{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,18]],"date-time":"2026-10-18T03:59:13Z","timestamp":1792295953661,"version":"4.4.0"},"reference-count":55,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100018554","name":"Science and Technology Program of Gansu Province","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100018554","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Journal of Molecular Graphics and Modelling"],"published-print":{"date-parts":[[2023,6]]},"DOI":"10.1016\/j.jmgm.2023.108454","type":"journal-article","created":{"date-parts":[[2023,3,15]],"date-time":"2023-03-15T09:58:43Z","timestamp":1678874323000},"page":"108454","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":19,"special_numbering":"C","title":["NoiseMol: A noise-robusted data augmentation via perturbing noise for molecular property prediction"],"prefix":"10.1016","volume":"121","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5648-2323","authenticated-orcid":false,"given":"Jing","family":"Jiang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6585-2656","authenticated-orcid":false,"given":"Ruisheng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongna","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tongfeng","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gaili","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhili","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhixuan","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"6","key":"10.1016\/j.jmgm.2023.108454_b1","doi-asserted-by":"crossref","first-page":"2545","DOI":"10.1021\/acs.jcim.9b00266","article-title":"Deep learning in chemistry","volume":"59","author":"Mater","year":"2019","journal-title":"J. Chem. Inf. Model."},{"issue":"19","key":"10.1016\/j.jmgm.2023.108454_b2","doi-asserted-by":"crossref","first-page":"4573","DOI":"10.1093\/bioinformatics\/btac550","article-title":"MultiGran-SMILES: Multi-granularity SMILES learning for molecular property prediction","volume":"38","author":"Jiang","year":"2022","journal-title":"Bioinformatics"},{"key":"10.1016\/j.jmgm.2023.108454_b3","doi-asserted-by":"crossref","DOI":"10.1016\/j.drudis.2022.103373","article-title":"Deep learning methods for molecular representation and property prediction","author":"Li","year":"2022","journal-title":"Drug Discov. Today"},{"key":"10.1016\/j.jmgm.2023.108454_b4","series-title":"International Conference on Artificial Intelligence and Statistics","first-page":"8906","article-title":"Structured multi-task learning for molecular property prediction","author":"Liu","year":"2022"},{"key":"10.1016\/j.jmgm.2023.108454_b5","doi-asserted-by":"crossref","DOI":"10.1016\/j.drudis.2022.03.017","article-title":"Machine-learning-guided early drug discovery of small molecules","author":"Pillai","year":"2022","journal-title":"Drug Discov. Today"},{"issue":"6","key":"10.1016\/j.jmgm.2023.108454_b6","doi-asserted-by":"crossref","first-page":"1241","DOI":"10.1016\/j.drudis.2018.01.039","article-title":"The rise of deep learning in drug discovery","volume":"23","author":"Chen","year":"2018","journal-title":"Drug Discov. Today"},{"key":"10.1016\/j.jmgm.2023.108454_b7","series-title":"Smiles transformer: Pre-trained molecular fingerprint for low data drug discovery","author":"Honda","year":"2019"},{"key":"10.1016\/j.jmgm.2023.108454_b8","first-page":"29935","article-title":"Data augmentation can improve robustness","volume":"34","author":"Rebuffi","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.jmgm.2023.108454_b9","doi-asserted-by":"crossref","unstructured":"G. Ghiasi, Y. Cui, A. Srinivas, R. Qian, T.-Y. Lin, E.D. Cubuk, Q.V. Le, B. Zoph, Simple copy-paste is a strong data augmentation method for instance segmentation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 2918\u20132928.","DOI":"10.1109\/CVPR46437.2021.00294"},{"key":"10.1016\/j.jmgm.2023.108454_b10","doi-asserted-by":"crossref","unstructured":"Z. Zhong, L. Zheng, G. Kang, S. Li, Y. Yang, Random erasing data augmentation, in: Proceedings of the AAAI Conference on Artificial Intelligence, 2020, pp. 13001\u201313008.","DOI":"10.1609\/aaai.v34i07.7000"},{"issue":"1","key":"10.1016\/j.jmgm.2023.108454_b11","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1021\/ci00057a005","article-title":"SMILES, a chemical language and information system. 1. Introduction to methodology and encoding rules","volume":"28","author":"Weininger","year":"1988","journal-title":"J. Chem. Inf. Comput. Sci."