A spatial hierarchical network learning framework for drug repositioning allowing interpretation from macro to micro scale.
Journal
Communications biology
ISSN: 2399-3642
Titre abrégé: Commun Biol
Pays: England
ID NLM: 101719179
Informations de publication
Date de publication:
30 Oct 2024
30 Oct 2024
Historique:
received:
11
06
2024
accepted:
21
10
2024
medline:
31
10
2024
pubmed:
31
10
2024
entrez:
31
10
2024
Statut:
epublish
Résumé
Biomedical network learning offers fresh prospects for expediting drug repositioning. However, traditional network architectures struggle to quantify the relationship between micro-scale drug spatial structures and corresponding macro-scale biomedical networks, limiting their ability to capture key pharmacological properties and complex biomedical information crucial for drug screening and therapeutic discovery. Moreover, challenges such as difficulty in capturing long-range dependencies hinder current network-based approaches. To address these limitations, we introduce the Spatial Hierarchical Network, modeling molecular 3D structures and biological associations into a unified network. We propose an end-to-end framework, SpHN-VDA, integrating spatial hierarchical information through triple attention mechanisms to enhance machine understanding of molecular functionality and improve the accuracy of virus-drug association identification. SpHN-VDA outperforms leading models across three datasets, particularly excelling in out-of-distribution and cold-start scenarios. It also exhibits enhanced robustness against data perturbation, ranging from 20% to 40%. It accurately identifies critical motifs for binding sites, even without protein residue annotations. Leveraging reliability of SpHN-VDA, we have identified 25 potential candidate drugs through gene expression analysis and CMap. Molecular docking experiments with the SARS-CoV-2 spike protein further corroborate the predictions. This research highlights the broad potential of SpHN-VDA to enhance drug repositioning and identify effective treatments for various diseases.
Identifiants
pubmed: 39478146
doi: 10.1038/s42003-024-07107-3
pii: 10.1038/s42003-024-07107-3
doi:
Substances chimiques
Antiviral Agents
0
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
1413Subventions
Organisme : National Natural Science Foundation of China (National Science Foundation of China)
ID : 62131004
Organisme : National Natural Science Foundation of China (National Science Foundation of China)
ID : 62250028
Informations de copyright
© 2024. The Author(s).
Références
Dickson, M. & Gagnon, J. P. Key factors in the rising cost of new drug discovery and development. Nat. Rev. Drug Discov. 3, 417–429 (2004).
pubmed: 15136789
doi: 10.1038/nrd1382
Fernández-Torras, A., Duran-Frigola, M., Bertoni, M., Locatelli, M. & Aloy, P. Integrating and formatting biomedical data as pre-calculated knowledge graph embeddings in the Bioteque. Nat. Commun. 13, 5304 (2022).
pubmed: 36085310
pmcid: 9463154
doi: 10.1038/s41467-022-33026-0
Wang, R.-S. & Loscalzo, J. Repurposing drugs for the treatment of COVID-19 and its cardiovascular manifestations. Circ. Res. 132, 1374–1386 (2023).
pubmed: 37167362
pmcid: 10171294
doi: 10.1161/CIRCRESAHA.122.321879
Pushpakom, S. et al. Drug repurposing: progress, challenges and recommendations. Nat. Rev. Drug Discov. 18, 41–58 (2019).
pubmed: 30310233
doi: 10.1038/nrd.2018.168
Guy, R. K., DiPaola, R. S., Romanelli, F. & Dutch, R. E. Rapid repurposing of drugs for COVID-19. Sci 368, 829–830 (2020).
doi: 10.1126/science.abb9332
Galindez, G. et al. Lessons from the COVID-19 pandemic for advancing computational drug repurposing strategies. Nat. Comput. Sci. 1, 33–41 (2021).
pubmed: 38217166
doi: 10.1038/s43588-020-00007-6
Smith, D. P. et al. Expert-augmented computational drug repurposing identified baricitinib as a treatment for COVID-19. Front. Pharmacol. 12, 709856 (2021).
pubmed: 34393789
pmcid: 8356560
doi: 10.3389/fphar.2021.709856
Frantz, S. Drug discovery: playing dirty. Nature 437, 942 (2005).
