{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T05:30:21Z","timestamp":1786512621342,"version":"build-2736575974"},"publisher-location":"Cham","reference-count":23,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032353894","type":"print"},{"value":"9783032353900","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T00:00:00Z","timestamp":1786579200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T00:00:00Z","timestamp":1786579200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2027]]},"DOI":"10.1007\/978-3-032-35390-0_18","type":"book-chapter","created":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T05:03:41Z","timestamp":1786511021000},"page":"249-262","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Controlled Study of\u00a0Tokenizer Scale in\u00a0SMILES-Based Foundation Models"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-5241-0391","authenticated-orcid":false,"given":"Seongik","family":"Choi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-5191-7420","authenticated-orcid":false,"given":"Ju Hyung","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3084-6034","authenticated-orcid":false,"given":"Utku","family":"Ozbulak","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5813-5659","authenticated-orcid":false,"given":"Joris","family":"Vankerschaver","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8190-3839","authenticated-orcid":false,"given":"Wesley","family":"De Neve","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,8,13]]},"reference":[{"key":"18_CR1","doi-asserted-by":"crossref","unstructured":"Guo, F., et al.: Foundation models in bioinformatics. Natl. Sci. Rev. 12(4), nwaf028 (2025)","DOI":"10.1093\/nsr\/nwaf028"},{"key":"18_CR2","doi-asserted-by":"crossref","unstructured":"Qureshi, R., et al.: AI in drug discovery and its clinical relevance. Heliyon 9(7) (2023)","DOI":"10.1016\/j.heliyon.2023.e17575"},{"key":"18_CR3","unstructured":"Chithrananda, S., Grand, G., Ramsundar, B.: ChemBERTa: large-scale self-supervised pretraining for molecular property prediction (2020). arXiv preprint arXiv:2010.09885"},{"issue":"1","key":"18_CR4","doi-asserted-by":"publisher","first-page":"7181815","DOI":"10.1155\/2021\/7181815","volume":"2021","author":"J Li","year":"2021","unstructured":"Li, J., Jiang, X.: Mol-BERT: an effective molecular representation with BERT for molecular property prediction. Wirel. Commun. Mob. Comput. 2021(1), 7181815 (2021)","journal-title":"Wirel. Commun. Mob. Comput."},{"issue":"12","key":"18_CR5","doi-asserted-by":"publisher","first-page":"1256","DOI":"10.1038\/s42256-022-00580-7","volume":"4","author":"J Ross","year":"2022","unstructured":"Ross, J., Belgodere, B., Chenthamarakshan, V., Padhi, I., Mroueh, Y., Das, P.: Large-scale chemical language representations capture molecular structure and properties. Nat. Mach. Intell. 4(12), 1256\u20131264 (2022)","journal-title":"Nat. Mach. Intell."},{"key":"18_CR6","doi-asserted-by":"crossref","unstructured":"Radhakrishnan, S., Mody, K., Venkatesh, A., Venkatesh, A.: Optimizing SMILES token sequences via trie-based refinement and transition graph filtering. J. Cheminformatics (2026)","DOI":"10.1186\/s13321-025-01143-9"},{"key":"18_CR7","doi-asserted-by":"crossref","unstructured":"Weininger, D.: SMILES, a chemical language and information system. 1. Introduction to methodology and encoding rules. J. Chem. Inf. Comput. Sci. 28(1), 31\u201336 (1988)","DOI":"10.1021\/ci00057a005"},{"issue":"1","key":"18_CR8","doi-asserted-by":"publisher","first-page":"25016","DOI":"10.1038\/s41598-024-76440-8","volume":"14","author":"M Leon","year":"2024","unstructured":"Leon, M., Perezhohin, Y., Peres, F., Popovi\u010d, A., Castelli, M.: Comparing SMILES and SELFIES tokenization for enhanced chemical language modeling. Sci. Rep. 14(1), 25016 (2024)","journal-title":"Sci. Rep."},{"key":"18_CR9","doi-asserted-by":"crossref","unstructured":"Mswahili, M.E., Jeong, Y.-S.: Transformer-based models for chemical SMILES representation: a comprehensive literature review. Heliyon 10(20) (2024)","DOI":"10.1016\/j.heliyon.2024.e39038"},{"key":"18_CR10","first-page":"161527","volume":"38","author":"J Deng","year":"2026","unstructured":"Deng, J., Li, W., Zhou, J.T., He, Y.: SCOPE: saliency-coverage oriented token pruning for efficient multimodal LLMs. Adv. Neural. Inf. Process. Syst. 38, 161527\u2013161552 (2026)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"18_CR11","doi-asserted-by":"crossref","unstructured":"Lotz, J.F., Lopes, A.V., Peitz, S., Setiawan, H., Emili, L.: Beyond text compression: evaluating tokenizers across scales. In: Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 32155\u201332173 (2025)","DOI":"10.18653\/v1\/2025.acl-long.1546"},{"issue":"4","key":"18_CR12","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.: SMILES pair encoding: a data-driven substructure tokenization algorithm for deep learning. J. Chem. Inf. Model. 