- Physical Review Journals
All JournalsPhysics Magazine

PRX Life

Reuse & Permissions

It is not necessary to obtain permission to reuse this article or its components as it is available under the terms of the Creative Commons Attribution 4.0 International license. This license permits unrestricted use, distribution, and reproduction in any medium, provided attribution to the author(s) and the published article's title, journal citation, and DOI are maintained. Please note that some figures may have been included with permission from other third parties. It is your responsibility to obtain the proper permission from the rights holder directly for these figures.

Export citation

Export citation

Choose format for download:

Download Citation
  • Open Access

DockFormer: Affinity Prediction and Flexible Docking with Pair Transformer

Ben Shor* and Dina Schneidman-Duhovny†

  • *Contact author: ben.shor@mail.huji.ac.il
  • †Contact author: dina.schneidman@mail.huji.ac.il
PDF

PRX Life 3, 033024 – Published 18 September, 2025

DOI: https://doi.org/10.1103/1862-rs2k

Abstract

Protein-small molecule interactions, or receptor-ligand interactions, are essential for understanding biological processes and advancing drug design. Despite advancements, existing prediction models of these interactions still lack the capabilities and accuracy needed to replace traditional screening. In this paper, we introduce DockFormer, a method that leverages multimodal learning to predict both the binding affinity and structure of these interactions. DockFormer employs fully flexible docking, where no part of the receptor remains rigid, by adapting the AlphaFold2 architecture. Instead of relying on protein sequences and multiple sequence alignments, DockFormer uses predicted receptor structures as input. This modification enables the model to concentrate on ligand docking prediction, rather than protein folding, while preserving full receptor flexibility. The streamlined design also reduces the model size to just eight layers, compared to AlphaFold2's 48 layers, greatly accelerating the inference process and making it more efficient for large-scale screening. When evaluated on affinity benchmarks such as CASF-2016, PLINDER, and the recently released CASP16 ligand screening benchmark, DockFormer performs comparably to or better than state-of-the-art methods, which typically rely on templates or bound structures as input. On structural benchmarks such as PoseBusters and PLINDER, DockFormer demonstrated success rates of 20% and 15%, respectively.

View figure in article

Physics Subject Headings (PhySH)

Collections

This article appears in the following collection:

Machine Learning and Structural Biology

Curated by the organizers of the Machine Learning for Structural Biology Workshop at NeurIPS, this collection features studies at the intersection of computer science and biology, showcasing how machine learning is impacting our understanding of biological molecules and their processes.

Every article published in this collection underwent a rigorous peer review process, adhering to the same high standards applied to all papers handled by the journal. The PRX Life editorial team managed the peer review and made all editorial decisions.

Article Text

Supplemental Material

References (50)

