{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T09:00:32Z","timestamp":1780909232658,"version":"3.54.1"},"reference-count":184,"publisher":"American Chemical Society (ACS)","issue":"11","license":[{"start":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T00:00:00Z","timestamp":1779148800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T00:00:00Z","timestamp":1779148800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T00:00:00Z","timestamp":1779148800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-045"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["12371491"],"award-info":[{"award-number":["12371491"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key Project of the Qingdao Natural Science Foundation","award":["25-3-1-2-zyyd-jch"],"award-info":[{"award-number":["25-3-1-2-zyyd-jch"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Chem. Inf. Model."],"published-print":{"date-parts":[[2026,6,8]]},"DOI":"10.1021\/acs.jcim.6c00547","type":"journal-article","created":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T09:45:02Z","timestamp":1779183902000},"page":"6225-6249","source":"Crossref","is-referenced-by-count":0,"title":["Comprehensive Review of Contrastive and Generative Self-Supervised Learning for Small Molecular Representation"],"prefix":"10.1021","volume":"66","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3910-1493","authenticated-orcid":true,"given":"Zengqian","family":"Deng","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology","place":["Qingdao, China"]},{"name":"Qingdao University","place":["Qingdao, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-4410-1754","authenticated-orcid":true,"given":"Dongjiang","family":"Niu","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology","place":["Qingdao, China"]},{"name":"Qingdao University","place":["Qingdao, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiqiang","family":"Wei","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology","place":["Qingdao, China"]},{"name":"Qingdao University","place":["Qingdao, China"]},{"name":"College of Computer Science and Technology","place":["Qingdao, China"]},{"name":"Ocean University of China","place":["Qingdao, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5093-4221","authenticated-orcid":true,"given":"Zhen","family":"Li","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology","place":["Qingdao, China"]},{"name":"Qingdao University","place":["Qingdao, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"316","published-online":{"date-parts":[[2026,5,19]]},"reference":[{"key":"ref1\/cit1a","doi-asserted-by":"publisher","DOI":"10.1038\/s41589-024-01679-1"},{"key":"ref1\/cit1b","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-024-03434-4"},{"key":"ref2\/cit2","doi-asserted-by":"publisher","DOI":"10.1038\/s41563-019-0338-z"},{"key":"ref3\/cit3","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.3c00582"},{"key":"ref4\/cit4","doi-asserted-by":"publisher","DOI":"10.1126\/science.ade2574"},{"key":"ref5\/cit5","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-024-07487-w"},{"key":"ref6\/cit6a","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4453-4"},{"key":"ref6\/cit6b","doi-asserted-by":"publisher","DOI":"10.3390\/biomedinformatics4020079"},{"key":"ref6\/cit6c","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-024-00843-5"},{"key":"ref7\/cit7","first-page":"5812","volume":"33","author":"You Y.","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref8\/cit8","unstructured":"Chen, T.; Kornblith, S.; Norouzi, M.; Hinton, G.\n                      A Simple Framework for Contrastive Learning of Visual Representations\n                      , International conference on machine learning; PmLR, 2020; pp 1597\u20131607."},{"key":"ref9\/cit9","doi-asserted-by":"crossref","unstructured":"He, K.; Fan, H.; Wu, Y.; Xie, S.; Girshick, R.\n                      Momentum contrast for unsupervised visual representation learning\n                      , Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition; 2020; pp 9729\u20139738.","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref10\/cit10","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2978386"},{"key":"ref11\/cit11","unstructured":"Vaswani, A.; Shazeer, N.; Parmar, N.; Uszkoreit, J.; Jones, L.; Gomez, A. N.; Kaiser, \u0141.; Polosukhin, I. Attention is all you need\n                      Adv. Neural Inf. Process. Syst.