CoChat
Sign Up
PreprintCited by 7Computational Drug Discovery MethodsMachine Learning in BioinformaticsProtein Structure and Dynamics

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

Enhanced compound-protein binding affinity prediction by representing protein multimodal information via a coevolutionary strategy

Open access
Guo, Binjie, Zheng, Hanyu, Jiang, Haohan, Li, Xiaodan, Guan, Naiyu, Zuo, Yanming, Zhang, Yicheng, Yang, Hengfu, Wang, Xuhua·2022·Briefings in Bioinformatics
DOI 10.1101/2022.04.06.487274

Preprint — published as 10.1093/bib/bbac628 · Paper page

Open this paper in CoChat — free accountOpen PDF

Abstract

Due to the lack of a method to efficiently represent the multimodal information of a protein, including its structure and sequence information, predicting compound-protein binding affinity (CPA) still suffers from low accuracy when applying machine learning methods. To overcome this limitation, in a novel end-to-end architecture (named FeatNN), we develop a coevolutionary strategy to jointly represent the structure and sequence features of proteins and ultimately optimize the mathematical models for predicting CPA. Furthermore, from the perspective of data-driven approach, we proposed a rational method that can utilize both high- and low-quality databases to optimize the accuracy and generalization ability of FeatNN in CPA prediction tasks. Notably, we visually interpret the feature interaction process between sequence and structure in the rationally designed architecture. As a result, FeatNN considerably outperforms the state-of-the-art (SOTA) baseline in virtual drug screening tasks, indicating the feasibility of this approach for practical use. FeatNN provides an outstanding method for higher CPA prediction accuracy and better generalization ability by efficiently representing multimodal information of proteins via a coevolutionary strategy.

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 · 10.1101/2022.04.06.487274

