{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T03:58:05Z","timestamp":1773719885768,"version":"3.50.1"},"reference-count":68,"publisher":"Oxford University Press (OUP)","issue":"1","license":[{"start":{"date-parts":[[2023,11,30]],"date-time":"2023-11-30T00:00:00Z","timestamp":1701302400000},"content-version":"vor","delay-in-days":8,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2022YFC3600902"],"award-info":[{"award-number":["2022YFC3600902"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Zhejiang Province Soft Science Key Project","award":["2022C25013"],"award-info":[{"award-number":["2022C25013"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,11,22]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Although substantial efforts have been made using graph neural networks (GNNs) for artificial intelligence (AI)-driven drug discovery, effective molecular representation learning remains an open challenge, especially in the case of insufficient labeled molecules. Recent studies suggest that big GNN models pre-trained by self-supervised learning on unlabeled datasets enable better transfer performance in downstream molecular property prediction tasks. However, the approaches in these studies require multiple complex self-supervised tasks and large-scale datasets , which are time-consuming, computationally expensive and difficult to pre-train end-to-end. Here, we design a simple yet effective self-supervised strategy to simultaneously learn local and global information about molecules, and further propose a novel bi-branch masked graph transformer autoencoder (BatmanNet) to learn molecular representations. BatmanNet features two tailored complementary and asymmetric graph autoencoders to reconstruct the missing nodes and edges, respectively, from a masked molecular graph. With this design, BatmanNet can effectively capture the underlying structure and semantic information of molecules, thus improving the performance of molecular representation. BatmanNet achieves state-of-the-art results for multiple drug discovery tasks, including molecular properties prediction, drug\u2013drug interaction and drug\u2013target interaction, on 13 benchmark datasets, demonstrating its great potential and superiority in molecular representation learning.<\/jats:p>","DOI":"10.1093\/bib\/bbad400","type":"journal-article","created":{"date-parts":[[2023,11,30]],"date-time":"2023-11-30T20:44:50Z","timestamp":1701377090000},"source":"Crossref","is-referenced-by-count":11,"title":["BatmanNet: bi-branch masked graph transformer autoencoder for molecular representation"],"prefix":"10.1093","volume":"25","author":[{"given":"Zhen","family":"Wang","sequence":"first","affiliation":[{"name":"College of Electrical and Information Engineering, Hunan University , Changsha, 410082, Hunan , China"},{"name":"Hangzhou Institute of Medicine, Chinese Academy of Sciences , Hangzhou, 310018, Zhejiang , China"}]},{"given":"Zheng","family":"Feng","sequence":"additional","affiliation":[{"name":"Department of Health Outcomes & Biomedical Informatics , College of Medecine, , Gainesville, 32611, FL , USA"},{"name":"University of Florida , College of Medecine, , Gainesville, 32611, FL , USA"}]},{"given":"Yanjun","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Medicinal Chemistry , College of Pharmacy, , Gainesville, 32610, FL , USA"},{"name":"University of Florida , College of Pharmacy, , Gainesville, 32610, FL , USA"},{"name":"Center for Natural Products , Drug Discovery and Development, , Gainesville, 32610, FL , USA"},{"name":"University of Florida , Drug Discovery and Development, , Gainesville, 32610, FL , USA"}]},{"given":"Bowen","family":"Li","sequence":"additional","affiliation":[{"name":"Hangzhou Institute of Medicine, Chinese Academy of Sciences , Hangzhou, 310018, Zhejiang , China"}]},{"given":"Yongrui","family":"Wang","sequence":"additional","affiliation":[{"name":"Hangzhou Institute of Medicine, Chinese Academy of Sciences , Hangzhou, 310018, Zhejiang , China"}]},{"given":"Chulin","family":"Sha","sequence":"additional","affiliation":[{"name":"Hangzhou Institute of Medicine, Chinese Academy of Sciences , Hangzhou, 310018, Zhejiang , China"}]},{"given":"Min","family":"He","sequence":"additional","affiliation":[{"name":"College of Electrical