\n                      2017; Vol. 30."},{"key":"ref12\/cit12","doi-asserted-by":"publisher","DOI":"10.1021\/acscentsci.7b00572"},{"key":"ref13\/cit13","unstructured":"Kingma, D. P.; Welling, M. Auto-encoding variational bayes. 2013, arXiv:1312.6114. arXiv.org e-Print archive. https:\/\/arxiv.org\/abs\/1312.6114."},{"key":"ref14\/cit14","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref15\/cit15","doi-asserted-by":"crossref","unstructured":"He, K.; Chen, X.; Xie, S.; Li, Y.; Doll\u00e1r, P.; Girshick, R.\n                      Masked Autoencoders Are Scalable Vision Learners\n                      , Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition; 2022; pp 16000\u201316009.","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref16\/cit16","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.5b00559"},{"key":"ref17\/cit17","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.2c01253"},{"key":"ref18\/cit18","doi-asserted-by":"publisher","DOI":"10.3389\/fphar.2020.565644"},{"issue":"6","key":"ref19\/cit19","first-page":"58","volume":"25","author":"Shivanyuk A. N.","year":"2007","journal-title":"Chem. Today"},{"key":"ref20\/cit20","unstructured":"Adamczyk, J.; Poziemski, J.; Job, F.; Kr\u00f3l, M.; Makowski, M. Molpile-large-scale, diverse dataset for molecular representation learning. 2025, arXiv:2509.18353. arXiv.org e-Print archive. https:\/\/arxiv.org\/abs\/2509.18353."},{"key":"ref21\/cit21","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkr777"},{"key":"ref22\/cit22","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkae1059"},{"key":"ref23\/cit23","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-022-01288-4"},{"key":"ref24\/cit24a","doi-asserted-by":"publisher","DOI":"10.1186\/s13321-020-00478-9"},{"key":"ref24\/cit24b","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkae1063"},{"key":"ref25\/cit25","doi-asserted-by":"publisher","DOI":"10.1039\/C7SC02664A"},{"key":"ref26\/cit26","doi-asserted-by":"publisher","DOI":"10.1021\/acs.chemrestox.0c00264"},{"key":"ref27\/cit27","doi-asserted-by":"publisher","DOI":"10.1021\/acs.chemrestox.6b00135"},{"key":"ref28\/cit28a","unstructured":"Huang, K.; Fu, T.; Gao, W.; Zhao, Y.; Roohani, Y.; Leskovec, J.; Coley, C. W.; Xiao, C.; Sun, J.; Zitnik, M. Therapeutics data commons: Machine learning datasets and tasks for drug discovery and development. 2021, arXiv:2102.09548. arXiv.org e-Print archive. https:\/\/arxiv.org\/abs\/2102.09548."},{"key":"ref28\/cit28b","doi-asserted-by":"publisher","unstructured":"Velez-Arce, A.; Li, M. M.; Gao, W.; Lin, X.; Huang, K.; Fu, T.; Pentelute, B. L.; Kellis, M.; Zitnik, M. Signals in the cells: Multimodal and contextualized machine learning foundations for therapeutics\n                      bioRxiv\n                      2024 10.1101\/2024.06.12.598655.","DOI":"10.1101\/2024.06.12.598655"},{"key":"ref29\/cit29","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkl999"},{"key":"ref30\/cit30","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/28.1.27"},{"key":"ref31\/cit31","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkad976"},{"key":"ref32\/cit32","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkad1040"},{"key":"ref33\/cit33","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gks1111"},{"key":"ref34\/cit34","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4939-7000-1_26"},{"key":"ref35\/cit35","doi-asserted-by":"publisher","DOI":"10.1021\/jm048957q"},{"key":"ref36\/cit36","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkm911"},{"key":"ref37\/cit37","doi-asserted-by":"crossref","unstructured":"Cremer, J.; Irwin, R.; Tibo, A.; Janet, J. P.; Olsson, S.; Clevert, D.A. Flowr: Flow matching for structure-aware de novo, interaction-and fragment-based ligand generation. 2025, arXiv:2504.10564. arXiv.org e-Print archive. https:\/\/arxiv.org\/abs\/2504.10564.","DOI":"10.1038\/s43588-026-00998-8"},{"key":"ref38\/cit38","doi-asserted-by":"publisher","DOI":"10.1186\/s13321-015-0068-4"},{"key":"ref39\/cit39","doi-asserted-by":"crossref","unstructured":"O\u2019Boyle, N.; Dalke, A. Deepsmiles: An adaptation of smiles for use in machine-learning of chemical structures 2018 7.","DOI":"10.26434\/chemrxiv.7097960.v1"},{"key":"ref40\/cit40","doi-asserted-by":"publisher","DOI":"10.1016\/j.patter.2022.100588"},{"key":"ref41\/cit41","doi-asserted-by":"publisher","DOI":"10.1039\/D4DD00019F"},{"key":"ref42\/cit42","doi-asserted-by":"publisher","DOI":"10.1002\/cmdc.201900458"},{"key":"ref43\/cit43","doi-asserted-by":"publisher","DOI":"10.1111\/cbdd.13648"},{"key":"ref44\/cit44","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.1c00600"},{"key":"ref45\/cit45","unstructured":"Radford, A.; Kim, J. W.; Hallacy, C.; Ramesh, A.; Goh, G.; Agarwal, S.; Sastry, G.; Askell, A.; Mishkin, P.; Clark, J.