{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,29]],"date-time":"2026-08-29T11:14:08Z","timestamp":1788002048210,"version":"build-2784847793"},"reference-count":45,"publisher":"Elsevier BV","issue":"12","license":[{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2025,10,7]],"date-time":"2025-10-07T00:00:00Z","timestamp":1759795200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003512","name":"State Administration of Foreign Experts Affairs","doi-asserted-by":"publisher","award":["H20240802"],"award-info":[{"award-number":["H20240802"]}],"id":[{"id":"10.13039\/501100003512","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006579","name":"Ministry of Industry and Information Technology of the People's Republic of China","doi-asserted-by":"publisher","award":["GN2024-31-4700"],"award-info":[{"award-number":["GN2024-31-4700"]}],"id":[{"id":"10.13039\/501100006579","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005150","name":"Chinese Academy of Medical Sciences","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100005150","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62573367"],"award-info":[{"award-number":["62573367"]}],"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":["62472363"],"award-info":[{"award-number":["62472363"]}],"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":["62173282"],"award-info":[{"award-number":["62173282"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100019018","name":"CAMS Innovation Fund for Medical Sciences","doi-asserted-by":"publisher","award":["2021-I2M-1\\u2013069"],"award-info":[{"award-number":["2021-I2M-1\\u2013069"]}],"id":[{"id":"10.13039\/501100019018","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Journal of Pharmaceutical Analysis"],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1016\/j.jpha.2025.101465","type":"journal-article","created":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T04:07:08Z","timestamp":1760069228000},"page":"101465","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":3,"title":["Geometry-based BERT: An experimentally validated deep learning model for molecular property prediction in drug discovery"],"prefix":"10.1016","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-8564-7699","authenticated-orcid":false,"given":"Xiang","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenliang","family":"Qian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bochao","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongwei","family":"Jin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Song","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9567-3763","authenticated-orcid":false,"given":"Jie","family":"Xia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3523-1138","authenticated-orcid":false,"given":"Fan","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liangren","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.jpha.2025.101465_bib1","doi-asserted-by":"crossref","DOI":"10.1016\/j.ejps.2022.106324","article-title":"CADD, AI and ML in drug discovery: A comprehensive review","volume":"181","author":"Vemula","year":"2023","journal-title":"Eur. J. Pharm. Sci."},{"key":"10.1016\/j.jpha.2025.101465_bib2","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1016\/j.jhealeco.2016.01.012","article-title":"Innovation in the pharmaceutical industry: New estimates of R&D costs","volume":"47","author":"DiMasi","year":"2016","journal-title":"J. Health Econ."},{"key":"10.1016\/j.jpha.2025.101465_bib3","doi-asserted-by":"crossref","first-page":"152","DOI":"10.1007\/s11705-021-2060-z","article-title":"A computational toolbox for molecular property prediction based on quantum mechanics and quantitative structure-property relationship","volume":"16","author":"Liu","year":"2022","journal-title":"Front. Chem. Sci. Eng."},{"key":"10.1016\/j.jpha.2025.101465_bib4","doi-asserted-by":"crossref","DOI":"10.1016\/j.drudis.2022.103373","article-title":"Deep learning methods for molecular representation and property prediction","volume":"27","author":"Li","year":"2022","journal-title":"Drug Discov. Today"},{"key":"10.1016\/j.jpha.2025.101465_bib5","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":"10.1016\/j.jpha.2025.101465_bib6","doi-asserted-by":"crossref","first-page":"1273","DOI":"10.1021\/ci010132r","article-title":"Reoptimization of MDL keys for use in drug discovery","volume":"42","author":"Durant","year":"2002","journal-title":"J. Chem. Inf. Comput. Sci."