Abstract
The state of the art in protein structure prediction (PSP) is currently achieved by complex deep learning pipelines that require several input features. In this paper, we demonstrate the relevance of Geometric Algebra (GA) for modelling protein features in PSP. We do so by proposing a novel GA metric based on the relative orientations of amino acid residues. We then employ this metric as an additional input feature to a Graph Transformer (GT) to aid the prediction of the 3D coordinates of a protein. Adding this GA-based orientational information improves the accuracy of the predicted coordinates even after few learning iterations and on a small dataset.
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
Similar content being viewed by others
References
Jumper, J., et al.: Highly accurate protein structure prediction with AlphaFold. Nature 596(7873), 583–589 (2021)
Thornton, J.M., Laskowski, R.A., Borkakoti, N.: AlphaFold heralds a data-driven revolution in biology and medicine. Nat. Med. 27(10), 1666–1669 (2021)
Perrakis, A., Sixma, T.K.: AI revolutions in biology: the joys and perils of AlphaFold. EMBO Rep. 22(11), e54046 (2021)
Torrisi, M., Pollastri, G., Le, Q.: Deep learning methods in protein structure prediction. Comput. Struct. Biotechnol. J. 18, 1301–1310 (2020)
Kandathil, S.M., Greener, J.G., Jones, D.T.: Recent developments in deep learning applied to protein structure prediction. Proteins Struct. Funct. Bioinform. 87(12), 1179–1189 (2019)
Pakhrin, S.C., Shrestha, B., Adhikari, B., Kc, D.B.: Deep learning-based advances in protein structure prediction. Int. J. Mol. Sci. 22(11), 5553 (2021)
Baek, M., et al.: Accurate prediction of protein structures and interactions using a three-track neural network. Science 373(6557), 871–876 (2021)
Jaderberg, M., Simonyan, K., Zisserman, A.: Spatial transformer networks. Adv. Neural Inf. Process. Syst. 28 (2015)
Li, N., Liu, S., Liu, Y., Zhao, S., Liu, M.: Neural speech synthesis with transformer network. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, no. 01, pp. 6706–6713 (2019)
Kim, S., Lin, S., Jeon, S.R., Min, D., Sohn, K.: Recurrent transformer networks for semantic correspondence. Adv. Neural Inf. Process. Syst. 31 (2018)
Giuliari, F., Hasan, I., Cristani, M., Galasso, F.: Transformer networks for trajectory forecasting. In: 2020 25th International Conference on Pattern Recognition (ICPR), pp. 10335–10342. IEEE (2021)
Costa, A., Ponnapati, M., Jacobson, J.M., Chatterjee, P.: Distillation of MSA embeddings to folded protein structures with graph transformers. bioRxiv (2021)
Yang, J., Anishchenko, I., Park, H., Peng, Z., Ovchinnikov, S., Baker, D.: Improved protein structure prediction using predicted interresidue orientations. Proc. Natl. Acad. Sci. 117(3), 1496–1503 (2020)
Adhikari, B.: A fully open-source framework for deep learning protein real-valued distances. Sci. Rep. 10(1), 1–10 (2020)
Doran, C., Gullans, S.R., Lasenby, A., Lasenby, J., Fitzgerald, W.: Geometric Algebra for Physicists. Cambridge University Press, Cambridge (2003)
Dorst, L., Doran, C., Lasenby, J. (eds.): Springer, Heidelberg (2012). https://doi.org/10.1007/978-1-4612-0089-5
Lavor, C., Alves, R.: Oriented conformal geometric algebra and the molecular distance geometry problem. Adv. Appl. Clifford Algebras 29(1), 1–15 (2019)
Alves, R., Lavor, C.: Geometric algebra to model uncertainties in the discretizable molecular distance geometry problem. Adv. Appl. Clifford Algebras 27(1), 439–452 (2017)
Jumper, J., et al.: AlphaFold 2 (2020)
Lasenby, J., Hadfield, H., Lasenby, A.: Calculating the rotor between conformal objects. Adv. Appl. Clifford Algebras 29(5), 1–9 (2019)
Eide, E.R.: Master’s degree thesis. University of Cambridge, Camera Calibration using Conformal Geometric Algebra (2018)
Yun, S., Jeong, M., Kim, R., Kang, J., Kim, H.J.: Graph transformer networks. Adv. Neural Inf. Process. Syst. 32 (2019)
Hadfield H., Wieser E., Arsenovic A., Kern R.: The Pygae Team. Pygae/Clifford (2020)
Burley, S.K., Berman, H.M., Kleywegt, G.J., Markley, J.L., Nakamura, H., Velankar, S.: Protein Data bank (PDB): the single global macromolecular structure archive. Protein Crystallogr. 627–641 (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Pepe, A., Lasenby, J., Chacón, P. (2023). Using a Graph Transformer Network to Predict 3D Coordinates of Proteins via Geometric Algebra Modelling. In: Hitzer, E., Papagiannakis, G., Vasik, P. (eds) Empowering Novel Geometric Algebra for Graphics and Engineering. ENGAGE 2022. Lecture Notes in Computer Science, vol 13862. Springer, Cham. https://doi.org/10.1007/978-3-031-30923-6_7
Download citation
DOI: https://doi.org/10.1007/978-3-031-30923-6_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-30922-9
Online ISBN: 978-3-031-30923-6
eBook Packages: Computer ScienceComputer Science (R0)