pubmed: 16222266
doi: 10.1038/437942a
McLean, S. R. et al. Imatinib binding and cKIT inhibition is abrogated by the cKIT kinase domain I missense mutation Val654Ala. Mol. Cancer Ther. 4, 2008–2015 (2005).
pubmed: 16373716
doi: 10.1158/1535-7163.MCT-05-0070
Bang, D., Lim, S., Lee, S. & Kim, S. Biomedical knowledge graph learning for drug repurposing by extending guilt-by-association to multiple layers. Nat. Commun. 14, 3570 (2023).
pubmed: 37322032
pmcid: 10272215
doi: 10.1038/s41467-023-39301-y
Zhang, Z. et al. Overcoming cancer therapeutic bottleneck by drug repurposing. Signal Transduct. Target. Ther. 5, 1–25 (2020).
Hua, Y. et al. Drug repositioning: progress and challenges in drug discovery for various diseases. Eur. J. Med Chem. 234, 114239 (2022).
pubmed: 35290843
pmcid: 8883737
doi: 10.1016/j.ejmech.2022.114239
Long, Y. et al. Heterogeneous graph attention networks for drug virus association prediction. Methods 198, 11–18 (2022).
pubmed: 34419588
doi: 10.1016/j.ymeth.2021.08.003
Dotolo, S., Marabotti, A., Facchiano, A. & Tagliaferri, R. A review on drug repurposing applicable to COVID-19. Brief. Bioinformp 22, 726–741 (2021).
doi: 10.1093/bib/bbaa288
Chen, Z.-H., Zhao, B.-W., Li, J.-Q., Guo, Z.-H. & You, Z.-H. GraphCPIs: a novel graph-based computational model for potential compound-protein interactions. Mol. Ther. Nucleic Acids 32, 721–728 (2023).
pubmed: 37251691
pmcid: 10209012
doi: 10.1016/j.omtn.2023.04.030
Ren, Z.-H. et al. DeepMPF: deep learning framework for predicting drug–target interactions based on multi-modal representation with meta-path semantic analysis. J. Transl. Med. 21, 1–18 (2023).
doi: 10.1186/s12967-023-03876-3
Deepthi, K., Jereesh, A. & Liu, Y. A deep learning ensemble approach to prioritize antiviral drugs against novel coronavirus SARS-CoV-2 for COVID-19 drug repurposing. Appl. Soft Comput. 113, 107945 (2021).
doi: 10.1016/j.asoc.2021.107945
Wang, Y., Zhai, Y., Ding, Y. & Zou, Q. SBSM-Pro: support bio-sequence machine for Proteins. Sci. China Inf. Sci. 67, 212106 (2024).
Ren, Z.-H. et al. A biomedical knowledge graph-based method for drug–drug interactions prediction through combining local and global features with deep neural networks. Brief. Bioinform 23, bbac363 (2022).
pubmed: 36070624
doi: 10.1093/bib/bbac363
Wei, M.-M., Yu, C.-Q., Li, L.-P., You, Z.-H. & Wang, L. BCMCMI: a fusion model for predicting circRNA-miRNA interactions combining semantic and meta-path. J. Chem. Inf. Model. 63, 5384–5394 (2023).
Huang, Y.-a, Hu, P., Chan, K. C. & You, Z.-H. Graph convolution for predicting associations between miRNA and drug resistance. Bioinformatics 36, 851–858 (2020).
pubmed: 31397851
doi: 10.1093/bioinformatics/btz621
Gao, Z. et al. Hierarchical graph learning for protein–protein interaction. Nat. Commun. 14, 1093 (2023).
pubmed: 36841846
pmcid: 9968329
doi: 10.1038/s41467-023-36736-1
Chen, Z. et al. In silico prediction methods of self-interacting proteins: an empirical and academic survey. Front. Comput. Sci. 17, 173901 (2023).
doi: 10.1007/s11704-022-1563-1
Wang, X.-F. et al. A feature extraction method based on noise reduction for circRNA-miRNA interaction prediction combining multi-structure features in the association networks. Brief. Bioinform. 24, bbad111 (2023).
