The DOI matches its Crossref record; 17 of the 17 references it cites were found in a registry or an index.
Featurization strategies for protein–ligand interactions and their applications in scoring function development
Abstract
The predictive performance of classical scoring functions (SFs) seems to have reached a plateau. Currently, SFs relying on sophisticated machine learning techniques have shown great potential in binding affinity prediction and virtual screening. As one of the most indispensable components in the workflow of training a machine learning scoring function (MLSF), the featurization or representation process enables us to catch certain physical processes that are important for protein–ligand interactions and to obtain machine‐readable descriptors. Currently, according to how they are derived, the descriptors used in MLSFs for both continuous and binary binding affinity estimates can be grouped into two broad categories: handcrafted features and automated‐extraction features. Moreover, the automated‐extraction features emerge as a new featurization trend along with the application of deep learning algorithms. Here, we make a thorough summary of the advances in the featurization strategies for protein–ligand interactions in the context of MLSFs, with emphasis on the recently rising automated‐extraction features. We also discuss the similarity between protein–ligand interaction representations and small‐molecule representations, and the challenges confronted by the scientific community in characterizing protein–ligand interactions. We expect that this review could inspire the development of novel featurization approaches and boosted MLSFs. This article is categorized under: Data Science > Artificial Intelligence/Machine Learning Software > Molecular Modeling Molecular and Statistical Mechanics > Molecular 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.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“A reliable scoring scheme that results in the docking score of the correct binding poses was established by the number of molecular interactions (hydrogen, Pi, and hydrophobic interactions) [46].”
From Preparation and Evaluation of Chitosan/PVA Based Hydrogel Films Loaded with Honey for Wound Healing Application (2022) · cites this paper as [46]
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
Directory 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
Zomorodian, A., & Carlsson, G. (2005) · Discrete & Computational Geometry · doi:10.1007/s00454-004-1146-y · Cited by 1,591
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
Chen, L., Tan, X., Wang, D., Zhong, F., Liu, X., Yang, T., Luo, X., Chen, K., Jiang, H., & Zheng, M. (2020) · Bioinformatics · doi:10.1093/bioinformatics/btaa524 · Cited by 607
Huang, S.-Y., Grinter, S. Z., & Zou, X. (2010) · Physical Chemistry Chemical Physics · doi:10.1039/c0cp00151a · Cited by 508 · cited 2×
“7,9,10 It has been widely recognized that the reliability of docking heavily depends on the accuracy of the adopted SFs. 11,12 Therefore, it is essential to develop more accurate and credible SFs to improve the hit rates of docking-based virtual screening.”
BackgroundBoosting docking-based virtual screening with deep learning.
Pereira, J. C., Caffarena, E. R., & dos Santos, C. N. (2016) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.6b00355 · Cited by 395
Performance of machine-learning scoring functions in structure-based virtual screening.
Wójcikowski, M., Ballester, P. J., & Siedlecki, P. (2017) · Scientific Reports · doi:10.1038/srep46710 · Cited by 364
Ain, Q. U., Aleksandrova, A., Roessler, F. D., & Ballester, P. J. (2015) · WIREs Computational Molecular Science · doi:10.1002/wcms.1225 · Cited by 357
