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.

  • Protocol
  • Published:

Artificial intelligence–enabled virtual screening of ultra-large chemical libraries with deep docking

Nature Protocols volume 17, pages 672–697 (2022)Cite this article

Subjects

This article has been updated

Abstract

With the recent explosion of chemical libraries beyond a billion molecules, more efficient virtual screening approaches are needed. The Deep Docking (DD) platform enables up to 100-fold acceleration of structure-based virtual screening by docking only a subset of a chemical library, iteratively synchronized with a ligand-based prediction of the remaining docking scores. This method results in hundreds- to thousands-fold virtual hit enrichment (without significant loss of potential drug candidates) and hence enables the screening of billion molecule–sized chemical libraries without using extraordinary computational resources. Herein, we present and discuss the generalized DD protocol that has been proven successful in various computer-aided drug discovery (CADD) campaigns and can be applied in conjunction with any conventional docking program. The protocol encompasses eight consecutive stages: molecular library preparation, receptor preparation, random sampling of a library, ligand preparation, molecular docking, model training, model inference and the residual docking. The standard DD workflow enables iterative application of stages 3–7 with continuous augmentation of the training set, and the number of such iterations can be adjusted by the user. A predefined recall value allows for control of the percentage of top-scoring molecules that are retained by DD and can be adjusted to control the library size reduction. The procedure takes 1–2 weeks (depending on the available resources) and can be completely automated on computing clusters managed by job schedulers. This open-source protocol, at https://github.com/jamesgleave/DD_protocol, can be readily deployed by CADD researchers and can significantly accelerate the effective exploration of ultra-large portions of a chemical space.

Access through your institution
Buy or subscribe

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

Access options

Access through your institution

Buy this article

  • Purchase on SpringerLink
  • Instant access to full article PDF
Buy now

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

Fig. 1: AI-accelerated DD approach versus regular docking.
Fig. 2: Effect of varying training size and number of iterations on the number of remaining molecules (molecules that are classified as virtual hits, hence not discarded) for screening ZINC20 against the dimerization site of androgen receptor (PDB ID: 1R4I39).
Fig. 3: Chemical library preparation for DD.
Fig. 4: General DD workflow.
Fig. 5: Iterative model improvement during DD iterations (virtual screening of ZINC20 library against the active site of SARS-CoV-2 papain-like protease (PDB ID: 7LBR56) using Glide SP).

Similar content being viewed by others

Data availability

The prepared version of ZINC20 can be freely obtained from https://files.docking.org/zinc20-ML/. The example iteration is freely available from the Federated Research Data Repository (https://doi.org/10.20383/102.0489). Source data for Figs. 2 and 5 are freely available from the Federated Research Data Repository (https://doi.org/10.20383/102.0489).

Code availability

The DD code is freely available at https://github.com/jamesgleave/DD_protocol.

Change history

  • 27 March 2024

    In Step 34, the text “Run the procedure from Steps 16–31” originally read “14–31”. This has now been amended in the HTML and PDF versions of the article.

References

  1. Lyu, J. et al. Ultra-large library docking for discovering new chemotypes. Nature 566, 224–229 (2019).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  2. Gorgulla, C. et al. An open-source drug discovery platform enables ultra-large virtual screens. Nature 580, 663–668 (2020).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  3. Stein, R. M. et al. Virtual discovery of melatonin receptor ligands to modulate circadian rhythms. Nature 579, 609–614 (2020).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  4. Grygorenko, O. O. et al. Generating multibillion chemical space of readily accessible screening compounds. iScience 23, 101681 (2020).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  5. Acharya, A. et al. Supercomputer-based ensemble docking drug discovery pipeline with application to Covid-19. J. Chem. Inf. Model. 60, 5832–5852 (2020).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  6. Shoichet, B. K. Virtual screening of chemical libraries. Nature 432, 862–865 (2004).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  7. Cherkasov, A., Ban, F., Li, Y., Fallahi, M. & Hammond, G. L. Progressive docking: a hybrid QSAR/docking approach for accelerating in silico high throughput screening. J. Med. Chem. 49, 7466–7478 (2006).

    Article  CAS  PubMed  Google Scholar 

  8. Svensson, F., Norinder, U. & Bender, A. Improving screening efficiency through iterative screening using docking and conformal prediction. J. Chem. Inf. Model. 57, 439–444 (2017).

