Review article · 2021 · Open access

Learning from Docked Ligands: Ligand-Based Features Rescue Structure-Based Scoring Functions When Trained on Docked Poses

Fergus Boyles, Charlotte Mary Deane, Garrett M. Morris

Journal of Chemical Information and Modeling, 62(22), 5329–5341 · Published 1 September 2021 · DOI 10.1021/acs.jcim.1c00096

Read the free full textView at the publisherCite this paper

In brief

“Learning from Docked Ligands: Ligand-Based Features Rescue Structure-Based Scoring Functions When Trained on Docked Poses” is a 2021 review article by Fergus Boyles and 2 co-authors, published in Journal of Chemical Information and Modeling. OpenAlex counts 24 citations as of 16 November 2026. It is open access under a CC BY licence: the full text is free to read at ChemRxiv.

Citations
24
Most cited in
2023 (7)
Field-weighted impact
0.36
References
50
Authors
3

Abstract

Machine learning scoring functions for protein-ligand binding affinity have been found to consistently outperform classical scoring functions when trained and tested on crystal structures of bound protein-ligand complexes. However, it is less clear how these methods perform when applied to docked poses of complexes. We explore how the use of docked rather than crystallographic poses for both training and testing affects the performance of machine learning scoring functions. Using the PDBbind Core Sets as benchmarks, we show that the performance of a structure-based machine learning scoring function trained and tested on docked poses is lower than that of the same scoring function trained and tested on crystallographic poses. We construct a hybrid scoring function by combining both structure-based and ligand-based features, and show that its ability to predict binding affinity using docked poses is comparable to that of purely structure-based scoring functions trained and tested on crystal poses. We also present a new, freely available validation set─the Updated DUD-E Diverse Subset─for binding affinity prediction using data from DUD-E and ChEMBL. Despite strong performance on docked poses of the PDBbind Core Sets, we find that our hybrid scoring function sometimes generalizes poorly to a protein target not represented in the training set, demonstrating the need for improved scoring functions and additional validation benchmarks.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Boyles, F., Deane, C. M., & Morris, G. M. (2021). Learning from Docked Ligands: Ligand-Based Features Rescue Structure-Based Scoring Functions When Trained on Docked Poses. Journal of Chemical Information and Modeling, 62(22), 5329–5341. https://doi.org/10.1021/acs.jcim.1c00096

MLA 9

Boyles, Fergus, et al. “Learning from Docked Ligands: Ligand-Based Features Rescue Structure-Based Scoring Functions When Trained on Docked Poses.” Journal of Chemical Information and Modeling, vol. 62, no. 22, 2021, pp. 5329–5341. https://doi.org/10.1021/acs.jcim.1c00096.

Chicago

Boyles, Fergus, Charlotte Mary Deane, and Garrett M. Morris. 2021. “Learning from Docked Ligands: Ligand-Based Features Rescue Structure-Based Scoring Functions When Trained on Docked Poses.” Journal of Chemical Information and Modeling 62 (22): 5329–5341. https://doi.org/10.1021/acs.jcim.1c00096.

Harvard

Boyles, F., Deane, C. M. and Morris, G. M. (2021) ‘Learning from Docked Ligands: Ligand-Based Features Rescue Structure-Based Scoring Functions When Trained on Docked Poses’, Journal of Chemical Information and Modeling, 62(22), pp. 5329–5341. doi:10.1021/acs.jcim.1c00096.

IEEE

F. Boyles, C. M. Deane, and G. M. Morris, “Learning from Docked Ligands: Ligand-Based Features Rescue Structure-Based Scoring Functions When Trained on Docked Poses,” Journal of Chemical Information and Modeling, vol. 62, no. 22, pp. 5329–5341, 2021, doi: 10.1021/acs.jcim.1c00096.

BibTeX

@article{boyles2021learning,
  title     = {{Learning from Docked Ligands: Ligand-Based Features Rescue Structure-Based Scoring Functions When Trained on Docked Poses}},
  author    = {Boyles, Fergus and Deane, Charlotte Mary and Morris, Garrett M.},
  journal   = {Journal of Chemical Information and Modeling},
  year      = {2021},
  volume    = {62},
  number    = {22},
  pages     = {5329--5341},
  doi       = {10.1021/acs.jcim.1c00096},
  url       = {https://doi.org/10.1021/acs.jcim.1c00096}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Citations by year

YearCitationsShare of the best year
202111
202255
202377
202455
202544
202622

Its field-weighted citation impact is 0.36: it has been cited 0.36 times as often as the average work of the same field, type and year (1.00 is the world average).

Topic and keywords

Life Sciences › Pharmacology, Toxicology and Pharmaceutics › Drug Discovery › Computational Drug Discovery Methods

  • machine learning scoring functions
  • protein-ligand binding affinity
  • binding affinity prediction
  • benchmark validation

Work with this paper

Most-cited papers in Pharmacology, Toxicology and Pharmaceutics

All highly cited Pharmacology, Toxicology and Pharmaceutics papers

Questions about this paper

How do I cite this paper in APA style?

Boyles, F., Deane, C. M., & Morris, G. M. (2021). Learning from Docked Ligands: Ligand-Based Features Rescue Structure-Based Scoring Functions When Trained on Docked Poses. Journal of Chemical Information and Modeling, 62(22), 5329–5341. https://doi.org/10.1021/acs.jcim.1c00096

How many times has this paper been cited?

24 times, according to OpenAlex on 16 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access: read the free full text at ChemRxiv.

Who wrote this paper?

Fergus Boyles, Charlotte Mary Deane, Garrett M. Morris.

What is the DOI of this paper?

10.1021/acs.jcim.1c00096. The permanent link is https://doi.org/10.1021/acs.jcim.1c00096.

Bibliographic data from OpenAlex (CC0), last checked 16 November 2026. ResearchGuru does not host this paper; the links go to the publisher or the repository that does.