{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T04:28:31Z","timestamp":1772166511859,"version":"3.50.1"},"reference-count":47,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T00:00:00Z","timestamp":1763424000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T00:00:00Z","timestamp":1763424000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"DOI":"10.13039\/501100001711","name":"Swiss National Science Foundation","doi-asserted-by":"crossref","award":["194606"],"award-info":[{"award-number":["194606"]}],"id":[{"id":"10.13039\/501100001711","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001711","name":"Swiss National Science Foundation","doi-asserted-by":"crossref","award":["194606"],"award-info":[{"award-number":["194606"]}],"id":[{"id":"10.13039\/501100001711","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001711","name":"Swiss National Science Foundation","doi-asserted-by":"crossref","award":["194606"],"award-info":[{"award-number":["194606"]}],"id":[{"id":"10.13039\/501100001711","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Cheminform"],"DOI":"10.1186\/s13321-025-01099-w","type":"journal-article","created":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T10:18:50Z","timestamp":1763461130000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Beyond performance: how design choices shape chemical language models"],"prefix":"10.1186","volume":"17","author":[{"given":"Inken","family":"Fender","sequence":"first","affiliation":[]},{"given":"Jannik Adrian","family":"Gut","sequence":"additional","affiliation":[]},{"given":"Thomas","family":"Lemmin","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,11,18]]},"reference":[{"key":"1099_CR1","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1021\/ci00057a005","volume":"28","author":"D Weininger","year":"1988","unstructured":"Weininger D (1988) Smiles, a chemical language and information system. J Chem Inf Comput Sci 28:31\u201336","journal-title":"J Chem Inf Comput Sci"},{"key":"1099_CR2","unstructured":"Chithrananda S, Grand G, Ramsundar B (2020) Chemberta: large-scale self-supervised pretraining for molecular property prediction. arXiv preprint arXiv:2010.09885"},{"key":"1099_CR3","unstructured":"Ahmad W, Simon E, Chithrananda S, Grand G, Ramsundar B (2022) Chemberta-2: Towards chemical foundation models. arXiv preprint arXiv:2209.01712"},{"key":"1099_CR4","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 Cent Sci 5:1572\u20131583","journal-title":"ACS Cent Sci"},{"key":"1099_CR5","doi-asserted-by":"publisher","first-page":"5832","DOI":"10.1021\/acs.jcim.4c00512","volume":"64","author":"G Chilingaryan","year":"2024","unstructured":"Chilingaryan G et al (2024) Bartsmiles: generative masked language models for molecular representations. J Chem Inf Model 64:5832\u20135843","journal-title":"J Chem Inf Model"},{"key":"1099_CR6","doi-asserted-by":"publisher","first-page":"225","DOI":"10.1186\/s12859-024-05847-x","volume":"25","author":"S Sadeghi","year":"2024","unstructured":"Sadeghi S, Bui A, Forooghi A, Lu J, Ngom A (2024) Can large language models understand molecules? BMC Bioinformatics 25:225","journal-title":"BMC Bioinf"},{"key":"1099_CR7","doi-asserted-by":"publisher","first-page":"1256","DOI":"10.1038\/s42256-022-00580-7","volume":"4","author":"J Ross","year":"2022","unstructured":"Ross J et al (2022) Large-scale chemical language representations capture molecular structure and properties. Nature Machine Intelligence 4:1256\u20131264 (https:\/\/www.nature.com\/articles\/s42256-022-00580-7)","journal-title":"Nat Mach Intell"},{"key":"1099_CR8","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/aba947","volume":"1","author":"M Krenn","year":"2020","unstructured":"Krenn M, H\u00e4se F, Nigam A, Friederich