Abstract
Protein structural properties are often determined by experimental techniques such as X-ray crystallography and nuclear magnetic resonance. However, both approaches are time-consuming and expensive. Conversely, protein amino acid sequences may be readily obtained from inexpensive high-throughput techniques, although such sequences lack structural information, which is essential for numerous applications such as gene therapy, in which maximisation of the payload, or volume, is required. This paper proposes a novel solution to volume prediction, based on deep learning and finite element analysis. We introduce a multi-attention, multi-resolution deep learning architecture that predicts protein volumes from their amino acid sequences. Experimental results demonstrate the efficiency of the ProVolOne framework.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Adams, P.D., et al.: Announcing mandatory submission of PDBx/mmCIF format files for crystallographic depositions to the Protein Data Bank (PDB). Acta Crystallogr. Sect. D 75(4), 451–454 (2019)
Aslanidi, G., et al.: Optimization of the capsid of recombinant adeno-associated virus 2 (aav2) vectors: the final threshold? PLoS One 8(3) (2013). https://doi.org/10.1371/journal.pone.0059142
Burley, S., et al.: RCSB protein data bank: powerful new tools for exploring 3D structures of biological macromolecules for basic and applied research and education in fundamental biology, biomedicine, biotechnology, bioengineering and energy sciences. Nucleic Acids Res. 49(1), D437–D451 (2021). https://doi.org/10.1093/nar/gkaa1038
Bylaklak, K., Charles, A.G.: The once and future gene therapy. Nat. Commun. 11, 1–4 (2020)
Celik, R.: RCEV heteroscedasticity test based on the studentized residuals. Commun. Stat. Theory Methods 48(13), 3258–268 (2019)
Chandra, A.A., Sharma, A., Dehganzi, A., Tsunoda, T.: Evolstruct-phogly: incorporating structural properties and evolutionary information from profile bigrams for the phos-phoglycerylation prediction. BMC Genomics 984–992 (2019)
Chung, T.J.: Computational Fluid Dynamics. Cambridge University Press, Cambridge, UK (2010)
Gelman, A., Carlin, J.B., Stern, H.S., Dunson, D.B., Vehtari, A., Rubin, D.B.: Bayesian Data Analysis. CRC Press, Boca Raton, FL (2013)
Gu, J., et al.: Recent advances in convolutional neural networks. Pattern Recogn. 77, 354–377 (2018)
Jumper, J., et al.: Highly accurate protein structure prediction with AlphaFold. Nature 596, 583–589 (2021)
Kingma, D., Ba, J.: Adam: a method for stochastic optimization, December 2014. ArXiv: 1412.6980
Kuhlman, B., Bradley, P.: Advances in protein structure prediction and design. Nature 20, 681–697 (2019)
Li, H., Xu, Z., Taylor, G., Studer, C., Goldstein, T.: Visualizing the loss land-scape of neural nets. In: 32nd Conference on Neural In-formation Processing Systems, p. 11, Montréal, Canada, December 2018
Lill, M.A., Danielson, M.L.: Computer-aided drug design platform using PyMOL. J. Comput. Aided Mol. Des. 25, 13–19 (2011)
Lin, Z., et al.: Language models of protein sequences at the scale of evolution enable accurate structure prediction. BioRxiv 2022.07.20.500902 (October 2022)
Lovric, J.: Introducing Proteomics: From Concepts to Sample Separation, Mass Spectrometry and Data Analysis. John Wiley & Sons, Oxford, UK (2011)
Pang, G., Shen, C., Cao, L.: Deep learning for anomaly detection: a review. ACM Comput. Surv. 54((2)38), 1–38 (2022)
Rodríguez, P., Bautista, M.A., Gonzàlez, J., Escalera, S.: Beyond one-hot encoding: Lower dimensional target embedding. Image Vis. Comput. 75, 21–31 (2018)
Vaswani, A., et al.: Attention is all you need. In: 31st Conference on Neural Information Processing Systems (Neurips 2017), December 2017
Xu, D., Zhang, Y.: Generating triangulated macromolecular surfaces by Euclidean distance transform. PLoS ONE 4(12) (2009)
Zienkiewicz, O.C., Taylor, R.L., Fox, D.D.: The Finite Element Method for Solid and Structural Mechanics. Elsevier, London, UK (2013)
Acknowledgements
This research was funded by the Artificial Intelligence For Design (AI4Design) Challenge Program from the Digital Technologies Research Centre of the National Research Council (NRC) of Canada.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Appendix
Appendix
Architecture of the deep neural network.
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Paquet, E., Viktor, H., Michalowski, W., St-Pierre-Lemieux, G. (2024). ProVolOne – Protein Volume Prediction Using a Multi-attention, Multi-resolution Deep Neural Network and Finite Element Analysis. In: Nicosia, G., Ojha, V., La Malfa, E., La Malfa, G., Pardalos, P.M., Umeton, R. (eds) Machine Learning, Optimization, and Data Science. LOD 2023. Lecture Notes in Computer Science, vol 14505. Springer, Cham. https://doi.org/10.1007/978-3-031-53969-5_21
Download citation
DOI: https://doi.org/10.1007/978-3-031-53969-5_21
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-53968-8
Online ISBN: 978-3-031-53969-5
eBook Packages: Computer ScienceComputer Science (R0)