Predicting or Pretending: Artificial Intelligence for Protein-Ligand Interactions Lack of Sufficiently Large and Unbiased Datasets
Open accessThe DOI matches its Crossref record; 15 of the 15 references it cites were found in a registry or an index.
Abstract
Predicting protein-ligand interactions using artificial intelligence (AI) models has attracted great interest in recent years. However, data-driven AI models unequivocally suffer from a lack of sufficiently large and unbiased datasets. Here, we systematically investigated the data biases on the PDBbind and DUD-E datasets. We examined the model performance of atomic convolutional neural network (ACNN) on the PDBbind core set and achieved a Pearson R2 of 0.73 between experimental and predicted binding affinities. Strikingly, the ACNN models did not require learning the essential protein-ligand interactions in complex structures and achieved similar performance even on datasets containing only ligand structures or only protein structures, while data splitting based on similarity clustering (protein sequence or ligand scaffold) significantly reduced the model performance. We also identified the property and topology biases in the DUD-E dataset which led to the artificially increased enrichment performance of virtual screening. The property bias in DUD-E was reduced by enforcing the more stringent ligand property matching rules, while the topology bias still exists due to the use of molecular fingerprint similarity as a decoy selection criterion. Therefore, we believe that sufficiently large and unbiased datasets are desirable for training robust AI models to accurately predict protein-ligand interactions.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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
Breiman, L. (2001) · Machine Learning · doi:10.1023/a:1010933404324 · Cited by 133,538 · cited 1×
“Two feature sets for decoy selection were used to build the RF models (Breiman, 2001) to evaluate the bias in the DUD-E dataset.”
MethodBengio, Y., Louradour, J., Collobert, R., & Weston, J. (2009) · Proceedings of the 26th Annual International Conference on Machine Learning · doi:10.1145/1553374.1553380 · Cited by 5,366 · cited 1×
“This training strategy is similar to the “ curriculum learning ” strategy (Bengio et al., 2009) because it reduces the dif fi culty of learning via training on the organized data.”
ResultDirectory of useful decoys, enhanced (DUD-E): better ligands and decoys for better benchmarking.
Mysinger, M. M., Carchia, M., Irwin, J. J., & Shoichet, B. K. (2012) · Journal of Medicinal Chemistry · doi:10.1021/jm300687e · Cited by 2,412 · cited 1×
“…public available benchmarking datasets, including the Community Structure-Activity Resource (CSAR) (Dunbar et al., 2011), the PDBbind (Liu et al., 2017), the Directory of Useful Decoys (DUD) (Huang et al., 2006b), and the Directory of Useful Decoys - Enhanced (DUD-E) (Mysinger et al., 2012).”
MethodThe rise of deep learning in drug discovery
Chen, H., Engkvist, O., Wang, Y., Olivecrona, M., & Blaschke, T. (2018) · Drug Discovery Today · doi:10.1016/j.drudis.2018.01.039 · Cited by 1,770
Molecular graph convolutions: moving beyond fingerprints
Kearnes, S., McCloskey, K., Berndl, M., Pande, V., & Riley, P. (2016) · Journal of Computer-Aided Molecular Design · doi:10.1007/s10822-016-9938-8 · Cited by 1,631 · cited 1×
“Topology Bias in DUD-E In DUD and DUD-E, the actives and decoys against the same target are dissimilar on topology and can be easily differentiated based on fingerprint (von Korff et al., 2009; Venkatraman et al., 2010;Hu et al., 2012; Lagarde et al., 2015; Kearnes et al., 2016; Sieg et al., 2019).”
BackgroundDeep learning enables rapid identification of potent DDR1 kinase inhibitors
Zhavoronkov, A., Ivanenkov, Y. A., Aliper, A., Veselov, M. S., Aladinskiy, V. A., Aladinskaya, A. V., Terentiev, V. A., Polykovskiy, D. A., Kuznetsov, M. D., Asadulaev, A., et al. (2019) · Nature Biotechnology · doi:10.1038/s41587-019-0224-x · Cited by 1,573
Virtual screening of chemical libraries
Shoichet, B. K. (2004) · Nature · doi:10.1038/nature03197 · Cited by 1,425
Benchmarking sets for molecular docking.
