{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T10:43:31Z","timestamp":1784889811926,"version":"3.55.0"},"reference-count":66,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,2,5]],"date-time":"2025-02-05T00:00:00Z","timestamp":1738713600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,2,5]],"date-time":"2025-02-05T00:00:00Z","timestamp":1738713600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Cheminform"],"DOI":"10.1186\/s13321-025-00959-9","type":"journal-article","created":{"date-parts":[[2025,2,5]],"date-time":"2025-02-05T14:51:32Z","timestamp":1738767092000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["Positional embeddings and zero-shot learning using BERT for molecular-property prediction"],"prefix":"10.1186","volume":"17","author":[{"given":"Medard Edmund","family":"Mswahili","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"JunHa","family":"Hwang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jagath C.","family":"Rajapakse","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kyuri","family":"Jo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Young-Seob","family":"Jeong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,2,5]]},"reference":[{"key":"959_CR1","first-page":"1","volume":"2021","author":"J Li","year":"2021","unstructured":"Li J, Jiang X (2021) Mol-bert: an effective molecular representation with bert for molecular property prediction. Wirel Commun Mobile Comput 2021:1\u20137","journal-title":"Wirel Commun Mobile Comput"},{"key":"959_CR2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmgm.2022.108344","volume":"118","author":"Y Liu","year":"2023","unstructured":"Liu Y et al (2023) Molrope-bert: an enhanced molecular representation with rotary position embedding for molecular property prediction. J Mol Graph Model 118:108344","journal-title":"J Mol Graph Model"},{"key":"959_CR3","unstructured":"Lee I, Nam H (2022) Infusing linguistic knowledge of smiles into chemical language models. arXiv preprint arXiv:2205.00084"},{"key":"959_CR4","doi-asserted-by":"publisher","first-page":"463","DOI":"10.1038\/s41573-019-0024-5","volume":"18","author":"J Vamathevan","year":"2019","unstructured":"Vamathevan J et al (2019) Applications of machine learning in drug discovery and development. Nat Rev Drug Discov 18:463\u2013477","journal-title":"Nat Rev Drug Discov"},{"key":"959_CR5","doi-asserted-by":"publisher","first-page":"435","DOI":"10.1038\/s41563-019-0338-z","volume":"18","author":"S Ekins","year":"2019","unstructured":"Ekins S et al (2019) Exploiting machine learning for end-to-end drug discovery and development. Nat Mater 18:435\u2013441","journal-title":"Nat Mater"},{"key":"959_CR6","doi-asserted-by":"publisher","first-page":"263","DOI":"10.1021\/acs.accounts.0c00699","volume":"54","author":"WP Walters","year":"2020","unstructured":"Walters WP, Barzilay R (2020) Applications of deep learning in molecule generation and molecular property prediction. Acc Chem Res 54:263\u2013270","journal-title":"Acc Chem Res"},{"key":"959_CR7","doi-asserted-by":"publisher","first-page":"513","DOI":"10.1039\/C7SC02664A","volume":"9","author":"Z Wu","year":"2018","unstructured":"Wu Z et al (2018) Moleculenet: a benchmark for molecular machine learning. Chem Sci 9:513\u2013530","journal-title":"Chem Sci"},{"key":"959_CR8","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1039\/C9SC04944D","volume":"11","author":"A Thakkar","year":"2020","unstructured":"Thakkar A, Kogej T, Reymond J-L, Engkvist O, Bjerrum EJ (2020) Datasets and their influence on the development of computer assisted synthesis planning tools in the pharmaceutical domain. Chem Sci 