CoChat
Sign Up
Cited by 2Computational Drug Discovery MethodsMachine Learning in BioinformaticsProtein Structure and Dynamics

The DOI matches its Crossref record; 6 of the 6 references it cites were found in a registry or an index.

Sequence-based drug-target binding site pre-training enables cryptic pocket detection and improves binding affinity and kinetics prediction

Open access
Zhang, Shuo, Xie, Li, Tiourine, Daniel, Xie, Lei·2026·Journal of Cheminformatics
DOI 10.1186/s13321-026-01227-0PMC PMC13371367

Published version of a preprint

Open this paper in CoChat — free account

Abstract

Accurately characterizing protein-ligand binding, such as binding site, affinity and kinetics, is critical for accelerating drug discovery. However, many existing computational methods face key limitations, including insufficient integration of comprehensive databases, inadequate representation of protein structural dynamics, and incomplete modeling of microscale protein-ligand interactions. To address these challenges, we introduce ProMoNet, a sequence-based pre-training and fine-tuning framework to enhance the prediction of protein-ligand binding characteristics. ProMoNet leverages protein and molecular foundation models to expand data coverage and enhance diversity. It also introduces a pre-training strategy based on protein-ligand binding site prediction, which bridges protein- and ligand-level representations to support downstream prediction tasks involving protein-ligand complexes. Our pre-training module effectively models microscale protein-ligand interactions and captures the dynamic nature of proteins, including binding site crypticity, without relying on 3-dimensional structural inputs. Notably, this module surpasses or matches state-of-the-art structure-based methods in identifying exposed and cryptic binding sites while maintaining high efficiency. Our fine-tuning module then efficiently transfers the pre-trained knowledge to downstream tasks such as binding affinity and binding kinetics prediction, achieving superior performance. The combination of ProMoNet's strong performance and demonstrated efficiency across multiple tasks highlights its potential for broad applications in drug discovery.Scientific Contribution We propose ProMoNet, a sequence-based pre-training and fine-tuning framework for protein-ligand binding characteristic prediction, where protein-ligand binding site prediction is introduced as a pre-training strategy to bridge independent protein- and ligand-level representations for downstream complex-level tasks. We design two dedicated modules, including a pre-training module that models microscale protein-ligand interactions and captures protein dynamics, as well as a fine-tuning module that efficiently integrates the pre-trained representations for downstream tasks. Even compared to structure-based methods, ProMoNet matches state-of-the-art performance in exposed and cryptic binding site identification and delivers superior results in binding affinity and kinetics prediction, making it a promising tool for drug discovery.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1186/s13321-026-01227-0

Cites

6 of 6 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Flagged first, then by citations