Cang, Z., & Wei, G.-W. (2017) · PLOS Computational Biology · doi:10.1371/journal.pcbi.1005690 · Cited by 330
Cang, Z., Mu, L., & Wei, G.-W. (2018) · PLOS Computational Biology · doi:10.1371/journal.pcbi.1005929 · Cited by 257
Research works printed but not linked: 130
- 10.1038/nature03197 · DOI · Paper page
- 10.1021/acs.chemrev.8b00728 · DOI · Paper page
- 10.1021/jm401908w · DOI
- 10.1021/acs.jmedchem.5b00921 · DOI
- 10.1016/j.ejmech.2020.112479 · DOI
- 10.1038/nrd1549 · DOI · Paper page
- 10.3390/ijms20184574 · DOI · Paper page
- 10.3390/ijms20184331 · DOI · Paper page
- 10.2174/0929867325666180904115000 · DOI
- 10.1093/bib/bbaa070 · DOI
- 10.1016/j.artmed.2015.02.002 · DOI
- 10.1021/ci100369f · DOI · Paper page
- 10.1093/bib/bbz173 · DOI
- 10.1002/wcms.18 · DOI
- 10.1021/ci300493w · DOI · Paper page
- 10.1093/bioinformatics/btq112 · DOI · Paper page
- 10.1021/ci100244v · DOI · Paper page
- 10.1002/wcms.1429 · DOI · Paper page
- 10.1093/bib/bbaa095 · DOI
- 10.1093/nar/28.1.235 · DOI · Paper page
- 10.1021/acs.jcim.8b00545 · DOI · Paper page
- 10.1093/nar/gkw1074 · DOI · Paper page
- 10.1021/ci8002649 · DOI · Paper page
- 10.1016/j.drudis.2018.05.010 · DOI · Paper page
- 10.1002/wcms.1183 · DOI · Paper page
- 10.1021/acs.jcim.7b00310 · DOI
- 10.1021/acs.jmedchem.0c00385 · DOI · Paper page
- 10.3389/fphar.2018.01089 · DOI · Paper page
- 10.1021/acs.jcim.7b00564 · DOI · Paper page
- 10.1093/bib/bbaa107 · DOI
- 10.1021/ci400450h · DOI
- 10.1093/bioinformatics/btu104 · DOI · Paper page
- 10.1039/C6CP08232G · DOI
- 10.1021/acs.jcim.9b00645 · DOI
- 10.1021/ci500731a · DOI · Paper page
- 10.1002/wcms.1465 · DOI
- 10.1002/wcms.1478 · DOI · Paper page
- 10.1007/s12539-019-00327-w · DOI · Paper page
- 10.1021/ci400120b · DOI · Paper page
- 10.1002/prot.22058 · DOI
- 10.1021/acs.jcim.8b00712 · DOI · Paper page
- 10.1371/journal.pone.0220113 · DOI · Paper page
- 10.3389/fphar.2020.00069 · DOI
- 10.1093/bib/bbaa410 · DOI
- 10.1016/j.jmgm.2006.06.002 · DOI · Paper page
- 10.1021/ci400321r · DOI
- 10.1002/jcc.21256 · DOI · Paper page
- 10.1021/ci500028u · DOI
- 10.1002/jcc.21334 · DOI · Paper page
- 10.1002/prot.21086 · DOI · Paper page
- 10.1002/jcc.24667 · DOI · Paper page
- 10.1021/ci200078f · DOI
- 10.1021/acs.jcim.9b00977 · DOI
- 10.1093/bib/bbaa094 · DOI
- 10.1007/s10822-019-00248-2 · DOI
- 10.1007/s00214-017-2083-1 · DOI
- 10.1073/pnas.2000585117 · DOI · Paper page
- 10.3390/ijms21249548 · DOI
- Boyles F, 2020, Learning from the ligand: using ligand‐based features to improve binding affinity prediction, Bioinformatics, 36, 758, 10.1093/bioinformatics/btz665 · DOI
- 10.1021/ci9000053 · DOI · Paper page
- 10.1021/ci500091r · DOI · Paper page
- 10.1093/bioinformatics/btz183 · DOI
- 10.1021/jm030331x · DOI · Paper page
- 10.1142/S021972001100577X · DOI
- 10.1021/acsomega.9b01997 · DOI · Paper page
- 10.1093/bioinformatics/btaa982 · DOI
- 10.1021/ci100490w · DOI
- 10.1021/acs.jcim.5b00709 · DOI
- 10.1021/ci050372x · DOI · Paper page
- 10.1021/acs.jcim.9b00356 · DOI
- 10.1021/acs.jctc.8b00516 · DOI
- 10.1021/acs.jcim.0c00026 · DOI
- 10.1021/ci2003889 · DOI · Paper page
- 10.1016/j.jmgm.2011.01.004 · DOI · Paper page
- 10.1021/ci500319f · DOI · Paper page
- 10.1093/nar/gkv1082 · DOI · Paper page
- 10.1021/ci9004139 · DOI
- 10.1093/bioinformatics/bty757 · DOI · Paper page
- 10.1021/ci100050t · DOI · Paper page
- 10.1016/j.csbj.2014.05.004 · doi:10.1016/j.csbj.2014.05.004
- 10.1021/ci900382e · DOI
- 10.1038/srep24817 · DOI
- 10.1093/bib/bbab054 · DOI
- 10.1021/acs.jcim.7b00017 · DOI
- 10.1021/acs.jcim.8b00673 · DOI
- 10.1007/s10822-019-00237-5 · DOI
- 10.1039/C9CP06554G · DOI
- 10.1002/jcc.25213 · DOI
- EdelsbrunnerH LetscherD ZomorodianA.Topological persistence and simplification. In: Proceedings 41st annual symposium on foundations of computer science. IEEE;2000.