},{"issue":"2","key":"10.1016\/j.jmgm.2023.108454_b12","doi-asserted-by":"crossref","first-page":"97","DOI":"10.1021\/ci00062a008","article-title":"SMILES. 2. Algorithm for generation of unique SMILES notation","volume":"29","author":"Weininger","year":"1989","journal-title":"J. Chem. Inf. Comput. Sci."},{"key":"10.1016\/j.jmgm.2023.108454_b13","series-title":"SMILES enumeration as data augmentation for neural network modeling of molecules","author":"Bjerrum","year":"2017"},{"issue":"3","key":"10.1016\/j.jmgm.2023.108454_b14","doi-asserted-by":"crossref","first-page":"bbaa092","DOI":"10.1093\/bib\/bbaa092","article-title":"Different molecular enumeration influences in deep learning: An example using aqueous solubility","volume":"22","author":"Chen","year":"2021","journal-title":"Brief. Bioinform."},{"issue":"1","key":"10.1016\/j.jmgm.2023.108454_b15","doi-asserted-by":"crossref","first-page":"bbab367","DOI":"10.1093\/bib\/bbab367","article-title":"A general optimization protocol for molecular property prediction using a deep learning network","volume":"23","author":"Chen","year":"2022","journal-title":"Brief. Bioinform."},{"key":"10.1016\/j.jmgm.2023.108454_b16","first-page":"1","article-title":"TranGRU: Focusing on both the local and global information of molecules for molecular property prediction","author":"Jiang","year":"2022","journal-title":"Appl. Intell."},{"issue":"1","key":"10.1016\/j.jmgm.2023.108454_b17","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41467-020-19266-y","article-title":"State-of-the-art augmented NLP transformer models for direct and single-step retrosynthesis","volume":"11","author":"Tetko","year":"2020","journal-title":"Nature Commun."},{"issue":"6","key":"10.1016\/j.jmgm.2023.108454_b18","doi-asserted-by":"crossref","first-page":"bbab327","DOI":"10.1093\/bib\/bbab327","article-title":"Learning to SMILES: BAN-based strategies to improve latent representation learning from molecules","volume":"22","author":"Wu","year":"2021","journal-title":"Brief. Bioinform."},{"issue":"3","key":"10.1016\/j.jmgm.2023.108454_b19","doi-asserted-by":"crossref","first-page":"bbac131","DOI":"10.1093\/bib\/bbac131","article-title":"Knowledge-based BERT: A method to extract molecular features like computational chemists","volume":"23","author":"Wu","year":"2022","journal-title":"Brief. Bioinform."},{"key":"10.1016\/j.jmgm.2023.108454_b20","unstructured":"K.L. Jacob Devlin, L.K.T. Toutanova, BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding, in: Proceedings of NAACL-HLT, 2019, pp. 4171\u20134186."},{"issue":"6","key":"10.1016\/j.jmgm.2023.108454_b21","doi-asserted-by":"crossref","first-page":"bbab152","DOI":"10.1093\/bib\/bbab152","article-title":"MG-BERT: Leveraging unsupervised atomic representation learning for molecular property prediction","volume":"22","author":"Zhang","year":"2021","journal-title":"Brief. Bioinform."},{"key":"10.1016\/j.jmgm.2023.108454_b22","article-title":"Masked molecule modeling: A new paradigm of molecular representation learning for chemistry understanding","author":"He","year":"2022","journal-title":"Res. Square"},{"issue":"1","key":"10.1016\/j.jmgm.2023.108454_b23","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41467-021-23415-2","article-title":"Masked graph modeling for molecule generation","volume":"12","author":"Mahmood","year":"2021","journal-title":"Nature Commun."},{"key":"10.1016\/j.jmgm.2023.108454_b24","doi-asserted-by":"crossref","unstructured":"S. Wang, Y. Guo, Y. Wang, H. Sun, J. Huang, Smiles-bert: Large scale unsupervised pre-training for molecular property prediction, in: Proceedings of the 10th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics, 2019, pp. 429\u2013436.","DOI":"10.1145\/3307339.3342186"},{"key":"10.1016\/j.jmgm.2023.108454_b25","series-title":"Chemberta: Large-scale self-supervised pretraining for molecular property prediction","author":"Chithrananda","year":"2020"},{"key":"10.1016\/j.jmgm.2023.108454_b26","first-page":"17441","article-title":"Property-aware relation networks for few-shot molecular property prediction","volume":"34","author":"Wang","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.jmgm.2023.108454_b27","doi-asserted-by":"crossref","first-page":"693","DOI":"10.1007\/s10822-005-9008-0","article-title":"Substructural fragments: An universal language to encode reactions, molecular and supramolecular structures","volume":"19","author":"Varnek","year":"2005","journal-title":"J. Comput. Aided Mol. Des."