P, Aspuru-Guzik A (2020) Self-referencing embedded strings (selfies): a 100% robust molecular string representation. Machine Learning Science and Technology 1:045024","journal-title":"Mach Learn Sci Technol"},{"key":"1099_CR9","doi-asserted-by":"crossref","unstructured":"Kudo T, Richardson J, Blanco E, Lu W (eds) (2018) SentencePiece: A simple and language independent subword tokenizer and detokenizer for neural text processing. (eds Blanco E, Lu W) Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, 66\u201371 (Association for Computational Linguistics, Brussels, Belgium, 2018). https:\/\/aclanthology.org\/D18-2012\/","DOI":"10.18653\/v1\/D18-2012"},{"key":"1099_CR10","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":"1099_CR11","doi-asserted-by":"crossref","unstructured":"Krenn M et\u00a0al. (2022) Selfies and the future of molecular string representations. Patterns 3","DOI":"10.1016\/j.patter.2022.100588"},{"key":"1099_CR12","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 (2024) Comparing smiles and selfies tokenization for enhanced chemical language modeling. Sci Rep 14:25016","journal-title":"Sci Rep"},{"key":"1099_CR13","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/acdb30","volume":"4","author":"A Y\u00fcksel","year":"2023","unstructured":"Y\u00fcksel A, Ulusoy E, \u00dcnl\u00fc A, Do\u011fan T (2023) Selformer: molecular representation learning via selfies language models. Machine Learning Science and Technology 4:025035","journal-title":"Mach Learn Sci Technol"},{"key":"1099_CR14","doi-asserted-by":"publisher","first-page":"3293","DOI":"10.1038\/s41467-022-30839-x","volume":"13","author":"D Flam-Shepherd","year":"2022","unstructured":"Flam-Shepherd D, Zhu K, Aspuru-Guzik A (2022) Language models can learn complex molecular distributions. Nat Commun 13:3293","journal-title":"Nat Commun"},{"key":"1099_CR15","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":"1099_CR16","volume":"1","author":"TB Kimber","year":"2021","unstructured":"Kimber TB, Gagnebin M, Volkamer A (2021) Maxsmi: maximizing molecular property prediction performance with confidence estimation using smiles augmentation and deep learning. Artificial Intelligence in the Life Sciences 1:100014","journal-title":"Artif Intell Life Sci"},{"key":"1099_CR17","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":"1099_CR18","doi-asserted-by":"publisher","unstructured":"Landrum G et\u00a0al. (2025) rdkit\/rdkit: 2024_09_5 (q3 2024) release. https:\/\/doi.org\/10.5281\/zenodo.14779836","DOI":"10.5281\/zenodo.14779836"},{"key":"1099_CR19","unstructured":"Wolf T et\u00a0al. (2020) Transformers: State-of-the-art natural language processing 38\u201345. https:\/\/www.aclweb.org\/anthology\/2020.emnlp-demos.6"},{"key":"1099_CR20","unstructured":"Liu Y et\u00a0al. (2019) Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692"},{"key":"1099_CR21","doi-asserted-by":"crossref","unstructured":"Lewis M et\u00a0al. (2020) BART: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics 7871\u20137880","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"1099_CR22","unstructured":"Vaswani A et\u00a0al. (2017) Attention is all you need. Advances in neural information processing systems 30"},{"key":"1099_CR23","doi-asserted-by":"crossref","unstructured":"Devlin J, Chang M-W, Lee K, Toutanova K (2019) Bert: Pre-training of deep bidirectional transformers for language understanding. 