11:154\u2013168","journal-title":"Chem Sci"},{"key":"959_CR9","doi-asserted-by":"publisher","first-page":"4852","DOI":"10.1021\/acs.jcim.2c00715","volume":"62","author":"H Abdel-Aty","year":"2022","unstructured":"Abdel-Aty H, Gould IR (2022) Large-scale distributed training of transformers for chemical fingerprinting. J Chem Inf Model 62:4852\u20134862","journal-title":"J Chem Inf Model"},{"key":"959_CR10","doi-asserted-by":"publisher","first-page":"1692","DOI":"10.1039\/C8SC04175J","volume":"10","author":"R Winter","year":"2019","unstructured":"Winter R, Montanari F, No\u00e9 F, Clevert D-A (2019) Learning continuous and data-driven molecular descriptors by translating equivalent chemical representations. Chem Sci 10:1692\u20131701","journal-title":"Chem Sci"},{"key":"959_CR11","doi-asserted-by":"publisher","first-page":"673","DOI":"10.1038\/s41586-023-05905-z","volume":"616","author":"AV Sadybekov","year":"2023","unstructured":"Sadybekov AV, Katritch V (2023) Computational approaches streamlining drug discovery. Nature 616:673\u2013685","journal-title":"Nature"},{"key":"959_CR12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13321-019-0341-z","volume":"11","author":"J Ar\u00fas-Pous","year":"2019","unstructured":"Ar\u00fas-Pous J et al (2019) Exploring the GDB-13 chemical space using deep generative models. J Cheminform 11:1\u201314","journal-title":"J Cheminform"},{"key":"959_CR13","unstructured":"Fabian B et al (2020) Molecular representation learning with language models and domain-relevant auxiliary tasks. arXiv preprint arXiv:2011.13230"},{"key":"959_CR14","doi-asserted-by":"publisher","first-page":"10793","DOI":"10.1021\/acs.jpclett.1c03058","volume":"12","author":"D Chen","year":"2021","unstructured":"Chen D, Zheng J, Wei G-W, Pan F (2021) Extracting predictive representations from hundreds of millions of molecules. J Phys Chem Lett 12:10793\u201310801","journal-title":"J Phys Chem Lett"},{"key":"959_CR15","unstructured":"Balaji S, Magar R, Jadhav Y et al (2023) Gpt-molberta: Gpt molecular features language model for molecular property prediction. arXiv preprint arXiv:2310.03030"},{"key":"959_CR16","doi-asserted-by":"publisher","DOI":"10.1016\/j.sbi.2023.102527","volume":"79","author":"F Grisoni","year":"2023","unstructured":"Grisoni F (2023) Chemical language models for de novo drug design: challenges and opportunities. Curr Opin Struct Biol 79:102527","journal-title":"Curr Opin Struct Biol"},{"key":"959_CR17","unstructured":"Dai AM, Le QV (2015) Semi-supervised sequence learning. Advances in neural information processing systems; 2015. p. 28"},{"key":"959_CR18","doi-asserted-by":"publisher","first-page":"323","DOI":"10.1093\/bfgp\/elab036","volume":"20","author":"L Yu","year":"2021","unstructured":"Yu L, Su Y, Liu Y, Zeng X (2021) Review of unsupervised pretraining strategies for molecules representation. Brief Funct Genomics 20:323\u2013332","journal-title":"Brief Funct Genomics"},{"key":"959_CR19","doi-asserted-by":"publisher","first-page":"2593","DOI":"10.1016\/j.drudis.2021.06.009","volume":"26","author":"Z Liu","year":"2021","unstructured":"Liu Z et al (2021) Ai-based language models powering drug discovery and development. Drug Discov Today 26:2593\u20132607","journal-title":"Drug Discov Today"},{"key":"959_CR20","doi-asserted-by":"crossref","unstructured":"Xu Z, Wang S, Zhu F, Huang J (2017) 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. pp 285\u2013294","DOI":"10.1145\/3107411.3107424"},{"key":"959_CR21","doi-asserted-by":"crossref","unstructured":"Zhang X et al (2018) 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. pp 404\u2013413","DOI":"10.1145\/3233547.3233548"},{"key":"959_CR22","doi-asserted-by":"crossref","unstructured":"Wang