Please wait a minute...
Big Data Mining and Analytics  2021, Vol. 4 Issue (2): 76-83    DOI: 10.26599/BDMA.2020.9020007
Special Section on Artificial Intelligence and Big Data Analytics for Coronavirus (COVID-19)     
Analysis of Protein-Ligand Interactions of SARS-CoV-2 Against Selective Drug Using Deep Neural Networks
Natarajan Yuvaraj(),Kannan Srihari*(),Selvaraj Chandragandhi(),Rajan Arshath Raja(),Gaurav Dhiman(),Amandeep Kaur()
St. Peter’s Institute of Higher Education and Research, Chennai 600054, India
Information Communication Technology Academy, Chennai 600096, India
Department of Computer Science and Engineering, SNS College of Engineering, Coimbatore 641107, India
Department of Computer Science and Engineering, Jagannath Educational Health and Charitable Trust College of Engineering and Technology, Coimbatore 641105, India
B. S. Abdur Rahman Crescent Institute of Science and Technology, Chennai 600048, India
Department of Computer Science, Government Bikram College of Commerce, Patiala 147001, India
Department of Computer Science and Engineering, Sri Guru Granth Sahib World University, Fatehgarh 140406, India
Download: PDF (1660 KB)      HTML  
Export: BibTeX | EndNote (RIS)      

Abstract  

In recent time, data analysis using machine learning accelerates optimized solutions on clinical healthcare systems. The machine learning methods greatly offer an efficient prediction ability in diagnosis system alternative with the clinicians. Most of the systems operate on the extracted features from the patients and most of the predicted cases are accurate. However, in recent time, the prevalence of COVID-19 has emerged the global healthcare industry to find a new drug that suppresses the pandemic outbreak. In this paper, we design a Deep Neural Network (DNN) model that accurately finds the protein-ligand interactions with the drug used. The DNN senses the response of protein-ligand interactions for a specific drug and identifies which drug makes the interaction that combats effectively the virus. With limited genome sequence of Indian patients submitted to the GISAID database, we find that the DNN system is effective in identifying the protein-ligand interactions for a specific drug.



Key wordsDeep Neural Network (DNN)      coronavirus      protein-ligand interactions      deep learning      clinical healthcare system     
Received: 04 June 2020      Published: 09 July 2020
Corresponding Authors: Kannan Srihari     E-mail: yraj1989@gmail.com;harionto@gmail.com;chandragandhi09@gmail. com;arshathraja.ru@gmail.com;gdhiman0001@gmail.com;sweetchintoo2008@gmail.com
About author: Natarajan Yuvaraj received the BEng and MEng degrees in computer science engineering from Anna University, Tamil Nadu, India in 2010 and 2012, respectively. He is pursuing the PhD degree in computer science engineering at St. Peter’s Institute of Higher Education and Research, Chennai, India. From 2012 to 2015, he was an assistant professor at various educational institutes. Currently, he is working as a deputy manager of research & development department at Information Communication Technology Academy, Tamil Nadu, India. His research interest includes data mining, wireless sensor networks, and mobile computing. He has filed 5 Indian patents, wrote 2 text books, and published 4 book chapters in Elsevier, Springer, CRC Taylor and Francis, and John Wiley and Sons. He has also published 40 research papers in SCI, Scopus, and international and national conferences.|Kannan Srihari received the MEng and PhD degrees from Anna University, Tamil Nadu, India in 2009 and 2013, respectively. He is currently working as an associate professor at Department of Computer Science and Engineering, SNS College of Engineering, India. He published over 60 papers in international journals. His research area includes semantic search engines, microprocessor, FPGA, big data, and cloud computing. He has guided 6 PhD students and currently he is guiding 4 scholars.