Skip to main content

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

  • Article
  • Published:

Evaluating protein binding interfaces with transformer networks

Nature Machine Intelligence volume 5, pages 1042–1053 (2023)Cite this article

Subjects

A preprint version of the article is available at bioRxiv.

Abstract

Computational protein-binding studies are widely used to investigate fundamental biological processes and facilitate the development of modern drugs, vaccines and therapeutics. Scoring functions aim to assess and rank the binding strength of the predicted protein complex. However, accurate scoring of protein binding interfaces remains a challenge. Here we show that our evaluating Protein binding Interfaces with Transformer Networks (PIsToN) approach can distinguish native-like protein complexes from incorrect conformations. Protein interfaces are transformed into a collection of two-dimensional images (interface maps), each corresponding to a geometric or biochemical property. Pixel intensities represent the feature values. A neural network was adapted from a popular vision transformer with several enhancements: a hybrid component to accept empirical-based energy terms, a multi-attention module to highlight essential features and binding sites, and the use of contrastive learning for better ranking performance. The resulting PIsToN model substantially outperforms state-of-the-art scoring functions on well-known datasets.

This is a preview of subscription content, access via your institution

Access options

Buy this article

  • Purchase on Springer Link
  • Instant access to full article PDF
Buy now

Prices may be subject to local taxes which are calculated during checkout

Fig. 1: PIsToN framework.
Fig. 2: PIsToN training process.
Fig. 3: PIsToN explainability.

Similar content being viewed by others

Data availability

The lists of training/testing protein complexes and pre-computed interface maps are available on Zenodo at https://doi.org/10.5281/zenodo.7948337.

Code availability

The PIsToN software and benchmark datasets are available under license from https://biorg.cis.fiu.edu/piston/. The specific version of PIsToN used in this study is readily available for access via Zenodo84.

References

  1. Jumper, J. et al. Highly accurate protein structure prediction with AlphaFold. Nature 596, 583–589 (2021).

    Article  Google Scholar 

  2. Callaway, E. After AlphaFold: protein-folding contest seeks next big breakthrough. Nature 604, 234–238 (2022).

    Article  Google Scholar 

  3. Vakser, I. A. Protein–protein docking: from interaction to interactome. Biophys. J. 107, 1785–1793 (2014).

    Article  Google Scholar 

  4. Shin, W.-H., Christoffer, C. W. & Kihara, D. In silico structure-based approaches to discover protein–protein interaction-targeting drugs. Methods 131, 22–32 (2017).

    Article  Google Scholar 

  5. Meng, X.-Y., Zhang, H.-X., Mezei, M. & Cui, M. Molecular docking: a powerful approach for structure-based drug discovery. Curr. Comput. Aided Drug Des. 7, 146–157 (2011).

    Article  Google Scholar 

  6. Scior, T. et al. Recognizing pitfalls in virtual screening: a critical review. J. Chem. Inf. Model. 52, 867–881 (2012).

    Article  Google Scholar 

  7. Gupta, M., Sharma, R. & Kumar, A. Docking techniques in pharmacology: how much promising? Comput. Biol. Chem. 76, 210–217 (2018).

    Article  Google Scholar 

  8. Huang, S.-Y. Search strategies and evaluation in protein–protein docking: principles, advances and challenges. Drug Discov. Today 19, 1081–1096 (2014).

    Article  Google Scholar 

  9. Shen, C. et al. From machine learning to deep learning: advances in scoring functions for protein–ligand docking. Wiley Interdiscip. Rev. Comput. Mol. Sci. 10, e1429 (2020).

    Article  Google Scholar 

  10. Moal, I. H., Torchala, M., Bates, P. A. & Fernández-Recio, J. The scoring of poses in protein–protein docking: current capabilities and future directions. BMC Bioinformatics 14, 286 (2013).

  11. Adeshina, Y. O., Deeds, E. J. & Karanicolas, J. Machine learning classification can reduce false positives in structure-based virtual screening. Proc. Natl Acad. Sci. USA 117, 18477–18488 (2020).

    Article  Google Scholar 

  12. Li, J., Fu, A. & Zhang, L. An overview of scoring functions used for protein–ligand interactions in molecular docking. Interdiscip. Sci. Comput. Life Sci. 11, 320–328 (2019).

    Article  Google Scholar 

  13. Kortemme, T. & Baker, D. A simple physical model for binding energy hot spots in protein–protein complexes. Proc. Natl Acad. Sci. USA 99, 14116–14121 (2002).