},{"key":"10.1016\/j.jpha.2025.101465_bib7","doi-asserted-by":"crossref","DOI":"10.1016\/j.drudis.2022.103356","article-title":"Concepts and applications of chemical fingerprint for hit and lead screening","volume":"27","author":"Yang","year":"2022","journal-title":"Drug Discov. Today"},{"key":"10.1016\/j.jpha.2025.101465_bib8","doi-asserted-by":"crossref","first-page":"58","DOI":"10.1016\/j.ymeth.2014.08.005","article-title":"Molecular fingerprint similarity search in virtual screening","volume":"71","author":"Cereto-Massagu\u00e9","year":"2015","journal-title":"Methods"},{"key":"10.1016\/j.jpha.2025.101465_bib9","doi-asserted-by":"crossref","first-page":"2928","DOI":"10.1021\/acs.jcim.3c00045","article-title":"Fingerprint-enhanced graph attention network (FinGAT) model for antibiotic discovery","volume":"63","author":"Choo","year":"2023","journal-title":"J. Chem. Inf. Model."},{"key":"10.1016\/j.jpha.2025.101465_bib10","doi-asserted-by":"crossref","first-page":"1666","DOI":"10.1016\/j.csbj.2024.04.030","article-title":"Multimodal fused deep learning for drug property prediction: Integrating chemical language and molecular graph","volume":"23","author":"Lu","year":"2024","journal-title":"Comput. Struct. Biotechnol. J."},{"key":"10.1016\/j.jpha.2025.101465_bib11","doi-asserted-by":"crossref","first-page":"1668","DOI":"10.3390\/molecules27051668","article-title":"Accurate physical property predictions via deep learning","volume":"27","author":"Hou","year":"2022","journal-title":"Molecules"},{"key":"10.1016\/j.jpha.2025.101465_bib12","article-title":"Multilingual molecular representation learning via contrastive pre-training","author":"Guo","year":"2021","journal-title":"arXiv"},{"key":"10.1016\/j.jpha.2025.101465_bib13","series-title":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management, October 17\u201321, 2022, Atlanta, USA","first-page":"1461","article-title":"MORN: Molecular property prediction based on textual-topological-spatial multi-view learning","author":"Ma","year":"2022"},{"key":"10.1016\/j.jpha.2025.101465_bib14","article-title":"A systematic survey of chemical pre-trained models","author":"Xia","year":"2022","journal-title":"arXiv"},{"key":"10.1016\/j.jpha.2025.101465_bib15","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv"},{"key":"10.1016\/j.jpha.2025.101465_bib16","doi-asserted-by":"crossref","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.jpha.2025.101465_bib17","series-title":"Proceedings of the International Conference on Learning Representations, May 1\u20135, 2023, Kigali, Rwanda","first-page":"1","article-title":"Mole-bert: Rethinking pre-training graph neural networks for molecules","author":"Xia","year":"2023"},{"key":"10.1016\/j.jpha.2025.101465_bib18","doi-asserted-by":"crossref","DOI":"10.1016\/j.jmgm.2022.108344","article-title":"MolRoPE-BERT: An enhanced molecular representation with rotary Position Embedding for molecular property prediction","volume":"118","author":"Liu","year":"2023","journal-title":"J. Mol. Graph. Model."},{"key":"10.1016\/j.jpha.2025.101465_bib19","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."},{"key":"10.1016\/j.jpha.2025.101465_bib20","doi-asserted-by":"crossref","first-page":"2003","DOI":"10.1093\/bioinformatics\/btac039","article-title":"Cross-dependent graph neural networks for molecular property prediction","volume":"38","author":"Ma","year":"2022","journal-title":"Bioinformatics"},{"key":"10.1016\/j.jpha.2025.101465_bib21","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.jpha.2025.101465_bib22","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":"10.1016\/j.jpha.2025.101465_bib23","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":"10.1016\/j.jpha.2025.101465_bib24","doi-asserted-by":"crossref","DOI":"10.1016\/j.foodchem.2020.128617","article-title":"Multicriteria decision making for evergreen problems in food science by sum of ranking differences","volume":"344","author":"Gere","year":"2021","journal-title":"Food Chem."},{"key":"10.1016\/j.jpha.2025.101465_bib25","doi-asserted-by":"crossref","DOI":"10.1016\/j.ijbiomac.2024.132024","article-title":"Discovery of a novel chemotype as DYRK1A inhibitors against Alzheimer's disease: Computational modeling and biological evaluation","volume":"269","author":"Qiu","year":"2024","journal-title":"Int. J. Biol. Macromol."},{"key":"10.1016\/j.jpha.2025.101465_bib26","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.jpha.2025.101465_bib27","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1186\/s13321-022-00619-2","article-title":"Blood-brain barrier penetration prediction enhanced by uncertainty estimation","volume":"14","author":"Tong","year":"2022","journal-title":"J. Cheminf."},{"key":"10.1016\/j.jpha.2025.101465_bib28","doi-asserted-by":"crossref","first-page":"2719","DOI":"10.1021\/jm901137j","article-title":"New substructure filters for removal of pan assay interference compounds (PAINS) from screening libraries and for their exclusion in bioassays","volume":"53","author":"Baell","year":"2010","journal-title":"J. Med. Chem."