نوع مقاله : مقاله کامل پژوهشی

نویسندگان

1 دانشجوی کارشناسی ارشد مهندسی‏ کامپیوتر گرایش هوش ‏مصنوعی و رباتیک-دانشگاه علم و صنعت ایران

2 استادیار دانشکده مهندسی‏ کامپیوتر-دانشگاه علم و صنعت ایران

10.22041/ijbme.2012.13170

چکیده

کشف داروهای جدید و بررسی اثرات ‎جانبی آن‏ها یکی از زمینه‏های مهم پژوهشی است که دانشمندان داروساز در آن به فعالیت مشغولند. به دلیل اثرِ مستقیمِ محصولات دارویی بر سلامت انسان‏ها، تحقیقات داروسازی از حساسیت بالایی برخوردار بوده و رسیدن به جوابی مطلوب در این تحقیقات اغلب زمان زیادی احتیاج خواهدداشت. پیش‏بینی ساختار دارو به کمک نرم‏افزارهای شبیه‏سازی، راهکاری است که در سال‏های اخیر مورد توجه محققین داروسازی بوده‏است. در این مسئله دانشمندان به دنبال یافتن بهترین برهم‏کنشِ بین ساختار دارو و گیرنده‏ می‏باشند. این مسئله در منابع علمی با نام پهلوگیری‏مولکولی شناخته می‏شود و می‏توان آن‏را به عنوان یک مسئله جستجو در نظر گرفت که فضای جستجو در آن حالت‏های مختلف برهم‏کنش دارو وگیرنده می‏باشد. هدف نهایی از حل این مسئله انتخاب بهترین برهم‏کنش از میان این فضای جستجو است. در این مقاله از الگوریتم‏ تکامل‏تفاضلی مبتنی بر نقطه مقابل برای یافتن بهترین حالت برهم‏کنش دارو و گیرنده استفاده شده‎است. برای بهبود نتایج، الگوریتم مذکور با یک روش جستجوی محلی و یک عملگر نخبه‏گرا تلفیق شده‏است. الگوریتم ارائه‏شده، مانند دیگر الگوریتم‏های فرااکتشافی یک الگوریتم تکرار شونده می‏باشد که به کمک جمعیتی از بردارهای جواب سعی در یافتن بهترین برهم‏کنش دارد. همچنین تابع ارزیاب استفاده شده در این پژوهش تابع ارزیاب AutoDock می‏باشد. برای ارزیابی الگوریتم پیشنهادی شش ساختار متفاوت گیرنده-دارو استفاده شده‏است. نتایج حاصل از پیش‏بینی ساختار دارو برای هر یک از این شش گیرنده با نتایج الگوریتم ژنتیک لامارکی و الگوریتم سردسازی شبیه‌سازی شده و الگوریتم‏ تکامل‏تفاضلی معمولی مقایسه شده‏است. بر اساس نتایج الگوریتم ارائه شده نسبت به الگوریتم‏های دیگر از عملکرد بهتری برخوردار است.

کلیدواژه‌ها

موضوعات

عنوان مقاله [English]

Suitable drug structure prediction with Opposition-Based Differential Evolution

نویسندگان [English]

  • Mohammad Koohimoghadam 1
  • Adel Torkamaan Rahmani 2

1 M.Sc Student, Department of Computer Engineering, Iran University of Science and Technology

2 Assistant Professor, Department of Computer Engineering, Iran University of Science and Technology

چکیده [English]

Discovery of new drugs and study of their side effects has been an important research field in recent years. Because of direct effect of the pharmaceutical products on human health usually the drug design projects are challenging and technically demanding. The incorporation of computer simulations into drug design projects is one of the best ways to optimize drugs' potency. In this approach, researchers try to find the best interaction between protein structure and drug in a virtual environment; this procedure is called "molecular docking". The molecular docking problem can be considered as a search problem. The search space in this problem is defined with all possible protein-ligand interactions and the best interaction is the solution of problem. In this paper, a new approach for finding the best interaction is proposed. The proposed method is based on opposition based differential evolution algorithm. Also the proposed method is enhanced by a local search algorithm and a pseudo-elitism operator. Like other metaheuristic algorithms, our method uses a population of possible solution and AutoDock scoring function is used to evaluate each vector in the population. Six different protein-ligand complexes are used to verify the efficiency of the proposed algorithm. The experimental results show that the proposed algorithm is more robust and reliable than other algorithms such as simulated annealing and Lamarckian genetic algorithm.

کلیدواژه‌ها [English]

