The DOI matches its Crossref record; 1 of the 1 references it cites were found in a registry or an index.
Deciphering DEL Pocket Patterns through Contrastive Learning
Open accessPreprint — published as 10.1038/s41467-026-69663-y · Paper page
Abstract
DNA-encoded libraries (DELs) facilitate high-throughput screening of trillions of molecules against protein targets through split-pool synthesis and DNA tagging. Despite their potential, only a few DEL-derived compounds have advanced to clinical trials or reached the market. A better understanding of the defining characteristics of target proteins, particularly those with binding pockets suitable for DEL screening, is critical to improving success rates. However, existing approaches remain limited in assessing pocket flexibility and functional similarity. Here, we present ErePOC, a pocket representation model based on contrastive learning with ESM-2 embeddings to address these challenges. ErePOC captures both structural and functional features of binding pockets, enabling identification of shared characteristics among DEL targets. By integrating analyses of low-dimensional physicochemical properties and high-dimensional ErePOC embeddings, we provide a comprehensive view of DEL target space. With 98% precision in downstream classification tasks, ErePOC demonstrates high performance in pocket representation, which is then applied to predict human proteins suitable for DEL screening, with enrichment uncovered across 18 functional categories. This work establishes a new framework for enhancing DEL-based drug discovery through more effective target selection and pocket similarity analysis.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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
Varadi, M., Bertoni, D., Magana, P., Paramval, U., Pidruchna, I., Radhakrishnan, M., Tsenkov, M., Nair, S., Mirdita, M., Yeo, J., et al. (2024) · Nucleic Acids Research · doi:10.1093/nar/gkad1011 · Cited by 2,052
Flagged first, then by citations
Research works printed but not linked: 50
- 2024, Evolution of chemistry and selection technology for DNA-encoded library, Acta Pharmaceutica Sinica B, 14, 492, 10.1016/j.apsb.2023.10.001 · DOI
- 2021, DNA-encoded chemical libraries: a comprehensive review with succesful stories and future challenges, ACS Pharmacology & Translational Science, 4, 1265, 10.1021/acsptsci.1c00118 · DOI · Paper page
- 2023, Development of highly potent noncovalent inhibitors of SARS-CoV-2 3CLpro, ACS central science, 9, 217, 10.1021/acscentsci.2c01359 · DOI
- 2021, Discovery of soluble epoxide hydrolase inhibitors through DNA-encoded library technology (ELT), Bioorganic & Medicinal Chemistry, 41, 116216, 10.1016/j.bmc.2021.116216 · DOI
- 10.1021/acs.jmedchem.0c00688 · DOI
- 10.1021/acs.jmedchem.6b01751 · DOI
- 10.1038/s41573-023-00713-6 · DOI
- 10.1021/acs.chemrev.4c00284 · DOI
- 10.1126/science.ade2574 · DOI · Paper page
- Ouyang-Zhang J , Diaz D , Klivans A , Krähenbühl P . Predicting a protein’s stability under a million mutations. In: Advances in Neural Information Processing Systems, (2023).
- 2024, Protein function prediction as approximate semantic entailment, Nature Machine Intelligence, 6, 220, 10.1038/s42256-024-00795-w · DOI · Paper page
- Wang D , et al. S-PLM: Structure-Aware Protein Language Model via Contrastive Learning Between Sequence and Structure. Adv Sci (Weinh ), e2404212 (2024). · DOI
- 10.1016/j.molcel.2024.01.021 · DOI
- 2020, Deciphering interaction fingerprints from protein molecular surfaces using geometric deep learning, Nature Methods, 17, 184, 10.1038/s41592-019-0666-6 · DOI
- Zhou G , et al. Uni-mol: A universal 3d molecular representation learning framework. In: The Eleventh International Conference on Learning Representations, (2023). · DOI
- 2023, PocketAnchor: Learning structure-based pocket representations for protein-ligand interaction prediction, Cell Systems, 14, 692, 10.1016/j.cels.2023.05.005 · DOI
- Luo Z , Wu W , Sun Q , Wang J . Accurate and transferable drug–target interaction prediction with DrugLAMP. Bioinformatics 40, btae693 (2024). · DOI
- 10.1093/bioinformatics/btae594 · DOI
- Chen T , Kornblith S , Norouzi M , Hinton G . A simple framework for contrastive learning of visual representations. In: International conference on machine learning, (2020).