\n                      Learning Transferable Visual Models from Natural Language Supervision\n                      , International conference on machine learning; PmLR, 2021; pp 8748\u20138763."},{"key":"ref46\/cit46","unstructured":"Zbontar, J.; Jing, L.; Misra, I.; LeCun, Y.; Deny, S.\n                      Barlow Twins: Self-Supervised Learning Via Redundancy Reduction\n                      , International conference on machine learning; PMLR, 2021; pp 12310\u201312320."},{"key":"ref47\/cit47","first-page":"58058","volume":"37","author":"Qin J.","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref48\/cit48","doi-asserted-by":"publisher","DOI":"10.1021\/ci00057a005"},{"key":"ref49\/cit49","doi-asserted-by":"publisher","DOI":"10.1021\/ci100050t"},{"key":"ref50\/cit50","doi-asserted-by":"crossref","DOI":"10.1039\/9781849733069","volume-title":"Nomenclature of Organic Chemistry: Iupac Recommendations and Preferred Names 2013","author":"Favre H. A.","year":"2013"},{"key":"ref51\/cit51","doi-asserted-by":"crossref","unstructured":"Quiles, M. G.; Ribeiro, P. A.; Pinheiro, G. A.; Prati, R. C.; Silva, J. L. d.\n                      Enhancing Low-cost Molecular Property Prediction with Contrastive Learning on Smiles Representations\n                      , International conference on computational science and its applications; Springer, 2024; pp 387\u2013401.","DOI":"10.1007\/978-3-031-65329-2_26"},{"key":"ref52\/cit52","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbab327"},{"key":"ref53\/cit53","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btad258"},{"key":"ref54\/cit54","doi-asserted-by":"publisher","unstructured":"Guo, Z.; Sharma, P. K.; Du, L.; Abraham, R. Mm-deacon: Multimodal molecular domain embedding analysis via contrastive learning\n                      bioRxiv\n                      2021 10.1101\/2021.09.17.460864.","DOI":"10.1101\/2021.09.17.460864"},{"key":"ref55\/cit55","doi-asserted-by":"publisher","DOI":"10.1016\/j.drudis.2022.103373"},{"key":"ref56\/cit56","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-022-00447-x"},{"key":"ref57\/cit57","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2025.103195"},{"key":"ref58\/cit58","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btad371"},{"key":"ref59\/cit59","doi-asserted-by":"crossref","unstructured":"Sun, M.; Xing, J.; Wang, H.; Chen, B.; Zhou, J.\n                      Mocl: Data-driven Molecular Fingerprint Via Knowledge-aware Contrastive Learning from Molecular Graph\n                      , Proceedings of the 27th ACM SIGKDD conference on knowledge discovery & data mining; 2021; pp 3585\u20133594.","DOI":"10.1145\/3447548.3467186"},{"key":"ref60\/cit60","doi-asserted-by":"publisher","unstructured":"Fang, Y.; Zhang, Q.; Yang, H.; Zhuang, X.; Deng, S.; Zhang, W.; Qin, M.; Chen, Z.; Fan, X.; Chen, H.\n                      Molecular Contrastive Learning with Chemical Element Knowledge Graph\n                      , Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 36; 2022; pp 3968\u20133976 10.1609\/aaai.v36i4.20313.","DOI":"10.1609\/aaai.v36i4.20313"},{"key":"ref61\/cit61","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00654-0"},{"key":"ref62\/cit62","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.2c00495"},{"key":"ref63\/cit63","doi-asserted-by":"crossref","first-page":"17584","DOI":"10.52202\/075280-0771","volume":"36","author":"Luong K.-D.","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref64\/cit64","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3364059"},{"key":"ref65\/cit65","doi-asserted-by":"publisher","DOI":"10.1186\/s13321-024-00815-2"},{"key":"ref66\/cit66","unstructured":"Liu, X.; Lu, Z.; Liao, Y.; Fan, C.; Li, H.b. Local-global multimodal contrastive learning for molecular property prediction. 2026, arXiv:2601.22610. arXiv.org e-Print archive. https:\/\/arxiv.org\/abs\/2601.22610."},{"key":"ref67\/cit67","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.2c00521"},{"key":"ref68\/cit68","unstructured":"Guo, Z.; Sharma, P.; Martinez, A.; Du, L.; Abraham, R. Multilingual molecular representation learning via contrastive pre-training. 