    Article  CAS  PubMed  Google Scholar 

  9. Ahmed, L. et al. Efficient iterative virtual screening with Apache Spark and conformal prediction. J. Cheminform. 10, 8 (2018).

    Article  PubMed  PubMed Central  Google Scholar 

  10. Gentile, F. et al. Deep Docking: a deep learning platform for augmentation of structure based drug discovery. ACS Cent. Sci. 6, 939–949 (2020).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  11. Sterling, T. & Irwin, J. J. ZINC 15—ligand discovery for everyone. J. Chem. Inf. Model. 55, 2324–2337 (2015).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  12. McGann, M. FRED pose prediction and virtual screening accuracy. J. Chem. Inf. Model. 51, 578–596 (2011).

    Article  CAS  PubMed  Google Scholar 

  13. Friesner, R. A. et al. Glide: a new approach for rapid, accurate docking and scoring. 1. Method and assessment of docking accuracy. J. Med. Chem. 47, 1739–1749 (2004).

    Article  CAS  PubMed  Google Scholar 

  14. Ton, A.-T., Gentile, F., Hsing, M., Ban, F. & Cherkasov, A. Rapid identification of potential inhibitors of SARS-CoV-2 main protease by deep docking of 1.3 billion compounds. Mol. Inf. 39, e2000028 (2020).

    Article  Google Scholar 

  15. Muratov, E. N. et al. A critical overview of computational approaches employed for COVID-19 drug discovery. Chem. Soc. Rev. 50, 9121–9151 (2021).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  16. Gentile, F., Ton, A.-T., Mslati, H., Ban, F. & Cherkasov, A. Discovery of SARS-CoV-2 main protease inhibitors through Deep Docking of 1.36 billion compounds. in 26th Congress of the European Society of Biomechanics (European Society of Biomechanics, 2021).

  17. Rossetti, G. G. et al. Identification of low micromolar SARS-CoV-2 Mpro inhibitors from hits identified by in silico screens. Preprint at bioRxiv https://doi.org/10.1101/2020.12.03.409441(2020).

  18. Jastrzębski, S. et al. Emulating docking results using a deep neural network: a new perspective for virtual screening. J. Chem. Inf. Model. 60, 4246–4262 (2020).

    Article  PubMed  Google Scholar 

  19. Al Saadi, A. et al. IMPECCABLE: Integrated Modeling PipelinE for COVID Cure by Assessing Better LEads. in ACM International Conference Proceeding Series (Association for Computing Machinery, 2021); https://doi.org/10.1145/3472456.3473524

  20. Berenger, F., Kumar, A., Zhang, K. Y. J. & Yamanishi, Y. Lean-docking: exploiting ligands’ predicted docking scores to accelerate molecular docking. J. Chem. Inf. Model. 61, 2341––2352 (2021).

    Article  CAS  PubMed  Google Scholar 

  21. Graff, D. E., Shakhnovich, E. I. & Coley, C. W. Accelerating high-throughput virtual screening through molecular pool-based active learning. Chem. Sci. 12, 7866–7881 (2021).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  22. Yang, Y. et al. Efficient exploration of chemical space with docking and deep-learning. Preprint at https://chemrxiv.org/engage/chemrxiv/article-details/60c755bf842e65adc6db4393 (2021).

  23. Sessions, Z. et al. Recent progress on cheminformatics approaches to epigenetic drug discovery. Drug Discov. Today 25, 2268–2276 (2020).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  24. Coley, C. W. Defining and exploring chemical spaces. Trends Chem. 3, 133–145 (2021).

    Article  CAS  Google Scholar 

  25. Irwin, J. J. et al. ZINC20—a free ultralarge-scale chemical database for ligand discovery. J. Chem. Inf. Model. 60, 6065–6073 (2020).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  26. Enamine. REAL Database https://enamine.net/library-synthesis/real-compounds/real-database# (2021).

  27. Enamine. REAL Space https://enamine.net/compound-collections/real-compounds/real-space-navigator (2021).

  28. Hawkins, P. C. D., Skillman, A. G., Warren, G. L., Ellingson, B. A. & Stahl, M. T. Conformer generation with OMEGA: algorithm and validation using high quality structures from the Protein Databank and Cambridge Structural Database. J. Chem. Inf. Model. 50, 572–584 (2010).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  29. The RDKit Documentation—The RDKit 2020.03.1 Documentation. https://www.rdkit.org/docs/ (2020).