},{"key":"10.1016\/j.jpha.2025.101465_bib29","doi-asserted-by":"crossref","first-page":"101","DOI":"10.1016\/j.trac.2009.09.009","article-title":"Sum of ranking differences compares methods or models fairly","volume":"29","author":"H\u00e9berger","year":"2010","journal-title":"Trac. Trends Anal. Chem."},{"key":"10.1016\/j.jpha.2025.101465_bib30","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1021\/acs.jcim.3c01250","article-title":"Chemprop: A machine learning package for chemical property prediction","volume":"64","author":"Heid","year":"2024","journal-title":"J. Chem. Inf. Model."},{"key":"10.1016\/j.jpha.2025.101465_bib31","doi-asserted-by":"crossref","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.jpha.2025.101465_bib32","article-title":"Infograph: Unsupervised and semi-supervised graph-level representation learning via mutual information maximization","author":"Sun","year":"2019","journal-title":"arXiv"},{"key":"10.1016\/j.jpha.2025.101465_bib33","article-title":"GPT-GNN: Generative pre-training of graph neural networks","author":"Hu","year":"2020","journal-title":"arXiv"},{"key":"10.1016\/j.jpha.2025.101465_bib34","article-title":"Inductive representation learning on large graphs","author":"Hamilton","year":"2017","journal-title":"arXiv"},{"key":"10.1016\/j.jpha.2025.101465_bib35","article-title":"Strategies for pre-training graph neural networks","author":"Hu","year":"2019","journal-title":"arXiv"},{"key":"10.1016\/j.jpha.2025.101465_bib36","article-title":"Self-supervised graph-level representation learning with local and global structure","author":"Xu","year":"2021","journal-title":"arXiv"},{"key":"10.1016\/j.jpha.2025.101465_bib37","article-title":"Self-supervised graph transformer on large-scale molecular data","author":"Rong","year":"2020","journal-title":"arXiv"},{"key":"10.1016\/j.jpha.2025.101465_bib38","article-title":"Adversarial graph augmentation to improve graph contrastive learning","author":"Suresh","year":"2021","journal-title":"arXiv"},{"key":"10.1016\/j.jpha.2025.101465_bib39","article-title":"Graph contrastive learning automated","author":"You","year":"2020","journal-title":"arXiv"},{"key":"10.1016\/j.jpha.2025.101465_bib40","series-title":"Proceedings of the ACM Web Conference 2022","first-page":"1070","article-title":"SimGRACE: A simple framework for graph contrastive learning without data augmentation","author":"Xia","year":"2022"},{"key":"10.1016\/j.jpha.2025.101465_bib41","article-title":"Graph contrastive learning with augmentations","author":"You","year":"2020","journal-title":"arXiv"},{"key":"10.1016\/j.jpha.2025.101465_bib42","series-title":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Washington DC USA","first-page":"594","article-title":"GraphMAE: Self-supervised masked graph autoencoders","author":"Hou","year":"2022"},{"key":"10.1016\/j.jpha.2025.101465_bib43","series-title":"Proceedings of Machine Learning Research, International Conference on Machine Learning, 17\u201323 July 2022, Baltimore, Maryland, USA","first-page":"20479","article-title":"3d infomax improves gnns for molecular property prediction","author":"St\u00e4rk","year":"2022"},{"key":"10.1016\/j.jpha.2025.101465_bib44","article-title":"Pre-training molecular graph representation with 3d geometry","author":"Liu","year":"2021","journal-title":"arXiv"},{"key":"10.1016\/j.jpha.2025.101465_bib45","article-title":"Motif-based graph self-supervised learning for molecular property prediction","author":"Zhang","year":"2021","journal-title":"arXiv"}],"container-title":["Journal of Pharmaceutical Analysis"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2095177925002825?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2095177925002825?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T10:46:22Z","timestamp":1773917182000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S2095177925002825"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12]]},"references-count":45,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2025,12]]}},"alternative-id":["S2095177925002825"],"URL":"https:\/\/doi.org\/10.1016\/j.jpha.2025.101465","relation":{},"ISSN":["2095-1779"],"issn-type":[{"value":"2095-1779","type":"print"}],"subject":[],"published":{"date-parts":[[2025,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Geometry-based BERT: An experimentally validated deep learning model for molecular property prediction in drug discovery","name":"articletitle","label":"Article Title"},{"value":"Journal of Pharmaceutical Analysis","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.jpha.2025.101465","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 The Authors. Published by Elsevier B.V. on behalf of Xi\u2019an Jiaotong University.","name":"copyright","label":"Copyright"}],"article-number":"101465"}}