and Information Engineering, Hunan University , Changsha, 410082, Hunan , China"},{"name":"Hangzhou Institute of Medicine, Chinese Academy of Sciences , Hangzhou, 310018, Zhejiang , China"}]},{"given":"Xiaolin","family":"Li","sequence":"additional","affiliation":[{"name":"Hangzhou Institute of Medicine, Chinese Academy of Sciences , Hangzhou, 310018, Zhejiang , China"},{"name":"ElasticMind Inc , Hangzhou, 310018, Zhejiang , China"}]}],"member":"286","published-online":{"date-parts":[[2023,11,29]]},"reference":[{"issue":"10","key":"2024011119352474700_ref1","doi-asserted-by":"crossref","first-page":"1784","DOI":"10.1016\/j.drudis.2018.06.016","article-title":"Neural network and deep-learning algorithms used in QSAR studies: merits and drawbacks","volume":"23","author":"Ghasemi","year":"2018","journal-title":"Drug Discov Today"},{"issue":"18","key":"2024011119352474700_ref2","doi-asserted-by":"crossref","first-page":"E4304","DOI":"10.1073\/pnas.1803294115","article-title":"Deep learning improves prediction of drug\u2013drug and drug\u2013food interactions","volume":"115","author":"Ryu","year":"2018","journal-title":"Proc Natl Acad Sci"},{"issue":"11","key":"2024011119352474700_ref3","doi-asserted-by":"crossref","first-page":"2100","DOI":"10.2174\/0929867327666200907141016","article-title":"Deep learning in drug target interaction prediction: current and future perspectives","volume":"28","author":"Abbasi","year":"2021","journal-title":"Curr Med Chem"},{"issue":"4","key":"2024011119352474700_ref4","doi-asserted-by":"crossref","first-page":"748","DOI":"10.1016\/j.drudis.2020.03.003","article-title":"Machine learning models for drug\u2013target interactions: current knowledge and future directions","volume":"25","author":"D\u2019Souza","year":"2020","journal-title":"Drug Discov Today"},{"key":"2024011119352474700_ref5","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1109\/BIBM47256.2019.8982964","article-title":"Deepatom: a framework for protein-ligand binding affinity prediction","volume-title":"2019 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","author":"Li","year":"2019"},{"key":"2024011119352474700_ref6","doi-asserted-by":"crossref","first-page":"5550","DOI":"10.1021\/acs.jcim.2c00926","article-title":"Dyscore: a boosting scoring method with dynamic properties for identifying true binders and non-binders in structure-based drug discovery","volume":"62","author":"Li","year":"2022","journal-title":"J Chem Inf Model"},{"issue":"1","key":"2024011119352474700_ref7","doi-asserted-by":"crossref","first-page":"6775","DOI":"10.1038\/s41467-021-27137-3","article-title":"A unified drug\u2013target interaction prediction framework based on knowledge graph and recommendation system","volume":"12","author":"Ye","year":"2021","journal-title":"Nat Commun"},{"key":"2024011119352474700_ref8","first-page":"2323","article-title":"Junction tree variational autoencoder for molecular graph generation","volume-title":"International Conference on Machine Learning","author":"Jin","year":"2018"},{"key":"2024011119352474700_ref9","first-page":"4839","article-title":"Hierarchical generation of molecular graphs using structural motifs","volume-title":"International Conference on Machine Learning","author":"Jin","year":"2020"},{"issue":"10","key":"2024011119352474700_ref10","doi-asserted-by":"crossref","first-page":"914","DOI":"10.1038\/s42256-021-00403-1","article-title":"Multi-constraint molecular generation based on conditional transformer, knowledge distillation and reinforcement learning","volume":"3","author":"Wang","year":"2021","journal-title":"Nat Mach Intell"},{"key":"2024011119352474700_ref11","article-title":"Learn molecular representations from large-scale unlabeled molecules for drug discovery.","author":"Li","year":"2020"},{"key":"2024011119352474700_ref12","article-title":"A survey of pretraining on graphs: taxonomy, methods, and applications","author":"Xia","year":"2022"},{"key":"2024011119352474700_ref13","doi-asserted-by":"crossref","DOI":"10.1093\/bib\/bbab109","article-title":"An effective self-supervised framework for learning expressive molecular global representations to drug discovery","volume":"22","author":"Li","year":"2021","journal-title":"Brief