S, Guo Y, Wang Y, Sun H, Huang J (2019) 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. pp 429\u2013436","DOI":"10.1145\/3307339.3342186"},{"key":"959_CR23","unstructured":"Chithrananda S, Grand G, Ramsundar B (2020) Chemberta: large-scale self-supervised pretraining for molecular property prediction. arXiv preprint arXiv:2010.09885"},{"key":"959_CR24","unstructured":"Ahmad W, Simon E, Chithrananda S, Grand G, Ramsundar B (2022) Chemberta-2: towards chemical foundation models. arXiv preprint arXiv:2209.01712"},{"key":"959_CR25","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1186\/s13321-024-00886-1","volume":"16","author":"C Zhang","year":"2024","unstructured":"Zhang C et al (2024) Transfer learning across different chemical domains: virtual screening of organic materials with deep learning models pretrained on small molecule and chemical reaction data. J Cheminform 16:89","journal-title":"J Cheminform"},{"key":"959_CR26","doi-asserted-by":"publisher","first-page":"bbad398","DOI":"10.1093\/bib\/bbad398","volume":"24","author":"B Li","year":"2023","unstructured":"Li B, Lin M, Chen T, Wang L (2023) Fg-bert: a generalized and self-supervised functional group-based molecular representation learning framework for properties prediction. Brief Bioinform 24:bbad398","journal-title":"Brief Bioinform"},{"key":"959_CR27","doi-asserted-by":"publisher","first-page":"bbab152","DOI":"10.1093\/bib\/bbab152","volume":"22","author":"X-C Zhang","year":"2021","unstructured":"Zhang X-C et al (2021) Mg-bert: leveraging unsupervised atomic representation learning for molecular property prediction. Brief Bioinform 22:bbab152","journal-title":"Brief Bioinform"},{"key":"959_CR28","unstructured":"Devlin J, Chang MW, Lee K, Toutanova K (2018) Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805"},{"key":"959_CR29","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063","volume":"568","author":"J Su","year":"2024","unstructured":"Su J et al (2024) Roformer: enhanced transformer with rotary position embedding. Neurocomputing 568:127063","journal-title":"Neurocomputing"},{"key":"959_CR30","doi-asserted-by":"publisher","DOI":"10.26434\/chemrxiv.7097960.v1","author":"N O\u2019Boyle","year":"2018","unstructured":"O\u2019Boyle N, Dalke A (2018) Deepsmiles: an adaptation of smiles for use in machine-learning of chemical structures. ChemRxiv. https:\/\/doi.org\/10.26434\/chemrxiv.7097960.v1","journal-title":"ChemRxiv"},{"key":"959_CR31","doi-asserted-by":"publisher","first-page":"6259","DOI":"10.1021\/acs.jcim.4c00747","volume":"64","author":"A Sultan","year":"2024","unstructured":"Sultan A, Sieg J, Mathea M, Volkamer A (2024) Transformers for molecular property prediction: lessons learned from the past five years. J Chem Inf Model 64:6259\u20136280","journal-title":"J Chem Inf Model"},{"key":"959_CR32","unstructured":"Labrak Y, Rouvier M, Dufour R (2023) A zero-shot and few-shot study of instruction-finetuned large language models applied to clinical and biomedical tasks. arXiv preprint arXiv:2307.12114"},{"key":"959_CR33","doi-asserted-by":"publisher","first-page":"1757","DOI":"10.1021\/ci3001277","volume":"52","author":"JJ Irwin","year":"2012","unstructured":"Irwin JJ, Sterling T, Mysinger MM, Bolstad ES, Coleman RG (2012) Zinc: a free tool to discover chemistry for biology. J Chem Inf Model 52:1757\u20131768","journal-title":"J Chem Inf Model"},{"key":"959_CR34","doi-asserted-by":"publisher","first-page":"6065","DOI":"10.1021\/acs.jcim.0c00675","volume":"60","author":"JJ Irwin","year":"2020","unstructured":"Irwin JJ et al (2020) Zinc20-a free ultralarge-scale