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) 4171\u20134186","DOI":"10.18653\/v1\/N19-1423"},{"key":"1099_CR24","doi-asserted-by":"crossref","unstructured":"Ott M et\u00a0al. (2019) fairseq: A fast, extensible toolkit for sequence modeling","DOI":"10.18653\/v1\/N19-4009"},{"key":"1099_CR25","unstructured":"Wu Z et\u00a0al. (2017) Moleculenet: A benchmark for molecular machine learning. CoRR abs\/1703.00564"},{"key":"1099_CR26","unstructured":"Ramsundar B et\u00a0al. (2019) Deep Learning for the Life Sciences (O\u2019Reilly Media)"},{"key":"1099_CR27","doi-asserted-by":"crossref","unstructured":"Bishop CM (1995) Neural networks for pattern recognition (Oxford university press)","DOI":"10.1093\/oso\/9780198538493.001.0001"},{"key":"1099_CR28","first-page":"273","volume":"20","author":"C Cortes","year":"1995","unstructured":"Cortes C, Vapnik V (1995) Support-vector networks Machine learning 20:273\u2013297","journal-title":"Support-vector networks Machine learning"},{"key":"1099_CR29","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa F et al (2011) Scikit-learn: machine learning in python. J Mach Learn Res 12:2825\u20132830","journal-title":"J Mach Learn Res"},{"key":"1099_CR30","doi-asserted-by":"crossref","unstructured":"Hall LH, Kier LB (1991) The molecular connectivity chi indexes and kappa shape indexes in structure-property modeling. Reviews in computational chemistry 367\u2013422","DOI":"10.1002\/9780470125793.ch9"},{"key":"1099_CR31","doi-asserted-by":"publisher","first-page":"868","DOI":"10.1021\/ci990307l","volume":"39","author":"SA Wildman","year":"1999","unstructured":"Wildman SA, Crippen GM (1999) Prediction of physicochemical parameters by atomic contributions. J Chem Inf Comput Sci 39:868\u2013873","journal-title":"J Chem Inf Comput Sci"},{"key":"1099_CR32","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1038\/nchem.1243","volume":"4","author":"GR Bickerton","year":"2012","unstructured":"Bickerton GR, Paolini GV, Besnard J, Muresan S, Hopkins AL (2012) Quantifying the chemical beauty of drugs. Nat Chem 4:90\u201398","journal-title":"Nat Chem"},{"key":"1099_CR33","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1038\/s43586-024-00363-x","volume":"4","author":"J Healy","year":"2024","unstructured":"Healy J, McInnes L (2024) Uniform manifold approximation and projection. Nature Reviews Methods Primers 4:82. https:\/\/doi.org\/10.1038\/s43586-024-00363-x","journal-title":"Nat Rev Methods Prim"},{"key":"1099_CR34","doi-asserted-by":"publisher","first-page":"267","DOI":"10.1111\/j.2517-6161.1996.tb02080.x","volume":"58","author":"R Tibshirani","year":"2018","unstructured":"Tibshirani R (2018) Regression shrinkage and selection via the lasso. J Roy Stat Soc: Ser B (Methodol) 58:267\u2013288. https:\/\/doi.org\/10.1111\/j.2517-6161.1996.tb02080.x","journal-title":"J Roy Stat Soc: Ser B (Methodol)"},{"key":"1099_CR35","doi-asserted-by":"publisher","DOI":"10.1063\/5.0019056","volume":"153","author":"X He","year":"2020","unstructured":"He X, Man VH, Yang W, Lee T-S, Wang J (2020) A fast and high-quality charge model for the next generation general amber force field. J Chem Phys 153:114502. https:\/\/doi.org\/10.1063\/5.0019056","journal-title":"J Chem Phys"},{"key":"1099_CR36","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1016\/j.jmgm.2005.12.005","volume":"25","author":"J Wang","year":"2006","unstructured":"Wang J, Wang W, Kollman PA, Case DA (2006) Automatic atom type and bond type perception in molecular mechanical calculations. J Mol Graph Model 25:247\u2013260","journal-title":"J Mol Graph Model"},{"key":"1099_CR37","doi-asserted-by":"crossref","unstructured":"Lehner MT, Katzberger P, Maeder N, Landrum GA, Riniker S (2024) Dash properties: Estimating atomic and molecular properties from a dynamic attention-based substructure hierarchy. The Journal of chemical physics 161","DOI":"10.1063\/5.0218154"},{"key":"1099_CR38","doi-asserted-by":"publisher","first-page":"1833","DOI":"10.1063\/1.1740588","volume":"23","author":"RS Mulliken","year":"1955","unstructured":"Mulliken RS (1955) Electronic population analysis on lcao-mo molecular