CoChat
Sign Up
PreprintCited by 97Computational Drug Discovery MethodsMachine Learning in Materials ScienceProtein Degradation and Inhibitors

The DOI matches its Crossref record; 1 of the 1 references it cites were found in a registry or an index.

PocketFlow: an autoregressive flow model incorporated with chemical knowledge for generating drug-like molecules inside protein pockets

Open access
Yang, Shengyong, Jiang, Yuanyuan, Zhang, Guo, You, Jing, Zhang, Hailin, Yao, Rui, Xie, Huanzhang, Xia, Ziyi, Dai, Mengzhe, Wu, Yunjie·2023·Nature Machine Intelligence
DOI 10.21203/rs.3.rs-3077992/v1

Preprint — published as 10.1038/s42256-024-00808-8 · Paper page

Open this paper in CoChat — free accountOpen PDF

Abstract

Identifying an active seed compound against a specific target protein is the first but challenging step for initiating a new drug development project. Newly emerging deep generative models (DGMs) providea rapid strategy to directly generate potential seed compounds inside protein pockets. However, the poor quality of generated molecules remains a major challenge, and whether these DGMs can generate bioactive molecules has not yet been wet-lab verified. We herein propose a new structure-based DGM, PocketFlow, which is an autoregressive flow model with chemical knowledge incorporated in molecular generation. PocketFlow can generate high-quality drug-like molecules with 100% chemical validity. In various evaluations, PocketFlow outperforms the current state-of-the-art DGMs. We applied PocketFlow to two new target proteins, HAT1 and YTHDC1, and successfully obtained wet-lab validated bioactive lead compounds. Overall, PocketFlow is the first wet-lab verified structure-based molecular DGM, highlighting the great potential of structure-based DGMs in drug discovery.

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.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.21203/rs.3.rs-3077992/v1

Cites

1 of 1 references verified0 citation errors · 0 not checkable

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.

A few free checks a day · papers already verified open instantly · results are public

