{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T21:34:22Z","timestamp":1784583262333,"version":"3.55.0"},"reference-count":53,"publisher":"Oxford University Press (OUP)","issue":"4","license":[{"start":{"date-parts":[[2024,5,27]],"date-time":"2024-05-27T00:00:00Z","timestamp":1716768000000},"content-version":"vor","delay-in-days":4,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100018625","name":"Science and Technology Innovation Plan of Shanghai Science and Technology Commission","doi-asserted-by":"crossref","award":["23S41900400"],"award-info":[{"award-number":["23S41900400"]}],"id":[{"id":"10.13039\/501100018625","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62076070"],"award-info":[{"award-number":["62076070"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,5,23]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Self-supervised learning plays an important role in molecular representation learning because labeled molecular data are usually limited in many tasks, such as chemical property prediction and virtual screening. However, most existing molecular pre-training methods focus on one modality of molecular data, and the complementary information of two important modalities, SMILES and graph, is not fully explored. In this study, we propose an effective multi-modality self-supervised learning framework for molecular SMILES and graph. Specifically, SMILES data and graph data are first tokenized so that they can be processed by a unified Transformer-based backbone network, which is trained by a masked reconstruction strategy. In addition, we introduce a specialized non-overlapping masking strategy to encourage fine-grained interaction between these two modalities. Experimental results show that our framework achieves state-of-the-art performance in a series of molecular property prediction tasks, and a detailed ablation study demonstrates efficacy of the multi-modality framework and the masking strategy.<\/jats:p>","DOI":"10.1093\/bib\/bbae256","type":"journal-article","created":{"date-parts":[[2024,5,27]],"date-time":"2024-05-27T15:40:51Z","timestamp":1716824451000},"source":"Crossref","is-referenced-by-count":16,"title":["Complementary multi-modality molecular self-supervised learning via non-overlapping masking for property prediction"],"prefix":"10.1093","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-1937-6855","authenticated-orcid":false,"given":"Ao","family":"Shen","sequence":"first","affiliation":[{"name":"Digital Medical Research Center , School of Basic Medical Sciences, , 131 Dong\u2019an Road, 200032, Shanghai , China"},{"name":"Fudan University , School of Basic Medical Sciences, , 131 Dong\u2019an Road, 200032, Shanghai , China"},{"name":"Shanghai Key Laboratory of Medical Image Computing and Computer Assisted Intervention, Fudan University , 131 Dong\u2019an Road, 200032, Shanghai , China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1322-7530","authenticated-orcid":false,"given":"Mingzhi","family":"Yuan","sequence":"additional","affiliation":[{"name":"Digital Medical Research Center , School of Basic Medical Sciences, , 131 Dong\u2019an Road, 200032, Shanghai , China"},{"name":"Fudan University , School of Basic Medical Sciences, , 131 Dong\u2019an Road, 200032, Shanghai , China"},{"name":"Shanghai Key Laboratory of Medical Image Computing and Computer Assisted Intervention, Fudan University , 131 Dong\u2019an Road, 200032, Shanghai , China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-7335-785X","authenticated-orcid":false,"given":"Yingfan","family":"Ma","sequence":"additional","affiliation":[{"name":"Digital Medical Research Center , School of Basic Medical Sciences, , 131 Dong\u2019an Road, 200032, Shanghai , China"},{"name":"Fudan University , School of Basic Medical Sciences, , 131 Dong\u2019an Road, 200032, Shanghai , China"},{"name":"Shanghai Key Laboratory of Medical Image Computing and Computer Assisted Intervention, Fudan University , 131 Dong\u2019an Road, 200032, Shanghai , China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Du","sequence":"additional","affiliation":[{"name":"Digital Medical Research Center , School of Basic Medical Sciences, , 131 Dong\u2019an Road, 200032, Shanghai , China"},{"name":"Fudan University , School of Basic Medical Sciences, , 131 Dong\u2019an Road, 200032, Shanghai , China"},{"name":"Shanghai Key Laboratory of Medical Image Computing and Computer Assisted Intervention, Fudan University , 131 Dong\u2019an Road, 200032, Shanghai , China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9255-3897","authenticated-orcid":false,"given":"Manning","family":"Wang","sequence":"additional","affiliation":[{"name":"Digital Medical Research