Bioinform"},{"key":"2024011119352474700_ref14","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"},{"key":"2024011119352474700_ref15","article-title":"Chemberta: large-scale self-supervised pretraining for molecular property prediction.","author":"Chithrananda","year":"2020"},{"issue":"2","key":"2024011119352474700_ref16","doi-asserted-by":"crossref","first-page":"97","DOI":"10.1021\/ci00062a008","article-title":"2. Algorithm for generation of unique smiles notation","volume":"29","author":"Weininger","year":"1989","journal-title":"J Chem Inf Comput Sci"},{"key":"2024011119352474700_ref17","article-title":"Strategies for pre-training graph neural networks","author":"Hu","year":"2019"},{"key":"2024011119352474700_ref18","first-page":"12559","article-title":"Self-supervised graph transformer on large-scale molecular data","volume":"33","author":"Rong","year":"2020","journal-title":"Adv Neural Inform Process Syst"},{"key":"2024011119352474700_ref19","doi-asserted-by":"crossref","first-page":"857","DOI":"10.1145\/3534678.3539426","article-title":"Kpgt: knowledge-guided pre-training of graph transformer for molecular property prediction","volume-title":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","author":"Li","year":"2022"},{"issue":"2","key":"2024011119352474700_ref20","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"},{"issue":"7715","key":"2024011119352474700_ref21","doi-asserted-by":"crossref","first-page":"547","DOI":"10.1038\/s41586-018-0337-2","article-title":"Machine learning for molecular and materials science","volume":"559","author":"Butler","year":"2018","journal-title":"Nature"},{"key":"2024011119352474700_ref22","first-page":"1","article-title":"Admetlab: a platform for systematic admet evaluation based on a comprehensively collected admet database","volume":"10","author":"Dong","year":"2018","journal-title":"J Chem"},{"issue":"3","key":"2024011119352474700_ref23","doi-asserted-by":"crossref","first-page":"192","DOI":"10.1038\/nrd1032","article-title":"Admet in silico modelling: towards prediction paradise?","volume":"2","author":"Van De Waterbeemd","year":"2003","journal-title":"Nat Rev Drug Discov"},{"issue":"8","key":"2024011119352474700_ref24","doi-asserted-by":"crossref","first-page":"1757","DOI":"10.1021\/acs.jcim.6b00601","article-title":"Convolutional embedding of attributed molecular graphs for physical property prediction","volume":"57","author":"Coley","year":"2017","journal-title":"J Chem Inf Model"},{"key":"2024011119352474700_ref25","article-title":"Convolutional networks on graphs for learning molecular fingerprints","volume":"28","author":"Duvenaud","year":"2015","journal-title":"Adv Neural Inform Process Syst"},{"key":"2024011119352474700_ref26","doi-asserted-by":"crossref","first-page":"285","DOI":"10.1145\/3107411.3107424","article-title":"Seq2seq fingerprint: an unsupervised deep molecular embedding for drug discovery","volume-title":"Proceedings of the 8th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics","author":"Xu","year":"2017"},{"key":"2024011119352474700_ref27","article-title":"Smiles transformer: pre-trained molecular fingerprint for low data drug discovery.","author":"Honda","year":"2019"},{"issue":"1","key":"2024011119352474700_ref28","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41467-020-18671-7","article-title":"Transfer learning enables the molecular transformer to predict regio-and stereoselective reactions on carbohydrates","volume":"11","author":"Pesciullesi","year":"2020","journal-title":"Nat Commun"},{"issue":"6","key":"2024011119352474700_ref29","doi-asserted-by":"crossref","first-page":"1692","DOI":"10.1039\/C8SC04175J","article-title":"Learning continuous and data-driven molecular descriptors by translating equivalent chemical representations","volume":"10","author":"Winter","year":"2019","journal-title":"Chem Sci"},{"issue":"2","key":"2024011119352474700_ref30","doi-asserted-by":"crossref","first-page":"268","DOI":"10.1021\/acscentsci.7b00572","article-title":"Automatic chemical design using a data-driven continuous representation of molecules","volume":"4","author":"G\u00f3mez-Bombarelli","year":"2018","journal-title":"ACS Central Sci"},{"issue":"8","key":"2024011119352474700_ref31","doi-asserted-by":"crossref","first-page":"595","DOI":"10.1007\/s10822-016-9938-8","article-title":"Molecular