|Selvaraj Chandragandhi received the BTech and MTech degrees from Anna University, India in 2008 and 2013, respectively. She is working as an assistant professor at Jagannath Educational Health and Charitable Trust College of Engineering and Technology. She has published 5 Scopus papers. Her research area is IoT, bio medical, and block chain.|Rajan Arshath Raja received the bachelor of engineering degree in electronics and communication engineering from Anna University in 2012. He received the master of engineering degree in communication systems from Sree Sastha Institute of Engineering and Technology in 2014. He is currently pursuing the PhD degree in wireless communication at B. S. Abdur Rahman Crescent Institute of Science and Technology. He is currently working as a senior research associate of research & development department at Information Communication Technology Academy, India. His research interest includes the wireless communication, machine learning, and artificial intelligence. He has filed 2 Indian patents, and published 4 book chapters in Elsevier, Springer, CRC Taylor and Francis, and John Wiley and Sons. He also published 10 research papers in SCI, Scopus, and international and national conferences.|Gaurav Dhiman received the master and PhD degrees in computer engineering from Thapar Institute of Engineering & Technology, Patiala, India in 2015 and 2019, respectively. He is currently working as an assistant professor at Department of Computer Science, Government Bikram College of Commerce, Patiala, India. He was selected as the outstanding reviewer from knowledge-based systems (Elsevier). He has published more than 50 peer-reviewed research papers (indexed in SCI-SCIE) and 5 international books. He is also serving as the guest editor of more than five special issues in various peer-reviewed journals. He is also with editorial board members of Current Chinese Computer Science (Bentham Science), Current Dissertations (Bentham Science), and Journal of Fuzzy Logic and Modeling in Engineering (Bentham Science). His research interest includes single- and multi-objectives optimization (bio-inspired, evolutionary, and quantum), soft computing (type-1 and type-2 fuzzy sets), power systems, and change detection using remotely sensed high-resolution satellite data. His research articles can be found in Knowledge-Based Systems (Elsevier), Advances in Engineering Software (Elsevier), Applied Intelligence (Springer), Journal of Computational Science (Elsevier), Engineering with Computers (Springer), Applied Soft Computing (Elsevier), etc.|Amandeep Kaur received the master and PhD degrees in computer engineering from Thapar Institute of Engineering & Technology, Patiala, India in 2012 and 2020, respectively. She is currently working as an assistant professor at Department of Computer Science and Engineering, Sri Guru Granth Sahib World University, India. Her research interest includes single- and multi-objectives optimization (bio-inspired, evolutionary, and quantum), soft computing (type-1 and type-2 fuzzy sets), power systems, and change detection using remotely sensed high-resolution satellite data.
Cite this article:

Natarajan Yuvaraj,Kannan Srihari,Selvaraj Chandragandhi,Rajan Arshath Raja,Gaurav Dhiman,Amandeep Kaur. Analysis of Protein-Ligand Interactions of SARS-CoV-2 Against Selective Drug Using Deep Neural Networks. Big Data Mining and Analytics, 2021, 4(2): 76-83.

URL:

http://bigdata.tsinghuajournals.com/10.26599/BDMA.2020.9020007     OR     http://bigdata.tsinghuajournals.com/Y2021/V4/I2/76

LigandBinding energy (kcalmol-?1)Bond length (?)
Ketoamide-5.802.8
Lopinavir-6.082.7
Nelfinavir-7.543.0
Remdesivir-5.512.7
Ritonavir-5.962.7
Table 1 Binding energy and bond length of COVID-19 protease inhibitors.
Fig. 1 Architecture of DNN.
Fig. 2 Feed-forward DNN with 3 hidden layers.
Fig. 3 Feature extraction of protein structure using artificial neural network.
Fig. 4 Classification accuracy of training models of DNN with three pre-trained networks.
AlgorithmAccuracyPrecisionRecallF1-score
DNN0.92080.93890.60640.7356
DBN0.92100.93940.61000.7369
ANN0.92110.93950.61520.7421
FFNN0.92200.93980.63130.7529
BPNN0.92220.93990.63630.7597
Table 2 Performance of ketoamide drug interaction with SARS-CoV-2 virus over Indian datasets.
