in quantitative structure activity relationship (QSAR) studies. Chemical and biological activity of a drug is closely related to its properties known as descriptors. The goal is to find a model which will correlate the inputs (properties) with a target (biological activity). The methodology is known as Quantitative Structure-Activity / Property Relationship (QSAR/QSPR). QSAR/QSPR correlates topological, electronic and quantum properties of compounds with their biological activities. Virtual Screening (VS) method “screen” compounds with known chemical motifs called “pharmacophores” amid millions of other compounds in a data base. These screened compounds are potential drugs and can be tested experimentally for their biological activities. The ANN technology is used to study interactions and dynamics between compounds and receptor proteins or nucleic acids in the area of pharmacokinetics and pharmacodynamics. Some more applications of ANN are: data analysis, comparison/ classification of drug libraries, study of HIV-1 reverse transcriptase, gene prediction and homology searches in protein. Comparative molecular surface analysis (COMSA), a 3D QSAR method uses ANN to map the mean electrostatic potential on the molecular surface. Genetic algorithms (GAs) are stochastic optimization methods. A QSAR model can be made by variable selection, PLS (partial least squares) and cross validation using GA. Pharmacophore modelling is done by comparing some important electronic and 3D structural features required for a potent group of ligands/drugs when the receptor or target is unknown. This article discusses immense application of ANNs and GAs in the drug discovery process. The future prospect of Artificial Intelligence in drug and vaccine design, COVID-19 management and prediction are also discussed.