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

Flagged first, then by citations

Show all 1 references

Research works printed but not linked: 44

  1. Li, Y., et al., Generative deep learning enables the discovery of a potent and selective RIPK1 inhibitor. Nature Communications, 2022. 13(1): p. 6891. · DOI
  2. Isert, C., K. Atz, and G. Schneider, Structure-based drug design with geometric deep learning. Current Opinion in Structural Biology, 2023. 79: p. 102548. · DOI · Paper page
  3. Moret, M., et al., Leveraging molecular structure and bioactivity with chemical language models for de novo drug design. Nature Communications, 2023. 14(1): p. 114. · DOI
  4. Tong, X., et al., Generative Models for De Novo Drug Design. Journal of Medicinal Chemistry, 2021. 64(19): p. 14011–14027. · DOI
  5. Wang, J., et al., Multi-constraint molecular generation based on conditional transformer, knowledge distillation and reinforcement learning. Nature Machine Intelligence, 2021. 3(10): p. 914–922. · DOI
  6. Li, Y., J. Pei, and L. Lai, Structure-based de novo drug design using 3D deep generative models. Chemical Science, 2021. 12(41): p. 13664–13675. · DOI
  7. Zheng, S., et al., Accelerated rational PROTAC design via deep learning and molecular simulations. Nature Machine Intelligence, 2022. 4(9): p. 739–748. · DOI
  8. Zhang, J. and H. Chen, De Novo Molecule Design Using Molecular Generative Models Constrained by Ligand–Protein Interactions. Journal of Chemical Information and Modeling, 2022. 62(14): p. 3291–3306. · DOI
  9. Godinez, W.J., et al., Design of potent antimalarials with generative chemistry. Nature Machine Intelligence, 2022. 4(2): p. 180–186. · DOI
  10. Bagal, V., et al., MolGPT: Molecular Generation Using a Transformer-Decoder Model. Journal of Chemical Information and Modeling, 2022. 62(9): p. 2064–2076. · DOI
  11. Blaschke, T., et al., REINVENT 2.0: An AI Tool for De Novo Drug Design. Journal of Chemical Information and Modeling, 2020. 60(12): p. 5918–5922. · DOI · Paper page
  12. Peng, X., et al. Pocket2mol: Efficient molecular sampling based on 3d protein pockets. in International Conference on Machine Learning. 2022. PMLR.
  13. Ragoza, M., T. Masuda, and D.R. Koes, Generating 3D molecules conditional on receptor binding sites with deep generative models. Chemical Science, 2022. 13(9): p. 2701–2713. · DOI
  14. Francoeur, P.G., et al., Three-Dimensional Convolutional Neural Networks and a Cross-Docked Data Set for Structure-Based Drug Design. Journal of Chemical Information and Modeling, 2020. 60(9): p. 4200–4215. · DOI
  15. Pan, Y., Heading toward Artificial Intelligence 2.0. Engineering, 2016. 2(4): p. 409–413. · DOI
  16. Cheng, G., X.-G. Gong, and W.-J. Yin, Crystal structure prediction by combining graph network and optimization algorithm. Nature Communications, 2022. 13(1): p. 1492. · DOI
  17. Jiang, Y., et al., Coupling complementary strategy to flexible graph neural network for quick discovery of coformer in diverse co-crystal materials. Nature Communications, 2021. 12(1): p. 5950. · DOI
  18. O'Boyle, N.M., et al., Open Babel: An open chemical toolbox. Journal of Cheminformatics, 2011. 3(1): p. 33. · DOI
  19. Cai, C., et al., Transfer Learning for Drug Discovery. Journal of Medicinal Chemistry, 2020. 63(16): p. 8683–8694. · DOI
  20. Aykent, S. and T. Xia. Gbpnet: Universal geometric representation learning on protein structures. in Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 2022.
  21. Deng, C., et al. Vector neurons: A general framework for so (3)-equivariant networks. in Proceedings of the IEEE/CVF International Conference on Computer Vision. 2021.
  22. Luo, Y., K. Yan, and S. Ji. Graphdf: A discrete flow model for molecular graph generation. in International Conference on Machine Learning. 2021. PMLR.
  23. Bickerton, G.R., et al., Quantifying the chemical beauty of drugs. Nature Chemistry, 2012. 4(2): p. 90–98. · DOI
  24. Ertl, P. and A. Schuffenhauer, Estimation of synthetic accessibility score of drug-like molecules based on molecular complexity and fragment contributions. Journal of Cheminformatics, 2009. 1(1): p. 8. · DOI · Paper page
  25. Copeland, R.A., The drug–target residence time model: a 10-year retrospective. Nature Reviews Drug Discovery, 2016. 15(2): p. 87–95. · DOI
  26. Hopkins, A.L., C.R. Groom, and A. Alex, Ligand efficiency: a useful metric for lead selection. Drug Discovery Today, 2004. 9(10): p. 430–431. · DOI
  27. Kenny, P.W., The nature of ligand efficiency. Journal of Cheminformatics, 2019. 11(1): p. 8. · DOI
  28. Chen, H., et al., 2.08 - Fragment-Based Drug Design: Strategic Advances and Lessons Learned, in Comprehensive Medicinal Chemistry III, S. Chackalamannil, D. Rotella, and S.E. Ward, Editors. 2017, Elsevier: Oxford. p. 212–232. · DOI
  29. Verdonk, M.L., et al., Docking Performance of Fragments and Druglike Compounds. Journal of Medicinal Chemistry, 2011. 54(15): p. 5422–5431. · DOI
  30. Eldridge, M.D., et al., Empirical scoring functions: I. The development of a fast empirical scoring function to estimate the binding affinity of ligands in receptor complexes. Journal of Computer-Aided Molecular Design, 1997. 11(5): p. 425–445. · DOI
  31. Hartshorn, M.J., et al., Diverse, High-Quality Test Set for the Validation of Protein – Ligand Docking Performance. Journal of Medicinal Chemistry, 2007. 50(4): p. 726–741. · DOI
  32. Wu, H., et al., Structural basis for substrate specificity and catalysis of human histone acetyltransferase 1. Proceedings of the National Academy of Sciences, 2012. 109(23): p. 8925–8930.
  33. Gruber, J.J., et al., HAT1 Coordinates Histone Production and Acetylation via H4 Promoter Binding. Molecular Cell, 2019. 75(4): p. 711–724.e5. · DOI
  34. Yang, G., et al., Histone acetyltransferase 1 is a succinyltransferase for histones and non-histones and promotes tumorigenesis. EMBO reports, 2021. 22(2): p. e50967. · DOI
  35. Fan, P., et al., Overexpressed histone acetyltransferase 1 regulates cancer immunity by increasing programmed death-ligand 1 expression in pancreatic cancer. Journal of Experimental & Clinical Cancer Research, 2019. 38(1): p. 47. · DOI
  36. Xue, L., et al., RNAi screening identifies HAT1 as a potential drug target in esophageal squamous cell carcinoma. Int J Clin Exp Pathol, 2014. 7(7): p. 3898–907.
  37. Xia, P., et al., MicroRNA-377 exerts a potent suppressive role in osteosarcoma through the involvement of the histone acetyltransferase 1-mediated Wnt axis. Journal of Cellular Physiology, 2019. 234(12): p. 22787–22798. · DOI
  38. Roundtree, I.A., et al., YTHDC1 mediates nuclear export of N6-methyladenosine methylated mRNAs. eLife, 2017. 6: p. e31311. · DOI
  39. Xiao, W., et al., Nuclear m6A Reader YTHDC1 Regulates mRNA Splicing. Molecular Cell, 2016. 61(4): p. 507–519. · DOI · Paper page
  40. Sheng, Y., et al., A critical role of nuclear m6A reader YTHDC1 in leukemogenesis by regulating MCM complex–mediated DNA replication. Blood, 2021. 138(26): p. 2838–2852. · DOI
  41. Maas, A.L., A.Y. Hannun, and A.Y. Ng. Rectifier nonlinearities improve neural network acoustic models. in Proc. icml. 2013. Atlanta, Georgia, USA.
  42. Ba, J.L., J.R. Kiros, and G.E.J.a.p.a. Hinton, Layer normalization. 2016.
  43. Papamakarios, G., T. Pavlakou, and I.J.A.i.n.i.p.s. Murray, Masked autoregressive flow for density estimation. 2017. 30.
  44. Irwin, J.J., et al., ZINC20—A Free Ultralarge-Scale Chemical Database for Ligand Discovery. Journal of Chemical Information and Modeling, 2020. 60(12): p. 6065–6073. · DOI