Huang, N., Shoichet, B. K., & Irwin, J. J. (2006) · Journal of Medicinal Chemistry · doi:10.1021/jm0608356 · Cited by 1,318 · cited 1×
“…public available benchmarking datasets, including the Community Structure-Activity Resource (CSAR) (Dunbar et al., 2011), the PDBbind (Liu et al., 2017), the Directory of Useful Decoys (DUD) (Huang et al., 2006b), and the Directory of Useful Decoys - Enhanced (DUD-E) (Mysinger et al., 2012).”
MethodSelf-citationUltra-large library docking for discovering new chemotypes
Lyu, J., Wang, S., Balius, T. E., Singh, I., Levit, A., Moroz, Y. S., O’Meara, M. J., Che, T., Algaa, E., Tolmachova, K., et al. (2019) · Nature · doi:10.1038/s41586-019-0917-9 · Cited by 998
Wang, Z., Sun, H., Yao, X., Li, D., Xu, L., Li, Y., Tian, S., & Hou, T. (2016) · Physical Chemistry Chemical Physics · doi:10.1039/c6cp01555g · Cited by 946
Cited by
Jiang, D., Hsieh, C.-Y., Wu, Z., Kang, Y., Wang, J., Wang, E., Liao, B., Shen, C., Xu, L., Wu, J., et al. (2021) · Journal of Medicinal Chemistry · doi:10.1021/acs.jmedchem.1c01830 · Cited by 262
Self-citationDhakal, A., McKay, C., Tanner, J. J., & Cheng, J. (2022) · Briefings in Bioinformatics · doi:10.1093/bib/bbab476 · Cited by 256
MISATO: machine learning dataset of protein–ligand complexes for structure-based drug discovery
Siebenmorgen, T., Menezes, F., Benassou, S., Merdivan, E., Didi, K., Mourão, A. S. D., Kitel, R., Liò, P., Kesselheim, S., Piraud, M., et al. (2024) · Nature Computational Science · doi:10.1038/s43588-024-00627-2 · Cited by 75
Plasticity of the binding pocket in peptide transporters underpins promiscuous substrate recognition
Kotov, V., Killer, M., Jungnickel, K. E. J., Lei, J., Finocchio, G., Steinke, J., Bartels, K., Strauss, J., Dupeux, F., Humm, A.-S., et al. (2023) · Cell Reports · doi:10.1016/j.celrep.2023.112831 · Cited by 20
MISATO - Machine learning dataset of protein-ligand complexes for structure-based drug discovery
(2023) · doi:10.1101/2023.05.24.542082 · Cited by 18
Metadata
- Authors
- Yang, J., Shen, C., & Huang, N.
- Venue
- Frontiers in Pharmacology
- Publisher
- Frontiers Media SA
- Published
- 2020-02-25
- Volume
- 11
- Pages
- 69-69
- ISSN
- 1663-9812 (ISSN-L)
- OpenAlex
- W3001433048
- Cited by
- 124
- References
- 15
- FWCI
- 9.05
- Type
- journal article
- Language
- en
- Open access
- gold
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Predicting or Pretending: Artificial Intelligence for Protein-Ligand Interactions Lack of Sufficiently Large and Unbiased Datasets. https://app.cochat.ai/papers/10.3389/fphar.2020.00069
- The paper
- Yang, J., Shen, C., & Huang, N. (2020). Predicting or Pretending: Artificial Intelligence for Protein-Ligand Interactions Lack of Sufficiently Large and Unbiased Datasets. Frontiers in Pharmacology. https://doi.org/10.3389/fphar.2020.00069
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.