Skip to content
naulon
Get started

No retraction, correction or concern found when last checked on Oct 17, 2026.

Development and evaluation of a deep learning model for protein–ligand binding affinity prediction

Marta M Stepniewska-Dziubinska, Piotr Zielenkiewicz, Pawel Siedlecki

Bioinformatics · 2018 · CC BY

doi:10.1093/bioinformatics/bty374

Abstract

Motivation. Structure based ligand discovery is one of the most successful approaches for augmenting the drug discovery process. Currently, there is a notable shift towards machine learning (ML) methodologies to aid such procedures. Deep learning has recently gained considerable attention as it allows the model to ‘learn’ to extract features that are relevant for the task at hand.

Results. We have developed a novel deep neural network estimating the binding affinity of ligand–receptor complexes. The complex is represented with a 3D grid, and the model utilizes a 3D convolution to produce a feature map of this representation, treating the atoms of both proteins and ligands in the same manner. Our network was tested on the CASF-2013 ‘scoring power’ benchmark and Astex Diverse Set and outperformed classical scoring functions.

Availability and implementation. The model, together with usage instructions and examples, is available as a git repository at http://gitlab.com/cheminfIBB/pafnucy.

Supplementary information. Supplementary data are available at Bioinformatics online.

Full text

Its licence does not allow us to show the full text. Read it at PubMed Central:

Read at PubMed Central

References 50

  1. 1.

    Abadi M. et al (2015 ) TensorFlow: large-scale machine learning on heterogeneous distributed systems. arXiv preprint arXiv: 1603.04467.

    Not in our library

  2. 2.

    Alipanahi B. et al (2015 ) Predicting the sequence specificities of DNA- and RNA-binding proteins by deep learning. Nat. Biotechnol., 33, 831–838.

    Not in our library10.1038/nbt.3300

  3. 3.
    Deep learning for computational biology · 2016
    No notice
  4. 4.

    Bajusz D. et al (2017 ) Structure-based virtual screening approaches in kinase-directed drug discovery. Curr. Top. Med. Chem., 17, 2235–2259.

    Not in our library10.2174/1568026617666170224121313

  5. 5.

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

    Not in our library10.1093/bioinformatics/btq112

  6. 6.

    Breiman L. et al (1984 ) Classification and Regression Trees. CRC Press, Boca Raton, FL, USA.

    Not in our library

  7. 7.
    Structure-Based Virtual Screening for Drug Discovery: a Problem-Centric Review · 2012
    No notice
  8. 8.

    Dahl G.E. et al (2014 ) Multi-task neural networks for QSAR predictions. arXiv preprint arXiv: 14061231v1, 1–21.

    Not in our library

  9. 9.

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

    Not in our library10.1021/ci100244v

  10. 10.

    Durrant J.D., McCammon J.A. (2011 ) NNScore 2.0: a neural-network receptor–ligand scoring function. J. Chem. Inf. Model., 51, 2897–2903.

    Not in our library10.1021/ci2003889

  11. 11.

    Duvenaud D.K. et al (2015 ) Convolutional networks on graphs for learning molecular fingerprints. In: Cortes,C. (ed.) Neural Information Processing Systems, pp. 2215–2223.

    Not in our library

  12. 12.

    Ertl P. et al (2017 ) In silico generation of novel, drug-like chemical matter using the lstm neural network. arXiv preprint arXiv: 1712.07449.

    Not in our library

  13. 13.

    Fradera X., Babaoglu K. (2017 ) Overview of methods and strategies for conducting virtual small molecule screening. Curr. Protoc. Chem. Biol., 9, 196–212.

    Not in our library10.1002/cpch.27

  14. 14.

    Gomes J. et al (2017 ) Atomic convolutional networks for predicting protein–ligand binding affinity. arXiv preprint arXiv: 170310603.

    Not in our library

  15. 15.
    Automatic Chemical Design Using a Data-Driven Continuous Representation of Molecules · 2018
    Not checked
  16. 16.

    Goodfellow I. et al (2016 ) Deep Learning. MIT Press, Cambridge, MA.

    Not in our library

  17. 17.

    Hartshorn M.J. et al (2007 ) Diverse, high-quality test set for the validation of protein–ligand docking performance. J. Med. Chem., 50, 726–741.

    Not in our library10.1021/jm061277y

  18. 18.

    Jastrzȩbski S. et al (2016 ). Learning to SMILE(S). In: International Conference on Learning Representation 2016 (Workshop track).

    Not in our library

  19. 19.

    Jiménez J. et al (2017 ) Deepsite: protein-binding site predictor using 3d-convolutional neural networks. Bioinformatics, 33, 3036–3042.

    Not in our library10.1093/bioinformatics/btx350

  20. 20.

    Jurtz V.I. et al (2017 ) An introduction to deep learning on biological sequence data: examples and solutions. Bioinformatics, 33, 3685–3690.

    Not in our library10.1093/bioinformatics/btx531

  21. 21.

    Kearnes S. et al (2016 ) Molecular graph convolutions: moving beyond fingerprints. J. Comput. Aided Mol. Des., 30, 595–608.

    Not in our library10.1007/s10822-016-9938-8

  22. 22.

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

    Not in our library10.1021/ci100369f

  23. 23.
    Beyond the hype: deep neural networks outperform established methods using a ChEMBL bioactivity benchmark set · 2017
    No notice
  24. 24.

    Leung M.K.K. et al (2014 ) Deep learning of the tissue-regulated splicing code. Bioinformatics, 30, i121–i129.

    Not in our library10.1093/bioinformatics/btu277

  25. 25.