graph convolutions: moving beyond fingerprints","volume":"30","author":"Kearnes","year":"2016","journal-title":"J Comput Aided Mol Des"},{"key":"2024011119352474700_ref32","article-title":"Schnet: a continuous-filter convolutional neural network for modeling quantum interactions","volume":"30","author":"Sch\u00fctt","year":"2017","journal-title":"Adv Neural Inform Process Syst"},{"key":"2024011119352474700_ref33","doi-asserted-by":"crossref","DOI":"10.1038\/ncomms13890","article-title":"Quantum-chemical insights from deep tensor neural networks","volume":"8","author":"Sch\u00fctt","year":"2017","journal-title":"Nat Commun"},{"key":"2024011119352474700_ref34","article-title":"Deeply learning molecular structure-property relationships using attention-and gate-augmented graph convolutional network.","author":"Ryu","year":"2018"},{"issue":"16","key":"2024011119352474700_ref35","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"},{"key":"2024011119352474700_ref36","article-title":"Graph attention networks.","author":"Veli\u010dkovi\u0107","year":"2017"},{"key":"2024011119352474700_ref37","first-page":"1263","article-title":"Neural message passing for quantum chemistry","volume-title":"International Conference on Machine Learning","author":"Gilmer","year":"2017"},{"key":"2024011119352474700_ref38","article-title":"Directional message passing for molecular graphs","author":"Gasteiger","year":"2020"},{"issue":"8","key":"2024011119352474700_ref39","doi-asserted-by":"crossref","first-page":"3370","DOI":"10.1021\/acs.jcim.9b00237","article-title":"Analyzing learned molecular representations for property prediction","volume":"59","author":"Yang","year":"2019","journal-title":"J Chem Inf Model"},{"key":"2024011119352474700_ref40","first-page":"1052","article-title":"Molecular property prediction: a multilevel quantum interactions modeling perspective","volume-title":":Proceedings of the AAAI Conference on Artificial Intelligence","author":"Chengqiang","year":"2019"},{"key":"2024011119352474700_ref41","first-page":"16000","article-title":"Masked autoencoders are scalable vision learners","author":"He","year":"2022"},{"key":"2024011119352474700_ref42","article-title":"Bert: pre-training of deep bidirectional transformers for language understanding.","author":"Devlin","year":"2018"},{"key":"2024011119352474700_ref43","article-title":"N-gram graph: simple unsupervised representation for graphs, with applications to molecules","volume":"32","author":"Liu","year":"2019","journal-title":"Adv Neural Inform Process Syst"},{"key":"2024011119352474700_ref44","article-title":"Graph masked autoencoder","author":"Chen","year":"2022"},{"key":"2024011119352474700_ref45","article-title":"Mgae: masked autoencoders for self-supervised learning on graphs.","author":"Tan","year":"2022"},{"key":"2024011119352474700_ref46","article-title":"Pre-training molecular graph representation with 3d geometry","volume-title":"International Conference on Learning Representations","author":"Liu","year":"2021"},{"key":"2024011119352474700_ref47","doi-asserted-by":"crossref","DOI":"10.1145\/3534678.3539321","article-title":"Graphmae: self-supervised masked graph autoencoders.","author":"Hou","year":"2022"},{"key":"2024011119352474700_ref48","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv Neural Inform Process Syst"},{"key":"2024011119352474700_ref49","article-title":"Supervised community detection with line graph neural networks.","author":"Chen","year":"2017"},{"issue":"5","key":"2024011119352474700_ref50","doi-asserted-by":"crossref","first-page":"742","DOI":"10.1021\/ci100050t","article-title":"Extended-connectivity fingerprints","volume":"50","author":"Rogers","year":"2010","journal-title":"J Chem Inf Model"},{"key":"2024011119352474700_ref51","article-title":"Massively multitask networks for drug discovery.","author":"Ramsundar","year":"2015"},{"key":"2024011119352474700_ref52","article-title":"Semi-supervised classification with graph convolutional networks","volume-title":"International Conference on Learning Representations","author":"Welling","year":"2017"},{"issue":"4","key":"2024011119352474700_ref53","doi-asserted-by":"crossref","first-page":"bbaa266","DOI":"10.1093\/bib\/bbaa266","article-title":"Trimnet: learning molecular representation from