2021, arXiv:2109.08830. arXiv.org e-Print archive. https:\/\/arxiv.org\/abs\/2109.08830."},{"key":"ref69\/cit69","doi-asserted-by":"publisher","unstructured":"Li, S.; Zhou, J.; Xu, T.; Dou, D.; Xiong, H.\n                      Geomgcl: Geometric Graph Contrastive Learning for Molecular Property Prediction\n                      , Proceedings of the AAAI conference on artificial intelligence, Vol. 36; 2022; pp 4541\u20134549 10.1609\/aaai.v36i4.20377.","DOI":"10.1609\/aaai.v36i4.20377"},{"key":"ref70\/cit70","unstructured":"Seidl, P.; Vall, A.; Hochreiter, S.; Klambauer, G.\n                      Enhancing activity prediction models in drug discovery with the ability to understand human language\n                      , Proceedings of the 40th International Conference on Machine Learning, Proceedings of Machine Learning Research; 2023."},{"key":"ref71\/cit71","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btae386"},{"key":"ref72\/cit72","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.3c01468"},{"key":"ref73\/cit73","doi-asserted-by":"publisher","DOI":"10.1109\/TCBB.2023.3326145"},{"key":"ref74\/cit74","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btae164"},{"key":"ref75\/cit75","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3458405"},{"key":"ref76\/cit76","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2024.111970"},{"key":"ref77\/cit77","unstructured":"Zheng, Y.; Wu, S.; Lin, J.; Ren, Y.; He, J.; Pu, X.; He, L.\n                      Cross-View Contrastive Fusion for Enhanced Molecular Property Prediction\n                      , Proccedings of the Thirty-Third International Joint Conference on Artificial Intelligence; Vol. 2. 2024."},{"key":"ref78\/cit78","doi-asserted-by":"publisher","DOI":"10.1002\/minf.202400169"},{"key":"ref79\/cit79","doi-asserted-by":"publisher","DOI":"10.1145\/3665894"},{"key":"ref80\/cit80","unstructured":"Liu, S.; Wang, H.; Liu, W.; Lasenby, J.; Guo, H.; Tang, J. Pre-training molecular graph representation with 3d geometry. 2021, arXiv:2110.07728. arXiv.org e-Print archive. https:\/\/arxiv.org\/abs\/2110.07728."},{"key":"ref81\/cit81","unstructured":"Kim, S.; Nam, J.; Kim, J.; Lee, H.; Ahn, S.; Shin, J.\n                      Fragment-based multi-view molecular contrastive learning\n                      , Workshop on\u2019\u2019Machine Learning for Materials\u2019\u2019 ICLR 2023; 2023."},{"key":"ref82\/cit82","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btae524"},{"key":"ref83\/cit83","doi-asserted-by":"crossref","unstructured":"Lin, J.; Zheng, Y.; Chen, X.; Ren, Y.; Pu, X.; He, J.\n                      Cross-View Contrastive Unification Guides Generative Pretraining for Molecular Property Prediction\n                      , Proceedings of the 32nd ACM International Conference on Multimedia, Melbourne VIC, Australia; 2024.","DOI":"10.1145\/3664647.3681193"},{"key":"ref84\/cit84","unstructured":"St\u00e4rk, H.; Beaini, D.; Corso, G.; Tossou, P.; Dallago, C.; G\u00fcnnemann, S.; Li\u00f3, P.\n                      3d infomax improves gnns for molecular property prediction\n                      , Proceedings of the 39th International Conference on Machine Learning, Proceedings of Machine Learning Research; 2022."},{"key":"ref85\/cit85","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102784"},{"key":"ref86\/cit86","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2024.3479194"},{"key":"ref87\/cit87","unstructured":"St\u00e4rk, H.; Beaini, D.; Corso, G.; Tossou, P.; Dallago, C.; G\u00fcnnemann, S.; Li\u00f2, P.\n                      3d infomax improves gnns for molecular property prediction\n                      , International Conference on Machine Learning; PMLR, 2022; pp 20479\u201320502."},{"key":"ref88\/cit88","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-025-66685-w"},{"key":"ref89\/cit89","doi-asserted-by":"publisher","unstructured":"Cho, S.; Jeong, D.W.; Ko, S. M.; Kim, J.; Han, S.; Hong, S.; Lee, H.; Lee, M.\n                      3d denoisers are good 2d teachers: Molecular pretraining via denoising and cross-modal distillation\n                      , Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 39; 2025; pp 110\u2013118 10.1609\/aaai.v39i1.31986.","DOI":"10.1609\/aaai.v39i1.31986"},{"key":"ref90\/cit90","unstructured":"Zaidi, S.; Schaarschmidt, M.; Martens, J.; Kim, H.; Teh, Y. W.; Sanchez-Gonzalez, A.; Battaglia, P.; Pascanu, R.; Godwin, J. Pre-training via denoising for molecular property prediction. 