    Article  Google Scholar 

  14. Liu, X., Peng, L. & Zhang, J. Z. Accurate and efficient calculation of protein–protein binding free energy-interaction entropy with residue type-specific dielectric constants. J. Chem. Inf. Model. 59, 272–281 (2018).

    Article  Google Scholar 

  15. Huang, S.-Y., Grinter, S. Z. & Zou, X. Scoring functions and their evaluation methods for protein–ligand docking: recent advances and future directions. Phys. Chem. Chem. Phys. 12, 12899–12908 (2010).

    Article  Google Scholar 

  16. Durham, E., Dorr, B., Woetzel, N., Staritzbichler, R. & Meiler, J. Solvent accessible surface area approximations for rapid and accurate protein structure prediction. J. Mol. Model. 15, 1093–1108 (2009).

    Article  Google Scholar 

  17. Eldridge, M. D., Murray, C. W., Auton, T. R., Paolini, G. V. & Mee, R. P. Empirical scoring functions: I. The development of a fast empirical scoring function to estimate the binding affinity of ligands in receptor complexes. J. Comput. Aided Mol. Des. 11, 425–445 (1997).

    Article  Google Scholar 

  18. Trott, O. & Olson, A. J. AutoDock Vina: improving the speed and accuracy of docking with a new scoring function, efficient optimization, and multithreading. J. Comput. Chem. 31, 455–461 (2010).

    Google Scholar 

  19. Chen, Y.-C. Beware of docking! Trends Pharmacol. Sci. 36, 78–95 (2015).

    Article  Google Scholar 

  20. Muley, L. et al. Enhancement of hydrophobic interactions and hydrogen bond strength by cooperativity: synthesis, modeling, and molecular dynamics simulations of a congeneric series of thrombin inhibitors. J. Med. Chem. 53, 2126–2135 (2010).

    Article  Google Scholar 

  21. Liu, J. & Wang, R. Classification of current scoring functions. J. Chem. Inf. Mode. 55, 475–482 (2015).

    Article  Google Scholar 

  22. Kinnings, S. L. et al. A machine learning-based method to improve docking scoring functions and its application to drug repurposing. J. Chem. Inf. Model. 51, 408–419 (2011).

    Article  Google Scholar 

  23. Das, S. & Chakrabarti, S. Classification and prediction of protein–protein interaction interface using machine learning algorithm. Sci. Rep. 11, 1761 (2021).

  24. Zilian, D. & Sotriffer, C. A. SFCscore(RF): a random forest-based scoring function for improved affinity prediction of protein–ligand complexes. J. Chem. Inf. Model. 53, 1923–1933 (2013).

    Article  Google Scholar 

  25. Durrant, J. D. & McCammon, J. A. NNScore: a neural-network-based scoring function for the characterization of protein–ligand complexes. J. Chem. Inf. Model. 50, 1865–1871 (2010).

    Article  Google Scholar 

  26. Ballester, P. J. & Mitchell, J. B. A machine learning approach to predicting protein–ligand binding affinity with applications to molecular docking. Bioinformatics 26, 1169–1175 (2010).

    Article  Google Scholar 

  27. Li, H., Leung, K.-S., Wong, M.-H. & Ballester, P. J. Substituting random forest for multiple linear regression improves binding affinity prediction of scoring functions: Cyscore as a case study. BMC Bioinformatics 15, 291 (2014).

  28. Li, Y., Zhang, X. & Cao, D. The role of shape complementarity in the protein–protein interactions. Sci. Rep. 3, 3271 (2013).

  29. Wallach, I., Dzamba, M. & Heifets, A. AtomNet: a deep convolutional neural network for bioactivity prediction in structure-based drug discovery. Preprint at https://arxiv.org/abs/1510.02855 (2015).

  30. Imrie, F., Bradley, A. R., van der Schaar, M. & Deane, C. M. Protein family-specific models using deep neural networks and transfer learning improve virtual screening and highlight the need for more data. J. Chem. Inf. Model. 58, 2319–2330 (2018).

    Article  Google Scholar 

  31. Balci, A. et al. DeepInterface: protein–protein interface validation using 3D convolutional neural networks. Preprint at bioRxiv https://doi.org/10.1101/617506 (2019).

