Exploring Material Design Space with a Deep-Learning Guided Genetic Algorithm

Authors Kuan-Lin Chen, Rebecca Schulman



PDF
Thumbnail PDF

File

LIPIcs.DNA.28.4.pdf
  • Filesize: 1.08 MB
  • 14 pages

Document Identifiers

Author Details

Kuan-Lin Chen
  • Department of Chemical and Biomolecular Engineering, Johns Hopkins University, Baltimore, MD, USA
Rebecca Schulman
  • Department of Chemical and Biomolecular Engineering, Johns Hopkins University, Baltimore, MD, USA
  • Department of Computer Science, Johns Hopkins University, Baltimore, MD, USA
  • Department of Chemistry, Johns Hopkins University, Baltimore, MD, USA

Acknowledgements

We would like to thank the Maryland Advanced Research Computing Center (MARCC) for providing cloud computing GPU services.

Cite AsGet BibTex

Kuan-Lin Chen and Rebecca Schulman. Exploring Material Design Space with a Deep-Learning Guided Genetic Algorithm. In 28th International Conference on DNA Computing and Molecular Programming (DNA 28). Leibniz International Proceedings in Informatics (LIPIcs), Volume 238, pp. 4:1-4:14, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2022)
https://doi.org/10.4230/LIPIcs.DNA.28.4

Abstract

Designing complex, dynamic yet multi-functional materials and devices is challenging because the design spaces for these materials have numerous interdependent and often conflicting constraints. Taking inspiration from advances in artificial intelligence and their applications in material discovery, we propose a computational method for designing metamorphic DNA-co-polymerized hydrogel structures. The method consists of a coarse-grained simulation and a deep learning-guided optimization system for exploring the immense design space of these structures. Here, we develop a simple numeric simulation of DNA-co-polymerized hydrogel shape change and seek to find designs for structured hydrogels that can fold into the shapes of different Arabic numerals in different actuation states. We train a convolutional neural network to classify and score the geometric outputs of the coarse-grained simulation to provide autonomous feedback for design optimization. We then construct a genetic algorithm that generates and selects large batches of material designs that compete with one another to evolve and converge on optimal objective-matching designs. We show that we are able to explore the large design space and learn important parameters and traits. We identify vital relationships between the material scale size and the range of shape change that can be achieved by individual domains and we elucidate trade-offs between different design parameters. Finally, we discover material designs capable of transforming into multiple different digits in different actuation states.

Subject Classification

ACM Subject Classification
  • Computing methodologies → Artificial intelligence
  • Computing methodologies → Modeling and simulation
Keywords
  • Machine Learning
  • Deep Learning
  • Computational Material Design
  • Multi-Objective Optimization
  • DNA Nanotechnology

Metrics

  • Access Statistics
  • Total Accesses (updated on a weekly basis)
    0
    PDF Downloads