wave functions. i. The Journal of chemical physics 23:1833\u20131840","journal-title":"J Chem Phys"},{"key":"1099_CR39","doi-asserted-by":"publisher","first-page":"205","DOI":"10.1021\/jp046577a","volume":"109","author":"C Morell","year":"2005","unstructured":"Morell C, Grand A, Toro-Labb\u00e9 A (2005) New dual descriptor for chemical reactivity. J Phys Chem A 109:205\u2013212","journal-title":"J Phys Chem A"},{"key":"1099_CR40","doi-asserted-by":"publisher","first-page":"3894","DOI":"10.1021\/acs.jctc.6b00456","volume":"12","author":"T Verstraelen","year":"2016","unstructured":"Verstraelen T et al (2016) Minimal basis iterative stockholder: atoms in molecules for force-field development. J Chem Theory Comput 12:3894\u20133912","journal-title":"J Chem Theory Comput"},{"key":"1099_CR41","doi-asserted-by":"publisher","first-page":"10269","DOI":"10.1021\/j100142a004","volume":"97","author":"CI Bayly","year":"1993","unstructured":"Bayly CI, Cieplak P, Cornell W, Kollman PA (1993) A well-behaved electrostatic potential based method using charge restraints for deriving atomic charges: the resp model. J Phys Chem 97:10269\u201310280","journal-title":"J Phys Chem"},{"key":"1099_CR42","first-page":"1014","volume":"9","author":"E Kreyszig","year":"2008","unstructured":"Kreyszig E, Stroud K, Stephenson G (2008) Advanced engineering mathematics. Integration 9:1014","journal-title":"Integration"},{"key":"1099_CR43","doi-asserted-by":"crossref","unstructured":"Wilcoxon F (1992) Individual comparisons by ranking methods. Breakthroughs in statistics: Methodology and distribution 196\u2013202","DOI":"10.1007\/978-1-4612-4380-9_16"},{"key":"1099_CR44","doi-asserted-by":"publisher","first-page":"4993","DOI":"10.1038\/s41467-024-49388-6","volume":"15","author":"J-N Wu","year":"2024","unstructured":"Wu J-N et al (2024) T-smiles: a fragment-based molecular representation framework for de novo ligand design. Nat Commun 15:4993","journal-title":"Nat Commun"},{"key":"1099_CR45","doi-asserted-by":"crossref","unstructured":"O\u2019Boyle N, Dalke A (2018) Deepsmiles: An adaptation of smiles for use in machine-learning of chemical structures. chemrxiv preprint chemrxiv:7097960","DOI":"10.26434\/chemrxiv.7097960.v1"},{"key":"1099_CR46","unstructured":"Achiam J et\u00a0al. (2023) Gpt-4 technical report. arXiv preprint arXiv:2303.08774"},{"key":"1099_CR47","first-page":"12559","volume":"33","author":"Y Rong","year":"2020","unstructured":"Rong Y et al (2020) Self-supervised graph transformer on large-scale molecular data. Adv Neural Inf Process Syst 33:12559\u201312571","journal-title":"Adv Neural Inf Process Syst"}],"container-title":["Journal of Cheminformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13321-025-01099-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13321-025-01099-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13321-025-01099-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T10:18:54Z","timestamp":1763461134000},"score":1,"resource":{"primary":{"URL":"https:\/\/jcheminf.biomedcentral.com\/articles\/10.1186\/s13321-025-01099-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,18]]},"references-count":47,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["1099"],"URL":"https:\/\/doi.org\/10.1186\/s13321-025-01099-w","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-6732063\/v1","asserted-by":"object"}]},"ISSN":["1758-2946"],"issn-type":[{"value":"1758-2946","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,18]]},"assertion":[{"value":"23 May 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 September 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 November 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":"None declared.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"173"}}