Ruiz, C., Zitnik, M. & Leskovec, J. Identification of disease treatment mechanisms through the multiscale interactome. Nat. Commun. 12, 1796 (2021).
pubmed: 33741907
pmcid: 7979814
doi: 10.1038/s41467-021-21770-8
Yang, J. et al. Deep learning identifies explainable reasoning paths of mechanism of action for drug repurposing from multilayer biological network. Brief. Bioinform 23, bbac469 (2022).
pubmed: 36347526
doi: 10.1093/bib/bbac469
Zeng, X. et al. deepDR: a network-based deep learning approach to in silico drug repositioning. Bioinformatics 35, 5191–5198 (2019).
pubmed: 31116390
pmcid: 6954645
doi: 10.1093/bioinformatics/btz418
Wang, X.-F. et al. KS-CMI: a circRNA-miRNA interaction prediction method based on the signed graph neural network and denoising autoencoder. iScience 26, 107478 (2023).
Su, X. et al. A deep learning method for repurposing antiviral drugs against new viruses via multi-view nonnegative matrix factorization and its application to SARS-CoV-2. Brief. Bioinform 23, bbab526 (2022).
pubmed: 34965582
doi: 10.1093/bib/bbab526
Li, M., Cai, X., Xu, S. & Ji, H. Metapath-aggregated heterogeneous graph neural network for drug–target interaction prediction. Brief. Bioinform 24, bbac578 (2023).
pubmed: 36592060
doi: 10.1093/bib/bbac578
Himmelstein, D. S. et al. Systematic integration of biomedical knowledge prioritizes drugs for repurposing. eLife 6, e26726 (2017).
pubmed: 28936969
pmcid: 5640425
doi: 10.7554/eLife.26726
Wang, X. et al. DeepR2cov: deep representation learning on heterogeneous drug networks to discover anti-inflammatory agents for COVID-19. Brief. Bioinform 22, bbab226 (2021).
pubmed: 34117734
doi: 10.1093/bib/bbab226
Song, Y., Zhou, C., Wang, X. & Lin Z. Ordered GNN: ordering message passing to deal with heterophily and over-smoothing. In The Eleventh International Conference on Learning Representations (Ithaca, 2023).
Montavon, G., Samek, W. & Müller, K.-R. Methods for interpreting and understanding deep neural networks. Digital Signal Process. 73, 1–15 (2018).
doi: 10.1016/j.dsp.2017.10.011
Belkoura, S., Zanin, M. & LaTorre, A. Fostering interpretability of data mining models through data perturbation. Expert Syst. Appl. 137, 191–201 (2019).
doi: 10.1016/j.eswa.2019.07.001
Yu, J.-L., Dai, Q.-Q. & Li, G.-B. Deep learning in target prediction and drug repositioning: Recent advances and challenges. Drug Discov. Today 27, 1796–1814 (2022).
pubmed: 34718208
doi: 10.1016/j.drudis.2021.10.010
Zhang, Y., Tiňo, P., Leonardis, A. & Tang, K. A survey on neural network interpretability. IEEE Trans. Emerg. Top. Comput. Intell. 5, 726–742 (2021).
doi: 10.1109/TETCI.2021.3100641
Sun, H., Wang, G., Liu, Q., Yang, J. & Zheng, M. An explainable molecular property prediction via multi-granularity. Inf. Sci. 642, 119094 (2023).
doi: 10.1016/j.ins.2023.119094
Wang, H., Huang, F., Xiong, Z. & Zhang, W. A heterogeneous network-based method with attentive meta-path extraction for predicting drug–target interactions. Brief. Bioinform 23, bbac184 (2022).
pubmed: 35641162
doi: 10.1093/bib/bbac184
Esser-Skala, W. & Fortelny, N. Reliable interpretability of biology-inspired deep neural networks. NPJ Syst. Biol. Appl. 9, 50 (2023).
pubmed: 37816807
pmcid: 10564878
doi: 10.1038/s41540-023-00310-8
Frolichs, K. M., Rosenblau, G. & Korn, C. W. Incorporating social knowledge structures into computational models. Nat. Commun. 13, 6205 (2022).