References

  1. Dhiraj Bhatia, Christian Wunder, and Ludger Johannes. Self-assembled, programmable dna nanodevices for biological and biomedical applications. ChemBioChem, 22(5):763-778, 2021. Google Scholar
  2. Angelo Cangialosi, ChangKyu Yoon, Jiayu Liu, Qi Huang, Jingkai Guo, Thao D. Nguyen, David H. Gracias, and Rebecca Schulman. Dna sequence−directed shape change of photopatterned hydrogels via high-degree swelling. Science, 357(6356):1126-1130, 2017. URL: https://doi.org/10.1126/science.aan3925.
  3. VF Cardoso, C Ribeiro, and S Lanceros-Mendez. Metamorphic biomaterials. Bioinspired Materials for Medical Applications, pages 69-99, 2017. Google Scholar
  4. N. Chakraborti. Genetic algorithms in materials design and processing. International Materials Reviews, 49(3-4):246-260, 2004. URL: https://doi.org/10.1179/095066004225021909.
  5. Peter W Deelman, Lisa F Edge, and Clayton A Jackson. Metamorphic materials for quantum computing. MRS Bulletin, 41(3):224-230, 2016. Google Scholar
  6. Li Deng. The mnist database of handwritten digit images for machine learning research [best of the web]. IEEE signal processing magazine, 29(6):141-142, 2012. Google Scholar
  7. Abhijith M Gopakumar, Prasanna V Balachandran, Dezhen Xue, James E Gubernatis, and Turab Lookman. Multi-objective optimization for materials discovery via adaptive design. Scientific reports, 8(1):1-12, 2018. Google Scholar
  8. Mustapha Jamal, Sachin S Kadam, Rui Xiao, Faraz Jivan, Tzia-Ming Onn, Rohan Fernandes, Thao D Nguyen, and David H Gracias. Bio-origami hydrogel scaffolds composed of photocrosslinked peg bilayers. Advanced healthcare materials, 2(8):1142-1150, 2013. Google Scholar
  9. Paul C Jennings, Steen Lysgaard, Jens Strabo Hummelshøj, Tejs Vegge, and Thomas Bligaard. Genetic algorithms for computational materials discovery accelerated by machine learning. NPJ Computational Materials, 5(1):1-6, 2019. Google Scholar
  10. Michał Joachimczak, Reiji Suzuki, and Takaya Arita. Artificial metamorphosis: Evolutionary design of transforming, soft-bodied robots. Artificial life, 22(3):271-298, 2016. Google Scholar
  11. Yongfei Juan, Yongbing Dai, Yang Yang, and Jiao Zhang. Accelerating materials discovery using machine learning. Journal of Materials Science & Technology, 79:178-190, 2021. URL: https://doi.org/10.1016/j.jmst.2020.12.010.
  12. Diederik P Kingma and Jimmy Ba. Adam: A method for stochastic optimization. arXiv preprint, 2014. URL: http://arxiv.org/abs/1412.6980.
  13. Y. Lecun, L. Bottou, Y. Bengio, and P. Haffner. Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11):2278-2324, 1998. URL: https://doi.org/10.1109/5.726791.
  14. Yue Liu, Tianlu Zhao, Wangwei Ju, and Siqi Shi. Materials discovery and design using machine learning. Journal of Materiomics, 3(3):159-177, 2017. URL: https://doi.org/10.1016/j.jmat.2017.08.002.
  15. Arun Mannodi-Kanakkithodi and Maria KY Chan. Computational data-driven materials discovery. Trends in Chemistry, 3(2):79-82, 2021. Google Scholar
  16. Tarak K. Patra, Venkatesh Meenakshisundaram, Jui-Hsiang Hung, and David S. Simmons. Neural-network-biased genetic algorithms for materials design: Evolutionary algorithms that learn. ACS Combinatorial Science, 19(2):96-107, 2017. URL: https://doi.org/10.1021/acscombsci.6b00136.
  17. Anjali Rajwar, Sumit Kharbanda, Arun Richard Chandrasekaran, Sharad Gupta, and Dhiraj Bhatia. Designer, programmable 3d dna nanodevices to probe biological systems. ACS Applied Bio Materials, 3(11):7265-7277, 2020. Google Scholar
  18. Ruohong Shi, Joshua Fern, Weinan Xu, Sisi Jia, Qi Huang, Gayatri Pahapale, Rebecca Schulman, and David H Gracias. Multicomponent dna polymerization motor gels. Small, 16(37):2002946, 2020. Google Scholar
  19. Changwon Suh, Clyde Fare, James A Warren, and Edward O Pyzer-Knapp. Evolving the materials genome: How machine learning is fueling the next generation of materials discovery. Annual Review of Materials Research, 50:1-25, 2020. Google Scholar
  20. Rama Vasudevan, Ghanshyam Pilania, and Prasanna V Balachandran. Machine learning for materials design and discovery, 2021. Google Scholar
  21. Zhi Zhao, Chao Wang, Hao Yan, and Yan Liu. Soft robotics programmed with double crosslinking dna hydrogels. Advanced Functional Materials, 29(45):1905911, 2019. Google Scholar
Questions / Remarks / Feedback
X

Feedback for Dagstuhl Publishing


Thanks for your feedback!

Feedback submitted

Could not send message

Please try again later or send an E-mail