chemical database for ligand discovery. J Chem Inf Model 60:6065\u20136073","journal-title":"J Chem Inf Model"},{"key":"959_CR35","doi-asserted-by":"publisher","first-page":"D1102","DOI":"10.1093\/nar\/gky1033","volume":"47","author":"S Kim","year":"2019","unstructured":"Kim S et al (2019) Pubchem 2019 update: improved access to chemical data. Nucleic Acids Res 47:D1102\u2013D1109","journal-title":"Nucleic Acids Res"},{"key":"959_CR36","doi-asserted-by":"publisher","first-page":"D1373","DOI":"10.1093\/nar\/gkac956","volume":"51","author":"S Kim","year":"2023","unstructured":"Kim S et al (2023) Pubchem 2023 update. Nucleic Acids Res 51:D1373\u2013D1380","journal-title":"Nucleic Acids Res"},{"key":"959_CR37","doi-asserted-by":"publisher","first-page":"D945","DOI":"10.1093\/nar\/gkw1074","volume":"45","author":"A Gaulton","year":"2017","unstructured":"Gaulton A et al (2017) The chembl database in 2017. Nucleic Acids Res 45:D945\u2013D954","journal-title":"Nucleic Acids Res"},{"key":"959_CR38","doi-asserted-by":"publisher","first-page":"D1100","DOI":"10.1093\/nar\/gkr777","volume":"40","author":"A Gaulton","year":"2012","unstructured":"Gaulton A et al (2012) Chembl: a large-scale bioactivity database for drug discovery. Nucleic Acids Res 40:D1100\u2013D1107","journal-title":"Nucleic Acids Res"},{"key":"959_CR39","doi-asserted-by":"publisher","first-page":"1472","DOI":"10.3390\/app14041472","volume":"14","author":"ME Mswahili","year":"2024","unstructured":"Mswahili ME, Ndomba GE, Jo K, Jeong Y-S (2024) Graph neural network and bert model for antimalarial drug predictions using plasmodium potential targets. Appl Sci 14:1472","journal-title":"Appl Sci"},{"key":"959_CR40","doi-asserted-by":"publisher","first-page":"1323","DOI":"10.3390\/app11031323","volume":"11","author":"ME Mswahili","year":"2021","unstructured":"Mswahili ME et al (2021) Cocrystal prediction using machine learning models and descriptors. Appl Sci 11:1323","journal-title":"Appl Sci"},{"key":"959_CR41","doi-asserted-by":"crossref","unstructured":"Mswahili ME, Hwang J, Jeong YS, Kim Y (2022) Graph neural network models for chemical compound activeness prediction for covid-19 drugs discovery using lipinski\u2019s descriptors. In: 2022 5th international conference on artificial intelligence for industries (AI4I). IEEE. pp 20\u201321","DOI":"10.1109\/AI4I54798.2022.00011"},{"key":"959_CR42","doi-asserted-by":"publisher","DOI":"10.3389\/fgene.2021.744170","volume":"12","author":"E Harigua-Souiai","year":"2021","unstructured":"Harigua-Souiai E et al (2021) Deep learning algorithms achieved satisfactory predictions when trained on a novel collection of anticoronavirus molecules. Front Genet 12:744170","journal-title":"Front Genet"},{"key":"959_CR43","doi-asserted-by":"publisher","first-page":"5953","DOI":"10.2174\/0109298673290511240404053224","volume":"31","author":"ME Mswahili","year":"2024","unstructured":"Mswahili ME, Jo K, Jeong Y-S, Lee S (2024) Graph neural networks with multi-features for predicting cocrystals using APIS and coformers interactions. Curr Med Chem 31:5953\u20135968","journal-title":"Curr Med Chem"},{"key":"959_CR44","doi-asserted-by":"publisher","first-page":"4641","DOI":"10.1109\/ACCESS.2018.2789428","volume":"6","author":"M Zhu","year":"2018","unstructured":"Zhu M et al (2018) Class weights random forest algorithm for processing class imbalanced medical data. IEEE Access 6:4641\u20134652","journal-title":"IEEE Access"},{"key":"959_CR45","unstructured":"DeepChem tokenizers. https:\/\/deepchem.readthedocs.io\/en\/2.4.0\/api_reference\/tokenizers.html. Accessed 25 Sept 2023"},{"key":"959_CR46","unstructured":"Ramsundar B et al (2016) Democratizing deep-learning for drug discovery, quantum chemistry, materials science and biology. GitHub repository"},{"key":"959_CR47","doi-asserted-by":"crossref","unstructured":"Wolf T et al (2020) Transformers: state-of-the-art natural language processing. In: Proceedings of the 2020 conference on empirical methods in natural language processing: system demonstrations. pp 38\u201345","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"959_CR48","doi-asserted-by":"publisher","first-page":"144","DOI":"10.1038\/s42256-020-00284-w","volume":"3","author":"P Schwaller","year":"2021","unstructured":"Schwaller P et al (2021) Mapping the space of chemical reactions using attention-based neural networks. Nat Mach Intell 3:144\u2013152","journal-title":"Nat Mach Intell"},{"key":"959_CR49","doi-asserted-by":"publisher","first-page":"1572","DOI":"10.1021\/acscentsci.9b00576","volume":"5","author":"P Schwaller","year":"2019","unstructured":"Schwaller P et al (2019) Molecular transformer: a model for uncertainty-calibrated chemical reaction prediction. ACS Central Sci 5:1572\u20131583","journal-title":"ACS Central Sci"},{"key":"959_CR50","doi-asserted-by":"crossref","unstructured":"Huang Z, Liang D, Xu P, Xiang B (2020) Improve transformer models with better relative position embeddings. arXiv preprint arXiv:2009.13658","DOI":"10.18653\/v1\/2020.findings-emnlp.298"},{"key":"959_CR51","doi-asserted-by":"crossref","unstructured":"Qu A, Niu J, Mo S (2021) Explore better relative position embeddings from encoding perspective for transformer models. In: Proceedings of the 2021 conference on empirical methods in natural language processing. pp 2989\u20132997","DOI":"10.18653\/v1\/2021.emnlp-main.237"},{"key":"959_CR52","unstructured":"Vaswani A et al (2017) Attention is all you need. Advances in neural information processing systems. p 30"},{"key":"959_CR53","doi-asserted-by":"crossref","unstructured":"Shaw P, Uszkoreit J, Vaswani A (2018) Self-attention with relative position representations. arXiv preprint. arXiv:1803.02155","DOI":"10.18653\/v1\/N18-2074"},{"key":"959_CR54","doi-asserted-by":"publisher","first-page":"94","DOI":"10.1016\/j.neunet.2023.05.039","volume":"165","author":"Q Lv","year":"2023","unstructured":"Lv Q, Zhou J, Yang Z, He H, Chen CY-C (2023) 3d graph neural network with few-shot learning for predicting drug-drug interactions in scaffold-based cold start scenario. Neural Netw 165:94\u2013105","journal-title":"Neural Netw"},{"key":"959_CR55","unstructured":"Molecule Splitters scaffoldsplitter. https:\/\/deepchem.readthedocs.io\/en\/latest\/api_reference\/splitters.html#scaffoldsplitter. Accessed 26 Dec 2024"},{"key":"959_CR56","unstructured":"We need better benchmarks for machine learning in drug discovery. https:\/\/practicalcheminformatics.blogspot.com\/2023\/08\/we-need-better-benchmarks-for-machine.html. Accessed 27 Nov 2024"},{"key":"959_CR57","unstructured":"The benchmarking platform for drug discovery. https:\/\/polarishub.io\/. Accessed 27 Nov 2024"},{"key":"959_CR58","doi-asserted-by":"publisher","first-page":"1750","DOI":"10.3390\/biom11121750","volume":"11","author":"ME Mswahili","year":"2021","unstructured":"Mswahili ME, Martin GL, Woo J, Choi GJ, Jeong Y-S (2021) Antimalarial drug predictions using molecular descriptors and machine learning against Plasmodium falciparum. Biomolecules 11:1750","journal-title":"Biomolecules"},{"key":"959_CR59","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0204644","volume":"13","author":"S Egieyeh","year":"2018","unstructured":"Egieyeh S, Syce J, Malan SF, Christoffels A (2018) Predictive classifier models built from natural products with antimalarial