AlgorithmAccuracyPrecisionRecallF1-score
DNN0.94600.95680.69680.6256
DBN0.94420.95640.67860.6103
ANN0.94360.95590.67510.6057
FFNN0.94290.95580.66620.6024
BPNN0.94140.95420.65890.5844
Table 3 Performance of lopinavir drug interaction with SARS-CoV-2 virus over Indian datasets.
AlgorithmAccuracyPrecisionRecallF1-score
DNN0.96650.97620.96420.8958
DBN0.95870.97610.96380.8956
ANN0.94520.97600.95710.8854
FFNN0.94030.97580.95530.8854
BPNN0.93820.97580.95440.8643
Table 4 Performance of nelfinavir drug interaction with SARS-CoV-2 virus over Indian datasets.
AlgorithmAccuracyPrecisionRecallF1-score
DNN0.99690.99840.94430.9155
DBN0.99680.99820.94380.9151
ANN0.99610.99730.93640.9015
FFNN0.99610.99730.93510.9012
BPNN0.99540.99630.92700.8806
Table 5 Performance of remdesivir drug interaction with SARS-CoV-2 virus over Indian datasets.
AlgorithmAccuracyPrecisionRecallF1-score
DNN0.98220.69630.99990.8197
DBN0.98200.69130.99980.8129
ANN0.98110.67520.99950.8021
FFNN0.98100.67000.99940.7969
BPNN0.98080.66640.99890.7956
Table 6 Performance of ritonavir drug interaction with SARS-CoV-2 virus over Indian datasets.
[1]   Singh A. K., Singh A., Shaikh A., Singh R., and Misra A., Chloroquine and hydroxychloroquine in the treatment of COVID-19 with or without diabetes: A systematic search and a narrative review with a special reference to India and other developing countries, Diabetes Metab. Syndr. Clin. Res. Rev., vol. 14, no. 3, pp. 241-246, 2020.
[2]   Yang J. Y., Roy A., and Zhang Y., Protein-ligand binding site recognition using complementary binding-specific substructure comparison and sequence profile alignment, Bioinformatics, vol. 29, no. 20, pp. 2588-2595, 2013.
[3]   Cui Y. F., Dong Q. W., Hong D. C., and Wang X., Predicting protein-ligand binding residues with deep convolutional neural networks, BMC Bioinformatics, vol. 20, no. 1, p. 93, 2019.
[4]   Wang S., Sun S. Q., Li Z., Zhang R. Y., and Xu J. B., Accurate de novo prediction of protein contact map by ultra-deep learning model, PLoS Comput. Biol., vol. 13, no. 1, p. e1005324, 2017.
[5]   Yang J. Y., Ro A., and Zhang Y., BioLiP: A semi-manually curated database for biologically relevant ligand-protein interactions, Nucl. Acids Res., vol. 41, no. D1, pp. D1096-D1103, 2012.
[6]   Mothay D. and Ramesh K. V., Binding site analysis of potential protease inhibitors of COVID-19 using AutoDock, VirusDis., vol. 31, no. 2, pp. 194-199, 2020.
[7]   Huang L., Han R., Ai T., Yu P. X., Kang H., Tao Q., and Xia L. M., Serial quantitative chest CT assessment of COVID-19: Deep-learning approach, Radiol. Cardiothorac. Imaging, vol. 2, no. 2, p. e200075, 2020.
[8]   Li L., Qin L. X., Xu Z. G., Yin Y. B., Wang X., Kong B., J Bai J., Lu Y., Fang Z. H., Song Q., et al., Artificial intelligence distinguishes COVID-19 from community acquired pneumonia on chest CT, , 2020.
doi: https://doi.org/10.1148/radiol.2020200905
[9]   Apostolopoulos I. D. and Mpesiana T. A., Covid-19: Automatic detection from X-ray images utilizing transfer learning with convolutional neural networks, Phys. Eng. Sci. Med., vol. 431, pp. 635-640, 2020.