},{"key":"10.1016\/j.jmgm.2023.108454_b28","doi-asserted-by":"crossref","unstructured":"A. Chakrabarty, O.A. Pandit, U. Garain, Context sensitive lemmatization using two successive bidirectional gated recurrent networks, in: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Vol. 1: Long Papers), 2017, pp. 1481\u20131491.","DOI":"10.18653\/v1\/P17-1136"},{"key":"10.1016\/j.jmgm.2023.108454_b29","unstructured":"A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A.N. Gomez, \u0141. Kaiser, I. Polosukhin, Attention is all you need, in: Advances in Neural Information Processing Systems, 2017, pp. 5998\u20136008."},{"key":"10.1016\/j.jmgm.2023.108454_b30","doi-asserted-by":"crossref","unstructured":"K. Cho, B. van Merri\u00ebnboer, D. Bahdanau, Y. Bengio, On the Properties of Neural Machine Translation: Encoder\u2013Decoder Approaches, in: Proceedings of SSST-8, Eighth Workshop on Syntax, Semantics and Structure in Statistical Translation, 2014, pp. 103\u2013111.","DOI":"10.3115\/v1\/W14-4012"},{"key":"10.1016\/j.jmgm.2023.108454_b31","unstructured":"J. Godwin, M. Schaarschmidt, A.L. Gaunt, A. Sanchez-Gonzalez, Y. Rubanova, P. Veli\u010dkovi\u0107, J. Kirkpatrick, P. Battaglia, Simple GNN regularisation for 3D molecular property prediction and beyond, in: International Conference on Learning Representations, Poster, 2022."},{"key":"10.1016\/j.jmgm.2023.108454_b32","series-title":"KPGT: Knowledge-guided pre-training of graph transformer for molecular property prediction","author":"Li","year":"2022"},{"key":"10.1016\/j.jmgm.2023.108454_b33","doi-asserted-by":"crossref","unstructured":"Z. Guo, P. Sharma, A. Martinez, L. Du, R. Abraham, Multilingual Molecular Representation Learning via Contrastive Pre-training, in: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics, (Vol. 1: Long Papers), 2022, pp. 3441\u20133453.","DOI":"10.18653\/v1\/2022.acl-long.242"},{"issue":"8","key":"10.1016\/j.jmgm.2023.108454_b34","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput."},{"key":"10.1016\/j.jmgm.2023.108454_b35","series-title":"SMILES2vec: Predicting chemical properties from text representations","author":"Goh","year":"2018"},{"key":"10.1016\/j.jmgm.2023.108454_b36","doi-asserted-by":"crossref","unstructured":"Z. Guo, W. Yu, C. Zhang, M. Jiang, N.V. Chawla, GraSeq: Graph and sequence fusion learning for molecular property prediction, in: Proceedings of the 29th ACM International Conference on Information & Knowledge Management, 2020, pp. 435\u2013443.","DOI":"10.1145\/3340531.3411981"},{"issue":"6","key":"10.1016\/j.jmgm.2023.108454_b37","doi-asserted-by":"crossref","first-page":"bbab317","DOI":"10.1093\/bib\/bbab317","article-title":"Mol2Context-vec: Learning molecular representation from context awareness for drug discovery","volume":"22","author":"Lv","year":"2021","journal-title":"Brief. Bioinform."},{"key":"10.1016\/j.jmgm.2023.108454_b38","doi-asserted-by":"crossref","unstructured":"Z. Xu, S. Wang, F. Zhu, J. Huang, Seq2seq fingerprint: An unsupervised deep molecular embedding for drug discovery, in: Proceedings of the 8th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics, 2017, pp. 285\u2013294.","DOI":"10.1145\/3107411.3107424"},{"issue":"6","key":"10.1016\/j.jmgm.2023.108454_b39","doi-asserted-by":"crossref","first-page":"2099","DOI":"10.1093\/bib\/bbz125","article-title":"A novel molecular representation with BiGRU neural networks for learning atom","volume":"21","author":"Lin","year":"2020","journal-title":"Brief. Bioinform."},{"key":"10.1016\/j.jmgm.2023.108454_b40","doi-asserted-by":"crossref","first-page":"225","DOI":"10.1016\/j.aiopen.2021.08.002","article-title":"Pre-trained models: Past, present and future","volume":"2","author":"Han","year":"2021","journal-title":"AI Open"},{"key":"10.1016\/j.jmgm.2023.108454_b41","doi-asserted-by":"crossref","unstructured":"J. Hao, X. Wang, B. Yang, L. Wang, J. Zhang, Z. Tu, Modeling Recurrence for Transformer, in: Proceedings of NAACL-HLT, 2019, pp. 1198\u20131207.","DOI":"10.18653\/v1\/N19-1122"},{"key":"10.1016\/j.jmgm.2023.108454_b42","series-title":"2021 IEEE International Conference on Bioinformatics and Biomedicine","first-page":"2896","article-title":"MolCloze: A unified cloze-style self-supervised molecular structure learning model for chemical property prediction","author":"Wang","year":"2021"},{"key":"10.1016\/j.jmgm.2023.108454_b43","first-page":"28877","article-title":"Do transformers really perform badly for graph representation?","volume":"34","author":"Ying","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"2","key":"10.1016\/j.jmgm.2023.108454_b44","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1109\/72.279181","article-title":"Learning long-term dependencies with gradient descent is difficult","volume":"5","author":"Bengio","year":"1994","journal-title":"IEEE Trans. Neural Netw."