AI-Assisted Genetic Algorithm Framework for DNA Staple Sequence Stability Optimization

This paper presented a lightweight, AI-assisted Genetic Algorithm system for pre-screening and optimizing individual DNA staple sequences ahead of full thermodynamic analysis. By combining complementary base-pair count, GC content ratio, hairpin detection, and pseudoknot avoidance into a single fitness function, and implementing selection, crossover, and mutation operators from first principles, the system demonstrates consistent fitness improvement over a random-search baseline and reasonable agreement with NUPACK on a sample of test sequences. The tool is intended as a fast pre-filter that reduces the computational and laboratory burden associated with downstream thermodynamic analysis and wet-lab synthesis, rather than as a substitute for research-grade tools. Future work will focus on (i) extending the fitness function to incorporate condition-dependent thermodynamic terms such as salt concentration, pH, and temperature; (ii) benchmarking the system on a larger and more structurally diverse sequence dataset; (iii) exploring hybrid GA/molecular-dynamics approaches in line with recent trends in the literature [8],[10]; and (iv) integrating the pre-filter directly into existing DNA origami design tools such as caDNAno [3].

[1] J. SantaLucia Jr., “A unified view of polymer, dumbbell, and oligonucleotide DNA nearest-neighbor thermodynamics,” Proc. Natl. Acad. Sci. USA, vol. 95, no. 4, pp. 1460-1465, 1998. [2] J. N. Zadeh, C. D. Steenberg, J. S. Bois, B. R. Wolfe, M. B. Pierce, A. R. Khan, R. M. Dirks, and N. A. Pierce, “NUPACK: Analysis and design of nucleic acid systems,” J. Comput. Chem., vol. 32, no. 1, pp. 170-173, 2011. [3] S. M. Douglas, A. H. Marblestone, S. Teerapittayanon, A. Vazquez, G. M. Church, and W. M. Shih, “Rapid prototyping of 3D DNA-origami shapes with caDNAno,” Nucleic Acids Res., vol. 37, no. 15, pp. 5001-5006, 2009. [4] S. Y. Shin, I. H. Lee, D. Kim, and B. T. Zhang, “Multiobjective evolutionary optimization of DNA sequences for reliable DNA computing,” IEEE Trans. Evol. Comput., vol. 9, no. 2, pp. 143-158, 2005. [5] X. Li, Z. Q. Wei, B. Wang, and T. Song, “Stable DNA sequence over close-ending and pairing sequences constraint,” Front. Genet., vol. 12, art. 644484, 2021. [6] K. Deb, A. Pratap, S. Agarwal, and T. Meyarivan, “A fast and elitist multiobjective genetic algorithm: NSGA-II,” IEEE Trans. Evol. Comput., vol. 6, no. 2, pp. 182-197, 2002. [7] Q. Zhang and X. Xia, “The quality optimization of DNA sequences with improved genetic algorithm,” J. Comput. Theor. Nanosci., vol. 10, no. 5, pp. 1192-1195, 2013. [8] C. Maffeo and A. Aksimentiev, “MrDNA: A multi-resolution model for predicting the structure and dynamics of DNA systems,” Nucleic Acids Res., vol. 48, no. 9, pp. 5135-5146, 2020. [9] J. Y. Lee et al., “Investigating the sequence-dependent mechanical properties of DNA nicks for twisted DNA nanostructure design,” Nucleic Acids Res., vol. 47, no. 1, pp. 93-102, 2019. [10] C. M. Huang, A. Kucinic, J. V. Le, C. E. Castro, and H. J. Su, “Uncertainty quantification of a DNA origami mechanism with a coarse-grained model and kinematic variance analysis,” Nanoscale, vol. 11, no. 4, pp. 1647-1660, 2019.