Research works printed but not linked: 86

  1. Kitchen DB, Decornez H, Furr JR, Bajorath J (2004) Docking and scoring in virtual screening for drug discovery: methods and applications. Nat Rev Drug Discov 3(11):935–949 · DOI
  2. Śledź P, Caflisch A (2018) Protein structure-based drug design: from docking to molecular dynamics. Curr Opin Struct Biol 48:93–102 · DOI
  3. Perozzo R, Folkers G, Scapozza L (2004) Thermodynamics of protein-ligand interactions: history, presence, and future aspects. J Recept Signal Transduct 24(1–2):1–52 · DOI
  4. Copeland RA, Pompliano DL, Meek TD (2006) Drug-target residence time and its implications for lead optimization. Nat Rev Drug Discov 5(9):730–739 · DOI · Paper page
  5. Du X, Li Y, Xia Y-L, Ai S-M, Liang J, Sang P, Ji X-L, Liu S-Q (2016) Insights into protein-ligand interactions: mechanisms, models, and methods. Int J Mol Sci 17(2):144 · DOI
  6. Dhakal A, McKay C, Tanner JJ, Cheng J (2022) Artificial intelligence in the prediction of protein-ligand interactions: recent advances and future directions. Brief Bioinform 23(1):476 · DOI
  7. Cai C, Wang S, Xu Y, Zhang W, Tang K, Ouyang Q, Lai L, Pei J (2020) Transfer learning for drug discovery. J Med Chem 63(16):8683–8694 · DOI
  8. Krivák R, Hoksza D (2018) P2rank: machine learning based tool for rapid and accurate prediction of ligand binding sites from protein structure. J Cheminform 10:1–12 · DOI
  9. Lu W, Wu Q, Zhang J, Rao J, Li C, Zheng S (2022) Tankbind: trigonometry-aware neural networks for drug-protein binding structure prediction. Adv Neural Inf Process Syst 35:7236–7249 · DOI
  10. Scardino V, Filippo D, Cavasotto JI, Cavasotto CN (2023) How good are alphafold models for docking-based virtual screening? Iscience 26(1):105920 · DOI · Paper page
  11. Wang DD, Ou-Yang L, Xie H, Zhu M, Yan H (2020) Predicting the impacts of mutations on protein-ligand binding affinity based on molecular dynamics simulations and machine learning methods. Comput Struct Biotechnol J 18:439–454 · DOI
  12. Decherchi S, Cavalli A (2020) Thermodynamics and kinetics of drug-target binding by molecular simulation. Chem Rev 120(23):12788–12833 · DOI
  13. Kuzmanic A, Bowman GR, Juarez-Jimenez J, Michel J, Gervasio FL (2020) Investigating cryptic binding sites by molecular dynamics simulations. Acc Chem Res 53(3):654–661 · DOI
  14. Meller A, Ward M, Borowsky J, Kshirsagar M, Lotthammer JM, Oviedo F, Ferres JL, Bowman GR (2023) Predicting locations of cryptic pockets from single protein structures using the pocketminer graph neural network. Nat Commun 14(1):1177 · DOI
  15. Wang J, Do HN, Koirala K, Miao Y (2023) Predicting biomolecular binding kinetics: a review. J Chem Theory Comput 19(8):2135–2148 · DOI
  16. Qiao Z, Nie W, Vahdat A (2024) State-specific protein-ligand complex structure prediction with a multiscale deep generative model. Nat Mach Intell 6(2):195–208 · DOI
  17. Lu W, Zhang J, Huang W et al (2024) Dynamicbind: predicting ligand-specific protein-ligand complex structure with a deep equivariant generative model. Nat Commun 15(1):1071 · DOI
  18. Öztürk H, Özgür A, Ozkirimli E (2018) Deepdta: deep drug-target binding affinity prediction. Bioinformatics 34(17):821–829 · DOI
  19. Nguyen T, Le H, Quinn TP, Nguyen T, Le TD, Venkatesh S (2021) Graphdta: predicting drug-target binding affinity with graph neural networks. Bioinformatics 37(8):1140–1147 · DOI
  20. Badkul A, Xie L, Zhang S, Xie L (2025) Multimodal out-of-distribution individual uncertainty quantification enhances binding affinity prediction for polypharmacology. Nat Mach Intell 7(12):1985–1995 · DOI
  21. Li S, Zhou J, Xu T, Huang L, Wang F, Xiong H, Huang W, Dou D, Xiong H (2021) Structure-aware interactive graph neural networks for the prediction of protein-ligand binding affinity. In: Proceedings of the 27th ACM SIGKDD conference on knowledge discovery & data mining, pp 975–985 · DOI
  22. Zhang S, Liu Y, Xie L (2023) A universal framework for accurate and efficient geometric deep learning of molecular systems. Sci Rep 13(1):19171 · DOI · Paper page
  23. Koh HY, Nguyen AT, Pan S, May LT, Webb GI (2024) Physicochemical graph neural network for learning protein-ligand interaction fingerprints from sequence data. Nat Mach Intell 6(6):673–87 · DOI
  24. Bommasani R, Hudson DA, Adeli E, Altman R, Arora S, Arx S, Bernstein MS, Bohg J, Bosselut A, Brunskill E (2021) On the opportunities and risks of foundation models. arXiv:2108.07258 · arXiv
  25. Zhang Q, Ding K, Lyv T, Wang X, Yin Q, Zhang Y, Yu J, Wang Y, Li X, Xiang Z et al. (2024) Scientific large language models: a survey on biological & chemical domains. arXiv:2401.14656 · arXiv
  26. Li Q, Hu Z, Wang Y, Li L, Fan Y, King I, Song L, Li Y (2024) Progress and opportunities of foundation models in bioinformatics. arXiv:2402.04286 · DOI
  27. Wang X, Chen G, Qian G, Gao P, Wei X-Y, Wang Y, Tian Y, Gao W (2023) Large-scale multi-modal pre-trained models: a comprehensive survey. Mach Intell Res 20(4):447–482 · DOI
  28. Sledzieski S, Kshirsagar M, Baek M, Dodhia R, Lavista Ferres J, Berger B (2024) Democratizing protein language models with parameter-efficient fine-tuning. Proc Natl Acad Sci 121(26):2405840121 · DOI · Paper page