Metadata

Authors
Yang, S., Jiang, Y., Zhang, G., You, J., Zhang, H., Yao, R., Xie, H., Xia, Z., Dai, M., & Wu, Y.
Affiliations
  • Sichuan University (CN)
  • Minjiang University (CN)
ORCID
Venue
Nature Machine Intelligence
Publisher
Springer Science and Business Media LLC
Published
2023-09-27
Volume
6
Issue
3
Pages
326-337
ISSN
2522-5839 (ISSN-L)
DOI
10.21203/rs.3.rs-3077992/v1
OpenAlex
W4392653998
Cited by
97
References
1
Citations by year
2026: 34 · 2025: 50 · 2024: 13
FWCI
20.56
Type
journal article
Language
en
Open access
Licence
Locations
  • Nature Machine Intelligence (publishedVersion)
  • Research Square (acceptedVersion, cc-by)
Funders
  • National Natural Science Foundation of China (T2221004, 81930125, ZYGD18001, 82130104)
  • Sichuan University (ZYXY21001, ZYGD18001, 81930125, JCXK2227)
  • West China Hospital, Sichuan University (ZYXY21001, 81930125, ZYGD18001)
Topics
  • Life Sciences › Pharmacology, Toxicology and Pharmaceutics › Drug Discovery › Computational Drug Discovery Methods
  • Physical Sciences › Materials Science › Materials Chemistry › Machine Learning in Materials Science
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Protein Degradation and Inhibitors
Keywords
generative models, drug-like molecules, protein-ligand binding, deep generative models, molecular 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