2022, arXiv:2206.00133. arXiv.org e-Print archive. https:\/\/arxiv.org\/abs\/2206.00133."},{"key":"ref91\/cit91","doi-asserted-by":"crossref","unstructured":"Wang, X.; Zhao, H.; Tu, W.w.; Yao, Q.\n                      Automated 3d Pre-Training for Molecular Property Prediction\n                      , Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining; 2023; pp 2419\u20132430.","DOI":"10.1145\/3580305.3599252"},{"key":"ref92\/cit92","doi-asserted-by":"publisher","DOI":"10.3390\/ijms25073794"},{"key":"ref93\/cit93","unstructured":"Jin, W.; Barzilay, R.; Jaakkola, T.\n                      Junction Tree Variational Autoencoder for Molecular Graph Generation\n                      , Proceedings of the 35th International Conference on Machine Learning, Proceedings of Machine Learning Research; 2018."},{"key":"ref94\/cit94","unstructured":"Liu, Q.; Allamanis, M.; Brockschmidt, M.; Gaunt, A. Constrained graph variational autoencoders for molecule design\n                      Adv. Neural Inf. Process. Syst.\n                      2018; Vol. 31."},{"key":"ref95\/cit95","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btac296"},{"key":"ref96\/cit96","doi-asserted-by":"crossref","first-page":"55077","DOI":"10.52202\/075280-2405","volume":"36","author":"Chen J.","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref97\/cit97","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.125976"},{"key":"ref98\/cit98","doi-asserted-by":"publisher","DOI":"10.1038\/s42004-023-00825-5"},{"key":"ref99\/cit99","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.5c03128"},{"key":"ref100\/cit100","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.4c01193"},{"key":"ref101\/cit101","doi-asserted-by":"crossref","unstructured":"Zhu, J.; Xia, Y.; Wu, L.; Xie, S.; Qin, T.; Zhou, W.; Li, H.; Liu, T.Y.\n                      Unified 2d and 3d Pre-Training of Molecular Representations\n                      , Proceedings of the 28th ACM SIGKDD conference on knowledge discovery and data mining; 2022; pp 2626\u20132636.","DOI":"10.1145\/3534678.3539368"},{"key":"ref102\/cit102","doi-asserted-by":"crossref","unstructured":"Ma, Y.; Yu, S.; Shen, Y.\n                      Pretraining molecules with explicit substructure information\n                      , Proceedings of the 2024 SIAM International Conference on Data Mining (SDM); SIAM, 2024; pp 517\u2013525.","DOI":"10.1137\/1.9781611978032.60"},{"key":"ref103\/cit103","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-025-57828-0"},{"key":"ref104\/cit104","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.5c01068"},{"key":"ref105\/cit105","unstructured":"Yang, J.; Thost, V.; Ma, T.\n                      Masking in molecular graphs leveraging reaction context\n                      , ICML 2024 AI for Science Workshop; 2024."},{"key":"ref106\/cit106","unstructured":"Tang, H.; Feng, S.; Lin, B.; Ni, Y.; Liu, J.; Ma, W.Y.; Lan, Y. Contextual molecule representation learning from chemical reaction knowledge. 2024, arXiv:2402.13779. arXiv.org e-Print archive. https:\/\/arxiv.org\/abs\/2402.13779."},{"key":"ref107\/cit107","unstructured":"You, J.; Liu, B.; Ying, Z.; Pande, V.; Leskovec, J. Graph convolutional policy network for goal-directed molecular graph generation\n                      Adv. Neural Inf. Process. Syst.\n                      2018; Vol. 31."},{"key":"ref108\/cit108","unstructured":"De Cao, N.; Kipf, T. Molgan: An implicit generative model for small molecular graphs. 2018, arXiv:1805.11973. arXiv.org e-Print archive. https:\/\/arxiv.org\/abs\/1805.11973."},{"key":"ref109\/cit109","doi-asserted-by":"publisher","DOI":"10.1186\/s13321-019-0404-1"},{"key":"ref110\/cit110","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-50834-6"},{"key":"ref111\/cit111","doi-asserted-by":"publisher","DOI":"10.1109\/TCBB.2022.3219883"},{"key":"ref112\/cit112","doi-asserted-by":"crossref","unstructured":"Parameswara, M. A.; Mandala, R.\n                      Biogan-bert: Biogpt-2 fine tuned and gan-bert for extracting drug interaction based on biomedical texts\n                      , 2024 11th International Conference on Advanced Informatics: Concept, Theory and Application (ICAICTA); IEEE, 2024; pp 1\u20136.","DOI":"10.1109\/ICAICTA63815.2024.10762980"},{"key":"ref113\/cit113","first-page":"12559","volume":"33","author":"Rong Y.","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref114\/cit114","doi-asserted-by":"crossref","unstructured":"Wang, S.; Guo, Y.; Wang, Y.; Sun, H.; Huang, J.