{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T04:20:51Z","timestamp":1774671651500,"version":"3.50.1"},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,10,4]],"date-time":"2023-10-04T00:00:00Z","timestamp":1696377600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,10,4]],"date-time":"2023-10-04T00:00:00Z","timestamp":1696377600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["11974239"],"award-info":[{"award-number":["11974239"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Cheminform"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    In recent years, drug design has been revolutionized by the application of deep learning techniques, and molecule generation is a crucial aspect of this transformation. However, most of the current deep learning approaches do not explicitly consider and apply scaffold hopping strategy when performing molecular generation. In this work, we propose ScaffoldGVAE, a variational autoencoder based on multi-view graph neural networks, for scaffold generation and scaffold hopping of drug molecules. The model integrates several important components, such as node-central and edge-central message passing, side-chain embedding, and Gaussian mixture distribution of scaffolds. To assess the efficacy of our model, we conduct a comprehensive evaluation and comparison with baseline models based on seven general generative model evaluation metrics and four scaffold hopping generative model evaluation metrics. The results demonstrate that ScaffoldGVAE can explore the unseen chemical space and generate novel molecules distinct from known compounds. Especially, the scaffold hopped molecules generated by our model are validated by the evaluation of GraphDTA, LeDock, and MM\/GBSA. The case study of generating inhibitors of LRRK2 for the treatment of PD further demonstrates the effectiveness of ScaffoldGVAE in generating novel compounds through scaffold hopping. This novel approach can also be applied to other protein targets of various diseases, thereby contributing to the future development of new drugs. Source codes and data are available at\n                    <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/github.com\/ecust-hc\/ScaffoldGVAE\">https:\/\/github.com\/ecust-hc\/ScaffoldGVAE<\/jats:ext-link>\n                    .\n                  <\/jats:p>","DOI":"10.1186\/s13321-023-00766-0","type":"journal-article","created":{"date-parts":[[2023,10,4]],"date-time":"2023-10-04T07:01:44Z","timestamp":1696402904000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":35,"title":["ScaffoldGVAE: scaffold generation and hopping of drug molecules via a variational autoencoder based on multi-view graph neural networks"],"prefix":"10.1186","volume":"15","author":[{"given":"Chao","family":"Hu","sequence":"first","affiliation":[]},{"given":"Song","family":"Li","sequence":"additional","affiliation":[]},{"given":"Chenxing","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Jun","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Yi","family":"Xiong","sequence":"additional","affiliation":[]},{"given":"Guisheng","family":"Fan","sequence":"additional","affiliation":[]},{"given":"Hao","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Liang","family":"Hong","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,10,4]]},"reference":[{"key":"766_CR1","unstructured":"Jin W, Barzilay R, Jaakkola T (2018) Junction tree variational autoencoder for molecular graph generation. In: Proceedings of the 35th international conference on machine learning. PMLR, pp 2323\u20132332"},{"key":"766_CR2","unstructured":"Kusner MJ, Paige B, Hern\u00e1ndez-Lobato JM (2017) Grammar variational autoencoder. In: Proceedings of the 34th international conference on machine learning\u2014vol 70. JMLR.org, Sydney, NSW, Australia, pp 1945\u20131954"},{"key":"766_CR3","doi-asserted-by":"publisher","first-page":"412","DOI":"10.1007\/978-3-030-01418-6_41","volume-title":"Artificial