從2019年12月起新冠肺炎爆發，防疫措施愈來愈重要，隨著新型冠狀病毒的高傳播力和突變力，新的病毒株陸續出現，而這將導致疫苗防護力下降，甚至可能被突破，本研究將重點放在預測病毒株下一階段突變預測，把收集到的資料依照Nextstrain clade分類，將2021年1月以前非delta病毒出現前的DNA病毒序列提取出來，透過Variational AutoEncoder將DNA病毒序列提取其生物資訊後，使用高斯過程進行潛空間下比較不同kernel進行突變趨勢擬合，並生成之後1到6個月後的新DNA病毒序列，最後成功生成出新的病毒序列，並且突變出Dalta病毒株，說明DNA序列在Variational AutoEncoder上，成功提取其生物資訊，並能依時間演化建模，而這有助於提前開發新疫苗和預測新症狀等。

Since the outbreak of new coronary pneumonia in December 2019, epidemic prevention measures have become more and more important. With the high transmissibility and mutation power of the new coronavirus, new virus strains have emerged one after another, which will lead to a decline in vaccine protection and may even be broken through. This study will focus on predicting the next-stage mutation prediction of virus strains, and classify the collected data according to the Nextstrain clade. Using the Gaussian process to compare different kernels in the latent space to fit the mutation trend, and generate a new DNA virus sequence 1 to 6 months later, and finally successfully generate a new virus sequence, and mutate the Dalta virus strain. It shows that the biological information of the DNA sequence can be successfully extracted on the Variational AutoEncoder, and can be modeled according to the evolution of time, which is helpful for the development of new vaccines and the prediction of new symptoms in advance.

[1] L. van Dorp, M. Acman, D. Richard, et al., “Emergence of genomic diversity
and recurrent mutations in sars-cov-2,” Infection, Genetics and Evolution, vol. 83,
p. 104 351, 2020.
[2] S. Duffy, L. A. Shackelton, and E. C. Holmes, “Rates of evolutionary change
in viruses: Patterns and determinants,” Nature Reviews Genetics, vol. 9, no. 4,
pp. 267–276, 2008.
[3] J. Shaman and M. Galanti, “Will sars-cov-2 become endemic?” Science, vol. 370,
no. 6516, pp. 527–529, 2020.
[4] A. Kumar, “Model evolution in sars-cov-2 spike protein sequences using a generative
neural network,” bioRxiv, 2022.
[5] Y. Li, C. Huang, L. Ding, Z. Li, Y. Pan, and X. Gao, “Deep learning in bioinformatics: Introduction, application, and perspective in the big data era,” Methods,
vol. 166, pp. 4–21, 2019.
[6] S. Min, B. Lee, and S. Yoon, “Deep learning in bioinformatics,” Briefings in bioinformatics, vol. 18, no. 5, pp. 851–869, 2017.
[7] R. F. Mansour, J. Escorcia-Gutierrez, M. Gamarra, D. Gupta, O. Castillo, and
S. Kumar, “Unsupervised deep learning based variational autoencoder model for
covid-19 diagnosis and classification,” Pattern Recognition Letters, vol. 151, pp. 267–
274, 2021.
[8] S. Sinai, E. Kelsic, G. M. Church, and M. A. Nowak, “Variational auto-encoding
of protein sequences,” arXiv preprint arXiv:1712.03346, 2017.
[9] C. Doersch, “Tutorial on variational autoencoders,” arXiv preprint arXiv:1606.05908,
2016.
[10] S. N. Dean and S. A. Walper, “Variational autoencoder for generation of antimicrobial peptides,” ACS omega, vol. 5, no. 33, pp. 20 746–20 754, 2020.
[11] R. R. Eguchi, C. A. Choe, and P.-S. Huang, “Ig-vae: Generative modeling of protein
structure by direct 3d coordinate generation,” PLoS computational biology, vol. 18,
no. 6, e1010271, 2022.