\n                      Smiles-bert: Large scale unsupervised pre-training for molecular property prediction\n                      , Proceedings of the 10th ACM international conference on bioinformatics, computational biology and health informatics; 2019; pp 429\u2013436.","DOI":"10.1145\/3307339.3342186"},{"key":"ref115\/cit115","unstructured":"Liu, Y.; Ott, M.; Goyal, N.; Du, J.; Joshi, M.; Chen, D.; Levy, O.; Lewis, M.; Zettlemoyer, L.; Stoyanov, V. Roberta: A robustly optimized bert pretraining approach. 2019, arXiv:1907.11692. arXiv.org e-Print archive. https:\/\/arxiv.org\/abs\/1907.11692."},{"key":"ref116\/cit116","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/acdb30"},{"key":"ref117\/cit117","doi-asserted-by":"crossref","unstructured":"Xia, J.; Zhao, C.; Hu, B.; Gao, Z.; Tan, C.; Liu, Y.; Li, S.; Li, S. Z.\n                      Mole-bert: Rethinking Pre-Training Graph Neural Networks for Molecules\n                      , Eleventh International Conference on Learning Representations; 2023.","DOI":"10.26434\/chemrxiv-2023-dngg4"},{"key":"ref118\/cit118","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbad398"},{"key":"ref119\/cit119","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbab152"},{"key":"ref120\/cit120","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbad400"},{"key":"ref121\/cit121","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.102092"},{"key":"ref122\/cit122","unstructured":"Yu, Q.; Zhang, Y.; Ni, Y.; Feng, S.; Lan, Y.; Zhou, H.; Liu, J. Multimodal molecular pretraining via modality blending. 2023, arXiv:2307.06235. arXiv.org e-Print archive. https:\/\/arxiv.org\/abs\/2307.06235."},{"key":"ref123\/cit123","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2023.107666"},{"key":"ref124\/cit124","doi-asserted-by":"crossref","unstructured":"Li, H.; Zhao, D.; Zeng, J.\n                      Kpgt: Knowledge-guided pre-training of graph transformer for molecular property prediction\n                      , Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining; 2022; pp 857\u2013867.","DOI":"10.1145\/3534678.3539426"},{"key":"ref125\/cit125","unstructured":"Jiao, R.; Kong, X.; Yu, Z.; Huang, W.; Liu, Y.\n                      Equivariant Pretrained Transformer for Unified Geometric Learning on Multi-Domain 3d Molecules\n                      , ICLR 2024 Workshop on Generative and Experimental Perspectives for Biomolecular Design; 2024."},{"key":"ref126\/cit126","unstructured":"Liu, Y.; Wang, L.; Liu, M.; Zhang, X.; Oztekin, B.; Ji, S. Spherical message passing for 3d graph networks 2021, arXiv:2102.05013. arXiv.org e-Print archive. https:\/\/arxiv.org\/abs\/2102.05013."},{"key":"ref127\/cit127","unstructured":"Fang, Y.; Liang, X.; Zhang, N.; Liu, K.; Huang, R.; Chen, Z.; Fan, X.; Chen, H. Mol-instructions: A large-scale biomolecular instruction dataset for large language models. 2023, arXiv:2306.08018. arXiv.org e-Print archive. https:\/\/arxiv.org\/abs\/2306.08018."},{"key":"ref128\/cit128","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocae045"},{"key":"ref129\/cit129","unstructured":"Achiam, J.; Adler, S.; Agarwal, S.; Ahmad, L.; Akkaya, I.; Aleman, F. L.; Almeida, D.; Altenschmidt, J.; Altman, S.; Anadkat, S. Gpt-4 technical report. 2023, arXiv:2303.08774. arXiv.org e-Print archive. https:\/\/arxiv.org\/abs\/2303.08774."},{"key":"ref130\/cit130","unstructured":"Zhang, D.; Liu, W.; Tan, Q.; Chen, J.; Yan, H.; Yan, Y.; Li, J.; Huang, W.; Yue, X.; Ouyang, W. Chemllm: A chemical large language model. 2024, arXiv:2402.06852. arXiv.org e-Print archive. https:\/\/arxiv.org\/abs\/2402.06852."},{"key":"ref131\/cit131","unstructured":"Zhao, Z.; Ma, D.; Chen, L.; Sun, L.; Li, Z.; Xia, Y.; Xu, H.; Zhu, Z.; Zhu, S.; Fan, S.\n                      Chemdfm: A Large Language Foundation Model for Chemistry\n                      , Neurips 2024 Workshop Foundation Models for Science: Progress, Opportunities, and Challenges; 2024."},{"key":"ref132\/cit132","doi-asserted-by":"publisher","DOI":"10.34133\/research.0827"},{"key":"ref133\/cit133","unstructured":"Chitsaz, K.; Balaji, R.; Fournier, Q.; Bhatt, N. P.; Chandar, S. Novomolgen: Rethinking molecular language model pretraining. 2025, arXiv:2508.13408. arXiv.org e-Print archive. https:\/\/arxiv.org\/abs\/2508.13408."