neural networks and machine learning\u2014ICANN 2018","author":"M Simonovsky","year":"2018","unstructured":"Simonovsky M, Komodakis N (2018) GraphVAE: towards generation of small graphs using variational autoencoders. In: K\u016frkov\u00e1 V, Manolopoulos Y, Hammer B et al (eds) Artificial neural networks and machine learning\u2014ICANN 2018. Springer International Publishing, Cham, pp 412\u2013422"},{"key":"766_CR4","first-page":"114:4556","volume":"21","author":"B Samanta","year":"2020","unstructured":"Samanta B, De A, Jana G et al (2020) NEVAE: a deep generative model for molecular graphs. J Mach Learn Res 21:114:4556-114:4588","journal-title":"J Mach Learn Res"},{"key":"766_CR5","unstructured":"De Cao N, Kipf T (2022) MolGAN: an implicit generative model for small molecular graphs. arXiv preprint. https:\/\/arxiv.org\/abs\/1805.11973"},{"key":"766_CR6","unstructured":"Optimizing distributions over molecular space. An Objective-Reinforced Generative Adversarial Network for Inverse-design Chemistry (ORGANIC). ChemRxiv. https:\/\/chemrxiv.org\/engage\/chemrxiv\/article-details\/60c73d91702a9beea7189bc2."},{"key":"766_CR7","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1186\/s13321-018-0287-6","volume":"10","author":"Y Li","year":"2018","unstructured":"Li Y, Zhang L, Liu Z (2018) Multi-objective de novo drug design with conditional graph generative model. J Cheminform 10:33","journal-title":"J Cheminform"},{"key":"766_CR8","unstructured":"Popova M, Shvets M, Oliva J, Isayev O (2019) MolecularRNN: generating realistic molecular graphs with optimized properties. arXiv preprint. https:\/\/arxiv.org\/abs\/1905.13372"},{"key":"766_CR9","unstructured":"Xu M, Powers A, Dror R et al (2023) Geometric latent diffusion models for 3D molecule generation. arXiv preprint. https:\/\/arxiv.org\/abs\/2305.01140"},{"key":"766_CR10","unstructured":"Peng X, Guan J, Liu Q, Ma J (2023) MolDiff: addressing the atom-bond inconsistency problem in 3D molecule diffusion generation. arXiv preprint. https:\/\/arxiv.org\/abs\/2305.07508"},{"key":"766_CR11","doi-asserted-by":"publisher","first-page":"629","DOI":"10.4155\/fmc-2017-0043","volume":"9","author":"J Bajorath","year":"2017","unstructured":"Bajorath J (2017) Computational scaffold hopping: a cornerstone for the future of drug design? Fut Med Chem 9:629\u2013631","journal-title":"Fut Med Chem"},{"key":"766_CR12","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1186\/s13321-021-00565-5","volume":"13","author":"S Zheng","year":"2021","unstructured":"Zheng S, Lei Z, Ai H et al (2021) Deep scaffold hopping with multimodal transformer neural networks. J Cheminform 13:87","journal-title":"J Cheminform"},{"key":"766_CR13","doi-asserted-by":"publisher","first-page":"8312","DOI":"10.1039\/D0SC03126G","volume":"11","author":"Y Yang","year":"2020","unstructured":"Yang Y, Zheng S, Su S et al (2020) SyntaLinker: automatic fragment linking with deep conditional transformer neural networks. Chem Sci 11:8312\u20138322","journal-title":"Chem Sci"},{"key":"766_CR14","doi-asserted-by":"publisher","first-page":"1983","DOI":"10.1021\/acs.jcim.9b01120","volume":"60","author":"F Imrie","year":"2020","unstructured":"Imrie F, Bradley AR, van der Schaar M, Deane CM (2020) Deep generative models for 3D linker design. J Chem Inf Model 60:1983\u20131995","journal-title":"J Chem Inf Model"},{"key":"766_CR15","doi-asserted-by":"publisher","first-page":"4900","DOI":"10.1021\/acs.jcim.1c00608","volume":"61","author":"L Hu","year":"2021","unstructured":"Hu L, Yang Y, Zheng S et al (2021) Kinase inhibitor scaffold hopping with deep learning approaches. J Chem Inf Model 61:4900\u20134912","journal-title":"J Chem Inf Model"},{"key":"766_CR16","doi-asserted-by":"publisher","first-page":"22945","DOI":"10.1021\/acsomega.1c03613","volume":"6","author":"Y Yu","year":"2021","unstructured":"Yu Y, Xu