  29. Li S, Wan F, Shu H, Jiang T, Zhao D, Zeng J (2020) Monn: a multi-objective neural network for predicting compound-protein interactions and affinities. Cell Syst 10(4):308–322 · DOI
  30. Lee I, Nam H (2022) Sequence-based prediction of protein binding regions and drug-target interactions. J Cheminform 14(1):5 · DOI
  31. Seo S, Kim H, Lee J, Choi S, Park S (2024) Exploring the potential of compound-protein complex structure-free models in virtual screening using blendnet. Brief Bioinform 26(1):bbae712 · DOI
  32. Vajda S, Beglov D, Wakefield AE, Egbert M, Whitty A (2018) Cryptic binding sites on proteins: definition, detection, and druggability. Curr Opin Chem Biol 44:1–8 · DOI
  33. Desaphy J, Bret G, Rognan D, Kellenberger E (2015) sc-pdb: a 3d-database of ligandable binding sites-10 years on. Nucleic Acids Res 43(D1):399–404 · DOI
  34. Yang J, Roy A, Zhang Y (2012) Biolip: a semi-manually curated database for biologically relevant ligand-protein interactions. Nucleic Acids Res 41(D1):1096–1103 · DOI
  35. Zhou G, Gao Z, Ding Q (2022) Uni-mol: a universal 3d molecular representation learning framework. In: The Eleventh international conference on learning representations · DOI
  36. Weininger D (1988) Smiles, a chemical language and information system. 1. introduction to methodology and encoding rules. J Chem Inf Comput Sci 28(1):31–36 · DOI · Paper page
  37. Landrum G (2013) RDKit: A software suite for cheminformatics, computational chemistry, and predictive modeling. Academic Press
  38. Vassura M, Margara L, Di Lena P, Medri F, Fariselli P, Casadio R (2008) Reconstruction of 3d structures from protein contact maps. IEEE/ACM Trans Comput Biol Bioinf 5(3):357–367 · DOI
  39. Li J, Wang L, Zhu Z, Song C (2023) Exploring the alternative conformation of a known protein structure based on contact map prediction. J Chem Inf Model 64(1):301–315 · DOI
  40. Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser Ł, Polosukhin I (2017) Attention is all you need. Adv Neural Inf Process Syst, 30
  41. Su D, Xu Y, Winata GI, Xu P, Kim H, Liu Z, Fung P (2019) Generalizing question answering system with pre-trained language model fine-tuning. In: Proceedings of the 2nd workshop on machine reading for question answering, pp 203–211 · DOI
  42. Aggarwal R, Gupta A, Chelur V, Jawahar C, Priyakumar UD (2021) Deeppocket: ligand binding site detection and segmentation using 3d convolutional neural networks. J Chem Inf Model 62(21):5069–5079 · DOI
  43. Le Guilloux V, Schmidtke P, Tuffery P (2009) Fpocket: an open source platform for ligand pocket detection. BMC Bioinform 10(1):1–11 · DOI
  44. Jiménez J, Doerr S, Martínez-Rosell G, Rose AS, De Fabritiis G (2017) Deepsite: protein-binding site predictor using 3d-convolutional neural networks. Bioinformatics 33(19):3036–3042 · DOI
  45. Stepniewska-Dziubinska MM, Zielenkiewicz P, Siedlecki P (2020) Improving detection of protein-ligand binding sites with 3d segmentation. Sci Rep 10(1):5035 · DOI
  46. Kandel J, Tayara H, Chong KT (2021) Puresnet: prediction of protein-ligand binding sites using deep residual neural network. J Cheminform 13(1):1–14 · DOI
  47. Fang Y, Jiang Y, Wei L, Ma Q, Ren Z, Yuan Q, Wei D-Q (2023) Deepprosite: structure-aware protein binding site prediction using esmfold and pretrained language model. Bioinformatics 39(12):718 · DOI
  48. Seo S, Choi J, Choi S, Lee J, Park C, Park S (2024) Pseq2sites: enhancing protein sequence-based ligand binding-site prediction accuracy via the deep convolutional network and attention mechanism. Eng Appl Artif Intell 127:107257 · DOI
  49. Rogers D, Hahn M (2010) Extended-connectivity fingerprints. J Chem Inf Model 50(5):742–754 · DOI
  50. He X, Zhao L, Tian Y, Li R, Chu Q, Gu Z, Zheng M, Wang Y, Li S, Jiang H et al (2024) Highly accurate carbohydrate-binding site prediction with deepglycansite. Nat Commun 15(1):5163 · DOI
  51. Pandey M, Radaeva M, Mslati H, Garland O, Fernandez M, Ester M, Cherkasov A (2022) Ligand binding prediction using protein structure graphs and residual graph attention networks. Molecules 27(16):5114 · DOI
  52. Yuan W, Chen G, Chen CY-C (2022) Fusiondta: attention-based feature polymerizer and knowledge distillation for drug-target binding affinity prediction. Brief Bioinform 23(1):506 · DOI
  53. Jin Z, Wu T, Chen T, Pan D, Wang X, Xie J, Quan L, Lyu Q (2023) Capla: improved prediction of protein-ligand binding affinity by a deep learning approach based on a cross-attention mechanism. Bioinformatics 39(2):049 · DOI
  54. Lu R, Wang J, Li P, Li Y, Tan S, Pan Y, Liu H, Gao P, Xie G, Yao X (2023) Improving drug-target affinity prediction via feature fusion and knowledge distillation. Brief Bioinform 24(3):145 · DOI
  55. Cimermancic P, Weinkam P, Rettenmaier TJ (2016) al: Cryptosite: expanding the druggable proteome by characterization and prediction of cryptic binding sites. J Mol Biol 428(4):709–719 · DOI
  56. Stepniewska-Dziubinska MM, Zielenkiewicz P, Siedlecki P (2018) Development and evaluation of a deep learning model for protein-ligand binding affinity prediction. Bioinformatics 34(21):3666–3674 · DOI
  57. Zheng L, Fan J, Mu Y (2019) Onionnet: a multiple-layer intermolecular-contact-based convolutional neural network for protein-ligand binding affinity prediction. ACS Omega 4(14):15956–15965 · DOI
