Efficient Image Encoding for DNA Data Storage Using Latent Space Representation of Variational Autoencoder

Muhammad Rafi Muttaqin; Yeni Herdiyeni; Agus Buono; Karlisa Priandana; Iskandar Zulkarnaen Siregar

doi:10.21512/commit.v20i2.13987

Authors

Muhammad Rafi Muttaqin IPB University and Sekolah Tinggi Teknologi Wastukancana
Yeni Herdiyeni IPB University
Agus Buono IPB University
Karlisa Priandana IPB University
Iskandar Zulkarnaen Siregar IPB University

DOI:

https://doi.org/10.21512/commit.v20i2.13987

Keywords:

Biological Constraint, Deoxyribonucleic Acid (DNA) Data Storage, Image Compression, Latent Space Representation, Variational Autoencoder (VAE)

Abstract

Deoxyribonucleic Acid (DNA)-based data storage as a revolutionary approach to long-term, highdensity information storage faces the challenge of high costs and biological constraints in DNA synthesis. Unlike conventional binary encoding, DNA storage requires efficient data compression techniques to minimize the length of the resulting DNA sequence. The research explores the use of a Variational Autoencoder (VAE) as a deep learning-based compression method to reduce image complexity. VAE enables significant data reduction while retaining essential structural features. The dataset used is from the Modified National Institute of Standards and Technology (MNIST) database. The proposed method involves encoding images into latent variables, followed by binarization and translation into DNA sequences while applying biological constraints such as maintaining GC balance and avoiding homopolymers, to ensure stability and sequencing accuracy. Reconstruction quality is assessed using the Structural Similarity Index Measure (SSIM) and Peak Signal-to-Noise Ratio (PSNR), yielding an average SSIM of 0.8017 and an average PSNR of 18.91 dB. Analysis of variance shows that digits with greater variability suffer more noticeable degradation, whereas digits with lower variability preserve their structural integrity. These results suggest that integrating VAE into DNA data storage can reduce sequence complexity while still preserving recognizable image structures. The research contributes to the advancement of DNA-based data storage by presenting optimized coding techniques.

Dimensions

Author Biographies

Muhammad Rafi Muttaqin, IPB University and Sekolah Tinggi Teknologi Wastukancana

Doctoral Program in Computer Science, School of School of Data Science, Mathematics, and Informatics, IPB University

Informatic Engineering, Sekolah Tinggi Teknologi Wastukancana

Yeni Herdiyeni, IPB University

Artificial Intelligence Study Program, School of Data Science, Mathematics, and Informatics

Agus Buono, IPB University

Doctoral Program in Computer Science, School of School of Data Science, Mathematics, and Informatics

Karlisa Priandana, IPB University

Doctoral Program in Computer Science, School of School of Data Science, Mathematics, and Informatics

Iskandar Zulkarnaen Siregar, IPB University

Department of Silviculture, Faculty of Forestry

References

[1] A. Doricchi, C. M. Platnich, A. Gimpel, F. Horn, M. Earle, G. Lanzavecchia et al., “Emerging and prospects,” ACS Nano, vol. 16, no. 11, pp. 17 552–17 571, 2022.

[2] A. Akash, E. Bencurova, and T. Dandekar, “How to make DNA data storage more applicable,” Trends in Biotechnology, vol. 42, no. 1, pp. 17–30, 2024.

[3] Y. Hao, Q. Li, C. Fan, and F. Wang, “Data storage based on DNA,” Small Structures, vol. 2, no. 2, 2021.

[4] M. R. Muttaqin, Y. Herdiyeni, A. Buono, K. Priandana, and I. Z. Siregar, “Analysis and review of the possibility of using the generative model as a compression technique in DNA data storage: Review and future research agenda,” International Journal of Advances in Intelligent Informatics, vol. 9, no. 3, pp. 472–489, 2023.

[5] L. Organick, S. D. Ang, Y. J. Chen, R. Lopez, S. Yekhanin, K. Makarychev, M. Z. Racz et al., “Random access in large-scale DNA data storage,” Nature biotechnology, vol. 36, no. 3, pp. 242–248, 2018.