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

Research works printed but not linked: 72

  1. 2016, Drug-target interaction prediction: databases, web servers and computational models, Brief Bioinform, 17, 696
  2. 2008, From virtuality to reality - Virtual screening in lead discovery and lead optimization: a medicinal chemistry perspective, Curr Opin Drug Discov Devel, 11, 559
  3. 2016, BindingDB in 2015: A public database for medicinal chemistry, computational chemistry and systems pharmacology, Nucleic Acids Res, 44, D1045
  4. 2021, RCSB Protein Data Bank: Architectural Advances Towards Integrated Searching and Efficient Access to Macromolecular Structure Data from the PDB Archive, J Mol Biol, 433, 166704, 10.1016/j.jmb.2020.11.003 · DOI
  5. 10.1093/bioinformatics/bty593 · DOI
  6. 2020, Predicting drug–protein interaction using quasi-visual question answering system, Nature Machine Intelligence, 2, 134, 10.1038/s42256-020-0152-y · DOI
  7. 2021, Visualization of Protein-Drug Interactions for the Analysis of Drug Resistance in Lung Cancer, IEEE J Biomed Health Inform, 25, 1839, 10.1109/JBHI.2020.3027511 · DOI
  8. 10.1021/acs.jcim.0c01306 · DOI
  9. 2020, MONN: A Multi-objective Neural Network for Predicting Compound-Protein Interactions and Affinities, Cell Systems, 10, 308, 10.1016/j.cels.2020.03.002 · DOI
  10. Ru X , Ye X , Sakurai T et al. NerLTR-DTA: Drug-target binding affinity prediction based on neighbor relationship and learning to rank, Bioinformatics 2022. · DOI
  11. 10.1093/bioinformatics/btp433 · DOI
  12. 2014, Computational Prediction of DrugTarget Interactions Using Chemical, Biological, and Network Features, Mol Inform, 33, 669
  13. 10.1186/s12859-016-0977-x · DOI
  14. 10.1021/acs.jcim.6b00740 · DOI
  15. 10.1371/journal.pcbi.1007129 · DOI
  16. 10.1039/c9sc03414e · DOI
  17. 10.1016/j.sbi.2009.03.004 · DOI
  18. 10.1016/j.str.2011.09.022 · DOI
  19. 10.1093/bioinformatics/btq112 · DOI
  20. Bai Q , Liu S , Tian Y et al. Application advances of deep learning methods for de novo drug design and molecular dynamics simulation, WIREs Computational Molecular Science 2021;12. · DOI · Paper page
  21. 2018, Transforming Computational Drug Discovery with Machine Learning and AI, ACS Med Chem Lett, 9, 1065, 10.1021/acsmedchemlett.8b00437 · DOI
  22. 10.1038/nrd1549 · DOI
  23. 10.1021/acs.jmedchem.8b00718 · DOI
  24. 10.1093/bioinformatics/btn162 · DOI
  25. 10.1038/s42256-021-00438-4 · DOI
  26. Li S , Zhou J , Xu T et al. Structure-aware Interactive Graph Neural Networks for the Prediction of Protein-Ligand Binding Affinity. Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining. 2021, 975–985. · DOI
  27. 2021, InteractionGraphNet: A Novel and Efficient Deep Graph Representation Learning Framework for Accurate Protein-Ligand Interaction Predictions, J Med Chem, 64, 18209, 10.1021/acs.jmedchem.1c01830 · DOI
  28. 10.1021/jm048957q · DOI · Paper page
  29. Kipf TN , Welling M. Semi-Supervised Classification with Graph Convolutional Networks, CoRR 2016;abs/1609.02907.
  30. 10.1093/bioinformatics/btu626 · DOI
  31. 10.1093/nar/gku1088 · DOI
  32. 10.1016/j.jmb.2019.05.024 · DOI
  33. 10.1002/prot.20512 · DOI · Paper page
  34. Refaeilzadeh P TL , Liu H. Cross-validation, Encyclopedia of database systems 2009:532–538. · DOI
  35. 2021, GraphDTA: predicting drug-target binding affinity with graph neural networks, Bioinformatics, 37, 1140, 10.1093/bioinformatics/btaa921 · DOI
  36. Li M , Lu Z , Wu Y et al. BACPI: a bi-directional attention neural network for compound-protein interaction and binding affinity prediction, Bioinformatics 2022. · DOI
  37. Ishiguro KaM , Shin-ichi and Koyama, Masanori. Graph Warp Module: an Auxiliary Module for Boosting the Power of Graph Neural Networks in Molecular Graph Analysis, arXiv 2019.
  38. 10.1039/c8sc00148k · DOI · Paper page
  39. 2022, Machine learning to navigate fitness landscapes for protein engineering, Curr Opin Biotechnol, 75, 102713, 10.1016/j.copbio.2022.102713 · DOI
  40. Pengfei Liu WY , Jinlan Fu , Zhengbao Jiang , Hiroaki Hayashi , Graham Neubig . Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing, arXiv 2021.
  41. Hinton . LJPvdMaGE. Visualizing High-Dimensional Data Using t-SNE., Journal of Machine Learning Research 2008;9.
  42. Stachenfeld KaG , Jonathan and Battaglia, Peter. Graph Networks with Spectral Message Passing, arXiv 2021.
  43. Bai Q , Tan S , Xu T et al. MolAICal: a soft tool for 3D drug design of protein targets by artificial intelligence and classical algorithm, Brief Bioinform 2021;22. · DOI
  44. 2020, Structure of replicating SARS-CoV-2 polymerase, Nature, 584, 154, 10.1038/s41586-020-2368-8 · DOI
  45. 10.1186/s12985-020-01457-0 · DOI
  46. 2020, Antiviral Activity and Safety of Darunavir/Cobicistat for the Treatment of COVID-19, Open Forum Infect Dis, 7, ofaa241, 10.1093/ofid/ofaa241 · DOI
  47. Ahmed MH , Hassan A. Dexamethasone for the Treatment of Coronavirus Disease (COVID-19): a Review, SN Compr Clin Med 2020:1–10. · DOI
  48. 10.1021/acs.jmedchem.0c01063 · DOI
  49. 2019, Distinct functions of AKT isoforms in breast cancer: a comprehensive review, Cell Commun Signal, 17, 154, 10.1186/s12964-019-0450-3 · DOI
  50. 10.1001/jama.2021.3071 · DOI
  51. Shamsi A , Mohammad T , Anwar S et al. Glecaprevir and Maraviroc are high-affinity inhibitors of SARS-CoV-2 main protease: possible implication in COVID-19 therapy, Biosci Rep 2020;40. · DOI
  52. 2021, A head-to-head comparison of the inhibitory activities of 15 peptidomimetic SARS-CoV-2 3CLpro inhibitors, Bioorg Med Chem Lett, 48, 128263, 10.1016/j.bmcl.2021.128263 · DOI
  53. 2021, Identification of 3-chymotrypsin like protease (3CLPro) inhibitors as potential anti-SARS-CoV-2 agents, Commun Biol, 4, 93, 10.1038/s42003-020-01577-x · DOI
  54. 2022, Recent advances in developing small-molecule inhibitors against SARS-CoV-2, Acta Pharm Sin B, 12, 1591, 10.1016/j.apsb.2021.06.016 · DOI
  55. 2020, SARS-CoV-2: Recent Reports on Antiviral Therapies Based on Lopinavir/Ritonavir, Darunavir/Umifenovir, Hydroxychloroquine, Remdesivir, Favipiravir and other Drugs for the Treatment of the New Coronavirus, Curr Med Chem, 27, 4536
  56. 2021, Simeprevir Potently Suppresses SARS-CoV-2 Replication and Synergizes with Remdesivir, ACS Cent Sci, 7, 792, 10.1021/acscentsci.0c01186 · DOI
  57. 2020, Targeting severe acute respiratory syndrome-coronavirus (SARS-CoV-1) with structurally diverse inhibitors: a comprehensive review, RSC Adv, 10, 28287, 10.1039/D0RA04395H · DOI
  58. 10.1158/1535-7163.MCT-09-0986 · DOI
  59. 2017, BAY 1125976, a selective allosteric AKT1/2 inhibitor, exhibits high efficacy on AKT signaling-dependent tumor growth in mouse models, Int J Cancer, 140, 449, 10.1002/ijc.30457 · DOI
  60. 10.1158/0008-5472.CAN-07-5783 · DOI
  61. 10.1371/journal.pone.0012913 · DOI
  62. 2022, The emerging role of capivasertib in breast cancer, Breast, 63, 157, 10.1016/j.breast.2022.03.018 · DOI
  63. 2020, First-in-Human Study of AT13148, a Dual ROCK-AKT Inhibitor in Patients with Solid Tumors, Clin Cancer Res, 26, 4777
  64. 2018, Miransertib (ARQ 092), an orally-available, selective Akt inhibitor is effective against Leishmania, PLoS One, 13, e0206920, 10.1371/journal.pone.0206920 · DOI
  65. 10.1158/0008-5472.CAN-18-2861 · DOI
  66. 10.1158/1535-7163.MCT-17-0823 · DOI
  67. Iksen, Pothongsrisit S , Pongrakhananon V. Targeting the PI3K/AKT/mTOR Signaling Pathway in Lung Cancer: An Update Regarding Potential Drugs and Natural Products, Molecules 2021;26. · DOI
  68. He K , Zhang X , Ren S et al. Deep Residual Learning for Image Recognition, CoRR 2015;abs/1512.03385. · DOI · Paper page
  69. Chen M , Wei Z , Huang Z et al. Simple and Deep Graph Convolutional Networks, arXiv [cs.LG] 2020.
  70. Susan S , Kumar A. The balancing trick: Optimized sampling of imbalanced datasets—A brief survey of the recent State of the Art, Engineering Reports 2020;3. · DOI
  71. 2015, Three-dimensional compound comparison methods and their application in drug discovery, Molecules, 20, 12841, 10.3390/molecules200712841 · DOI
  72. 2022, AI in 3D compound design, Curr Opin Struct Biol, 73, 102326, 10.1016/j.sbi.2021.102326 · DOI