  30. QUACPAC 2.0.2.2. (OpenEye Scientific Software, 2019).

  31. O’Boyle, N. M. et al. Open Babel: an open chemical toolbox. J. Cheminform. 3, 33 (2011).

    Article  PubMed  PubMed Central  Google Scholar 

  32. Kochev, N. T., Paskaleva, V. H. & Jeliazkova, N. Ambit-Tautomer: an open source tool for tautomer generation. Mol. Inf. 32, 481–504 (2013).

    Article  CAS  Google Scholar 

  33. Morgan, H. L. The generation of a unique machine description for chemical structures—a technique developed at Chemical Abstracts Service. J. Chem. Doc. 5, 107–113 (1965).

    Article  CAS  Google Scholar 

  34. Rogers, D. & Hahn, M. Extended-connectivity fingerprints. J. Chem. Inf. Model. 50, 742–754 (2010).

    Article  CAS  PubMed  Google Scholar 

  35. Extended Connectivity Fingerprint ECFP https://docs.chemaxon.com/display/docs/extended-connectivity-fingerprint-ecfp.md (ChemAxon, 2021).

  36. Maestro v9.3. (Schrödinger, 2019).

  37. Molecular Operating Environment 2019 (Chemical Computing Group, 2019).

  38. Moustakas, D. T. et al. Development and validation of a modular, extensible docking program: DOCK 5. J. Comput. Aided Mol. Des. 20, 601–619 (2006).

    Article  CAS  PubMed  Google Scholar 

  39. Shaffer, P. L., Jivan, A., Dollins, D. E., Claessens, F. & Gewirth, D. T. Structural basis of androgen receptor binding to selective androgen response elements. Proc. Natl Acad. Sci. USA. 101, 4758–4763 (2004).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  40. Santos-Martins, D. et al. Accelerating AutoDock4 with GPUs and gradient-based local search. J. Chem. Theory Comput. 17, 1060–1073 (2021).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  41. Alhossary, A., Handoko, S. D., Mu, Y. & Kwoh, C.-K. Fast, accurate, and reliable molecular docking with QuickVina 2. Bioinformatics 31, 2214–2216 (2015).

    Article  CAS  PubMed  Google Scholar 

  42. Abagyan, R., Totrov, M. & Kuznetsov, D. ICM—a new method for protein modeling and design: applications to docking and structure prediction from the distorted native conformation. J. Comput. Chem. 15, 488–506 (1994).

    Article  CAS  Google Scholar 

  43. Neves, M. A. C., Totrov, M. & Abagyan, R. Docking and scoring with ICM: the benchmarking results and strategies for improvement. J. Comput. Aided Mol. Des. 26, 675–686 (2012).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  44. Giga Docking Guide—Orion Programming Guide. 1.0 documentation https://docs.eyesopen.com/orion-developer/2020-2-1/modules/large-scale-floes/docs/source/giga_docking_guide.html (OpenEye Software, 2020).

  45. LeGrand, S. et al. GPU-accelerated drug discovery with docking on the Summit supercomputer: porting, optimization, and application to COVID-19 research. Preprint at https://arxiv.org/abs/2007.03678 (2020).

  46. Bender, B. J. et al. A practical guide to large-scale docking. Nat. Protoc. 16, 4799–4832 (2021).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  47. Jorgensen, W. L. The many roles of computation in drug discovery. Science 303, 1813–1818 (2004).

    Article  CAS  PubMed  Google Scholar 

  48. OEDOCKING v3.3.0.3 (OpenEye Scientific Software, 2021).

  49. Abadi, M. et al. TensorFlow: a system for large-scale machine learning. Proceedings of the 12th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2016 265–283 (The USENIX Association, 2016).

  50. Pedregosa, F. et al. Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825–2830 (2012).

    Google Scholar 

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

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  52. Morris, G. M. et al. Automated docking using a Lamarckian genetic algorithm and an empirical binding free energy function. J. Comput. Chem. 19, 1639–1662 (1998).

    Article  CAS  Google Scholar 

  53. Melo, F. Area under the ROC curve. in Encyclopedia of Systems Biology (eds. Dubitzky, W. et al.) 38–39 (Springer, 2013).