  32. Wang, X., Terashi, G., Christoffer, C. W., Zhu, M. & Kihara, D. Protein docking model evaluation by 3D deep convolutional neural networks. Bioinformatics 36, 2113–2118 (2020).

    Article  Google Scholar 

  33. Renaud, N. et al. DeepRank: a deep learning framework for data mining 3D protein-protein interfaces. Nat. Commun. 12, 7068 (2021).

  34. Mohseni Behbahani, Y., Crouzet, S., Laine, E. & Carbone, A. Deep local analysis evaluates protein docking conformations with locally oriented cubes. Bioinformatics 38, 4505–4512 (2022).

    Article  Google Scholar 

  35. Kumawat, S. & Raman, S. LP-3DCNN: unveiling local phase in 3D convolutional neural networks. In Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition 4903–4912 (IEEE, 2019).

  36. Geng, C. et al. iScore: a novel graph kernel-based function for scoring protein–protein docking models. Bioinformatics 36, 112–121 (2020).

    Article  Google Scholar 

  37. Budowski-Tal, I., Kolodny, R. & Mandel-Gutfreund, Y. A novel geometry-based approach to infer protein interface similarity. Sci. Rep. 8, 1–10 (2018).

    Article  Google Scholar 

  38. Wang, X., Flannery, S. T. & Kihara, D. Protein docking model evaluation by graph neural networks. Front. Mol. Biosci. 8, 647915 (2021).

    Article  Google Scholar 

  39. Réau, M., Renaud, N., Xue, L. C. & Bonvin, A. M. DeepRank-GNN: a graph neural network framework to learn patterns in protein–protein interfaces. Bioinformatics 39, 759 (2023).

    Article  Google Scholar 

  40. Gainza, P. et al. Deciphering interaction fingerprints from protein molecular surfaces using geometric deep learning. Nat. Methods 17, 184–192 (2020).

    Article  Google Scholar 

  41. Sverrisson, F., Feydy, J., Correia, B. E. & Bronstein, M. M. Fast end-to-end learning on protein surfaces. In Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition 15272–15281 (IEEE, 2021).

  42. Zhai, X., Kolesnikov, A., Houlsby, N. & Beyer, L. Scaling vision transformers. In Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition 12104–12113 (IEEE, 2022).

  43. Dosovitskiy, A. et al. An image is worth 16x16 words: transformers for image recognition at scale. 9th International Conference on Learning Representations, ICLR (2020).

  44. Yan, Y., Tao, H., He, J. & Huang, S.-Y. The HDOCK server for integrated protein–protein docking. Nat. Protoc. 15, 1829–1852 (2020).

    Article  Google Scholar 

  45. Janin, J. et al. CAPRI: a critical assessment of predicted interactions. Proteins 52, 2–9 (2003).

    Article  Google Scholar 

  46. Khosla, P. et al. Supervised contrastive learning. Ad. Neural Inf. Process. Syst. 33, 18661–18673 (2020).

    Google Scholar 

  47. Chen, C. et al. This looks like that: deep learning for interpretable image recognition. Adv. Neural Inf. Process. Systems 32, 8930–8941 (2019).

  48. Altschul, S. F. et al. Gapped BLAST and PSI-BLAST: a new generation of protein database search programs. Nucleic Acids Res. 25, 3389–3402 (1997).

    Article  Google Scholar 

  49. Jones, D. T. Setting the standards for machine learning in biology. Nat. Rev. Mol. Cell Biol. 20, 659–660 (2019).

    Article  Google Scholar 

  50. Jeong, J.-J. et al. Characterization of the cupin-type phosphoglucose isomerase from the hyperthermophilic archaeon Thermococcus litoralis. FEBS Lett. 535, 200–204 (2003).

    Article  Google Scholar 

  51. Dominguez, C., Boelens, R. & Bonvin, A. M. HADDOCK: a protein–protein docking approach based on biochemical or biophysical information. J. Am. Chem. Soc. 125, 1731–1737 (2003).

    Article  Google Scholar 

  52. Wang, R., Fang, X., Lu, Y. & Wang, S. The PDBbind database: collection of binding affinities for protein–ligand complexes with known three-dimensional structures. J. Med. Chem. 47, 2977–2980 (2004).

    Article  Google Scholar 

  53. Evans, R. et al. Protein complex prediction with AlphaFold-Multimer. Preprint at bioRxiv https://doi.org/10.1101/2021.10.04.463034 (2021).