T, Li J et al (2021) A novel scalarized scaffold hopping algorithm with graph-based variational autoencoder for discovery of JAK1 inhibitors. ACS Omega 6:22945\u201322954","journal-title":"ACS Omega"},{"key":"766_CR17","doi-asserted-by":"publisher","first-page":"D945","DOI":"10.1093\/nar\/gkw1074","volume":"45","author":"A Gaulton","year":"2017","unstructured":"Gaulton A, Hersey A, Nowotka M et al (2017) The ChEMBL database in 2017. Nucleic Acids Res 45:D945","journal-title":"Nucleic Acids Res"},{"key":"766_CR18","doi-asserted-by":"publisher","first-page":"3930","DOI":"10.1093\/bioinformatics\/btaa219","volume":"36","author":"OB Scott","year":"2020","unstructured":"Scott OB, Edith Chan AW (2020) ScaffoldGraph: an open-source library for the generation and analysis of molecular scaffold networks and scaffold trees. Bioinformatics 36:3930\u20133931","journal-title":"Bioinformatics"},{"key":"766_CR19","unstructured":"Ma H, Bian Y, Rong Y et al (2020) Multi-view graph neural networks for molecular property prediction. arXiv preprint. https:\/\/arxiv.org\/abs\/2005.13607"},{"key":"766_CR20","unstructured":"Chung J, G\u00fcl\u00e7ehre \u00c7, Cho K, Bengio Y (2014) Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint https:\/\/arxiv.org\/abs\/1412.3555"},{"key":"766_CR21","unstructured":"Gilmer J, Schoenholz SS, Riley PF et al (2017) Neural message passing for quantum chemistry. In: Proceedings of the 34th international conference on machine learning\u2014vol 70. JMLR.org, Sydney, NSW, Australia, pp 1263\u20131272"},{"key":"766_CR22","unstructured":"Veli\u010dkovi\u0107 P, Cucurull G, Casanova A, et al (2018) Graph attention networks. arXiv preprint. https:\/\/arxiv.org\/abs\/1710.10903"},{"key":"766_CR23","doi-asserted-by":"crossref","unstructured":"Li J, Rong Y, Cheng H et al (2019) Semi-supervised graph classification: a hierarchical graph perspective. In: The World Wide Web conference. Association for Computing Machinery, New York, NY, USA, pp 972\u2013982","DOI":"10.1145\/3308558.3313461"},{"key":"766_CR24","doi-asserted-by":"publisher","first-page":"1700123","DOI":"10.1002\/minf.201700123","volume":"37","author":"T Blaschke","year":"2018","unstructured":"Blaschke T, Olivecrona M, Engkvist O et al (2018) Application of generative autoencoder in de novo molecular design. Mol Inf 37:1700123","journal-title":"Mol Inf"},{"key":"766_CR25","doi-asserted-by":"publisher","first-page":"268","DOI":"10.1021\/acscentsci.7b00572","volume":"4","author":"R G\u00f3mez-Bombarelli","year":"2018","unstructured":"G\u00f3mez-Bombarelli R, Wei JN, Duvenaud D et al (2018) Automatic chemical design using a data-driven continuous representation of molecules. ACS Cent Sci 4:268\u2013276","journal-title":"ACS Cent Sci"},{"key":"766_CR26","doi-asserted-by":"publisher","first-page":"10883","DOI":"10.18632\/oncotarget.14073","volume":"8","author":"A Kadurin","year":"2016","unstructured":"Kadurin A, Aliper A, Kazennov A et al (2016) The cornucopia of meaningful leads: Applying deep adversarial autoencoders for new molecule development in oncology. Oncotarget 8:10883\u201310890","journal-title":"Oncotarget"},{"key":"766_CR27","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1186\/s13321-019-0397-9","volume":"11","author":"O Prykhodko","year":"2019","unstructured":"Prykhodko O, Johansson SV, Kotsias P-C et al (2019) A de novo molecular generation method using the latent vector-based generative adversarial network. J Cheminform 11:74","journal-title":"J Cheminform"},{"key":"766_CR28","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1186\/s13321-019-0328-9","volume":"11","author":"S Zheng","year":"2019","unstructured":"Zheng S, Yan X, Gu Q et al (2019) QBMG: quasi-biogenic molecule generator with deep recurrent neural network. J Cheminform 11:5","journal-title":"J Cheminform"},{"key":"766_CR29","doi-asserted-by":"publisher","first-page":"565644","DOI":"10.3389\/fphar.2020.565644","volume":"11","author":"D