[12] K. Gregor, I. Danihelka, A. Graves, D. Rezende, and D. Wierstra, “Draw: A recurrent neural network for image generation,” in International conference on machine
learning, PMLR, 2015, pp. 1462–1471.
[13] D. P. Kingma and M. Welling, “Auto-encoding variational bayes,” arXiv preprint
arXiv:1312.6114, 2013.
[14] T. Salimans, D. Kingma, and M. Welling, “Markov chain monte carlo and variational inference: Bridging the gap,” in International conference on machine learning, PMLR, 2015, pp. 1218–1226.
[15] J. Walker, C. Doersch, A. Gupta, and M. Hebert, “An uncertain future: Forecasting
from static images using variational autoencoders,” in European Conference on
Computer Vision, Springer, 2016, pp. 835–851.
[16] G. P. Way and C. S. Greene, “Extracting a biologically relevant latent space from
cancer transcriptomes with variational autoencoders,” in PACIFIC SYMPOSIUM
ON BIOCOMPUTING 2018: Proceedings of the Pacific Symposium, World Scientific, 2018, pp. 80–91.
[17] X. Ding, Z. Zou, and C. L. Brooks III, “Deciphering protein evolution and fitness
landscapes with latent space models,” Nature communications, vol. 10, no. 1, pp. 1–
13, 2019.
[18] A. Hawkins-Hooker, F. Depardieu, S. Baur, G. Couairon, A. Chen, and D. Bikard,
“Generating functional protein variants with variational autoencoders,” PLoS computational biology, vol. 17, no. 2, e1008736, 2021.
[19] E. Schulz, M. Speekenbrink, and A. Krause, “A tutorial on gaussian process regression: Modelling, exploring, and exploiting functions,” Journal of Mathematical
Psychology, vol. 85, pp. 1–16, 2018.
[20] M. Seeger, “Gaussian processes for machine learning,” International journal of neural systems, vol. 14, no. 02, pp. 69–106, 2004.
[21] C. K. Williams and C. E. Rasmussen, Gaussian processes for machine learning.
MIT press Cambridge, MA, 2006.
[22] L. Cheng, S. Ramchandran, T. Vatanen, et al., “An additive gaussian process regression model for interpretable non-parametric analysis of longitudinal data,” Nature
communications, vol. 10, no. 1, pp. 1–11, 2019.
[23] S. Roberts, M. Osborne, M. Ebden, S. Reece, N. Gibson, and S. Aigrain, “Gaussian processes for time-series modelling,” Philosophical Transactions of the Royal
Society A: Mathematical, Physical and Engineering Sciences, vol. 371, no. 1984,
p. 20 110 550, 2013.
[24] P. A. Romero, A. Krause, and F. H. Arnold, “Navigating the protein fitness landscape with gaussian processes,” Proceedings of the National Academy of Sciences,
vol. 110, no. 3, E193–E201, 2013.
[25] S. King, X. E. Chen, S. W. Ng, et al., “Modeling the trajectory of sars-cov-2 spike
protein evolution in continuous latent space using a neural network and gaussian
process,” bioRxiv, 2021.
[26] Á. O’Toole, E. Scher, A. Underwood, et al., “Assignment of epidemiological lineages
in an emerging pandemic using the pangolin tool,” Virus evolution, vol. 7, no. 2,
veab064, 2021.
[27] J. Salvatier, T. V. Wiecki, and C. Fonnesbeck, “Probabilistic programming in
python using pymc3,” PeerJ Computer Science, vol. 2, e55, 2016.
[28] A. B. Abdessalem, N. Dervilis, D. J. Wagg, and K. Worden, “Automatic kernel
selection for gaussian processes regression with approximate bayesian computation
and sequential monte carlo,” Frontiers in Built Environment, vol. 3, p. 52, 2017.
[29] K. P. Murphy, Probabilistic machine learning: an introduction. MIT press, 2022.