References

• Alyasseri, Z. A. A., Al-Betar, M. A., Doush, I. A., Awadallah, M. A., Abasi, A. K., Makhadmeh, S. N., Alomari, O. A., Abdulkareem, K. H., Adam, A., Damasevicius, R., Mohammed, M. A., Zitar, R. A., Review on COVID-19 diagnosis models based on machine learning and deep learning approaches. Expert Systems, (2022), 39(3).
• Arash Keshavarzi Arshadi, Julia Webb, Milad Salem, Emmanuel Cruz, Stacie Calad-Thomson, Niloofar Ghadirian, Jennifer Collins, Elena Diez-Cecilia, Brendan Kelly, Hani Goodarzi and JiannShiun Yuan, Artificial Intelligence for COVID-19 Drug Discovery and Vaccine Development. Frontiers in Artificial Intelligence, August (2020), 3 (65)
• Breiman L., Random forests. Machine Learning, (2001), 45(1), 5–32
• Beck B. R., Shin B., Choi Y., Park S., and Kang K., Predicting commercially available antiviral drugs that may act on the novel coronavirus (SARS-CoV-2) through a drug-target interaction deep learning model. Computational and Structural Biotechnology Journal, (2020), 18: 784–790
• Batool M, Ahmad B. and Choi S., A structure-based drug discovery paradigm. International Journal of Molecular Sciences, (2019) 20(11), 2783
• Cramer R. D., Patterson D. E. and Bunce J. D., Comparative molecular field analysis (CoMFA). 1. Effect of shape on binding of steroids to carrier proteins. Journal of the American Chemical Society, (1988), 110(18): 5959–5967
• Cortes C. And Vapnik V., Support-vector networks. Machine Learning, (1995), 20(3): 273–297
• Dai, L., Gao, G. F., Viral targets for vaccines against COVID-19, Nature Reviews Immunology (2020) 21, 73–82
• Durrant J. D. and McCammon J. A., Molecular dynamics simulations and drug discovery. BMC Biology, (2011), 9(1): 1–9
• Dixon S. L., Smondyrev A. M. and Rao S. N., PHASE: a novel approach to pharmacophore modelling and 3D data- base searching, Chemical Biology & Drug Design, (2006), 67(5): 370–372
• Das S, Sarmah S, Lyndem S, Singha Roy A. An investigation into the identification of potential inhibitors of SARS-CoV-2 main protease using molecular docking study. J Biomol Struct Dyn. 2021 Jun; 39(9): 3347-3357. doi: 10.1080/07391102.2020.1763201
• Elfiky A. A., SARS-CoV-2 RNA dependent RNA polymerase (RdRp) targeting: an in-silico perspective. Journal of Biomolecular Structure and Dynamics, (2021), 39(9): 3204–3212
• Goyal B.and Goyal D., Targeting the dimerization of the main protease of coronaviruses: A potential broad-spectrum therapeutic strategy. ACS Combinatorial Science (2020), 22(6): 297–305
• Gunjan Arora, Jayadev Joshi, Rahul Shubhra Mandal, Nitisha Shrivastava, Richa Virmani and Tavpritesh Sethi, Review: Artificial Intelligence in Surveillance, Diagnosis, Drug Discovery and Vaccine Development against COVID-19. Pathogens, (2021), 10: 1048
• Huang S.Y. and. Zou X, Advances and challenges in protein-ligand docking. International Journal of Molecular Sciences, (2010), 11(8), 3016–3034
• Kalyaanamoorthy S. and Chen Y.P. P., Structure-based drug design to augment hit discovery. Drug Discovery Today, (2011), 16(17–18), 831–839
• Klebe G., Abraham U. and Mietzner T., Molecular similarity indices in a comparative analysis (CoMSIA) of drug molecules to correlate and predict their biological activity, Journal of Medicinal Chemistry, (1994), 37(24): 4130-4146
• Li H., Sutter J. and Hoffmann R., Hypo Gen: an automated system for generating 3D predictive pharmacophore models. Pharmacophore Perception, Development, and Use in Drug Design, (2000), 2: 171
• Dai L, Gao GF. Viral targets for vaccines against COVID-19. Nat Rev Immunol. 2021 Feb;21(2):73-82. doi: 10.1038/s41577-020-00480-0
• Lionta E., Spyrou G, Vassilatis D. K., and Cournia Z., Structure-based virtual screening for drug discovery: principles applications and recent advances. Current Topics in Medicinal Chemistry (2014), 14(16): 1923–1938
• Melo-Filho C. C., Braga R. C. and Andrade C. H., 3D-QSAR approaches in drug design: perspectives to generate reliable CoMFA models, Current Computer-Aided Drug Design, (2014), 10 (2):148–159
• Ma J., Sheridan R. P., Liaw A., Dahl G. E. and Svetnik V., Deep neural nets as a method for quantitative structure– activity relationships, Journal of Chemical Information and Modeling, (2015), 55 (2): 263–274
• Na Zhu, Dingyu Zhang, Wenling Wang, Xingwang Li, Bo Yang, Jingdong Song, Xiang Zhao, Baoying Huang, Weifeng Shi, Roujian Lu, Peihua Niu, Faxian Zhan, Xuejun Ma, Dayan Wang, Wenbo Xu, Guizhen Wu, George F Gao, Wenjie Tan; China Novel Coronavirus Investigating and Research Team A novel coronavirus from patients with pneumonia in China, 2019, 2020. New England Journal of Medicine, 382(8): 727–733
• Patel H., Noolvi M., Poonam Sharma, V. Jaiswal, S. Bansal, Sandeep Lohan, Suthar Sharad Kumar, Vikrant Abbot, Saurabh Dhiman, Varun Bhardwaj, Quantitative structure–activity relationship (QSAR) studies as strategic approach in drug discovery, Medicinal Chemistry Research, (2014), 23(12): 4991–5007