Center , School of Basic Medical Sciences, , 131 Dong\u2019an Road, 200032, Shanghai , China"},{"name":"Fudan University , School of Basic Medical Sciences, , 131 Dong\u2019an Road, 200032, Shanghai , China"},{"name":"Shanghai Key Laboratory of Medical Image Computing and Computer Assisted Intervention, Fudan University , 131 Dong\u2019an Road, 200032, Shanghai , China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2024,5,27]]},"reference":[{"issue":"2","key":"2024052715404274600_ref1","doi-asserted-by":"crossref","first-page":"263","DOI":"10.1021\/acs.accounts.0c00699","article-title":"Applications of deep learning in molecule generation and molecular property prediction","volume":"54","author":"Patrick Walters","year":"2020","journal-title":"Acc Chem Res"},{"issue":"6","key":"2024052715404274600_ref2","doi-asserted-by":"crossref","first-page":"bbad398","DOI":"10.1093\/bib\/bbad398","article-title":"Fg-bert: a generalized and self-supervised functional group-based molecular representation learning framework for properties prediction","volume":"24","author":"Li","year":"2023","journal-title":"Brief Bioinform"},{"issue":"9","key":"2024052715404274600_ref3","doi-asserted-by":"crossref","first-page":"653","DOI":"10.1038\/s41570-022-00416-3","article-title":"Extending machine learning beyond interatomic potentials for predicting molecular properties","volume":"6","author":"Fedik","year":"2022","journal-title":"Nat Rev Chem"},{"issue":"12","key":"2024052715404274600_ref4","doi-asserted-by":"crossref","first-page":"1023","DOI":"10.1038\/s42256-021-00418-8","article-title":"Geometric deep learning on molecular representations","volume":"3","author":"Atz","year":"2021","journal-title":"Nat Mach Intelle"},{"issue":"5","key":"2024052715404274600_ref5","doi-asserted-by":"crossref","first-page":"bbad306","DOI":"10.1093\/bib\/bbad306","article-title":"Transfoxmol: predicting molecular property with focused attention","volume":"24","author":"Gao","year":"2023","journal-title":"Brief Bioinform"},{"issue":"3","key":"2024052715404274600_ref6","doi-asserted-by":"crossref","first-page":"1096","DOI":"10.1021\/acs.jcim.8b00839","article-title":"Guacamol: benchmarking models for de novo molecular design","volume":"59","author":"Brown","year":"2019","journal-title":"J Chem Inf Model"},{"key":"2024052715404274600_ref7","first-page":"12559","article-title":"Self-supervised graph transformer on large-scale molecular data","volume":"33","author":"Rong","year":"2020","journal-title":"Adv Neural Inf Process Syst"},{"issue":"12","key":"2024052715404274600_ref8","doi-asserted-by":"crossref","first-page":"btad724","DOI":"10.1093\/bioinformatics\/btad724","article-title":"Proteinmae: masked autoencoder for protein surface self-supervised learning","volume":"39","author":"Yuan","year":"2023","journal-title":"Bioinformatics"},{"issue":"2","key":"2024052715404274600_ref9","doi-asserted-by":"crossref","first-page":"2412","DOI":"10.1109\/TPAMI.2022.3170559","article-title":"Self-supervised learning of graph neural networks: a unified review","volume":"45","author":"Xie","year":"2022","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2024052715404274600_ref10","doi-asserted-by":"crossref","DOI":"10.24963\/ijcai.2023\/760","article-title":"A systematic survey of chemical pre-trained models","volume-title":"Proceedings of the 32nd International Joint Conference on Artificial Intelligence","author":"Xia","year":"2023"},{"key":"2024052715404274600_ref11","article-title":"Chemberta: large-scale self-supervised pretraining for molecular property prediction","author":"Chithrananda","year":"2020"},{"key":"2024052715404274600_ref12","doi-asserted-by":"crossref","first-page":"429","DOI":"10.1145\/3307339.3342186","article-title":"Smiles-bert: large scale unsupervised pre-training for molecular property prediction","volume-title":"Proceedings of the 10th ACM international conference on bioinformatics, computational biology and health informatics","author":"Wang","year":"2019"},{"issue":"1","key":"2024052715404274600_ref13","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":"1","key":"2024052715404274600_ref14","first-page":"1","article-title":"Using smiles strings for the description of chemical connectivity in the crystallography open database","volume":"10","author":"Quir\u00f3s","year":"2018","journal-title":"J Chem"},{"key":"2024052715404274600_ref15","first-page":"1541","article-title":"A review on compound-protein interaction prediction methods: data, format, representation and model. Computational and structural","volume":"19","author":"Lim","year":"2021","journal-title":"Biotechnol J"},{"key":"2024052715404274600_ref16","doi-asserted-by":"crossref","first-page":"102327","DOI":"10.1016\/j.sbi.2021.102327","article-title":"Graph