  58. Jiang D, Hsieh C-Y, Wu Z, Kang Y, Wang J, Wang E, Liao B, Shen C, Xu L, Wu J et al (2021) Interactiongraphnet: a novel and efficient deep graph representation learning framework for accurate protein-ligand interaction predictions. J Med Chem 64(24):18209–18232 · DOI
  59. Koes DR, Baumgartner MP, Camacho CJ (2013) Lessons learned in empirical scoring with smina from the csar 2011 benchmarking exercise. J Chem Inf Model 53(8):1893–1904 · DOI
  60. McNutt AT, Francoeur P, Aggarwal R, Masuda T, Meli R, Ragoza M, Sunseri J, Koes DR (2021) Gnina 10: molecular docking with deep learning. J Cheminform 13(1):43 · DOI
  61. Sverrisson F, Feydy J, Correia BE, Bronstein MM (2021) Fast end-to-end learning on protein surfaces. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. pp 15272–15281 · DOI
  62. Lai H, Wang L, Qian R, Huang J, Zhou P, Ye G, Wu F, Wu F, Zeng X, Liu W (2025) Author correction: interformer: an interaction-aware model for protein-ligand docking and affinity prediction. Nat Commun 16:1566 · DOI
  63. Chen L, Tan X, Wang D, Zhong F, Liu X, Yang T, Luo X, Chen K, Jiang H, Zheng M (2020) Transformercpi: improving compound-protein interaction prediction by sequence-based deep learning with self-attention mechanism and label reversal experiments. Bioinformatics 36(16):4406–4414 · DOI · Paper page
  64. Huang K, Xiao C, Glass LM, Sun J (2021) Moltrans: molecular interaction transformer for drug-target interaction prediction. Bioinformatics 37(6):830–836 · DOI
  65. Bai P, Miljković F, John B, Lu H (2023) Interpretable bilinear attention network with domain adaptation improves drug-target prediction. Nat Mach Intell 5(2):126–136 · DOI
  66. Jiang M, Wang S, Zhang S, Zhou W, Zhang Y, Li Z (2022) Sequence-based drug-target affinity prediction using weighted graph neural networks. BMC Genomics 23(1):449 · DOI
  67. Wang P, Zheng S, Jiang Y, Li C, Liu J, Wen C, Patronov A, Qian D, Chen H, Yang Y (2022) Structure-aware multimodal deep learning for drug-protein interaction prediction. J Chem Inf Model 62(5):1308–1317 · DOI
  68. Passaro S, Corso G, Wohlwend J, Reveiz M, Thaler S, Somnath VR, Getz N, Portnoi T, Roy J, Stark H (2025) Boltz-2: Towards accurate and efficient binding affinity prediction. BioRxiv · DOI
  69. Su M, Yang Q, Du Y, Feng G, Liu Z, Li Y, Wang R (2018) Comparative assessment of scoring functions: the casf-2016 update. J Chem Inf Model 59(2):895–913 · DOI
  70. Carlson HA, Smith RD, Damm-Ganamet KL, Stuckey JA, Ahmed A, Convery MA, Somers DO, Kranz M, Elkins PA, Cui G et al (2016) Csar 2014: a benchmark exercise using unpublished data from pharma. J Chem Inf Model 56(6):1063–1077 · DOI
  71. Hartshorn MJ, Verdonk ML, Chessari G, Brewerton SC, Mooij WT, Mortenson PN, Murray CW (2007) Diverse, high-quality test set for the validation of protein- ligand docking performance. J Med Chem 50(4):726–741 · DOI
  72. Liu X, Feng H, Wu J, Xia K (2021) Persistent spectral hypergraph based machine learning (psh-ml) for protein-ligand binding affinity prediction. Brief Bioinform 22(5):127 · DOI
  73. Copeland RA (2011) Conformational adaptation in drug-target interactions and residence time. Future Med Chem 3(12):1491–1501 · DOI
  74. Pan AC, Borhani DW, Dror RO, Shaw DE (2013) Molecular determinants of drug-receptor binding kinetics. Drug Discov Today 18(13–14):667–673 · DOI
  75. Amangeldiuly N, Karlov D, Fedorov MV (2020) Baseline model for predicting protein-ligand unbinding kinetics through machine learning. J Chem Inf Model 60(12):5946–5956 · DOI
  76. Liu H, Su M, Lin H-X, Wang R, Li Y (2022) Public data set of protein-ligand dissociation kinetic constants for quantitative structure-kinetics relationship studies. ACS Omega 7(22):18985–18996 · DOI
  77. Liu T, Hwang L, Burley SK, Nitsche CI, Southan C, Walters WP, Gilson MK (2024) Bindingdb in 2024: a fair knowledgebase of protein-small molecule binding data. Nucleic Acids Res, 1075 · DOI
  78. Bemis GW, Murcko MA (1996) The properties of known drugs. 1. molecular frameworks. J Med Chem 39(15):2887–2893 · DOI
  79. Chen T, Guestrin C (2016) Xgboost. In: Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining, vol 13. ACM, pp 785–794 · DOI · Paper page
  80. Gasteiger J, Groß J, Günnemann S (2020) Directional message passing for molecular graphs. In: International conference on learning representations (ICLR)
  81. Ba L, Kiros J, Hinton JR, GE (2016) Layer normalization. ArXiv e-prints. p 1607
  82. Müllner D (2011) Modern hierarchical, agglomerative clustering algorithms. arXiv:1109.2378 · arXiv
  83. Wu Z, Ramsundar B, Feinberg EN, Gomes J, Geniesse C, Pappu AS, Leswing K, Pande V (2018) Moleculenet: a benchmark for molecular machine learning. Chem Sci 9(2):513–530 · DOI · Paper page
  84. Ramachandran P, Zoph B, Le QV (2017) Searching for activation functions. arXiv:1710.05941 · arXiv
  85. Meng EC, Goddard TD, Pettersen EF, Couch GS, Pearson ZJ, Morris JH, Ferrin TE (2023) Ucsf chimerax: tools for structure building and analysis. Protein Sci 32(11):4792 · DOI
  86. Mendez D, Gaulton A, Bento AP, Chambers J, De Veij M, Félix E, Magariños MP, Mosquera JF, Mutowo P, Nowotka M et al (2019) Chembl: towards direct deposition of bioassay data. Nucleic Acids Res 47(D1):930–940 · DOI · Paper page