• Patel L., Shukla T., Huang X., Ussery D. W., and Wang S., Machine learning methods in drug discovery, Molecules, (2020), 25(22): 5277
• Pillaiyar T., Meenakshisundaram S., and Manickam M., Recent discovery and development of inhibitors targeting coronaviruses, Drug Discovery Today (2020), 25(4): 668–688
• Quentin Haas, Nikolay Borisov, David Vicente Alvarez, Sohrab Ferdowsi, Leonhard von Mayenn, Douglas Teodoro, Poorya Amini, Vaccine Development in the Time of COVID-19: The Relevance of the Risklick AI to Assist in Risk Assessment and Optimize Performance, Front. Digit. Health. 02 November (2021)
• Quentin Haas, David Vicente Alvarez, Nikolay Borissov, Sohrab Ferdowsi, Leonhard von Meyenn, Sven Trelle, Douglas Teodoro, Poorya Amini, Utilizing artificial intelligence to manage COVID-19 scientific evidence torrent with Risklick AI: a critical tool for pharmacology and therapy development. Pharmacology (2021) 106: 244–253
• Quoc-Viet Pham1, Dinh C. Nguyen, Thien Huynh-The, Won-Joo Hwang and Pubudu N. Pathirana, Artificial Intelligence (AI) and Big Data for Coronavirus (COVID-19) Pandemic: A Survey on the State-of-the-Arts, IEEE ACCESS, (2020), 4.
• Rishi R. Gupta, Application of Artificial Intelligence and Machine Learning in Drug Discovery. Methods Mol Biol. (2022); 2390: 113-124
• Rakesh S Joshi, Shounak S Jagdale, Sneha B Bansode, S Shiva Shankar, Meenakshi B Tellis , Vaibhav Kumar Pandya, Anita Chugh , Ashok P Giri , Mahesh J Kulkarni , Discovery of potential multi-target-directed ligands by targeting host- specific SARS-CoV-2 structurally conserved main protease, Journal of Biomolecular Structure and Dynamics, (2020), 39(9): 1–16
• Selvaraj C, Dinesh DC, Panwar U, Abhirami R, Boura E, Singh SK. Structure-based virtual screening and molecular dynamics simulation of SARS-CoV-2 Guanine-N7 methyltransferase (nsp14) for identifying antiviral inhibitors against COVID-19. J Biomol Struct Dyn. 2021 Aug; 39(13): 4582-4593. doi: 10.1080/07391102.2020.1778535
• Sammut C. and Webb G. I., Naïve Bayes BT, Encyclopedia of Machine Learning, Springer Science & Business Media (2010)
• Sobhia M.E., Ghosh K, Sivangula S and Kumar G.S. Deciphering COVID-19 Enigma by Targeting SARS-COV-2 Main Protease Using IN-SILICOApproaches. IJPSR (2021), 12, (6): 3104-3119
• Stefania Monteleone, Tahsin F. Kellici, Michelle Southey, Michael J. Bodkin, Alexander Heifetz, Fighting COVID 19 with Artificial Intelligence, Methods Mol Biol. (2022); 2390: 103-112
• A. Khan, Zia K., Ashraf S., Uddin R. and Ul-Haq Z., Identification of chymotrypsin-like protease inhibitors of SARS- CoV-2 via integrated computational approach. Journal of Biomolecular Structure and Dynamics, (2020) vol. 39, no. 7, pp. 2607–2616
• Sinosh Skariyachan, Dharshini Gopal, Shweta Chakrabarti, Priya Kempanna, Akshay Uttarkar, Aditi G Muddebihalkar, Vidya Niranjan, Structural and molecular basis of the interaction mechanism of selected drugs towards multiple targets of SARS-CoV-2 by molecular docking and dynamic simulation studies- deciphering the scope of repurposed drugs. Computers in Biology and Medicine, (2020), 126, 104054
• Teodoro D, Ferdowsi S, Borissov N, Kashani E, Vicente Alvarez D, Copara J, Gouareb R, Naderi N, Amini P. Information Retrieval in an Infodemic: The Case of COVID-19 Publications. J Med Internet Res. 2021 Sep 17; 23(9): e30161. doi: 10.2196/30161
• Tânia Cova, Carla Vitorino, Márcio Ferreira, Sandra Nunes, Paola Rondon-Villarreal, Alberto Pais, Artificial Intelligence and Quantum Computing as the next Pharma Disrupters, Artificial Intelligence in Drug Design. (2021): 321–347
• Van Drie J. H, Generation of three-dimensional pharmacophore models, Wiley Interdisciplinary Reviews: Computational Molecular Science, (2013), 3(5): 449–464
• Wang L., Ding J., Pan L., Cao D., Jiang H., and Ding X., Artificial intelligence facilitates drug design in the big data era. Chemometrics and Intelligent Laboratory Systems, (2019), 194, 103850
• Wahedi H. M., Ahmad S. and Abbasi S. W., Stilbene-based natural compounds as promising drug candidates against COVID-19. Journal of Biomolecular Structure and Dynamics, (2021), 39(9): 3225–3234
• Wang L, Zhang Y, Wang D, Tong X, Liu T, Zhang S, Huang J, Zhang L, Chen L, Fan H and Clarke M, Artificial Intelligence for COVID-19: A Systematic Review. Med. 8: 704256
• Wenhao Dai, Bing Zhang, Xia-Ming Jiang, Haixia Su, Jian Li, Yao Zhao, Xiong Xie, Zhenmin Jin, Jingjing Peng, Fengjiang Liu, Chunpu Li, You Li, Fang Bai, Haofeng Wang, Xi Cheng, Xiaobo Cen, Shulei Hu, Xiuna Yang, Jiang Wang, Xiang Liu, Gengfu Xiao, Hualiang Jiang, Zihe Rao, Lei-Ke Zhang, Yechun Xu, Haitao Yang, Hong Liu, Structure-based design of antiviral drug candidates targeting the SARS-CoV-2 main protease. Science (2020), 368( 6497): 1331-1335

Download all article in PDF

WSN 183 (2023) 71-89

ADVERTISEMENT