neural network approaches for drug-target interactions","volume":"73","author":"Zhang","year":"2022","journal-title":"Curr Opin Struct Biol"},{"issue":"16","key":"2024052715404274600_ref17","doi-asserted-by":"crossref","first-page":"8749","DOI":"10.1021\/acs.jmedchem.9b00959","article-title":"Pushing the boundaries of molecular representation for drug discovery with the graph attention mechanism","volume":"63","author":"Xiong","year":"2019","journal-title":"J Med Chem"},{"issue":"1","key":"2024052715404274600_ref18","doi-asserted-by":"crossref","first-page":"76","DOI":"10.1021\/ci00001a012","article-title":"The electrotopological state: structure information at the atomic level for molecular graphs","volume":"31","author":"Hall","year":"1991","journal-title":"J Chem Inf Comput Sci"},{"key":"2024052715404274600_ref19","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1016\/j.aiopen.2021.01.001","article-title":"Graph neural networks: a review of methods and applications","volume":"1","author":"Zhou","year":"2020","journal-title":"AI open"},{"key":"2024052715404274600_ref20","article-title":"Pre-training molecular graph representation with 3d geometry","volume-title":"Proceedings of the Tenth International Conference on Learning Representations","author":"Liu"},{"key":"2024052715404274600_ref21","article-title":"Dual-view molecule pre-training","volume-title":"Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","author":"Zhu"},{"issue":"3","key":"2024052715404274600_ref22","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1038\/s42256-022-00447-x","article-title":"Molecular contrastive learning of representations via graph neural networks","volume":"4","author":"Wang","year":"2022","journal-title":"Nat Mach Intell"},{"key":"2024052715404274600_ref23","doi-asserted-by":"crossref","DOI":"10.1038\/s42256-023-00759-6","article-title":"Multi-modal molecule structure-text model for text-based retrieval and editing","volume-title":"Nat Mach Intell","author":"Liu"},{"key":"2024052715404274600_ref24","article-title":"Improving molecular pretraining with complementary featurizations","author":"Zhu","year":"2022"},{"key":"2024052715404274600_ref25","first-page":"5291","article-title":"Pimae: point cloud and image interactive masked autoencoders for 3d object detection","author":"Chen","year":"2023","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"2024052715404274600_ref26","first-page":"348","article-title":"Multimae: Multi-modal multi-task masked autoencoders","volume-title":"European Conference on Computer Vision","author":"Bachmann","year":"2022"},{"key":"2024052715404274600_ref27","article-title":"Mutex: learning unified policies from multimodal task specifications","volume-title":"Conference on Robot Learning (CoRL)","author":"Shah","year":"2023"},{"key":"2024052715404274600_ref28","article-title":"Boosting point-bert by multi-choice tokens","volume":"34","author":"Kexue","year":"2024","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"2024052715404274600_ref29","first-page":"e2301223","article-title":"A multimodal protein representation framework for quantifying transferability across biochemical downstream tasks. Advanced","volume":"10","author":"Fan","year":"2023","journal-title":"Science"},{"key":"2024052715404274600_ref30","article-title":"Frozen clip model is efficient point cloud backbone","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"Huang"},{"issue":"5","key":"2024052715404274600_ref31","doi-asserted-by":"crossref","first-page":"323","DOI":"10.1093\/bfgp\/elab036","article-title":"Review of unsupervised pretraining strategies for molecules representation","volume":"20","author":"Linhui","year":"2021","journal-title":"Brief Funct Genomics"},{"key":"2024052715404274600_ref32","first-page":"12096","article-title":"Does gnn pretraining help molecular representation","volume":"35","author":"Sun","year":"2022","journal-title":"Adv Neural Inf Process Syst"},{"key":"2024052715404274600_ref33","first-page":"2021","article-title":"Mol-bert: an effective molecular representation with bert for molecular property prediction","volume":"1\u20137","author":"Li","year":"2021","journal-title":"Wireless Commun Mobile Comput"},{"issue":"6","key":"2024052715404274600_ref34","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"},{"issue":"17","key":"2024052715404274600_ref35","doi-asserted-by":"crossref","first-page":"3948","DOI":"10.1021\/acs.jcim.2c00521","article-title":"Smiclr: contrastive learning on multiple molecular representations for semisupervised and unsupervised representation learning","volume":"62","author":"Pinheiro","year":"2022","journal-title":"J