Metadata

Authors
Zhang, S., Xie, L., Tiourine, D., & Xie, L.
Affiliations
  • City University of New York (US)
  • The Graduate Center, CUNY (US)
Corresponding author
Xie, Lei
ORCID
Venue
Journal of Cheminformatics
Publisher
Springer Science and Business Media LLC
Published
2026-05-20
Volume
18
Issue
1
ISSN
1758-2946 (ISSN-L)
DOI
10.1186/s13321-026-01227-0
PMC
PMC13371367
OpenAlex
W7161810072
Cited by
2
References
6
Citations by year
2026: 1
FWCI
3.63
Type
journal article
Language
en
Open access
Licence
Locations
  • Journal of Cheminformatics (publishedVersion, cc-by-nc-nd)
  • bioRxiv (Cold Spring Harbor Laboratory) (acceptedVersion, cc-by-nd)
  • PubMed Central (publishedVersion, cc-by-nc)
  • PubMed (publishedVersion)
  • PubMed Central (publishedVersion, cc-by-nc-nd)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion)
Funders
  • National Institutes of Health (R01GM122845)
  • National Science Foundation (NSF2230354)
  • Northeastern University USA
Topics
  • Life Sciences › Pharmacology, Toxicology and Pharmaceutics › Drug Discovery › Computational Drug Discovery Methods
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Machine Learning in Bioinformatics
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Protein Structure and Dynamics
Keywords
protein-ligand binding site prediction, cryptic binding sites, binding affinity prediction, protein structural dynamics, drug discovery

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review