  1. A. D. Attie and R. T. Raines, Analysis of receptor-ligand interactions, J. Chem. Educ. 72, 119 (1995).
  2. V. Cherezov, D. M. Rosenbaum, M. A. Hanson, S. G. F. Rasmussen, F. S. Thian, T. S. Kobilka, H.-J. Choi, P. Kuhn, W. I. Weis, B. K. Kobilka et al., High-resolution crystal structure of an engineered human β2-adrenergic G protein–coupled receptor, Science 318, 1258 (2007).
  3. A. M. De Vos, M. Ultsch, and A. A. Kossiakoff, Human growth hormone and extracellular domain of its receptor: Crystal structure of the complex, Science 255, 306 (1992).
  4. T. B. Kimber, Y. Chen, and A. Volkamer, Deep learning in virtual screening: Recent applications and developments, Int. J. Mol. Sci. 22, 4435 (2021).
  5. M. Karelina, J. J. Noh, and R. O. Dror, How accurately can one predict drug binding modes using AlphaFold models? Elife 12, RP89386 (2023).
  6. R. A. Friesner, J. L. Banks, R. B. Murphy, T. A. Halgren, J. J. Klicic, D. T. Mainz, M. P. Repasky, E. H. Knoll, M. Shelley, J. K. Perry et al., Glide: A new approach for rapid, accurate docking and scoring. 1. Method and assessment of docking accuracy, J. Med. Chem. 47, 1739 (2004).
  7. J. Eberhardt, D. Santos-Martins, A. F. Tillack, and S. Forli, AutoDock Vina 1.2.0: New docking methods, expanded force field, and Python bindings, J. Chem. Inf. Model. 61, 3891 (2021).
  8. D. Cao, M. Chen, R. Zhang, Z. Wang, M. Huang, J. Yu, X. Jiang, Z. Fan, W. Zhang, H. Zhou et al., SurfDock is a surface-informed diffusion generative model for reliable and accurate protein–ligand complex prediction, Nat. Methods 22, 310 (2024).
  9. G. Zhou, Z. Gao, Q. Ding, H. Zheng, H. Xu, Z. Wei, L. Zhang, and G. Ke, Uni-Mol: A universal 3D molecular representation learning framework, in Proceedings of the Eleventh International Conference on Learning Representations (ICLR) (2023).
  10. G. Corso, H. Stärk, B. Jing, R. Barzilay, and T. Jaakkola, Diffdock: Diffusion steps, twists, and turns for molecular docking, Proceedings of the International Conference on Learning Representations (ICLR) (2023).
  11. J. Abramson, J. Adler, J. Dunger, R. Evans, T. Green, A. Pritzel, O. Ronneberger, L. Willmore, A. J. Ballard, J. Bambrick et al., Accurate structure prediction of biomolecular interactions with AlphaFold 3, Nature (London) 630, 493 (2024).
  12. R. Krishna, J. Wang, W. Ahern, P. Sturmfels, P. Venkatesh, I. Kalvet, G. R. Lee, F. S. Morey-Burrows, I. Anishchenko, I. R. Humphreys et al., Generalized biomolecular modeling and design with RoseTTAFold All-Atom, Science 384, eadl2528 (2024).
  13. J. Jumper, R. Evans, A. Pritzel, T. Green, M. Figurnov, O. Ronneberger, K. Tunyasuvunakool, R. Bates, A. Žídek, A. Potapenko et al., Highly accurate protein structure prediction with AlphaFold, Nature (London) 596, 583 (2021).
  14. R. Evans, M. O'Neill, A. Pritzel, N. Antropova, A. Senior, T. Green, A. Žídek, R. Bates, S. Blackwell, J. Yim et al., Protein complex prediction with AlphaFold-Multimer, bioRxiv:2021.10.04.463034.
  15. J. P. Roney and S. Ovchinnikov, State-of-the-art estimation of protein model accuracy using AlphaFold, Phys. Rev. Lett. 129, 238101 (2022).
  16. P. Bryant, A. Kelkar, A. Guljas, C. Clementi, and F. Noé, Structure prediction of protein-ligand complexes from sequence information with Umol, Nat. Commun. 15, 4536 (2024).
  17. P. Csermely, R. Palotai, and R. Nussinov, Induced fit, conformational selection and independent dynamic segments: An extended view of binding events, Trends Biochem. Sci. 35, 539 (2010).
  18. K.-I. Okazaki and S. Takada, Dynamic energy landscape view of coupled binding and protein conformational change: Induced-fit versus population-shift mechanisms, Proc. Natl. Acad. Sci. USA 105, 11182 (2008).