},{"issue":"2","key":"10.1016\/j.jmgm.2023.108454_b45","doi-asserted-by":"crossref","first-page":"513","DOI":"10.1039\/C7SC02664A","article-title":"MoleculeNet: A benchmark for molecular machine learning","volume":"9","author":"Wu","year":"2018","journal-title":"Chem. Sci."},{"issue":"11","key":"10.1016\/j.jmgm.2023.108454_b46","doi-asserted-by":"crossref","first-page":"2324","DOI":"10.1021\/acs.jcim.5b00559","article-title":"ZINC 15\u2013ligand discovery for everyone","volume":"55","author":"Sterling","year":"2015","journal-title":"J. Chem. Inf. Model."},{"issue":"10","key":"10.1016\/j.jmgm.2023.108454_b47","doi-asserted-by":"crossref","first-page":"1936","DOI":"10.1021\/acs.jcim.6b00290","article-title":"Computational modeling of \u03b2-secretase 1 (BACE-1) inhibitors using ligand based approaches","volume":"56","author":"Subramanian","year":"2016","journal-title":"J. Chem. Inf. Model."},{"issue":"6","key":"10.1016\/j.jmgm.2023.108454_b48","doi-asserted-by":"crossref","first-page":"1686","DOI":"10.1021\/ci300124c","article-title":"A Bayesian approach to in silico blood-brain barrier penetration modeling","volume":"52","author":"Martins","year":"2012","journal-title":"J. Chem. Inf. Model."},{"key":"10.1016\/j.jmgm.2023.108454_b49","series-title":"Massively multitask networks for drug discovery","author":"Ramsundar","year":"2015"},{"key":"10.1016\/j.jmgm.2023.108454_b50","series-title":"Neural machine translation of rare words with subword units","author":"Sennrich","year":"2015"},{"key":"10.1016\/j.jmgm.2023.108454_b51","unstructured":"W.L. Hamilton, R. Ying, J. Leskovec, Inductive representation learning on large graphs, in: Proceedings of the 31st International Conference on Neural Information Processing Systems, 2017, pp. 1025\u20131035."},{"issue":"2","key":"10.1016\/j.jmgm.2023.108454_b52","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1038\/s42256-021-00438-4","article-title":"Geometry-enhanced molecular representation learning for property prediction","volume":"4","author":"Fang","year":"2022","journal-title":"Nat. Mach. Intell."},{"key":"10.1016\/j.jmgm.2023.108454_b53","unstructured":"D.P. Kingma, J. Ba, Adam: A Method for Stochastic Optimization, in: 3rd International Conference on Learning Representations, ICLR (Poster), 2015."},{"issue":"9","key":"10.1016\/j.jmgm.2023.108454_b54","doi-asserted-by":"crossref","first-page":"2579","DOI":"10.1093\/bioinformatics\/btac112","article-title":"Advanced graph and sequence neural networks for molecular property prediction and drug discovery","volume":"38","author":"Wang","year":"2022","journal-title":"Bioinformatics"},{"key":"10.1016\/j.jmgm.2023.108454_b55","doi-asserted-by":"crossref","unstructured":"X. Zhang, S. Wang, F. Zhu, Z. Xu, Y. Wang, J. Huang, Seq3seq fingerprint: Towards end-to-end semi-supervised deep drug discovery, in: Proceedings of the 2018 ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics, 2018, pp. 404\u2013413.","DOI":"10.1145\/3233547.3233548"}],"container-title":["Journal of Molecular Graphics and Modelling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1093326323000529?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1093326323000529?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T21:14:13Z","timestamp":1761081253000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1093326323000529"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6]]},"references-count":55,"alternative-id":["S1093326323000529"],"URL":"https:\/\/doi.org\/10.1016\/j.jmgm.2023.108454","relation":{},"ISSN":["1093-3263"],"issn-type":[{"value":"1093-3263","type":"print"}],"subject":[],"published":{"date-parts":[[2023,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"NoiseMol: A noise-robusted data augmentation via perturbing noise for molecular property prediction","name":"articletitle","label":"Article Title"},{"value":"Journal of Molecular Graphics and Modelling","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.jmgm.2023.108454","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2023 Elsevier Inc. All rights reserved.","name":"copyright","label":"Copyright"}],"article-number":"108454"}}