},{"key":"ref134\/cit134","first-page":"15870","volume":"34","author":"Zhang Z.","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref135\/cit135","doi-asserted-by":"publisher","DOI":"10.1038\/s44387-025-00066-y"},{"key":"ref136\/cit136","unstructured":"Hoogeboom, E.; Satorras, V. G.; Vignac, C.; Welling, M.\n                      Equivariant diffusion for molecule generation in 3d\n                      , International conference on machine learning; PMLR, 2022; pp 8867\u20138887."},{"key":"ref137\/cit137","unstructured":"Xu, M.; Yu, L.; Song, Y.; Shi, C.; Ermon, S.; Tang, J. Geodiff: A geometric diffusion model for molecular conformation generation. 2022, arXiv:2203.02923. arXiv.org e-Print archive. https:\/\/arxiv.org\/abs\/2203.02923."},{"key":"ref138\/cit138","doi-asserted-by":"publisher","DOI":"10.1021\/acsomega.5c10621"},{"key":"ref139\/cit139","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btaf426"},{"key":"ref140\/cit140","unstructured":"Corso, G.; St\u00e4rk, H.; Jing, B.; Barzilay, R.; Jaakkola, T. Diffdock: Diffusion steps, twists, and turns for molecular docking. 2022, arXiv:2210.01776. arXiv.org e-Print archive. https:\/\/arxiv.org\/abs\/2210.01776."},{"key":"ref141\/cit141","unstructured":"Vignac, C.; Krawczuk, I.; Siraudin, A.; Wang, B.; Cevher, V.; Frossard, P. Digress: Discrete denoising diffusion for graph generation. 2022, arXiv:2209.14734. arXiv.org e-Print archive. https:\/\/arxiv.org\/abs\/2209.14734."},{"key":"ref142\/cit142","doi-asserted-by":"publisher","DOI":"10.1039\/D4SC03523B"},{"key":"ref143\/cit143","first-page":"128798","volume":"37","author":"Hassan M.","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref144\/cit144","unstructured":"Dunn, I.; Koes, D. R. Flowmol3: Flow matching for 3d de novo small-molecule generation. 2025, arXiv:12629.v12621. arXiv.org e-Print archive. https:\/\/arxiv.org\/abs\/12629.v12621."},{"key":"ref145\/cit145","unstructured":"Luo, Y.; Yan, K.; Ji, S.\n                      Graphdf: A Discrete Flow Model for Molecular Graph Generation\n                      , International conference on machine learning; PMLR, 2021; pp 7192\u20137203."},{"key":"ref146\/cit146","unstructured":"Liu, S.; Du, W.; Ma, Z.M.; Guo, H.; Tang, J.\n                      A Group Symmetric Stochastic Differential Equation Model for Molecule Multi-Modal Pretraining\n                      , International Conference on Machine Learning; PMLR, 2023; pp 21497\u201321526."},{"key":"ref147\/cit147","doi-asserted-by":"crossref","unstructured":"Wang, Y.; Min, Y.; Chen, X.; Wu, J.\n                      Multi-View Graph Contrastive Representation Learning for Drug-drug Interaction Prediction\n                      , Proceedings of the web conference 2021; 2021; pp 2921\u20132933.","DOI":"10.1145\/3442381.3449786"},{"key":"ref148\/cit148","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbad324"},{"key":"ref149\/cit149","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-022-04372-9"},{"key":"ref150\/cit150","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2024.3350666"},{"key":"ref151\/cit151","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiolchem.2025.108426"},{"key":"ref152\/cit152","doi-asserted-by":"crossref","unstructured":"Hou, Z.; Liu, X.; Cen, Y.; Dong, Y.; Yang, H.; Wang, C.; Tang, J.\n                      Graphmae: Self-supervised masked graph autoencoders\n                      , Proceedings of the 28th ACM SIGKDD conference on knowledge discovery and data mining; 2022; pp 594\u2013604.","DOI":"10.1145\/3534678.3539321"},{"key":"ref153\/cit153","unstructured":"Wasi, A. T. Gflownets for learning better drug-drug interaction representations. 2025, arXiv:2508.06576. arXiv.org e-Print archive. https:\/\/arxiv.org\/abs\/2508.06576."},{"key":"ref154\/cit154","doi-asserted-by":"publisher","DOI":"10.3389\/fphar.2024.1484639"},{"key":"ref155\/cit155","doi-asserted-by":"publisher","DOI":"10.1007\/s12530-025-09689-7"},{"key":"ref156\/cit156","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2024.102778"},{"key":"ref157\/cit157","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiolchem.2024.108244"},{"key":"ref158\/cit158","doi-asserted-by":"publisher","DOI":"10.1109\/TCBB.2022.3153963"},{"key":"ref159\/cit159","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btab565"},{"key":"ref160\/cit160","unstructured":"Wu, F. A semi-supervised molecular learning framework for activity cliff estimation. 2026, arXiv:2601.04507. arXiv.org e-Print archive. https:\/\/arxiv.org\/abs\/2601.04507."