Multistage Genetic Algorithm and Q-learning for Flexible Ligand-Protein Docking

  • Authors

    • Erzam Marlisah
    • Razali Yaakob
    • Md. Nasir Sulaiman
    • Mohd Basyaruddin Abdul Rahman
    • M. N. Shah Zainudin
    2018-12-09
    https://doi.org/10.14419/ijet.v7i4.31.27824
  • Protein docking, genetic algorithm, reinforcement learning, Q-learning agent, optimization.

  • Protein-ligand docking is an optimization task involving translation and rotation of orientation and torsional angles of a small molecule (ligand) with respect to a target protein. Traditional genetic algorithm can be used to find the optimal conformation, however it often found poor structure with high docked energy due to premature convergence and its weakness in performing precision search. The proposed algorithm is a multistage genetic algorithm with Q-learning agent to overcome the limitations inherent in genetic algorithm and reinforcement learning algorithm. The idea is to combine the explorative speed of genetic algorithm in finding promising area in the search space and the ability of the reinforcement learning agent to do fine-grained search. Docking of ten ligands to thermolysin as the target protein shows the proposed algorithm is more efficient in finding the lowest docked energies and more reliable in finding similar structure every run compared to traditional genetic algorithm and AutoDock Vina in docking highly flexible ligand. The algorithm almost matches AutoDock  Vina in docking less flexible ligands and outperforms it in docking highly flexible ligands.

     

     

  • References

    1. [1] Shoichet, B. K., McGovern, S. L., Wei, B., & Irwin, J. J. Lead discovery using molecular docking. Curr. Opin. Chem. Biol. 6(4): 439–446, 2002.

      [2] Simonson, T., Archontis, G., & Karplus, M. Free energy simulations come of age: protein- ligand recognition. Acc. Chem. Res. 35(6), 430–437,2002.

      [3] Chen, H.-M., Liu, B.-F., Huang, H.-L., Hwang, S.-F., & Ho, S.-Y. SODOCK: swarm optimization for highly flexible protein-ligand docking. J. Comput. Chem. 28(2): 612–623, 2007.

      [4] Gardiner, E. J., Willett, P., & Artymiuk, P. J. Protein docking using a genetic algorithm. Proteins: Struct., Funct., Bioinf. 44(1): 44–56, 2001.

      [5] Jones, G., Willett, P., Glen, R. C., Leach, A. R., & Taylor, R. Development and validation of a genetic algorithm for flexible docking. J. Mol. Biol. 267(3): 727–48, 1997.

      [6] Thomsen, R. Flexible ligand docking using evolutionary algorithms: investigating the effects of variation operators and local search hybrids. Biosystems. 72(1–2): 57–73, 2003.

      [7] Morris, G. M., Goodsell, D. S., Halliday, R. S., Huey, R., Hart, W. E., Belew, R. K., and Olson, A. J. Automated docking using a Lamarckian genetic algorithm and an empirical binding free energy function. J. Comput. Chem. 19(14): 1639-1662, 1998.

      [8] Yang, J. and Kao, C. Flexible ligand docking using a robust evolutionary algorithm. J. Comput. Chem. 21(11): 988–998, 2000.

      [9] Sutton, R. S., & Barto, A. G. Reinforcement learning: An introduction (Vol. 1). MIT press Cambridge, 1998.

      [10] Watkins, C., & Dayan, P. Q-learning. Machine Learning 8(3-4): 279–292, 1992.

      [11] Abdoos, M., Mozayani, N., Ana, L., & Bazzan, C. Hierarchical control of traffic signals using Q-learning with tile coding. Applied Intelligence 40(2): 201-213, 2014.

      [12] Beom, H. R., & Cho, H. S.A sensor-based navigation for a mobile robot using fuzzy logic and reinforcement learning. IEEE Transactions on Systems, Man, and Cybernetics 25(3): 464–477, 1995.

      [13] Forbes, J. R. N. Reinforcement learning for autonomous vehicles. University of California, Berkeley, 2002.

      [14] Kim, H. J., Jordan, M. I., Sastry, S., and Ng, A. Y. Autonomous helicopter flight via reinforcement learning. In: Advances in neural information processing systems. MIT 799-806, 2004.

      [15] Wen, Z., O’Neill, D., & Maei, H. Optimal demand response using device-based reinforcement learning. IEEE Transactions on Smart Grid 6(5): 2312–2324, 2015.

      [16] De Magalhães, C. S., Barbosa, H. J. C., and Dardenne, L. E. A genetic algorithm for the ligand-protein docking problem. Genet. Mol. Biol. 27: 605–610, 2004.

      [17] Atilgan, E. and Hu, J. Efficient protein-ligand docking using sustainable evolutionary algorithms. In: 10th International Conference on Hybrid Intelligent Systems. 23 August 2010. IEEE 113–118, 2010.

      [18] Ng, M. C. K., Fong, S., and Siu, S. W. I. PSOVina: The hybrid particle swarm optimization algorithm for protein-ligand docking. J. Bioinform. Comput. Biol. 13(03): 1541007, 2015.

      [19] Trott, O. and Olson, A. AutoDock Vina: improving the speed and accuracy of docking with a new scoring function, efficient optimization, and multithreading. J. Comput. Chem. 31(2): 455–461, 2010.

      [20] Allen, M., and Fritzsche, P. Reinforcement learning with adaptive Kanerva coding for Xpilot game AI. In: Congress of Evolutionary Computation (CEC). 5 Jun 2011. IEEE 1521–1528, 2011.

      [21] Rahman, M. B. A., Jaafar, A. H., Basri, M., Rahman, R. N. Z. R. A., Salleh, A. B., and Wahab, H. A. Design of novel semisynethetic metalloenzyme from thermolysin. BMC Syst. Biol. 1(1): 1–2, 2007.

      [22] Berman, H. M., Westbrook, J., Feng, Z., Gilliland, G., Bhat, T. N., Weissig, H., Shindyalov, I.N. and Bourne, P. E. The Protein Data Bank. Nucleic Acids Research 28: 235-242, 2000.

      [23] Rahman, M. B. A., Jaafar, A. H., Basri, M., Rahman, R. N. Z. R. A., and Salleh, A. B. Biomolecular Design and Receptor-Ligand Interaction of a Potential Industrial Biocatalsyt: A Thermostable Thermolysin-Phosphoeth-anolamine-Ca 2 Protein Complex. J. Adv. Catal. Sci. Technol. 1: 1–5, 2014.

  • Downloads

  • How to Cite

    Marlisah, E., Yaakob, R., Nasir Sulaiman, M., Basyaruddin Abdul Rahman, M., & N. Shah Zainudin, M. (2018). Multistage Genetic Algorithm and Q-learning for Flexible Ligand-Protein Docking. International Journal of Engineering & Technology, 7(4.31), 528-532. https://doi.org/10.14419/ijet.v7i4.31.27824