  19. S. Vajda, D. Beglov, A. E. Wakefield, M. Egbert, and A. Whitty, Cryptic binding sites on proteins: Definition, detection, and druggability, Curr. Opin. Chem. Biol. 44, 1 (2018).
  20. X. Zhang, H. Gao, H. Wang, Z. Chen, Z. Zhang, X. Chen, Y. Li, Y. Qi, and R. Wang, Planet: A multi-objective graph neural network model for protein–ligand binding affinity prediction, J. Chem. Inf. Model. 64, 2205 (2024).
  21. M. M. Stepniewska-Dziubinska, P. Zielenkiewicz, and P. Siedlecki, Development and evaluation of a deep learning model for protein–ligand binding affinity prediction, Bioinformatics 34, 3666 (2018).
  22. Z. Cang, L. Mu, and G.-W. Wei, Representability of algebraic topology for biomolecules in machine learning based scoring and virtual screening, PLoS Comput. Biol. 14, e1005929 (2018).
  23. D. Jiang, C.-Y. Hsieh, Z. Wu, Y. Kang, J. Wang, E. Wang, B. Liao, C. Shen, L. Xu, J. Wu et al., InteractionGraphNet: A novel and efficient deep graph representation learning framework for accurate protein–ligand interaction predictions, J. Med. Chem. 64, 18209 (2021).
  24. L. Zheng, J. Fan, and Y. Mu, OnionNet: A multiple-layer intermolecular-contact-based convolutional neural network for protein–ligand binding affinity prediction, ACS Omega 4, 15956 (2019).
  25. J. Jiménez, M. Skalic, G. Martinez-Rosell, and G. De Fabritiis, KDEEP: Protein–ligand absolute binding affinity prediction via 3D-convolutional neural networks, J. Chem. Inf. Model. 58, 287 (2018).
  26. R. Singh, S. Sledzieski, B. Bryson, L. Cowen, and B. Berger, Contrastive learning in protein language space predicts interactions between drugs and protein targets, Proc. Natl. Acad. Sci. USA 120, e2220778120 (2023).
  27. M. Tsubaki, K. Tomii, and J. Sese, Compound–protein interaction prediction with end-to-end learning of neural networks for graphs and sequences, Bioinformatics 35, 309 (2019).
  28. M. Volkov, J.-A. Turk, N. Drizard, N. Martin, B. Hoffmann, Y. Gaston-Mathé, and D. Rognan, On the frustration to predict binding affinities from protein–ligand structures with deep neural networks, J. Med. Chem. 65, 7946 (2022).
  29. W. Lu, Q. Wu, J. Zhang, J. Rao, C. Li, and S. Zheng, Tankbind: Trigonometry-aware neural networks for drug-protein binding structure prediction, in Proceedings Advances in Neural Information Processing Systems 35, edited by S. Koyejo, S. Mohamad, A. Agarwal, D. Belgrave, K. Cho, and A. Oh (2022), pp. 7236–7249.
  30. H. Lai, L. Wang, R. Qian, J. Huang, P. Zhou, G. Ye, F. Wu, F. Wu, X. Zeng, and W. Liu, Interformer: An interaction-aware model for protein-ligand docking and affinity prediction, Nat. Commun. 15, 10223 (2024).
  31. W. Treyde, S. C. Kim, N. Bouatta, and M. AlQuraishi, Quickbind: A light-weight and interpretable molecular docking model, in Proceedings of the 19th Machine Learning in Computational Biology Meeting, edited by D. A. Knowles and S. Mostafavi (PMLR, Cambridge, 2024), Vol. 261, pp. 129–152.
  32. T. Standley, A. Zamir, D. Chen, L. Guibas, J. Malik, and S. Savarese, Which tasks should be learned together in multi-task learning? in Proceedings of the 37th International Conference on Machine Learning, edited by H. Daumé and A. Singh (JMLR, Brookline, 2020), pp. 9120–9132.
  33. T. Hayes, R. Rao, H. Akin, N. J. Sofroniew, D. Oktay, Z. Lin, R. Verkuil, V. Q. Tran, J. Deaton, M. Wiggert et al., Simulating 500 million years of evolution with a language model, Science 387, 850 (2025).
  34. G. Landrum, RDKit: Open-source cheminformatics software, https://github.com/rdkit/UGM_2016 (GitHub, San Francisco, 2016).