Polykovskiy","year":"2020","unstructured":"Polykovskiy D, Zhebrak A, Sanchez-Lengeling B et al (2020) Molecular sets (MOSES): a benchmarking platform for molecular generation models. Front Pharmacol 11:565644","journal-title":"Front Pharmacol"},{"key":"766_CR30","doi-asserted-by":"publisher","first-page":"1140","DOI":"10.1093\/bioinformatics\/btaa921","volume":"37","author":"T Nguyen","year":"2021","unstructured":"Nguyen T, Le H, Quinn TP et al (2021) GraphDTA: predicting drug-target binding affinity with graph neural networks. Bioinformatics 37:1140\u20131147","journal-title":"Bioinformatics"},{"key":"766_CR31","doi-asserted-by":"publisher","first-page":"12964","DOI":"10.1039\/C6CP01555G","volume":"18","author":"Z Wang","year":"2016","unstructured":"Wang Z, Sun H, Yao X et al (2016) Comprehensive evaluation of ten docking programs on a diverse set of protein\u2013ligand complexes: the prediction accuracy of sampling power and scoring power. Phys Chem Chem Phys 18:12964\u201312975","journal-title":"Phys Chem Chem Phys"},{"key":"766_CR32","doi-asserted-by":"publisher","first-page":"661","DOI":"10.20344\/amp.11978","volume":"32","author":"V Cabreira","year":"2019","unstructured":"Cabreira V, Massano J (2019) Doen\u00e7a de Parkinson: Revis\u00e3o Cl\u00ednica e Atualiza\u00e7\u00e3o. Acta Med Port 32:661\u2013670","journal-title":"Acta Med Port"},{"key":"766_CR33","doi-asserted-by":"publisher","first-page":"115475","DOI":"10.1016\/j.ejmech.2023.115475","volume":"256","author":"J Hu","year":"2023","unstructured":"Hu J, Zhang D, Tian K et al (2023) Small-molecule LRRK2 inhibitors for PD therapy: current achievements and future perspectives. Eur J Med Chem 256:115475","journal-title":"Eur J Med Chem"},{"key":"766_CR34","doi-asserted-by":"publisher","first-page":"10312","DOI":"10.1021\/acs.jmedchem.1c00720","volume":"64","author":"DS Williamson","year":"2021","unstructured":"Williamson DS, Smith GP, Mikkelsen GK et al (2021) Design and synthesis of Pyrrolo[2,3-d]pyrimidine-derived leucine-rich repeat kinase 2 (LRRK2) inhibitors using a checkpoint kinase 1 (CHK1)-derived crystallographic surrogate. J Med Chem 64:10312\u201310332","journal-title":"J Med Chem"},{"issue":"12","key":"766_CR35","doi-asserted-by":"publisher","first-page":"5918","DOI":"10.1021\/acs.jcim.0c00915","volume":"60","author":"T Blaschke","year":"2020","unstructured":"Blaschke T, Ar\u00fas-Pous J, Chen H, Margreitter C, Tyrchan C, Engkvist O, Papadopoulos K, Patronov A (2020) REINVENT 2.0: an AI tool for de novo drug design. J Chem Inf Model 60(12):5918\u20135922","journal-title":"J Chem Inf Model"}],"container-title":["Journal of Cheminformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13321-023-00766-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13321-023-00766-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13321-023-00766-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T16:36:25Z","timestamp":1700498185000},"score":1,"resource":{"primary":{"URL":"https:\/\/jcheminf.biomedcentral.com\/articles\/10.1186\/s13321-023-00766-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,4]]},"references-count":35,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,12]]}},"alternative-id":["766"],"URL":"https:\/\/doi.org\/10.1186\/s13321-023-00766-0","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-3254116\/v1","asserted-by":"object"}]},"ISSN":["1758-2946"],"issn-type":[{"value":"1758-2946","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,10,4]]},"assertion":[{"value":"11 August 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 September 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 October 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Chenxing Yang, Hao Liu, and Jun Chen are employees of Shanghai Matwings Technology Co., Ltd., Shanghai. Other authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"91"}}