pubmed: 36266284
pmcid: 9584930
doi: 10.1038/s41467-022-33418-2
Zheng, J., Li, Q., Liao, J. & Wang, S. Explainable link prediction based on multi-granularity relation-embedded representation. Knowl. Based Syst. 230, 107402 (2021).
doi: 10.1016/j.knosys.2021.107402
Verma, J., Khedkar, V. M. & Coutinho, E. C. 3D-QSAR in drug design-a review. Curr. Top. Med. Chem. 10, 95–115 (2010).
pubmed: 19929826
doi: 10.2174/156802610790232260
Yang, S.-Y. Pharmacophore modeling and applications in drug discovery: challenges and recent advances. Drug Discov. Today 15, 444–450 (2010).
pubmed: 20362693
doi: 10.1016/j.drudis.2010.03.013
Zeng, Z., Yao, Y., Liu, Z. & Sun, M. A deep-learning system bridging molecule structure and biomedical text with comprehension comparable to human professionals. Nat. Commun. 13, 862 (2022).
pubmed: 35165275
pmcid: 8844428
doi: 10.1038/s41467-022-28494-3
Schep, R. et al. Impact of chromatin context on Cas9-induced DNA double-strand break repair pathway balance. Mol. Cell 81, 2216–2230.e2210 (2021).
pubmed: 33848455
pmcid: 8153251
doi: 10.1016/j.molcel.2021.03.032
Sun, Y. et al. A graph neural network-based interpretable framework reveals a novel DNA fragility–associated chromatin structural unit. Genome Biol. 24, 90 (2023).
pubmed: 37095580
pmcid: 10124043
doi: 10.1186/s13059-023-02916-x
Lamb, J. et al. The Connectivity Map: using gene-expression signatures to connect small molecules, genes, and disease. Science 313, 1929–1935 (2006).
pubmed: 17008526
doi: 10.1126/science.1132939
Veličković, P. et al. Graph attention networks. In International Conference on Learning Representations (Ithaca, 2018).
Bai, P., Miljković, F., John, B. & Lu, H. Interpretable bilinear attention network with domain adaptation improves drug–target prediction. Nat. Mach. Intell. 5, 126–136 (2023).
doi: 10.1038/s42256-022-00605-1
Luo, Y. et al. A network integration approach for drug-target interaction prediction and computational drug repositioning from heterogeneous information. Nat. Commun. 8, 573 (2017).
pubmed: 28924171
pmcid: 5603535
doi: 10.1038/s41467-017-00680-8
Li, Y., Qiao, G., Gao, X. & Wang, G. Supervised graph co-contrastive learning for drug–target interaction prediction. Bioinformatics 38, 2847–2854 (2022).
pubmed: 35561181
doi: 10.1093/bioinformatics/btac164
Li, Z., Li, J., Nie, R., You, Z.-H. & Bao, W. A graph auto-encoder model for miRNA-disease associations prediction. Brief. Bioinform 22, bbaa240 (2021).
pubmed: 34293850
doi: 10.1093/bib/bbaa240
Sun, Y., Ming, Y., Zhu, X. & Li, Y. Out-of-distribution detection with deep nearest neighbors. In International Conference on Machine Learning (PMLR, 2022).
Schütt, K. et al. Schnet: a continuous-filter convolutional neural network for modeling quantum interactions. Adv. Neural Inf. Process. Syst. 30, 992–1002 (2017).
Hou, Z., Yang, Y., Ma, Z., Wong, K.-c & Li, X. Learning the protein language of proteome-wide protein-protein binding sites via explainable ensemble deep learning. Commun. Biol. 6, 73 (2023).
pubmed: 36653447
pmcid: 9849350
doi: 10.1038/s42003-023-04462-5
He, K., Zhang, X., Ren, S. & Sun, J. Deep residual learning for image recognition. In Proc. IEEE Conference on Computer Vision and Pattern Recognition (IEEE/CVF, 2016).
Van der Maaten, L. & Hinton G. Visualizing data using t-SNE. J. Mach. Learn. Res. 9, 2579–2605 (2008).