  35. A. Cohan, I. Beltagy, D. King, B. Dalvi, and D. S. Weld, Pretrained language models for sequential sentence classification, in Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, edited by S. Padó and R. Huang (Association for Computational Linguistics, Stroudsburg, 2019).
  36. T. Liu, Y. Lin, X. Wen, R. N. Jorissen, and M. K. Gilson, BindingDB: A web-accessible database of experimentally determined protein–ligand binding affinities, Nucl. Acids Res. 35, D198 (2007).
  37. J. Wohlwend, G. Corso, S. Passaro, M. Reveiz, K. Leidal, W. Swiderski, T. Portnoi, I. Chinn, J. Silterra, T. Jaakkola, and R. Barzilay, Boltz-1: Democratizing biomolecular interaction modeling, bioRxiv:2024.11.19.624167.
  38. J. Durairaj, Y. Adeshina, Z. Cao, X. Zhang, V. Oleinikovas, T. Duignan, Z. McClure, X. Robin, D. Kovtun, E. Rossi et al., PLINDER: The protein-ligand interactions dataset and evaluation resource, bioRxiv:2024.07.17.603955.
  39. M. Su, Q. Yang, Y. Du, G. Feng, Z. Liu, Y. Li, and R. Wang, Comparative assessment of scoring functions: The CASF-2016 update, J. Chem. Inf. Model. 59, 895 (2019).
  40. M. Gilson, J. Eberhardt, P. Škrinjar, J. Durairaj, X. Robin, and A. Kryshtafovych, Assessment of pharmaceutical protein-ligand pose and affinity predictions in CASP16. Proteins (2025).
  41. M. Buttenschoen, G. M. Morris, and C. M. Deane, Posebusters: AI-based docking methods fail to generate physically valid poses or generalise to novel sequences, Chem. Sci. 15, 3130 (2024).
  42. Z. Qiao, W. Nie, A. Vahdat, T. F. Miller III, and A. Anandkumar, State-specific protein–ligand complex structure prediction with a multiscale deep generative model, Nat. Mach. Intell. 6, 195 (2024).
  43. ByteDance AML AI4Science Team, X. Chen, Y. Zhang, C. Lu, W. Ma, J. Guan, C. Gong, J. Yang, H. Zhang, K. Zhang et al., Protenix—advancing structure prediction through a comprehensive AlphaFold3 reproduction, bioRxiv:2025.01.08.631967.
  44. See Supplemental Material at http://link.aps.org/supplemental/10.1103/1862-rs2k for details.
  45. F. Liu, O. Mailhot, I. S. Glenn, S. F. Vigneron, V. Bassim, X. Xu, K. Fonseca-Valencia, M. S. Smith, D. S. Radchenko, J. S. Fraser et al., The impact of library size and scale of testing on virtual screening, Nat. Chem. Biol. 21, 1039 (2025).
  46. D. Szklarczyk, R. Kirsch, M. Koutrouli, K. Nastou, F. Mehryary, R. Hachilif, A. L. Gable, T. Fang, N. T. Doncheva, S. Pyysalo et al., The STRING database in 2023: Protein–protein association networks and functional enrichment analyses for any sequenced genome of interest, Nucl. Acids Res. 51, D638 (2023).
  47. G. Ahdritz, N. Bouatta, C. Floristean, S. Kadyan, Q. Xia, W. Gerecke, T. J. O'Donnell, D. Berenberg, I. Fisk, N. Zanichelli et al., OpenFold: Retraining AlphaFold2 yields new insights into its learning mechanisms and capacity for generalization, Nat. Meth. 21, 1514 (2024).
  48. https://github.com/ben-shor/DockFormer.
  49. https://huggingface.co/spaces/benshor/DockFormer.
  50. https://huggingface.co/spaces/benshor/pinder_dockformer/tree/main.

Outline

Information

PRX Life 3, 033024– Published 18 September, 2025
  • Received 23 March 2025
  • Accepted 11 August 2025
Crossmark - Check for updates button
Creative Commons Logo

Published by the American Physical Society under the terms of the Creative Commons Attribution 4.0 International license. Further distribution of this work must maintain attribution to the author(s) and the published article's title, journal citation, and DOI.

Published by the American Physical Society

Sign In to Your Journals Account

Filter

Filter

Article Lookup

Enter a citation