[10]   Butt C., Gill J., Chun D., and Babu B. A., Deep learning system to screen coronavirus disease 2019 pneumonia, Appl. Intell., .
doi: 10.1007/s10489-020-01714-3
[11]   Zheng C. S., Deng X. B., Fu Q., Zhou Q., Feng J. P., Ma H., Liu W. Y., and Wang X. G., Deep learning-based detection for COVID-19 from chest CT using weak label, , 2020.
doi: https://doi.org/10.1101/2020.03.12.20027185
[12]   Li D. S., Wang D. W., Dong J. P., Wang N. N., Huang H., Xu H. W., and Xia C., False-negative results of real-time reverse-transcriptase polymerase chain reaction for severe acute respiratory syndrome coronavirus 2: Role of deep-learning-based CT diagnosis and insights from two cases, Korean J. Radiol., vol. 21, no. 4, pp. 505-508, 2020.
[13]   Zhang H. P., Saravanan K. M., Yang Y., Hossain M. T., Li J. X., Ren X. H., Pan Y., and Wei Y. J., Deep learning based drug screening for novel coronavirus 2019-nCov, Interdiscip. Sci. Comput. Life Sci., .
doi: 10.1007/s12539-020-00376-6
[14]   Torrisi M., Pollastri G., and Le Q., Deep learning methods in protein structure prediction, Comput. Structural Biotechnol. J., vol. 18, pp. 1301-1310, 2020.
[15]   Rumelhart D. E., Hinton G. E., and Williams R. J., Learning representations by back-propagating errors, Nature, vol. 323, no. 6088, pp. 533-536, 1986.
[16]   Senior A. W., Evans R., Jumper J., Kirkpatrick J., Sifre L., Green T., Qin C. L., ?ídek A., Nelson A. W. R., Bridgland A., et al., Improved protein structure prediction using potentials from deep learning, Nature, vol. 577, no. 7792, pp. 706-710, 2020.
[17]   Elman J. L., Finding structure in time, Cogn. Sci., vol. 14, no. 2, pp. 179-211, 1990.
[18]   Wang S., Peng J., Ma J. Z., and Xu J. B., Protein secondary structure prediction using deep convolutional neural fields, Sci. Rep., vol. 6, no. 1, p. 18 962, 2016.
[19]   LeCun Y., Bengio Y., and Hinton G., Deep learning, Nature, vol. 521, no. 7553, pp. 436-444, 2015.
[20]   Hinz H. J., Thermodynamics of protein-ligand interactions: Calorimetric approaches, Annu. Rev. Biophys. Bioeng., vol. 12, no. 1, pp. 285-317, 1983.
[21]   Simonson T., Archontis G., and Karplus M., Free energy simulations come of age: Protein-ligand recognition, Acc. Chem. Res., vol. 35, no. 6, pp. 430-437, 2002.
[22]   Perozzo R., Folkers G., and Scapozza L., Thermodynamics of protein-ligand interactions: History, presence, and future aspects, J. Recept. Signal Transduct. Res., vol. 24, nos. 1&?2, pp. 1-52, 2004.
[23]   Hendlich M., Bergner A., Günther J., and Klebe G., Relibase: Design and development of a database for comprehensive analysis of protein-ligand interactions, J. Mol. Biol., vol. 326, no. 2, pp. 607-620, 2003.
[24]   Lian L. Y., Barsukov I. L., Sutcliffe M. J., Sze K. H., and Roberts G. C., Protein-ligand interactions: Exchange processes and determination of ligand conformation and protein-ligand contacts, Meth. Enzymol., vol. 239, pp. 657-700, 1994.
[25]   Mirceva G. and Kulakov A., Improvement of protein binding sites prediction by selecting amino acid residues’ features, J. Struct. Biol., vol. 189, no. 1, pp. 9-19, 2015.
[26]   Yan C. H. and Wang Y. F., A graph kernel method for DNA-binding site prediction, BMC Syst. Biol., vol. 8, no. S4, p. S10, 2014.
[27]   Izidoro S. C., de Melo-Minardi R. C., and Pappa G. L., GASS: Identifying enzyme active sites with genetic algorithms, Bioinformatics, vol. 31, no. 6, pp. 864-870, 2015.