  • Drug
  • receptor
  • Molecular Docking
  • Differential Evolution Algorithm
  • scori
[1]     Krasky, et al., "A combined bioinformatics and chemoinformatics approach for the development of new antiparasitic drugs," Genomics, vol. 89, pp. 36- 43, 2007.
[2]     C. Steinbeck, et al., "Computational metabolomics–a field at the boundaries of cheminformatics and bioinformatics," Journal of Cheminformatics, vol. 3, pp. 1-1, 2011.
[3]   S. Mandal, et al., "Rational drug design," European journal of pharmacology, vol. 625, pp. 90-100, 2009.
[4]     Y. Chen and B. K. Shoichet, "Molecular docking and ligand specificity in fragment-based inhibitor discovery," Nature Chemical Biology, vol. 5, pp. 358- 364, 2009.
[5]   Oduguwa, et al., "An Overview of Soft Computing Techniques Used in the Drug Discovery Process," Applied Soft Computing Technologies: The Challenge of Complexity, pp. 465-480, 2006.
[6]     T. J. A. Ewing, et al., "DOCK 4.0: search strategies for automated molecular docking of flexible molecule databases," Journal of computer-aided molecular design, vol. 15, pp. 411-428, 2001.
[7]     G. M. Morris, et al., "Automated docking using a Lamarckian genetic algorithm and an empirical binding free energy function," Journal of computational chemistry, vol. 19, pp. 1639-1662, 1998.
[8]     G. M. Morris, et al., "AutoDock4 and AutoDockTools4: Automated docking with selective receptor flexibility," Journal of computational chemistry, vol. 30, pp. 2785-2791, 2009.
[9]     M. L. Verdonk, et al., "Improved protein–ligand docking using GOLD," Proteins: Structure, Function, and Bioinformatics, vol. 52, pp. 609-623, 2003.
[10] S. Joy, et al., "Detailed comparison of the proteinligand docking efficiencies of GOLD, a commercial package and ArgusLab, a licensable freeware," In silico biology, vol. 6, pp. 601-605, 2006.
[11] B. Kramer, et al., "Evaluation of the FLEXX incremental construction algorithm for protein–ligand docking," Proteins: Structure, Function, and Bioinformatics, vol. 37, pp. 228-241, 1999.
[12] D. Kuntz, et al., "A geometric approach to macromolecule-ligand interactions," Journal of molecular biology, vol. 161, pp. 269-288, 1982.
[13] M. Liu and S. Wang, "MCDOCK: a Monte Carlo simulation approach to the molecular docking problem," Journal of computer-aided molecular design, vol. 13, pp. 435-451, 1999.
[14] R. Meier, et al., "ParaDockS: A Framework for Molecular Docking with Population-Based Metaheuristics," Journal of Chemical Information and Modeling, vol. 50, pp. 879-889, 2010.
[15] B. S. Sadjad and Z. Zsoldos, "Toward a Robust Search Method for the Protein-Drug Docking Problem," IEEE IEEE/ACM Transactions on Computational Biology and Bioinformatics, pp. 1120- 1133, 2010.
[16] D. S. Goodsell and A. J. Olson, "Automated docking of substrates to proteins by simulated annealing," Proteins: Structure, Function, and Bioinformatics, vol. 8, pp. 195-202, 1990.
[17] S. Janson, et al., "Molecular docking with multiobjective Particle Swarm Optimization," Applied Soft Computing, vol. 8, pp. 666-675, 2008.
[18] Oduguwa, et al., "Multi-objective optimisation of the protein-ligand docking problem in drug discovery," 2006, pp. 1793 1800.
[19] O. Korb, et al., "PLANTS: Application of ant colony optimization to structure-based drug design," Ant Colony Optimization and Swarm Intelligence, pp. 247-258, 2006.
[20] R. Thomsen, "Flexible ligand docking using differential evolution," 2003, pp. 2354-2361 Vol. 4.
[21] S. Rahnamayan, "Opposition-based differential evolution," Doctor of Philosophy, Systems Design Engineering, University of Waterloo, 2008.
[22] H. R. Tizhoosh, "Reinforcement learning based on actions and opposite actions," 2005.
[23] L. Yao, et al., "Novel opportunities for computational biology and sociology in drug discovery:: Corrected paper," Trends in biotechnology, vol. 28, pp. 161- 170, 2010.
[24] S. Moreira, et al., "Protein–protein docking dealing with the unknown," Journal of computational chemistry, vol. 31, pp. 317-342, 2010.
[25] M. Totrov and R. Abagyan, "Flexible ligand dockingto multiple receptor conformations: a practical alternative," Current opinion in structural biology, vol. 18, pp. 178-184, 2008.
[26] M. Hartenfeller and G. Schneider, "De novo drug design," Meth Mol Biol, vol. 672, pp. 299-323, 2011.
[27] M. L. Teodoro, et al., "Molecular docking: A problem with thousands of degrees of freedom," 2001, pp. 960-965 vol. 1.
[28] R. Storn and K. Price, "Differential evolution-a simple and efficient adaptive scheme for global optimization over continuous spaces," International Computer Science Institute-Publications-TR, 1995.
[29] R. Storn and K. Price, "Differential evolution–a simple and efficient heuristic for global optimization over continuous spaces," Journal of Global Optimization, vol. 11, pp. 341-359, 1997.
[30] V. Price, et al., Differential evolution: Springer Berlin, Germany, 2005.
[31] H. R. Tizhoosh, "Opposition-based learning: A new scheme for machine intelligence," 2005, pp. 695-701.
[32] S. Rahnamayan, et al., "Opposition-based differential evolution," Evolutionary Computation, IEEE Transactions on, vol. 12, pp. 64-79, 2008.
[33] F. J. Solis, "Minimization by random search techniques," Mathematics of operations research, pp. 19-30, 1981.
[34] L. Mackay, "Quaternion transformation of molecular orientation," Acta Crystallographica Section A: Foundations of Crystallography, vol. 40, pp. 165-166, 1984.
[35] Shoemake, "Uniform Random Rotations," in Graphics Gems III, D. Kirk, Ed., ed New York and Orlando: Academic Press, 1992, pp. 124–132.
[36] W. D. Cornell, et al., "A second generation force field for the simulation of proteins, nucleic acids, and organic molecules," Journal of the American Chemical Society, vol. 117, pp. 5179-5197, 1995.
[37] R. Dias, et al., "Molecular docking algorithms," Current Drug Targets, vol. 9, pp. 1040-1047, 2008.