bioactivity using machine learning approach. PLoS ONE 13:e0204644","journal-title":"PLoS ONE"},{"key":"959_CR60","doi-asserted-by":"publisher","first-page":"543","DOI":"10.1080\/1062936X.2019.1635526","volume":"30","author":"Danishuddin","year":"2019","unstructured":"Danishuddin, Madhukar G, Malik M, Subbarao N (2019) Development and rigorous validation of antimalarial predictive models using machine learning approaches. SAR QSAR Environ Res 30:543\u2013560","journal-title":"SAR QSAR Environ Res"},{"key":"959_CR61","doi-asserted-by":"publisher","first-page":"5336","DOI":"10.1039\/C7CE00587C","volume":"19","author":"JG Wicker","year":"2017","unstructured":"Wicker JG et al (2017) Will they co-crystallize? CrystEngComm 19:5336\u20135340","journal-title":"CrystEngComm"},{"key":"959_CR62","doi-asserted-by":"publisher","first-page":"21711","DOI":"10.1002\/anie.202009467","volume":"59","author":"J-J Devogelaer","year":"2020","unstructured":"Devogelaer J-J, Meekes H, Tinnemans P, Vlieg E, De Gelder R (2020) Co-crystal prediction by artificial neural networks. Angew Chem Int Ed 59:21711\u201321718","journal-title":"Angew Chem Int Ed"},{"key":"959_CR63","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1186\/s13321-023-00725-9","volume":"15","author":"UV Ucak","year":"2023","unstructured":"Ucak UV, Ashyrmamatov I, Lee J (2023) Improving the quality of chemical language model outcomes with atom-in-smiles tokenization. J Cheminform 15:55","journal-title":"J Cheminform"},{"key":"959_CR64","doi-asserted-by":"publisher","first-page":"1560","DOI":"10.1021\/acs.jcim.0c01127","volume":"61","author":"X Li","year":"2021","unstructured":"Li X, Fourches D (2021) Smiles pair encoding: a data-driven substructure tokenization algorithm for deep learning. J Chem Inf Model 61:1560\u20131569","journal-title":"J Chem Inf Model"},{"key":"959_CR65","unstructured":"Domingo M, Garc\u0131a-Mart\u0131nez M, Helle A, Casacuberta F, Herranz M (2018) How much does tokenization affect neural machine translation? arXiv preprint arXiv:1812.08621"},{"key":"959_CR66","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3359657","author":"Q Lv","year":"2024","unstructured":"Lv Q, Chen G, Yang Z, Zhong W, Chen CY-C (2024) Meta-molnet: a cross-domain benchmark for few examples drug discovery. IEEE Trans Neural Netw Learn Syst. https:\/\/doi.org\/10.1109\/TNNLS.2024.3359657","journal-title":"IEEE Trans Neural Netw Learn Syst"}],"container-title":["Journal of Cheminformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13321-025-00959-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13321-025-00959-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13321-025-00959-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,5]],"date-time":"2025-02-05T22:46:56Z","timestamp":1738795616000},"score":1,"resource":{"primary":{"URL":"https:\/\/jcheminf.biomedcentral.com\/articles\/10.1186\/s13321-025-00959-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,5]]},"references-count":66,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["959"],"URL":"https:\/\/doi.org\/10.1186\/s13321-025-00959-9","relation":{},"ISSN":["1758-2946"],"issn-type":[{"value":"1758-2946","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2,5]]},"assertion":[{"value":"19 September 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 January 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 February 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This study does NOT involve any human or animal subjects.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"The authors declare no competing interests.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"17"}}