},{"key":"ref161\/cit161","doi-asserted-by":"crossref","unstructured":"Shen, W. X.; Cui, C.; Su, X.; Zhang, Z.; Velez-Arce, A.; Wang, J.; Shi, X.; Zhang, Y.; Wu, J.; Chen, Y. Z.; Zitnik, M. Activity cliff-informed contrastive learning for molecular property prediction\n                      Res. Square\n                      2024.","DOI":"10.26434\/chemrxiv-2023-5cz7s-v2"},{"key":"ref162\/cit162","unstructured":"Liu, Z.; Zhang, X.; Chen, Y.; Feng, B.; Yang, M.; Xu, Z.; Li, Y.; King, I. Dockedac: Empowering deep learning models with 3d protein-ligand data for activity cliff analysis."},{"key":"ref163\/cit163","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.5c00949"},{"key":"ref164\/cit164","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0332640"},{"key":"ref165\/cit165","unstructured":"Liu, Y.; Wang, L.; Liu, M.; Lin, Y.; Zhang, X.; Oztekin, B.; Ji, S.\n                      Spherical message passing for 3d molecular graphs\n                      , International Conference on Learning Representations (ICLR); 2022."},{"key":"ref166\/cit166","unstructured":"Cao, Y.H.; Wu, J. Rethinking self-supervised learning: Small is beautiful. 2021, arXiv:2103.13559. arXiv.org e-Print archive. https:\/\/arxiv.org\/abs\/2103.13559."},{"key":"ref167\/cit167","doi-asserted-by":"crossref","unstructured":"Zhou, G.; Gao, Z.; Ding, Q.; Zheng, H.; Xu, H.; Wei, Z.; Zhang, L.; Ke, G. Uni-mol: A universal 3d molecular representation learning framework. 2023.","DOI":"10.26434\/chemrxiv-2022-jjm0j-v4"},{"key":"ref168\/cit168a","unstructured":"Feng, S.; Ni, Y.; Li, M.; Huang, Y.; Ma, Z.M.; Ma, W.Y.; Lan, Y. Unicorn: A unified contrastive learning approach for multi-view molecular representation learning. 2024, arXiv:2405.10343. arXiv.org e-Print archive. https:\/\/arxiv.org\/abs\/2405.10343."},{"key":"ref168\/cit168b","unstructured":"Ariguib, B.; Niepert, M.; Manolache, A. Learning the neighborhood: Contrast-free multimodal self-supervised molecular graph pretraining. 2025, arXiv:2509.22468. arXiv.org e-Print archive. https:\/\/arxiv.org\/abs\/2509.22468."},{"key":"ref169\/cit169","doi-asserted-by":"publisher","DOI":"10.1021\/acs.chemrev.5c00461"},{"key":"ref170\/cit170","doi-asserted-by":"publisher","DOI":"10.1039\/D5DD00170F"},{"key":"ref171\/cit171","first-page":"5850","volume":"36","author":"Zhao H.","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref172\/cit172","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00759-6"},{"key":"ref173\/cit173","unstructured":"Praski, M.; Adamczyk, J.; Czech, W. Benchmarking pretrained molecular embedding models for molecular representation learning. 2025, arXiv:2508.06199. arXiv.org e-Print archive. https:\/\/arxiv.org\/abs\/2508.06199."},{"key":"ref174\/cit174","unstructured":"Antoniuk, E. R.; Zaman, S.; Ben-Nun, T.; Li, P.; Diffenderfer, J.; Sahin, B.; Smolenski, O.; Hsu, T.; Hiszpanski, A. M.; Chiu, K. Boom: Benchmarking out-of-distribution molecular property predictions of machine learning models. 2025, arXiv:2505.01912. arXiv.org e-Print archive. https:\/\/arxiv.org\/abs\/2505.01912."},{"key":"ref175\/cit175","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2020.01.021"},{"key":"ref176\/cit176","doi-asserted-by":"publisher","DOI":"10.1038\/s41589-023-01349-8"},{"key":"ref177\/cit177","doi-asserted-by":"publisher","DOI":"10.1038\/s41587-024-02143-0"},{"key":"ref178\/cit178","first-page":"12096","volume":"35","author":"Sun R.","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."}],"container-title":["Journal of Chemical Information and Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.acs.org\/doi\/pdf\/10.1021\/acs.jcim.6c00547","content-type":"application\/pdf","content-version":"vor","intended-application":"unspecified"},{"URL":"https:\/\/pubs.acs.org\/doi\/pdf\/10.1021\/acs.jcim.6c00547","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T08:11:47Z","timestamp":1780906307000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.acs.org\/doi\/10.1021\/acs.jcim.6c00547"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,19]]},"references-count":184,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2026,6,8]]}},"alternative-id":["10.1021\/acs.jcim.6c00547"],"URL":"https:\/\/doi.org\/10.1021\/acs.jcim.6c00547","relation":{},"ISSN":["1549-9596","1549-960X"],"issn-type":[{"value":"1549-9596","type":"print"},{"value":"1549-960X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,19]]}}}