[6] Y. Ji, A. Koeppe, P. Altschuh, D. Rajagopal, Y. Zhao, W. Chen et al., “Towards automatic feature extraction and sample generation of grain structure by variational autoencoder,” Computational Materials Science, vol. 232, 2024.

[7] C. Wang, G. Ma, D. Wei, X. Zhang, P. Wang, C. Li et al., “Mainstream encoding–decoding methods of DNA data storage,” CCF Transactions on High Performance Computing, vol. 4, no. 1, pp. 23–33, 2022.

[8] E. Upenik, D. Lazzarotto, M. Testolina, and T. Ebrahimi, “On the performance of learningbased image compression as source coding for JPEG DNA,” in Applications of Digital Image Processing XLVII, vol. 13137. California, United States: SPIE, 2024, pp. 257–268.

[9] A. A. Jovith, S. R. Sree, G. N. Rao, K. V. Kumar, W. Cho, G. P. Joshi, and S. W. Kim, “DNA computing with water strider based vector quantization for data storage systems,” Computers, Materials & Continua, vol. 74, no. 3, pp. 6429–6444, 2023.

[10] Y. Feng, Q. Guo, W. Chen, and C. Han, “A lowcomplexity deep learning model for predicting targeted sequencing depth from probe sequence,” Applied Sciences, vol. 13, no. 12, pp. 1–16, 2023.

[11] Y. Zheng, B. Cao, X. Zhang, S. Cui, B. Wang, and Q. Zhang, “DNA-QLC: An efficient and reliable image encoding scheme for dna storage,” BMC Genomics, vol. 25, pp. 1–10, 2024.

[12] Y. Su, L. Chu, W. Lin, X. Yao, P. Xu, and W. Liu, “A robust and efficient representationbased DNA storage architecture by deep learning,” Small Methods, vol. 9, no. 3, 2025.

[13] N. Goldman, P. Bertone, S. Chen, C. Dessimoz, E. M. LeProust, B. Sipos, and E. Birney, “Towards practical, high-capacity, low-maintenance information storage in synthesized DNA,” Nature, vol. 494, pp. 77–80, 2013.

[14] H. Shao, E. Ma, M. Zhu, X. Deng, and S. Zhai, “MNIST handwritten digit classification based on convolutional neural network with hyperparameter optimization,” Intelligent Automation & Soft Computing, vol. 36, no. 3, pp. 3595–3606, 2023.

[15] S. Bera, V. K. Shrivastava, and S. C. Satapathy, “Advances in hyperspectral image classification based on convolutional neural networks: A review,” Computer Modeling in Engineering & Sciences, vol. 133, no. 2, pp. 219–250, 2022.

[16] Z. Gao, H. Z. Xuan, H. Zhang, S. Wan, and K. K. R. Choo, “Adaptive fusion and categorylevel dictionary learning model for multiview human action recognition,” IEEE Internet of Things Journal, vol. 6, no. 6, pp. 9280–9293, 2019.

[17] Z. Gao, Y. Li, and S. Wan, “Exploring deep learning for view-based 3D model retrieval,” ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), vol. 16, no. 1, pp. 1–21, 2020.

[18] R. Herrera-Pereda, A. T. Crispi, D. Babin, W. Philips, and M. H. Costa, “A review on digital image processing techniques for in-Vivo confocal images of the cornea,” Medical Image Analysis, vol. 73, 2021.

[19] R. Janeliukstis and X. Chen, “Review of digital image correlation application to large-scale composite structure testing,” Composite Structures, vol. 271, 2021.

[20] S. R. Lowe, “Pattern recognition in handwriting,” in Advances in pattern recognition and artificialintelligence. World Scientific, 2022, pp. 77–95.

[21] Y. Zhao, H. Li, S. Wan, A. Sekuboyina, X. Hu, G. Tetteh et al., “Knowledge-aided convolutional neural network for small organ segmentation,” IEEE Journal of Biomedical and Health Informatics, vol. 23, no. 4, pp. 1363–1373, 2019.