- 10.1016/j.jmb.2007.01.086 · DOI
- 10.1073/pnas.1300011110 · DOI
- 2025, Macrophages direct location-dependent recall of B cell memory to vaccination, Cell, 188, 3477, 10.1016/j.cell.2025.04.005 · DOI
- 10.1093/nar/gkad630 · DOI
- 2023, AlphaFill: enriching AlphaFold models with ligands and cofactors, Nature Methods, 20, 205, 10.1038/s41592-022-01685-y · DOI · Paper page
- 10.1038/nchem.1243 · DOI
- 10.1038/nrd2445 · DOI · Paper page
- 10.1186/1471-2105-10-1 · DOI
- 10.1016/j.jmb.2016.12.004 · DOI
- 10.2174/156802608786786624 · DOI
- Van der Maaten L , Hinton G . Visualizing data using t-SNE. Journal of machine learning research 9, (2008).
- 10.1021/acs.jpcb.2c04525 · DOI
- 10.1093/nar/gki524 · DOI · Paper page
- 10.1073/pnas.0704422105 · DOI
- Iqbal S , et al. Evaluation of DNA encoded library and machine learning model combinations for hit discovery. npj Drug Discovery 2, (2025). · DOI
- 10.1038/s41586-019-0917-9 · DOI · Paper page
- 2025, The impact of library size and scale of testing on virtual screening, Nat Chem Biol, 21, 1039, 10.1038/s41589-024-01797-w · DOI
- 2024, MAT2A inhibition combats metabolic and transcriptional reprogramming in cancer, Drug Discov Today, 29, 104189, 10.1016/j.drudis.2024.104189 · DOI
- 10.1021/acs.jcim.1c00944 · DOI
- Zhan R , Zhang W , Huang J . Scrutinization on Docking Against Individually Generated Target Pockets for Each Ligand. bioRxiv, (2025). · DOI
- Nishimura T , Tsuboyama K , Nakagaki Y , Yamamoto E , Mizushima N . Rational engineering of lipid-binding probes via high-throughput protein-lipid interaction screening. bioRxiv, (2025). · DOI
- 2024, Testing the predictive power of reverse screening to infer drug targets, with the help of machine learning, Communications Chemistry, 7, 105, 10.1038/s42004-024-01179-2 · DOI
- 10.1021/acs.jcim.3c00293 · DOI
- 10.1038/s41586-023-06415-8 · DOI · Paper page
- 10.1038/s41586-024-08416-7 · DOI
- 2025, Rapid clearance of achiral small-molecule drugs using de novo-designed proteins and their cyclic and mirror-image variants, Nat Biomed Eng, 9, 1775, 10.1038/s41551-025-01404-w · DOI
- 10.1126/science.abb8330 · DOI
- 10.1186/s13321-020-00456-1 · DOI
- 10.1073/pnas.0506580102 · DOI · Paper page
- 2011, Open Babel: An open chemical toolbox, Journal of Cheminformatics, 3, 33, 10.1186/1758-2946-3-33 · DOI
- 10.1002/jcc.21334 · DOI · Paper page
Metadata
- Authors
- Zhang, W., Wang, Y., Zhan, R., Qian, R., Hu, Q., & Huang, J.
- Affiliations
- Westlake University (CN)
- Corresponding author
- Huang, Jing
- Venue
- Nature Communications
- Publisher
- openRxiv
- Published
- 2025-06-17
- Volume
- 17
- Issue
- 1
- ISSN
- 2041-1723 (ISSN-L)
- OpenAlex
- W7129060316
- Cited by
- 2
- References
- 1
- Citations by year
- 2026: 2
- FWCI
- 7.21
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Nature Communications (publishedVersion, cc-by)
- bioRxiv (Cold Spring Harbor Laboratory) (acceptedVersion, cc-by-nd)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- Westlake University
- National Natural Science Foundation of China (2023C03109, 32171247, 32501101, 2024SSYS0036)
- Natural Science Foundation of Zhejiang Province (LQ23F020011, 2024SSYS0036)
- Topics
- Life Sciences › Pharmacology, Toxicology and Pharmaceutics › Drug Discovery › Computational Drug Discovery Methods
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Machine Learning in Bioinformatics
- Physical Sciences › Chemistry › Organic Chemistry › Chemical Synthesis and Analysis
- Keywords
- DNA-encoded libraries, protein pockets, contrastive learning, ESM-2 embeddings, physicochemical properties, protein functional classification, high-throughput screening, drug discovery
- MeSH terms
- Machine Learning, Binding Sites, DNA, Humans, Models, Molecular, Protein Binding, Proteins, Small Molecule Libraries, Drug Discovery
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