  54. Hur, E. et al. Recognition and accommodation at the androgen receptor coactivator binding interface. PLoS Biol. 2, E274 (2004).

    Article  PubMed  PubMed Central  Google Scholar 

  55. Melo, F. Receiver operating characteristic (ROC) curve. in Encyclopedia of Systems Biology (eds. Dubitzky, W. et al.) 1818–1823 (Springer, 2013).

  56. Shen, Z. et al. Design of SARS-CoV-2 PLpro inhibitors for COVID-19 antiviral therapy leveraging binding cooperativity. J. Med. Chem. https://doi.org/10.1021/acs.jmedchem.1c01307 (2021).

Download references

Acknowledgements

F.G. is supported by fellowships from the Canadian Institutes for Health Research (MFE-171324), the Michael Smith Foundation for Health Research/VCHRI & VGH UBC Hospital Foundation (RT-2020-0408) and the Ermenegildo Zegna Foundation. F.B. is supported by a UBC Data Science Institute fellowship. We thank J. Irwin for his support in sharing the DD-prepared version of the ZINC20 library.

Author information

Author notes

  1. These authors contributed equally: Jean Charle Yaacoub, James Gleave.

Authors and Affiliations

  1. Vancouver Prostate Centre, Department of Urologic Sciences, The University of British Columbia, Vancouver, BC, Canada

    Francesco Gentile, Jean Charle Yaacoub, James Gleave, Michael Fernandez, Anh-Tien Ton, Fuqiang Ban & Artem Cherkasov

  2. NVIDIA Corporation, Santa Clara, CA, USA

    Abraham Stern

Authors
  1. Francesco Gentile
    View author publications

    Search author on:PubMed Google Scholar

  2. Jean Charle Yaacoub
    View author publications

    Search author on:PubMed Google Scholar

  3. James Gleave
    View author publications

    Search author on:PubMed Google Scholar

  4. Michael Fernandez
    View author publications

    Search author on:PubMed Google Scholar

  5. Anh-Tien Ton
    View author publications

    Search author on:PubMed Google Scholar

  6. Fuqiang Ban
    View author publications

    Search author on:PubMed Google Scholar

  7. Abraham Stern
    View author publications

    Search author on:PubMed Google Scholar

  8. Artem Cherkasov
    View author publications

    Search author on:PubMed Google Scholar

Contributions

F.G. and A.C. conceived the work. F.G. wrote the manuscript with the help of M.F., J.C.Y., J.G., A.-T.T. and F.B. F.G. developed the protocol, with the help of J.C.Y., J.G. and A.S. J.C.Y., J.G. and F.G. wrote the current version of the code. A.-T.T. and M.F. provided support with critical evaluation and tested user-friendliness of the protocol. A.S. contributed to discussing and revising the protocol. A.C. supervised experiments and edited the manuscript.

Corresponding author

Correspondence to Artem Cherkasov.

Ethics declarations

Competing interests

The authors declare no competing interests.

Peer review

Peer review information

Nature Protocols thanks John Karanicolas and Ying Yang 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.

Related links

Key references using this protocol

Gentile, F. et al. Chem. Sci. 12, 15960–15974 (2021): https://doi.org/10.1039/d1sc05579h

Gentile, F. et al. ACS Cent. Sci. 6, 939–949 (2020): https://doi.org/10.1021/acscentsci.0c00229

Ton, A.-T. et al. Mol. Inform. 39, e2000028 (2020): https://doi.org/10.1002/minf.202000028

Supplementary information

Supplementary Information

Supplementary Tables 1 and 2, Supplementary Figs. 1 and 2 and Supplementary References.

Reporting Summary

Supplementary Table 3

evaluation.csv file obtained from evaluating different training sizes in one DD iteration, screening the ZINC20 library against the AR dimerization site (PDB ID: 1R4I ; ref. 40) using Glide SP for docking and a recall of 0.90. Validation and test sets comprised 700,000 molecules each.

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

Gentile, F., Yaacoub, J.C., Gleave, J. et al. Artificial intelligence–enabled virtual screening of ultra-large chemical libraries with deep docking. Nat Protoc 17, 672–697 (2022). https://doi.org/10.1038/s41596-021-00659-2

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue date:

  • DOI: https://doi.org/10.1038/s41596-021-00659-2

This article is cited by

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