[22] H. Akrami, A. A. Joshi, J. Li, S. Ayd¨ore, and R. M. Leahy, “A robust variational autoencoder using beta divergence,” Knowledge-Based Systems, vol. 238, 2022.

[23] F. Mendonc¸a, S. S. Mostafa, F. Morgado-Dias, and A. G. Ravelo-Garc´ıa, “On the use of Kullback–Leibler divergence for kernel selection and interpretation in variational autoencoders for feature creation,” Information, vol. 14, no. 10, pp. 1–15, 2023.

[24] S. Cao, J. Li, K. P. Nelson, and M. A. Kon, “Coupled VAE: Improved accuracy and robustness of a variational autoencoder,” Entropy, vol. 24, no. 3, pp. 1–25, 2022.

[25] T. Ahmed and L. Longo, “Examining the size of the latent space of convolutional variational autoencoders trained with spectral topographic maps of EEG frequency bands,” IEEE Access, vol. 10, pp. 107 575–107 586, 2022.

[26] H. Tian, X. Jiang, S. Xiao, H. La Force, E. C. Larson, and P. Tao, “LAST: Latent Space-Assisted Adaptive Sampling for Protein Trajectories,” Journal of Chemical Information and Modeling, vol. 63, no. 1, pp. 67–75, 2022.

[27] A. Raj and R. D’Souza, “DNA computingenabled big data anonymization framework with a comparative study through existing anonymization tools,” in 2023 International Conference on the Confluence of Advancements in Robotics, Vision and Interdisciplinary Technology Management (IC-RVITM). Bangalore, India: IEEE, Nov. 28–29, 2023, pp. 1–6.

[28] J. Zhang, D. Fang, and H. Ren, “Image encryption algorithm based on DNA encoding and chaotic maps,” Mathematical Problems in Engineering, vol. 2014, no. 1, pp. 1–10, 2014.

[29] L. Organick, B. H. Nguyen, R. McAmis, W. D. Chen, A. X. Kohll, S. D. Ang et al., “An empirical comparison of preservation methods for synthetic DNA data storage,” Small Methods, vol. 5, no. 5, pp. 1–10, 2021.

[30] Y. Liu, X. He, and X. Tang, “Capacity-achieving constrained codes with GC-content and runlength limits for DNA storage,” in 2022 IEEE International Symposium on Information Theory (ISIT). Espoo, Finland: IEEE, June 26–July 1, 2022, pp. 198–203.

[31] M. R. Raigonda, “Signature verification system using SSIM in image processing,” Journal of Scientific Research and Technology, vol. 2, no. 1, pp. 5–11, 2024.

[32] Z. Wang, X. Li, M. Pu, L. Chen, F. Zhang, Q. Zhang et al., “Vectorial-optics-enabled multiview non-line-of-sight imaging with high signalto-noise ratio,” Laser & Photonics Reviews, vol. 18, no. 6, 2024.

[33] J. Yang, “acceleration system for single-precision floating-point arithmetic based on IEEE754 standard,” Highlights in Science, Engineering and Technology, vol. 87, p. 82–89, 2024.

[34] M. Roy, S. Chakraborty, and K. Mali, “Audio encryption framework based on chaotic map and DNA encoding,” Applied Acoustics, vol. 224, 2024.

[35] G. G. Dagher, A. P. Machado, E. C. Davis, T. Green, J. Martin, and M. Ferguson, “Data storage in cellular DNA: Contextualizing diverse encoding schemes,” Evolutionary Intelligence, vol. 14, no. 2, pp. 331–343, 2021.

[36] M. Welzel, P. M. Schwarz, H. F. L¨ochel, T. Kabdullayeva, S. Clemens, A. Becker et al., “DNAAeon provides flexible arithmetic coding for constraint adherence and error correction in DNA storage,” Nature Communications, vol. 14, pp. 1–10, 2023.

[37] W. Song, K. Cai, M. Zhang, and C. Yuen, “Codes with run-length and GC-content constraints for DNA-based data storage,” IEEE Communications Letters, vol. 22, no. 10, pp. 2004–2007, 2018.