triplet messages for biomedicine","volume":"22","author":"Li","year":"2021","journal-title":"Brief Bioinform"},{"issue":"1","key":"2024011119352474700_ref54","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1021\/acs.jcim.7b00616","article-title":"Mol2vec: unsupervised machine learning approach with chemical intuition","volume":"58","author":"Jaeger","year":"2018","journal-title":"J Chem Inf Model"},{"key":"2024011119352474700_ref55","first-page":"1945","article-title":"Grammar variational autoencoder","volume-title":"International Conference on Machine Learning","author":"Kusner","year":"2017"},{"issue":"11","key":"2024011119352474700_ref56","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"},{"key":"2024011119352474700_ref57","article-title":"Adam: a method for stochastic optimization.","author":"Kingma","year":"2014"},{"key":"2024011119352474700_ref58","first-page":"8024","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume-title":"Advances in Neural Information Processing Systems 32","author":"Paszke","year":"2019"},{"key":"2024011119352474700_ref59","article-title":"Umap: uniform manifold approximation and projection for dimension reduction","author":"McInnes","year":"2018"},{"issue":"2","key":"2024011119352474700_ref60","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"},{"issue":"15","key":"2024011119352474700_ref61","doi-asserted-by":"crossref","first-page":"2887","DOI":"10.1021\/jm9602928","article-title":"The properties of known drugs. 1. Molecular frameworks","volume":"39","author":"Bemis","year":"1996","journal-title":"J Med Chem"},{"key":"2024011119352474700_ref62","volume-title":"Deep Learning for the Life Sciences: Applying Deep Learning to Genomics, Microscopy, Drug Discovery, and More","author":"Ramsundar","year":"2019"},{"issue":"9","key":"2024011119352474700_ref63","doi-asserted-by":"crossref","first-page":"2147","DOI":"10.1038\/nprot.2014.151","article-title":"Similarity-based modeling in large-scale prediction of drug-drug interactions","volume":"9","author":"Vilar","year":"2014","journal-title":"Nat Protoc"},{"key":"2024011119352474700_ref64","first-page":"702","article-title":"Caster: predicting drug interactions with chemical substructure representation","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"Huang","year":"2020"},{"issue":"2","key":"2024011119352474700_ref65","doi-asserted-by":"crossref","first-page":"309","DOI":"10.1093\/bioinformatics\/bty535","article-title":"Compound\u2013protein interaction prediction with end-to-end learning of neural networks for graphs and sequences","volume":"35","author":"Tsubaki","year":"2019","journal-title":"Bioinformatics"},{"key":"2024011119352474700_ref66","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12859-019-3214-6","article-title":"Ddi-pulearn: a positive-unlabeled learning method for large-scale prediction of drug-drug interactions","volume":"20","author":"Zheng","year":"2019","journal-title":"BMC Bioinformatics"},{"key":"2024011119352474700_ref67","article-title":"Biosnap datasets: Stanford biomedical network dataset collection","author":"Zitnik","year":"2018"},{"issue":"125","key":"2024011119352474700_ref68","doi-asserted-by":"crossref","first-page":"125ra31","DOI":"10.1126\/scitranslmed.3003377","article-title":"Data-driven prediction of drug effects and interactions","volume":"4","author":"Tatonetti","year":"2012","journal-title":"Sci Transl Med"}],"container-title":["Briefings in Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/25\/1\/bbad400\/55464882\/bbad400.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/25\/1\/bbad400\/55464882\/bbad400.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,11]],"date-time":"2024-01-11T19:36:11Z","timestamp":1705001771000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bib\/article\/doi\/10.1093\/bib\/bbad400\/7455246"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,22]]},"references-count":68,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2023,11,22]]}},"URL":"https:\/\/doi.org\/10.1093\/bib\/bbad400","relation":{},"ISSN":["1467-5463","1477-4054"],"issn-type":[{"value":"1467-5463","type":"print"},{"value":"1477-4054","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024,1,1]]},"published":{"date-parts":[[2023,11,22]]},"article-number":"bbad400"}}