[28]   Park B., Im J., Tuvshinjargal N., Lee W., and Han K., Sequence-based prediction of protein-binding sites in DNA: Comparative study of two SVM models, Comp. Methods Programs Biomed., vol. 117, no. 2, pp. 158-167, 2014.
[29]   Bartlett G. J., Porter C. T., Borkakoti N., and Thornton J. M., Analysis of catalytic residues in enzyme active sites, J. Mol. Biol., vol. 324, no. 1, pp. 105-121, 2002.
[30]   Zvelebil M. J. J. M. and Sternberg M. J. E., Analysis and prediction of the location of catalytic residues in enzymes, Protein Eng. Des. Sel., vol. 2, no. 2, pp. 127-138, 1988.
[31]   Taroni C., Jones S., and Thornton J. M., Analysis and prediction of carbohydrate binding sites, Protein Eng. Des. Sel., vol. 13, no. 2, pp. 89-98, 2000.
[32]   AlQuraishi M., ProteinNet: A standardized data set for machine learning of protein structure, BMC Bioinform., vol. 20, no. 1, p. 311, 2019.
[1] Youssef Nait Malek,Mehdi Najib,Mohamed Bakhouya,Mohammed Essaaidi. Multivariate Deep Learning Approach for Electric Vehicle Speed Forecasting[J]. Big Data Mining and Analytics, 2021, 4(1): 56-64.
[2] Wei Zhong, Ning Yu, Chunyu Ai. Applying Big Data Based Deep Learning System to Intrusion Detection[J]. Big Data Mining and Analytics, 2020, 3(3): 181-195.
[3] Sunitha Basodi, Chunyan Ji, Haiping Zhang, Yi Pan. Gradient Amplification: An Efficient Way to Train Deep Neural Networks[J]. Big Data Mining and Analytics, 2020, 3(3): 196-207.
[4] Chaity Banerjee, Tathagata Mukherjee, Eduardo Pasiliao Jr.. Feature Representations Using the Reflected Rectified Linear Unit (RReLU) Activation[J]. Big Data Mining and Analytics, 2020, 3(2): 102-120.
[5] Zhenxing Guo, Shihua Zhang. Sparse Deep Nonnegative Matrix Factorization[J]. Big Data Mining and Analytics, 2020, 03(01): 13-28.
[6] Qile Zhu, Xiyao Ma, Xiaolin Li. Statistical Learning for Semantic Parsing: A Survey[J]. Big Data Mining and Analytics, 2019, 2(4): 217-239.
[7] Ying Yu, Min Li, Liangliang Liu, Yaohang Li, Jianxin Wang. Clinical Big Data and Deep Learning: Applications, Challenges, and Future Outlooks[J]. Big Data Mining and Analytics, 2019, 2(4): 288-305.
[8] Wenmao Wu, Zhizhou Yu, Jieyue He. A Semi-Supervised Deep Network Embedding Approach Based on the Neighborhood Structure[J]. Big Data Mining and Analytics, 2019, 2(3): 205-216.
[9] Jiangcheng Zhu, Shuang Hu, Rossella Arcucci, Chao Xu, Jihong Zhu, Yi-ke Guo. Model Error Correction in Data Assimilation by Integrating Neural Networks[J]. Big Data Mining and Analytics, 2019, 2(2): 83-91.
[10] Jin Liu, Yi Pan, Min Li, Ziyue Chen, Lu Tang, Chengqian Lu, Jianxin Wang. Applications of Deep Learning to MRI Images: A Survey[J]. Big Data Mining and Analytics, 2018, 1(1): 1-18.
[11] Ning Yu, Zhihua Li, Zeng Yu. Survey on Encoding Schemes for Genomic Data Representation and Feature Learning—From Signal Processing to Machine Learning[J]. Big Data Mining and Analytics, 2018, 01(03): 191-210.
[12] Qianyu Meng, Kun Wang, Xiaoming He, Minyi Guo. QoE-Driven Big Data Management in Pervasive Edge Computing Environment[J]. Big Data Mining and Analytics, 2018, 01(03): 222-233.