- 10.1002/cnm.3179 · DOI
- 10.1021/acs.jcim.0c01415 · DOI
- 10.1021/acs.jcim.9b00334 · DOI · Paper page
- Liu X, 2021, Persistent spectral hypergraph based machine learning (PSH‐ML) for protein–ligand binding affinity prediction, Brief Bioinform
- Liu X, 2021, Hypergraph‐based persistent cohomology (HPC) for molecular representations in drug design, Brief Bioinform
- 10.1093/bib/bbab136 · DOI
- 10.1109/TCBB.2012.36 · DOI
- AshtawyHM MahapatraNR.A comparative assessment of conventional and machine‐learning‐based scoring functions in predicting binding affinities of protein–ligand complexes. In: 2011 IEEE international conference on bioinformatics and biomedicine. IEEE;2011. · doi:10.1109/bibm.2011.128
- 10.1186/1471-2105-16-S4-S8 · DOI
- 10.1021/acs.jcim.7b00309 · DOI
- 10.1186/1471-2105-15-291 · DOI
- 10.1186/s13321-021-00507-1 · DOI
- 10.1002/cmdc.201700505 · DOI
- 10.1016/j.compbiomed.2017.09.007 · DOI
- WallachI DzambaM HeifetsA.AtomNet: a deep convolutional neural network for bioactivity prediction in structure‐based drug discovery. arXiv preprint arXiv:1510.02855;2015. · arXiv
- 10.1021/acs.jcim.6b00740 · DOI · Paper page
- 10.1021/acs.jcim.8b00350 · DOI
- 10.1021/acs.jcim.7b00650 · DOI · Paper page
- 10.1093/bioinformatics/bty758 · DOI
- 10.1093/bioinformatics/bty374 · DOI · Paper page
- 10.1021/acs.jcim.0c00411 · DOI · Paper page
- LiY RezaeiMA LiC LiX WuD.DeepAtom: a framework for protein–ligand binding affinity prediction. In: 2019 IEEE international conference on bioinformatics and biomedicine (BIBM). IEEE;2019. · DOI
- 10.3390/ijms21228424 · DOI
- 10.1093/bioinformatics/btz870 · DOI
- 10.1021/acscentsci.8b00507 · DOI · Paper page
- 10.1021/c160017a018 · DOI · Paper page
- 10.1021/ci00062a008 · DOI · Paper page
- GomesJ RamsundarB FeinbergEN PandeVS.Atomic convolutional networks for predicting protein–ligand binding affinity. arXiv preprint arXiv:1703.10603;2017. · arXiv
- 10.1021/acs.jcim.9b00387 · DOI · Paper page
- 10.1371/journal.pone.0249404 · DOI
- 10.1186/s13321-015-0078-2 · DOI · Paper page
- 10.1186/s13321-021-00486-3 · DOI
- 10.1093/bib/bbz150 · DOI
- 10.3390/molecules23112935 · doi:10.3390/molecules23112935
- 10.1002/(SICI)1521-3773(19991004)38:19<2894::AID-ANIE2894>3.0.CO;2-F · DOI · Paper page
- Mason JS, 2000, Library design and virtual screening using multiple 4‐point pharmacophore fingerprints, Pac Symp Biocomput, 5, 576
- 10.1186/s13321-015-0109-z · DOI · Paper page
- 10.1093/bib/bbaa194 · DOI
- 10.1093/bioinformatics/btu624 · DOI
- 10.1371/journal.pcbi.1007129 · DOI · Paper page
- 10.1038/s41592-019-0666-6 · DOI · Paper page
Cited by
Chopra, H., Bibi, S., Kumar, S., Khan, M. S., Kumar, P., & Singh, I. (2022) · Gels · doi:10.3390/gels8020111 · Cited by 245
Cao, D., Chen, M., Zhang, R., Wang, Z., Huang, M., Yu, J., Jiang, X., Fan, Z., Zhang, W., Zhou, H., et al. (2025) · Nature Methods · doi:10.1038/s41592-024-02516-y · Cited by 106
Self-citationRELATION: A Deep Generative Model for Structure-Based De Novo Drug Design
Wang, M., Hsieh, C.-Y., Wang, J., Wang, D., Weng, G., Shen, C., Yao, X., Bing, Z., Li, H., Cao, D., et al. (2022) · Journal of Medicinal Chemistry · doi:10.1021/acs.jmedchem.2c00732 · Cited by 99
Self-citationNordquist, E. B., Zhao, M., Kumar, A., & MacKerell, A. D. (2024) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.4c01189 · Cited by 15
Metadata
- Authors
- Xiong, G., Shen, C., Yang, Z., Jiang, D., Liu, S., Lu, A., Chen, X., Hou, T., & Cao, D.
- Venue
- WIREs Computational Molecular Science
- Publisher
- Wiley
- Published
- 2021-08-03
- Volume
- 12
- Issue
- 2
- ISSN
- 1759-0876
- 1759-0884
- Cited by
- 43
- References
- 17
- Language
- en
- Funders
- National Natural Science Foundation of China (21575128, 81773632)
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
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.