  54. Stebliankin, V. et al. EMoMiS: a pipeline for epitope-based molecular mimicry search in protein structures with applications to SARS-CoV-2. Preprint at bioRxiv https://doi.org/10.1101/2022.02.05.479274 (2022).

  55. Balbin, C. A. et al. Epitopedia: identifying molecular mimicry between pathogens and known immune epitopes. ImmunoInformatics 9, 100023 (2023).

    Article  Google Scholar 

  56. Berman, H. M. et al. The Protein Data Bank. Nucleic Acids Res. 28, 235–242 (2000).

    Article  Google Scholar 

  57. Valdes, C. et al. Microbiome maps: Hilbert curve visualizations of metagenomic profiles. Front. Bioinformatics 3, 1154588 (2023).

    Article  Google Scholar 

  58. Andrusier, N., Nussinov, R. & Wolfson, H. J. FireDock: fast interaction refinement in molecular docking. Proteins 69, 139–159 (2007).

    Article  Google Scholar 

  59. Gray, J. J. et al. Protein–protein docking with simultaneous optimization of rigid-body displacement and side-chain conformations. J. Mol. Biol. 331, 281–299 (2003).

    Article  Google Scholar 

  60. Zhang, C., Vasmatzis, G., Cornette, J. L. & DeLisi, C. Determination of atomic desolvation energies from the structures of crystallized proteins. J. Mol. Biol. 267, 707–726 (1997).

    Article  Google Scholar 

  61. Dunbrack Jr, R. L. & Cohen, F. E. Bayesian statistical analysis of protein side-chain rotamer preferences. Protein Sci. 6, 1661–1681 (1997).

    Article  Google Scholar 

  62. Neria, E., Fischer, S. & Karplus, M. Simulation of activation free energies in molecular systems. J. Chem. Phys. 105, 1902–1921 (1996).

    Article  Google Scholar 

  63. Crowley, P. B. & Golovin, A. Cation–π interactions in protein–protein interfaces. Proteins59, 231–239 (2005).

    Article  Google Scholar 

  64. Kabsch, W. & Sander, C. Dictionary of protein secondary structure: pattern recognition of hydrogen-bonded and geometrical features. Biopolymers 22, 2577–2637 (1983).

    Article  Google Scholar 

  65. Touw, W. G. et al. A series of PDB-related databanks for everyday needs. Nucleic Acids Res. 43, 364–368 (2015).

    Article  Google Scholar 

  66. Mead, A. Review of the development of multidimensional scaling methods. J. R. Stat. Soc. Ser. D 41, 27–39 (1992).

    Google Scholar 

  67. Ng, A. Y. Feature selection, L1 vs. L2 regularization, and rotational invariance. In Proc. Twenty-first International Conference on Machine Learning 78 (Association for Computing Machinery, 2004).

  68. Loshchilov, I. & Hutter, F. Decoupled weight decay regularization. 7th International Conference on Learning Representations, ICLR, 6–9 (2017).

  69. Lensink, M. F. & Wodak, S. J. Score_set: a CAPRI benchmark for scoring protein complexes. Proteins 82, 3163–3169 (2014).

    Article  Google Scholar 

  70. Zhang, C., Shine, M., Pyle, A. M. & Zhang, Y. US-align: universal structure alignments of proteins, nucleic acids, and macromolecular complexes. Nat. Methods 19, 1109–1115 (2022).

    Article  Google Scholar 

  71. Cheng, T. M.-K., Blundell, T. L. & Fernandez-Recio, J. pyDock: electrostatics and desolvation for effective scoring of rigid-body protein–protein docking. Proteins 68, 503–515 (2007).

    Article  Google Scholar 

  72. Leman, J. K. et al. Macromolecular modeling and design in Rosetta: recent methods and frameworks. Nat. Methods 17, 665–680 (2020).

    Article  MathSciNet  Google Scholar 

  73. Pierce, B. & Weng, Z. A combination of rescoring and refinement significantly improves protein docking performance. Proteins 72, 270–279 (2008).

    Article  Google Scholar 

  74. Viswanath, S., Ravikant, D. & Elber, R. Improving ranking of models for protein complexes with side chain modeling and atomic potentials. Proteins 81, 592–606 (2013).

    Article  Google Scholar 

  75. Pons, C., Talavera, D., De La Cruz, X., Orozco, M. & Fernandez-Recio, J. Scoring by intermolecular pairwise propensities of exposed residues (SIPPER): a new efficient potential for protein–protein docking. J. Chem. Inf. Model. 51, 370–377 (2011).

