Abstract
This paper proposes to model protein folding as an emergent process, using machine learning to infer the folding modeling only from information of known protein structures. Using the face-centered cubic lattice for protein conformation representation, the dynamic nature of protein folding is captured with an evolved neural cellular automaton that defines the amino acids moves along the protein chain and across time. The results of the final folded conformations are compared, using different protein benchmarks, with other methods used in the traditional protein structure prediction problem, highlighting the capabilities and problems found with this modeling.
Similar content being viewed by others
Notes
The acronym CA will be used either for Cellular Automata or for Cellular Automation.
References
Anfinsen CB (1973) Principles that govern the folding of proteins. Science 181(96):223–230
Backofen R, Will S (2006) A constraint-based approach to fast and exact structure prediction in three-dimensional protein models. Constraints 11(1):5–30
Backofen R, Will S, Clote P (2000) Algorithmic approach to quantifying the hydrophobic force contribution in protein folding. In: Proceedings of the Pacific symposium on biocomputing. Citeseer, pp 92–103
Calabretta R, Nolfi S, Parisi D (1995) An artificial life model for predicting the tertiary structure of unknown proteins that emulates the folding process. In: Proceedings of European conference on advances in artificial life—LNCS, vol 929, pp 862–875
Conway JH, Sloane NJA (1998) Sphere packings, lattices and groups. Springer, Berlin
Cutello V, Nicosia G, Pavone M, Timmis J (2007) An immune algorithm for protein structure prediction on lattice models. IEEE Trans Evolut Comput 11(1):101–117
Danks G, Stepney S, Caves L (2008) Protein folding with stochastic L-systems. In: Proceedings of artificial life XI, pp 150–157
Dill KA (1990) Dominant forces in protein folding. Biochemestry 29:7133–7155
Dotu I, Cebrián M, Van Hentenryck PV, Clote P (2011) On lattice protein structure prediction revisited. IEEE/ACM Trans Comput Biol Bioinform 8(6):1620–1632
Feig M, Mirjalili V (2016) Protein structure refinement via molecular-dynamics simulations: what works and what does not? Proteins Suppl 1:282–292
Hirst JD (1999) The evolutionary landscape of functional model proteins. Protein Eng 12(9):721–726
Ilachinski A (2001) Cellular automata, a discrete universe. World Scientific, Singapore
Krasnogor N, Hart WE, Smith J, Pelta DA (1999) Protein structure prediction with evolutionary algorithms. In: Proceedings of the genetic and evolutionary computation conference—GECCO’99, pp 1596–1601
Krasnogor N, Terrazas G, Pelta DA, Ochoa G (2002) A critical view of the evolutionary design of self-assembling systems. In: Proceedings of the 2005 conference on artificial evolution, LNCS, vol 3871, pp 179–188
Langton CG (1992) Life at the edge of chaos. In: Langton CG, Taylor C, Farmer JD, Rasmussen S (eds) Artificial life II. Addison-Wesley, Reading, pp 41–49
Levinthal C (1968) Are there pathways for protein folding? J Chim Phys 65:44–45
Metropolis N, Rosenbluth AW, Rosenbluth MN, Teller AH, Teller E (1953) Equation of state calculations by fast computing machines. J Chem Phys 21(6):1087–1092
Olson B, De-Jong K, Shehu A (2013) Off-lattice protein structure prediction with homologous crossover. In: Proceedings conference on genetic and evolutionary computation—GECCO 2013, pp 287–294
Patton WP, Punch WF, Goldman E (1995) A standard genetic algorithm approach to native protein conformation prediction. In: Proceedings of 6th international conference on genetic algorithms, pp 574–581
Price KV, Storn RM, Lampinen JA (2005) Differential evolution. A practical approach to global optimization. Natural computer series. Springer, Berlin
Rashid MA, Hoque MT, Newton MH, Pham DN, Sattar A (2012) A new genetic algorithm for simplified protein structure prediction. In: Proceedings Australasian joint conference on advances in artificial intelligence—AI 2012, LNCS, vol 7691, pp 107–119
Rosetta system. http://www.rosettacommons.org
Santos J, Diéguez M (2011) Differential evolution for protein structure prediction using the HP model. In: Lecture Notes in Computer Science, vol 6686, pp 323–323
Santos J, Villot P, Diéguez M (2013) Cellular automata for modeling protein folding using the HP model. In: Proceedings IEEE congress on evolutionary computation—IEEE-CEC 2013, pp 1586–1593
Santos J, Villot P, Diéguez M (2014) Emergent protein folding modeled with evolved neural cellular automata using the 3D HP model. J Comput Biol 21(11):823–845
Shatabda S, Newton MH, Pham DN, Sattar A (2012) Memory-based local search for simplified protein structure prediction. In: Proceedings of ACM conference on bioinformatics, computational biology and biomedicine—BCB’12, pp 345–352
Shatabda S, Newton MH, Rashid MA, Sattar A (2013) An efficient encoding for simplified protein structure prediction using genetic algorithms. In: Proceedings of IEEE congress on evolutionary computation—IEEE-CEC 2013, pp 1217–1224
Shmygelska A, Hoos HH (2005) An ant colony optimisation algorithm for the 2D and 3D hydrophobic polar protein folding problem. Bioinformatics 6:30
Tsay J-J, Su S-C (2013) An effective evolutionary algorithm for protein folding on 3D FCC HP model by lattice rotation and generalized move sets. Proteome Sci 11(1):S19
Unger R, Moult J (1993) Genetic algorithms for protein folding simulations. J Mol Biol 231(1):75–81
Varela D, Santos J (2017) Protein folding modeling with neural cellular automata using the face-centered cubic model. In: Proceedings international work-conference on the interplay between natural and artificial computation. LNCS, vol 10337, pp 125–134
Yue K, Fiebig KM, Thomas PD, Chan HS, Shakhnovich EI, Dill KA (1995) A test of lattice protein folding algorithms. In: Proceedings of the pacific symposium on biocomputing, vol 92, no 1, p 325
Zhao X (2008) Advances on protein folding simulations based on the lattice HP models with natural computing. Appl Soft Comput 8:1029–1040
Acknowledgements
This work was funded by Xunta de Galicia (Project GPC ED431B 2016/035), Xunta de Galicia (“Centro singular de investigación de Galicia” accreditation 2016-2019 ED431G/01) and the European Regional Development Fund (ERDF). D. Varela Grant has received financial support from the Xunta de Galicia and the European Union (European Social Fund – ESF).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Varela, D., Santos, J. Automatically obtaining a cellular automaton scheme for modeling protein folding using the FCC model. Nat Comput 18, 275–284 (2019). https://doi.org/10.1007/s11047-018-9705-y
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11047-018-9705-y