Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2023 Nov 13;63(21):6655-6666.
doi: 10.1021/acs.jcim.3c00722. Epub 2023 Oct 17.

Clustering Protein Binding Pockets and Identifying Potential Drug Interactions: A Novel Ligand-Based Featurization Method

Garrett A Stevenson  1 , Dan Kirshner  2 , Brian J Bennion  2 , Yue Yang  2 , Xiaohua Zhang  2 , Adam Zemla  3 , Marisa W Torres  3 , Aidan Epstein  3 , Derek Jones  3   4 , Hyojin Kim  5 , W F Drew Bennett  2 , Sergio E Wong  2 , Jonathan E Allen  3 , Felice C Lightstone  2
Affiliations

Clustering Protein Binding Pockets and Identifying Potential Drug Interactions: A Novel Ligand-Based Featurization Method

Garrett A Stevenson et al. J Chem Inf Model. .

Abstract

Protein-ligand interactions are essential to drug discovery and drug development efforts. Desirable on-target or multitarget interactions are the first step in finding an effective therapeutic, while undesirable off-target interactions are the first step in assessing safety. In this work, we introduce a novel ligand-based featurization and mapping of human protein pockets to identify closely related protein targets and to project novel drugs into a hybrid protein-ligand feature space to identify their likely protein interactions. Using structure-based template matches from PDB, protein pockets are featured by the ligands that bind to their best co-complex template matches. The simplicity and interpretability of this approach provide a granular characterization of the human proteome at the protein-pocket level instead of the traditional protein-level characterization by family, function, or pathway. We demonstrate the power of this featurization method by clustering a subset of the human proteome and evaluating the predicted cluster associations of over 7000 compounds.

PubMed Disclaimer

Conflict of interest statement

The authors declare no competing financial interest.

Figures

Figure 1
Figure 1
Protein pocket processing and featurization.
Figure 2
Figure 2
Preparing pocket featurizations for input to clustering.
Figure 3
Figure 3
Protein pocket cluster centers (core sample centroids) and 167 clusters visualized by their first three principal components and size.
Figure 4
Figure 4
Sample compounds (CID: PubChem compound identifier) that are not in clustering feature matrix B (panel 1); their pose in the protein structural model of the UniProt reference sequence included in clusters #58 and #140—the poses are derived by alignment of the PDB co-complex pockets that matched the structural model to the structural model of the UniProt sequence (panel 2); and the nearest—in feature space—ligands/structural models, again in poses derived by aligning the PDB co-complex to the structural model alignment (panel 3).
Figure 5
Figure 5
Compound 71520717 in cluster #117 with known and top-predicted activity.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

References

    1. Jeong J.; Kim D.; Choi J. Application of ToxCast/Tox21 Data for Toxicity Mechanism-Based Evaluation and Prioritization of Environmental Chemicals: Perspective and Limitations. Toxicol. In Vitro 2022, 84, 105451.10.1016/j.tiv.2022.105451. - DOI - PubMed
    1. Stevenson G. A.; et al.High-Throughput Virtual Screening of Small Molecule Inhibitors for SARS-CoV-2 Protein Targets with Deep Fusion Models. Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, New York: NY, USA, 2021.
    1. Lau E. Y.; Negrete O. A.; Bennett W. F. D.; Bennion B. J.; Borucki M.; Bourguet F.; Epstein A.; Franco M.; Harmon B.; He S.; et al. Discovery of Small-Molecule Inhibitors of SARS-CoV-2 Proteins Using a Computational and Experimental Pipeline. Front. Mol. Biosci. 2021, 8, 678701.10.3389/fmolb.2021.678701. - DOI - PMC - PubMed
    1. Sun D.; Gao W.; Hu H.; Zhou S. Why 90% of Clinical Drug Development Fails and How to Improve It?. Acta Pharm. Sin. B 2022, 12, 3049–3062. 10.1016/j.apsb.2022.02.002. - DOI - PMC - PubMed
    1. Tutone M.; Almerico A. M.. Targeting Enzymes for Pharmaceutical Development: Methods and Protocols; Labrou N. E., Ed.; Springer US: New York, NY, 2020; pp 29–39.

Publication types