    Li Y. et al (2014 ) Comparative assessment of scoring functions on an updated benchmark: 2. evaluation methods and general results. J. Chem. Inf. Model., 54, 1717–1736.

    Not in our library10.1021/ci500081m

  26. 26.

    Lima A.N. et al (2016 ) Use of machine learning approaches for novel drug discovery. Exp. Opin. Drug Discov., 11, 225–239.

    Not in our library10.1517/17460441.2016.1146250

  27. 27.

    Liu Z. et al (2017 ) Forging the basis for developing protein–ligand interaction scoring functions. Accounts Chem. Res., 50, 302–309.

    Not in our library10.1021/acs.accounts.6b00491

  28. 28.

    Lusci A. et al (2013 ) Deep architectures and deep learning in chemoinformatics: the prediction of aqueous solubility for drug-like molecules. J. Chem. Inf. Model., 53, 1563–1575.

    Not in our library10.1021/ci400187y

  29. 29.

    Ma D.-L. et al (2013 ) Drug repositioning by structure-based virtual screening. Chem. Soc. Rev., 42, 2130–2141.

    Not in our library10.1039/c2cs35357a

  30. 30.

    Ma J. et al (2015 ) Deep neural nets as a method for quantitative structure-activity relationships. J. Chem. Inf. Model., 55, 263–274.

    Not in our library10.1021/ci500747n

  31. 31.

    MacMullen C.M. et al (2017 ) Novel pde10a transcript diversity in the human striatum: insights into gene complexity, conservation and regulation. Gene, 606, 17–24.

    Not in our library10.1016/j.gene.2016.12.033

  32. 32.

    Morris G.M. et al (2009 ) AutoDock4 and AutoDockTools4: automated docking with selective receptor flexibility. J. Comput. Chem., 30, 2785–2791.

    Not in our library10.1002/jcc.21256

  33. 33.

    Muegge I. (2006 ) Pmf scoring revisited. J. Med. Chem., 49, 5895–5902.

    Not in our library10.1021/jm050038s

  34. 34.

    Nketia T.A. et al (2017 ) Analysis of live cell images: methods, tools and opportunities. Methods, 115, 65–79.

    Not in our library10.1016/j.ymeth.2017.02.007

  35. 35.
    Open Babel: An open chemical toolbox · 2011
    No notice
  36. 36.
    Molecular de-novo design through deep reinforcement learning · 2017
    No notice
  37. 37.

    Park Y., Kellis M. (2015 ) Deep learning for regulatory genomics. Nat. Biotechnol., 33, 825–826.

    Not in our library10.1038/nbt.3313

  38. 38.

    Pettersen E.F. et al (2004 ) UCSF Chimera–a visualization system for exploratory research and analysis. J. Comput. Chem., 25, 1605–1612.

    Not in our library10.1002/jcc.20084

  39. 39.

    Ragoza M. et al (2016 ) Protein–ligand scoring with convolutional neural networks. J. Chem. Inf. Model., 57, 942–957.

    Not in our library10.1021/acs.jcim.6b00740

  40. 40.

    Ramsundar B. et al (2017 ) Is multitask deep learning practical for pharma?J. Chem. Inf. Model., 57, 2068–2076.

    Not in our library10.1021/acs.jcim.7b00146

  41. 41.

    Segler M.H. et al (2017 ) Generating focussed molecule libraries for drug discovery with recurrent neural networks. ACS Cent. Sci., 4, 120–131.

    Not in our library10.1021/acscentsci.7b00512

  42. 42.
    DeCAF—Discrimination, Comparison, Alignment Tool for 2D PHarmacophores · 2017
    Not checked
  43. 43.

    Stierand K., Rarey M. (2010 ) Drawing the PDB: protein–ligand complexes in two dimensions. ACS Med. Chem. Lett., 1, 540–545.

    Not in our library10.1021/ml100164p

  44. 44.

    Verdonk M.L. et al (2003 ) Improved protein–ligand docking using gold. Proteins Struct. Funct. Bioinf., 52, 609–623.

    Not in our library10.1002/prot.10465

  45. 45.

    Wallach I. et al (2015 ) AtomNet: A deep convolutional neural network for bioactivity prediction in structure-based drug discovery. arXiv preprint arXiv: 151002855.

    Not in our library

  46. 46.
    Open Drug Discovery Toolkit (ODDT): a new open-source player in the drug discovery field · 2015
    No notice
  47. 47.
    Performance of machine-learning scoring functions in structure-based virtual screening · 2017
    No notice
  48. 48.

    Xu Y. et al (2015 ) Deep learning for drug-induced liver injury. J. Chem. Inf. Model., 55, 2085–2093.

    Not in our library10.1021/acs.jcim.5b00238

  49. 49.

    Xu Y. et al (2017 ) Demystifying multi-task deep neural networks for quantitative structure-activity relationships. J. Chem. Inf. Model., 57, 2490–2504.

    Not in our library10.1021/acs.jcim.7b00087

  50. 50.

    Zhang L. et al (2017 ) From machine learning to deep learning: progress in machine intelligence for rational drug discovery. Drug Discov. Today, 22, 1680–1685.

    Not in our library10.1016/j.drudis.2017.08.010

Cited by papers we hold 6

Reads

Read by people on this page

None yet.

Checked or read by AI through naulon

None yet.

A person counts once a day per paper. We keep no cookie and no address: a reader is a hash that changes every day. Any month under five reads shows no number.

Are you an author?

Is this your paper?

Claim it to add your note and be paid when agents cite it. Free.