    Article  Google Scholar 

  76. Ravikant, D. & Elber, R. Pie-efficient filters and coarse grained potentials for unbound protein–protein docking. Proteins 78, 400–419 (2010).

    Article  Google Scholar 

  77. Moal, I. H., Jiménez-García, B. & Fernández-Recio, J. CCharPPI web server: computational characterization of protein–protein interactions from structure. Bioinformatics 31, 123–125 (2015).

    Article  Google Scholar 

  78. Virtanen, P. et al. SciPy 1.0: fundamental algorithms for scientific computing in Python. Nat. Methods 17, 261–272 (2020).

    Article  Google Scholar 

  79. Renaud, N. & Geng, C. The pdb2sql Python package: parsing, manipulation and analysis of PDB files using SQL queries. J. Open Source Softw. 5, 2077 (2020).

    Article  Google Scholar 

  80. Paszke, A. et al. PyTorch: an imperative style, high-performance deep learning library. Adv. Neural Inf. Processing Syst. 32, 8024–8035 (2019).

  81. Collaborative Data Science (Plotly Technologies, 2015); https://plot.ly

  82. Camacho, C. et al. BLAST+: architecture and applications. BMC Bioinformatics 10, 421 (2009).

  83. The PyMOL Molecular Graphics System, Version 1.8 (Schrödinger, LLC, 2015).

  84. Stebliankin, V. stebliankin/piston: PIsToN (v.1.0.0). Zenodo https://doi.org/10.5281/zenodo.8102876 (2023).

  85. Shore, D., Issafras, H., Landais, E., Teyton, L. & Wilson, I. The crystal structure of CD8 in complex with YTS156. 7.7 Fab and interaction with other CD8 antibodies define the binding mode of CD8 αβ to MHC class I. J. Mol. Biol. 384, 1190–1202 (2008).

    Article  Google Scholar 

Download references

Acknowledgements

We thank the members of the Bioinformatics Research Group (BioRG) at FIU for their valuable feedback and comments. This work grew out of a project that was supported by grants from the National Science Foundation (CNS-2037374 and OAC-2118329). V.S. gratefully acknowledges funding for graduate assistantships from the Department of Education, the National Science Foundation, and the Knight Foundation School of Computing and Information Sciences

Author information

Authors and Affiliations

  1. Bioinformatics Research Group (BioRG), Knight Foundation School of Computing and Information Sciences, Florida International University, Miami, FL, USA

    Vitalii Stebliankin, Azam Shirali, Jimeng Shi & Giri Narasimhan

  2. Department of Physics, College of Arts, Science and Education, Florida International University, Miami, FL, USA

    Prabin Baral & Prem Chapagain

  3. Biomolecular Sciences Institute, Florida International University, Miami, FL, USA

    Prem Chapagain, Kalai Mathee & Giri Narasimhan

  4. Herbert Wertheim College of Medicine, Florida International University, Miami, FL, USA

    Kalai Mathee

Authors
  1. Vitalii Stebliankin
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Azam Shirali
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Prabin Baral
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Jimeng Shi
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Prem Chapagain
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Kalai Mathee
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Giri Narasimhan
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

G.N. conceptualized and supervised the project. V.S. designed, implemented and tested the PIsToN framework. V.S. and A.S. executed benchmarks. P.B., J.S., P.C. and K.M. assisted in the feature extraction design and interpretations. V.S., A.S., K.M. and G.N. contributed to the paper writing and rewriting.

Corresponding author

Correspondence to Giri Narasimhan.

Ethics declarations

Competing interests

The authors declare no competing interests.

Peer review

Peer review information

Nature Machine Intelligence thanks Alex Morehead and Jason Yim for their contribution to the peer review of this work.

Additional information

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary information

Supplementary Information

Supplementary Note 1, Figs. 1–6 and Tables 1 and 2.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Stebliankin, V., Shirali, A., Baral, P. et al. Evaluating protein binding interfaces with transformer networks. Nat Mach Intell 5, 1042–1053 (2023). https://doi.org/10.1038/s42256-023-00715-4

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1038/s42256-023-00715-4

Search

Advanced search

Quick links

Nature Briefing

Sign up for the Nature Briefing newsletter — what matters in science, free to your inbox daily.

Get the most important science stories of the day, free in your inbox. Sign up for Nature Briefing