{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T18:48:45Z","timestamp":1775760525158,"version":"3.50.1"},"reference-count":38,"publisher":"Oxford University Press (OUP)","issue":"4","license":[{"start":{"date-parts":[[2024,3,26]],"date-time":"2024-03-26T00:00:00Z","timestamp":1711411200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62072384"],"award-info":[{"award-number":["62072384"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61872309"],"award-info":[{"award-number":["61872309"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62072385"],"award-info":[{"award-number":["62072385"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61772441"],"award-info":[{"award-number":["61772441"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,3,29]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>Molecular representation learning plays an indispensable role in crucial tasks such as property prediction and drug design. Despite the notable achievements of molecular pre-training models, current methods often fail to capture both the structural and feature semantics of molecular graphs. Moreover, while graph contrastive learning has unveiled new prospects, existing augmentation techniques often struggle to retain their core semantics. To overcome these limitations, we propose a gradient-compensated encoder parameter perturbation approach, ensuring efficient and stable feature augmentation. By merging enhancement strategies grounded in attribute masking and parameter perturbation, we introduce MoleMCL, a new MOLEcular pre-training model based on multi-level contrastive learning.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>Experimental results demonstrate that MoleMCL adeptly dissects the structure and feature semantics of molecular graphs, surpassing current state-of-the-art models in molecular prediction tasks, paving a novel avenue for molecular modeling.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>The code and data underlying this work are available in GitHub at https:\/\/github.com\/BioSequenceAnalysis\/MoleMCL.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btae164","type":"journal-article","created":{"date-parts":[[2024,3,26]],"date-time":"2024-03-26T19:55:40Z","timestamp":1711482940000},"source":"Crossref","is-referenced-by-count":10,"title":["MoleMCL: a multi-level contrastive learning framework for molecular pre-training"],"prefix":"10.1093","volume":"40","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-9618-5799","authenticated-orcid":false,"given":"Xinyi","family":"Zhang","sequence":"first","affiliation":[{"name":"Department of Computer Science and Technology, Xiamen University , Xiamen 361005, China"}]},{"given":"Yanni","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Xiamen University , Xiamen 361005, China"}]},{"given":"Changzhi","family":"Jiang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Xiamen University , Xiamen 361005, China"}]},{"given":"Lian","family":"Shen","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Xiamen University , Xiamen 361005, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9885-1978","authenticated-orcid":false,"given":"Xiangrong","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Xiamen University , Xiamen 361005, China"},{"name":"National Institute for Data Science in Health and Medicine, Xiamen University , Xiamen 361005, China"}]}],"member":"286","published-online":{"date-parts":[[2024,3,26]]},"reference":[{"key":"2024040900213780800_btae164-B1","first-page":"1597","author":"Chen","year":"2020"},{"key":"2024040900213780800_btae164-B2","first-page":"4171","article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019","journal-title":"NAACL-HLT, Minneapolis, MN, USA"},{"key":"2024040900213780800_btae164-B3","first-page":"1180","author":"Ganin","year":"2015"},{"key":"2024040900213780800_btae164-B4","doi-asserted-by":"crossref","first-page":"D1100","DOI":"10.1093\/nar\/gkr777","article-title":"Chembl: a large-scale bioactivity database for drug discovery","volume":"40","author":"Gaulton","year":"2012","journal-title":"Nucleic Acids Res"},{"key":"2024040900213780800_btae164-B5","doi-asserted-by":"crossref","first-page":"4284","DOI":"10.1609\/aaai.v37i4.25547","article-title":"MA-GCL: model augmentation tricks for graph contrastive learning","volume":"37","author":"Gong","year":"2023","journal-title":"AAAI"},{"key":"2024040900213780800_btae164-B6","author":"Goodfellow","year":"2015"},{"key":"2024040900213780800_btae164-B7","author":"Grill","year":"2020"},{"key":"2024040900213780800_btae164-B8","first-page":"1024","author":"Hamilton","year":"2017"},{"key":"2024040900213780800_btae164-B9","first-page":"9726","author":"He","year":"2020"},{"key":"2024040900213780800_btae164-B10","first-page":"594","author":"Hou","year":"2022"},{"key":"2024040900213780800_btae164-B11","first-page":"813","author":"Hu","year":"2023"},{"key":"2024040900213780800_btae164-B12","author":"Hu"},{"key":"2024040900213780800_btae164-B13","doi-asserted-by":"crossref","first-page":"161102","DOI":"10.1063\/1.4964627","article-title":"Communication: understanding molecular representations in machine learning: the role of uniqueness and target similarity","volume":"145","author":"Huang","year":"2016","journal-title":"J Chem Phys"},{"key":"2024040900213780800_btae164-B14","doi-asserted-by":"crossref","first-page":"573","DOI":"10.1038\/s42256-020-00236-4","article-title":"Drug discovery with explainable artificial intelligence","volume":"2","author":"Jim\u00e9nez-Luna","year":"2020","journal-title":"Nat Mach Intell"},{"key":"2024040900213780800_btae164-B15","author":"Kipf","year":"2017"},{"key":"2024040900213780800_btae164-B16","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pcbi.1011214","article-title":"Bioseq-diabolo: biological sequence similarity analysis using diabolo","volume":"19","author":"Li","year":"2023","journal-title":"PLoS Comput Biol"},{"key":"2024040900213780800_btae164-B17","doi-asserted-by":"crossref","first-page":"e129","DOI":"10.1093\/nar\/gkab829","article-title":"Bioseq-blm: a platform for analyzing DNA, RNA and protein sequences based on biological language models","volume":"49","author":"Li","year":"2021","journal-title":"Nucleic Acids Res"},{"key":"2024040900213780800_btae164-B18","author":"Liu","year":"2022"},{"key":"2024040900213780800_btae164-B19","author":"Madry","year":"2018"},{"key":"2024040900213780800_btae164-B20","author":"Mesquita","year":"2020"},{"key":"2024040900213780800_btae164-B21","author":"Miyato","year":"2017"},{"key":"2024040900213780800_btae164-B22","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1038\/s42256-022-00463-x","article-title":"The transformational role of GPU computing and deep learning in drug discovery","volume":"4","author":"Pandey","year":"2022","journal-title":"Nat Mach Intell"},{"key":"2024040900213780800_btae164-B23","doi-asserted-by":"crossref","first-page":"1872","DOI":"10.1007\/s11431-020-1647-3","article-title":"Pre-trained models for natural language processing: a survey","volume":"63","author":"Qiu","year":"2020","journal-title":"Sci China Technol Sci"},{"key":"2024040900213780800_btae164-B24","volume-title":"Deep Learning for the Life Sciences: Applying Deep Learning to Genomics, Microscopy, Drug Discovery, and More.","author":"Ramsundar","year":"2019"},{"key":"2024040900213780800_btae164-B25","doi-asserted-by":"crossref","first-page":"2324","DOI":"10.1021\/acs.jcim.5b00559","article-title":"ZINC 15: ligand discovery for everyone","volume":"55","author":"Sterling","year":"2015","journal-title":"J Chem Inf Model"},{"key":"2024040900213780800_btae164-B26","doi-asserted-by":"crossref","first-page":"14360","DOI":"10.1021\/acsomega.9b02221","article-title":"Evolving concept of activity cliffs","volume":"4","author":"Stumpfe","year":"2019","journal-title":"ACS Omega"},{"key":"2024040900213780800_btae164-B27","author":"Sun","year":"2020"},{"key":"2024040900213780800_btae164-B28","first-page":"3585","author":"Sun","year":"2021"},{"key":"2024040900213780800_btae164-B29","author":"Veli\u010dkovi\u0107","year":"2019"},{"key":"2024040900213780800_btae164-B30","first-page":"9929","author":"Wang","year":"2020"},{"key":"2024040900213780800_btae164-B31","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"},{"key":"2024040900213780800_btae164-B32","first-page":"1070","author":"Xia","year":"2022"},{"key":"2024040900213780800_btae164-B33","author":"Xia","year":"2023"},{"key":"2024040900213780800_btae164-B34","first-page":"6787","author":"Xia","year":"2023"},{"key":"2024040900213780800_btae164-B35","author":"Xu","year":"2019"},{"key":"2024040900213780800_btae164-B36","author":"You","year":"2020"},{"key":"2024040900213780800_btae164-B37","first-page":"12121","author":"You","year":"2021"},{"key":"2024040900213780800_btae164-B38","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"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btae164\/57094088\/btae164.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/40\/4\/btae164\/57185943\/btae164.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/40\/4\/btae164\/57185943\/btae164.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,9]],"date-time":"2024-04-09T00:31:15Z","timestamp":1712622675000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btae164\/7635159"}},"subtitle":[],"editor":[{"given":"Jonathan","family":"Wren","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2024,3,26]]},"references-count":38,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2024,3,29]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btae164","relation":{},"ISSN":["1367-4811"],"issn-type":[{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024,4,1]]},"published":{"date-parts":[[2024,3,26]]},"article-number":"btae164"}}