Zhan, H., Zhu, X., Qiao, Z. & Hu, J. Graph neural tree: a novel and interpretable deep learning-based framework for accurate molecular property predictions. Anal. Chim. Acta 1244, 340558 (2023).
pubmed: 36737143
doi: 10.1016/j.aca.2022.340558
Zhang, Y. Bayesian semi-supervised learning for uncertainty-calibrated prediction of molecular properties and active learning. Chem. Sci. 10, 8154–8163 (2019).
pubmed: 31857882
pmcid: 6837061
doi: 10.1039/C9SC00616H
Ryu, S., Kwon, Y. & Kim, W. Y. A Bayesian graph convolutional network for reliable prediction of molecular properties with uncertainty quantification. Chem. Sci. 10, 8438–8446 (2019).
pubmed: 31803423
pmcid: 6839511
doi: 10.1039/C9SC01992H
De, P., Kar, S., Ambure, P. & Roy, K. Prediction reliability of QSAR models: an overview of various validation tools. Arch. Toxicol. 96, 1279–1295 (2022).
pubmed: 35267067
doi: 10.1007/s00204-022-03252-y
Lewell, X. Q., Judd, D. B., Watson, S. P. & Hann, M. M. Recap retrosynthetic combinatorial analysis procedure: a powerful new technique for identifying privileged molecular fragments with useful applications in combinatorial chemistry. J. Chem. Inf. Comput. Sci. 38, 511–522 (1998).
pubmed: 9611787
doi: 10.1021/ci970429i
Pinzi, L. & Rastelli, G. Molecular docking: shifting paradigms in drug discovery. Int J. Mol. Sci. 20, 4331 (2019).
pubmed: 31487867
pmcid: 6769923
doi: 10.3390/ijms20184331
Valencia, D. N. Brief review on COVID-19: the 2020 pandemic caused by SARS-CoV-2. Cureus 12, e7386 (2020).
Gupta, A. et al. Extrapulmonary manifestations of COVID-19. Nat. Med 26, 1017–1032 (2020).
pubmed: 32651579
doi: 10.1038/s41591-020-0968-3
Murakami, N. et al. Therapeutic advances in COVID-19. Nat. Rev. Nephrol. 19, 38–52 (2023).
pubmed: 36253508
doi: 10.1038/s41581-022-00642-4
Reghunathan, R. et al. Expression profile of immune response genes in patients with severe acute respiratory syndrome. BMC Immunol. 6, 1–11 (2005).
doi: 10.1186/1471-2172-6-2
Barrett, T. et al. NCBI GEO: archive for functional genomics data sets—update. Nucleic Acid Res. 41, D991–D995 (2012).
pubmed: 23193258
pmcid: 3531084
doi: 10.1093/nar/gks1193
Naasani, I. J. A. P. COMPARE analysis as an efficient bioinformatic approach to accelerate repurposing of existing drugs against Covid-19 and other emerging epidemics. Authorea Preprints at https://www.techrxiv.org/doi/full/10.22541/au.159611489.95884381 (2020).
Dyall, J. et al. Repurposing of clinically developed drugs for treatment of Middle East respiratory syndrome coronavirus infection. Antimicrob Agents Ch. 58, 4885–4893 (2014).
Hosseini, F. S. & Motamedi, M.R. Mulberrofuran G, a potent inhibitor of spike protein of SARS corona virus 2. J. Pharm. Care. 9, 74–81 (2021).
Hoffmann, M. et al. SARS-CoV-2 cell entry depends on ACE2 and TMPRSS2 and is blocked by a clinically proven protease inhibitor. Cell 181, 271–280.e8 (2020).
pubmed: 32142651
pmcid: 7102627
doi: 10.1016/j.cell.2020.02.052
Morris, G. M. et al. AutoDock4 and AutoDockTools4: automated docking with selective receptor flexibility. J. Comput. Chem. 30, 2785–2791 (2009).
pubmed: 19399780
pmcid: 2760638
doi: 10.1002/jcc.21256
Schenone, M., Dančík, V., Wagner, B. K. & Clemons, P. A. Target identification and mechanism of action in chemical biology and drug discovery. Nat. Chem. Biol. 9, 232–240 (2013).
pubmed: 23508189
pmcid: 5543995
doi: 10.1038/nchembio.1199
Ye, Q. et al. A unified drug–target interaction prediction framework based on knowledge graph and recommendation system. Nat. Commun. 12, 6775 (2021).
pubmed: 34811351
pmcid: 8635420
doi: 10.1038/s41467-021-27137-3
Li, J. et al. Semi-supervised graph classification: a hierarchical graph perspective. In 2019 The World Wide Web Conference (ACM, 2019).