Chem Inf Model"},{"key":"2024052715404274600_ref36","article-title":"Unimap: universal smiles-graph representation learning","author":"Feng","year":"2023"},{"key":"2024052715404274600_ref37","article-title":"Roberta: a robustly optimized bert pretraining approach","author":"Liu","year":"2019"},{"key":"2024052715404274600_ref38","doi-asserted-by":"crossref","DOI":"10.24963\/ijcai.2021\/309","article-title":"Learning attributed graph representations with communicative message passing transformer","volume-title":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","author":"Chen"},{"key":"2024052715404274600_ref39","article-title":"Keyulu Xu, Weihua Hu, jure Leskovec","volume-title":"Proceedings of the 7th International Conference on Learning Representations"},{"key":"2024052715404274600_ref40","doi-asserted-by":"crossref","first-page":"594","DOI":"10.1145\/3534678.3539321","article-title":"Graphmae: Self-supervised masked graph autoencoders","volume-title":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","author":"Hou","year":"2022"},{"key":"2024052715404274600_ref41","first-page":"1263","article-title":"Neural message passing for quantum chemistry","volume-title":"International conference on machine learning","author":"Gilmer","year":"2017"},{"key":"2024052715404274600_ref42","article-title":"Are learned molecular representations ready for prime time","author":"Yang","year":"2019"},{"key":"2024052715404274600_ref43","first-page":"2831","article-title":"Communicative representation learning on attributed molecular graphs","volume":"2020","author":"Song","year":"2020","journal-title":"In IJCAI"},{"key":"2024052715404274600_ref44","doi-asserted-by":"crossref","first-page":"435","DOI":"10.1145\/3340531.3411981","article-title":"Graseq: graph and sequence fusion learning for molecular property prediction","volume-title":"Proceedings of the 29th ACM international conference on information & knowledge management","author":"Guo","year":"2020"},{"key":"2024052715404274600_ref45","article-title":"N-gram graph: simple unsupervised representation for graphs, with applications to molecules","volume":"32","author":"Liu","year":"2019","journal-title":"Adv Neural Inf Process Syst"},{"key":"2024052715404274600_ref46","article-title":"Strategies for pre-training graph neural networks","volume-title":"Proceedings of the 8th International Conference on Learning Representations","author":"Hu"},{"key":"2024052715404274600_ref47","first-page":"15870","article-title":"Motif-based graph self-supervised learning for molecular property prediction","volume":"34","author":"Zhang","year":"2021","journal-title":"Adv Neural Inf Process Syst"},{"issue":"2","key":"2024052715404274600_ref48","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":"2024052715404274600_ref49","doi-asserted-by":"crossref","DOI":"10.26434\/chemrxiv-2023-dngg4","article-title":"Mole-bert: Rethinking pre-training graph neural networks for molecules","volume-title":"The Eleventh International Conference on Learning Representations","author":"Xia","year":"2023"},{"key":"2024052715404274600_ref50","first-page":"1","article-title":"Knowledge graph-enhanced molecular contrastive learning with functional prompt","author":"Fang","year":"2023","journal-title":"Nat Mach Intell"},{"issue":"11","key":"2024052715404274600_ref51","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":"2","key":"2024052715404274600_ref52","doi-asserted-by":"crossref","first-page":"513","DOI":"10.1039\/C7SC02664A","article-title":"Moleculenet: a benchmark for molecular machine learning","volume":"9","author":"Zhenqin","year":"2018","journal-title":"Chem Sci"},{"key":"2024052715404274600_ref53","volume-title":"Deep learning for the life sciences: applying deep learning to genomics, microscopy, drug discovery, and more","author":"Ramsundar","year":"2019"}],"container-title":["Briefings in Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/25\/4\/bbae256\/57927570\/bbae256.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/25\/4\/bbae256\/57927570\/bbae256.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,27]],"date-time":"2024-05-27T15:41:26Z","timestamp":1716824486000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bib\/article\/doi\/10.1093\/bib\/bbae256\/7683166"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,23]]},"references-count":53,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2024,5,23]]}},"URL":"https:\/\/doi.org\/10.1093\/bib\/bbae256","relation":{},"ISSN":["1467-5463","1477-4054"],"issn-type":[{"value":"1467-5463","type":"print"},{"value":"1477-4054","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024,7]]},"published":{"date-parts":[[2024,5,23]]},"article-number":"bbae256"}}