Metadata

Authors
Guo, B., Zheng, H., Jiang, H., Li, X., Guan, N., Zuo, Y., Zhang, Y., Yang, H., & Wang, X.
Affiliations
  • First Affiliated Hospital Zhejiang University (CN)
  • Zhejiang University (CN)
  • Hunan First Normal University (CN)
  • Nantong University (CN)
Corresponding author
Wang, Xuhua
ORCID
Venue
Briefings in Bioinformatics
Publisher
openRxiv
Published
2022-04-08
Volume
24
Issue
2
ISSN
1467-5463 (ISSN-L)
DOI
10.1101/2022.04.06.487274
OpenAlex
W4317703003
Cited by
7
References
1
Citations by year
2026: 1 · 2025: 1 · 2024: 3 · 2023: 2
FWCI
0.81
Type
journal article
Language
en
Open access
Locations
  • Briefings in Bioinformatics (publishedVersion)
  • bioRxiv (Cold Spring Harbor Laboratory) (acceptedVersion)
  • PubMed (publishedVersion)
  • arXiv (Cornell University) (submittedVersion)
  • arXiv (Cornell University)
Funders
  • National Natural Science Foundation of China (81971866, 2021ZD0200408, 2019R01007)
  • Fundamental Research Funds for the Central Universities (K20210195)
  • Natural Science Foundation of Zhejiang Province (LR20H090002, 2019R01007, 2021ZD0200408)
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
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Protein Structure and Dynamics
Keywords
feature interaction
MeSH terms
Machine Learning, Models, Theoretical, Protein Binding, Proteins

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