Katoh, K. & Standley, D. M. MAFFT multiple sequence alignment software version 7: improvements in performance and usability. Mol. Biol. Evol. 30, 772–780 (2013).
pubmed: 23329690
pmcid: 3603318
doi: 10.1093/molbev/mst010
Zeng, X. et al. Target identification among known drugs by deep learning from heterogeneous networks. Chem. Sci. 11, 1775–1797 (2020).
pubmed: 34123272
pmcid: 8150105
doi: 10.1039/C9SC04336E
O’Boyle, N. M. et al. Open Babel: an open chemical toolbox. J. Cheminform. 3, 1–14 (2011).
Fu, S., Wang, G. & Xu, J. hier2vec: interpretable multi-granular representation learning for hierarchy in social networks. Int. J. Mach. Learn. Cybern. 12, 2543–2557 (2021).
doi: 10.1007/s13042-021-01338-0
Deng, Y. et al. A multimodal deep learning framework for predicting drug–drug interaction events. Bioinformatics 36, 4316–4322 (2020).
pubmed: 32407508
doi: 10.1093/bioinformatics/btaa501
Shi, J.-Y., Mao, K.-T., Yu, H. & Yiu, S.-M. Detecting drug communities and predicting comprehensive drug–drug interactions via balance regularized semi-nonnegative matrix factorization. J. Cheminform. 11, 1–16 (2019).
doi: 10.1186/s13321-019-0352-9
Ren, Z.-H. et al. SAWRPI: a stacking ensemble framework with adaptive weight for predicting ncRNA-protein interactions using sequence information. Front. Genet. 13, 839540 (2022).
pubmed: 35360836
pmcid: 8963817
doi: 10.3389/fgene.2022.839540
Huang, J., Shen, H., Hou, L. & Cheng, X. SDGNN: learning node representation for signed directed networks. In Proc. AAAI Conference on Artificial Intelligence (AAAI, 2021).
Tosco, P., Stiefl, N. & Landrum, G. Bringing the MMFF force field to the RDKit: implementation and validation. J. Cheminform. 6, 1–4 (2014).
doi: 10.1186/s13321-014-0037-3
Meng, Y., Jin, M., Tang, X. & Xu, J. Drug repositioning based on similarity constrained probabilistic matrix factorization: COVID-19 as a case study. Appl. Soft Comput. 103, 107135 (2021).
pubmed: 33519322
pmcid: 7825831
doi: 10.1016/j.asoc.2021.107135
Andersen, P. I. et al. Discovery and development of safe-in-man broad-spectrum antiviral agents. Int J. Infect. Dis. 93, 268–276 (2020).
pubmed: 32081774
pmcid: 7128205
doi: 10.1016/j.ijid.2020.02.018
Shen, L. et al. VDA-RWLRLS: an anti-SARS-CoV-2 drug prioritizing framework combining an unbalanced bi-random walk and Laplacian regularized least squares. Comput Biol. Med. 140, 105119 (2022).
pubmed: 34902608
doi: 10.1016/j.compbiomed.2021.105119
Wishart, D. S. et al. DrugBank 5.0: a major update to the DrugBank database for 2018. Nucleic Acid Res. 46, D1074–D1082 (2018).
pubmed: 29126136
doi: 10.1093/nar/gkx1037
Sayers, E. W. et al. Database resources of the National Center for Biotechnology Information. Nucleic Acid Res. 49, D10 (2021).
pubmed: 33095870
doi: 10.1093/nar/gkaa892
White, J. PubMed 2.0. Med. Ref. Serv. Q. 39, 382–387.
Fawcett, T. An introduction to ROC analysis. Pattern Recognit. Lett. 27, 861–874 (2006).
doi: 10.1016/j.patrec.2005.10.010
Ren, Z. A spatial hierarchical network learning framework for drug repositioning allowing interpretation from macro to micro scale. https://doi.org/10.5281/zenodo.13881676 (2024).