61(4), 1560\u20131569 (2021)","journal-title":"J. Chem. Inf. Model."},{"issue":"3","key":"18_CR13","doi-asserted-by":"publisher","first-page":"1384","DOI":"10.1021\/acs.jcim.5c01856","volume":"66","author":"A Wadell","year":"2026","unstructured":"Wadell, A., Bhutani, A., Viswanathan, V.: Tokenization for molecular foundation models. J. Chem. Inf. Model. 66(3), 1384\u20131393 (2026)","journal-title":"J. Chem. Inf. Model."},{"issue":"1","key":"18_CR14","doi-asserted-by":"publisher","first-page":"554","DOI":"10.1038\/s41467-024-55462-w","volume":"16","author":"F Kretschmer","year":"2025","unstructured":"Kretschmer, F., Seipp, J., Ludwig, M., Klau, G.W., B\u00f6cker, S.: Coverage bias in small molecule machine learning. Nat. Commun. 16(1), 554 (2025)","journal-title":"Nat. Commun."},{"key":"18_CR15","doi-asserted-by":"crossref","unstructured":"Singh, R., et al.: ChemBERTa-3: an open source training framework for chemical foundation models. Digit. Discov. (2026)","DOI":"10.26434\/chemrxiv-2025-4glrl"},{"key":"18_CR16","unstructured":"Ahmad, W., Simon, E., Chithrananda, S., Grand, G., Ramsundar, B.: ChemBERTa-2: towards chemical foundation models (2022). arXiv preprint arXiv:2209.01712"},{"key":"18_CR17","doi-asserted-by":"publisher","first-page":"217","DOI":"10.1016\/S1574-1400(08)00012-1","volume":"4","author":"EE Bolton","year":"2008","unstructured":"Bolton, E.E., Wang, Y., Thiessen, P.A., Bryant, S.H.: PubChem: integrated platform of small molecules and biological activities. Ann. Rep. Comput. Chem. 4, 217\u2013241 (2008)","journal-title":"Ann. Rep. Comput. Chem."},{"key":"18_CR18","doi-asserted-by":"crossref","unstructured":"Devlin, J., Chang, M.-W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pp. 4171\u20134186 (2019)","DOI":"10.18653\/v1\/N19-1423"},{"key":"18_CR19","doi-asserted-by":"crossref","unstructured":"Wettig, A., Gao, T., Zhong, Z., Chen, D.: Should you mask 15% in masked language modeling? In: Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pp. 2985\u20133000 (2023)","DOI":"10.18653\/v1\/2023.eacl-main.217"},{"key":"18_CR20","unstructured":"DeepChem Contributors: MoleculeNet Datasets. DeepChem Documentation, https:\/\/deepchem.readthedocs.io\/en\/latest\/api_reference\/moleculenet.html. Accessed 25 Mar 2026"},{"issue":"2","key":"18_CR21","doi-asserted-by":"publisher","first-page":"513","DOI":"10.1039\/C7SC02664A","volume":"9","author":"Z Wu","year":"2018","unstructured":"Wu, Z., et al.: MoleculeNet: a benchmark for molecular machine learning. Chem. Sci. 9(2), 513\u2013530 (2018)","journal-title":"Chem. Sci."},{"key":"18_CR22","doi-asserted-by":"crossref","unstructured":"Karmarkar, A., Lawrence, R.: A Comparative Study of SMILES, SELFIES, and ECFP4 Representations for Molecular Similarity Search (2026)","DOI":"10.26434\/chemrxiv.15000460\/v1"},{"issue":"4","key":"18_CR23","doi-asserted-by":"publisher","first-page":"1499","DOI":"10.1021\/jacsau.4c01160","volume":"5","author":"J Choi","year":"2025","unstructured":"Choi, J., Nam, G., Choi, J., Jung, Y.: A perspective on foundation models in chemistry. JACS Au 5(4), 1499\u20131518 (2025)","journal-title":"JACS Au"}],"container-title":["Lecture Notes in Computer Science","Artificial Intelligence in Healthcare"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-35390-0_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T05:03:43Z","timestamp":1786511023000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-35390-0_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,13]]},"ISBN":["9783032353894","9783032353900"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-35390-0_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,13]]},"assertion":[{"value":"13 August 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","label":"Disclosure of Interests","group":{"name":"EthicsHeading","label":"Ethics"}},{"value":"AIiH","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on AI in Healthcare","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"London","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 August 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"aiih2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/aiih.cc\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}