{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T00:57:54Z","timestamp":1777510674958,"version":"3.51.4"},"reference-count":67,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,7,12]],"date-time":"2025-07-12T00:00:00Z","timestamp":1752278400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,7,12]],"date-time":"2025-07-12T00:00:00Z","timestamp":1752278400000},"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\/s13321-025-01016-1","type":"journal-article","created":{"date-parts":[[2025,7,12]],"date-time":"2025-07-12T11:03:29Z","timestamp":1752318209000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["A transformer based generative chemical language AI model for structural elucidation of organic compounds"],"prefix":"10.1186","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1114-3571","authenticated-orcid":false,"given":"Xiaofeng","family":"Tan","sequence":"first","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,7,12]]},"reference":[{"key":"1016_CR1","volume-title":"Spectrometric identification of organic compounds","author":"RM Silverstein","year":"2014","unstructured":"Silverstein RM, Webster FX, Kiemle DJ, Bryce DL (2014) Spectrometric identification of organic compounds. John Wiley & Sons, Hoboken"},{"key":"1016_CR2","volume-title":"Introduction to infrared and Raman spectroscopy","author":"NB Colthup","year":"1990","unstructured":"Colthup NB, Daly LH, Wiberley SE (1990) Introduction to infrared and Raman spectroscopy. Elsevier Science, Amsterdam"},{"key":"1016_CR3","volume-title":"Principles of instrumental analysis","author":"DA Skoog","year":"2007","unstructured":"Skoog DA, James Holler F, Crouch SR (2007) Principles of instrumental analysis. Thomson Brooks\/Cole, Monterey"},{"key":"1016_CR4","volume-title":"Techniques in organic chemistry","author":"TDW Claridge","year":"2016","unstructured":"Claridge TDW, High-Resolution NMR (2016) Techniques in organic chemistry. Elsevier Science & Technology, Amsterdam"},{"key":"1016_CR5","volume-title":"Techniques for chemistry research","author":"AE Derome","year":"1987","unstructured":"Derome AE, Modern NMR (1987) Techniques for chemistry research. Pergamon, Oxford"},{"key":"1016_CR6","doi-asserted-by":"publisher","DOI":"10.1002\/9780470516898","volume-title":"Introduction to mass spectrometry: instrumentation, applications, and strategies for data interpretation","author":"J Throck Watson","year":"2007","unstructured":"Throck Watson J, David SO (2007) Introduction to mass spectrometry: instrumentation, applications, and strategies for data interpretation. John Wiley & Sons, Hoboken"},{"key":"1016_CR7","doi-asserted-by":"publisher","first-page":"2973","DOI":"10.1021\/ja01039a025","volume":"91","author":"J Lederberg","year":"1969","unstructured":"Lederberg J, Sutherland GL, Buchanan BG, Feigenbaum EA, Robertson AV, Duffield AM et al (1969) Applications of artificial intelligence for chemical inference. I. Number of possible organic compounds. Acyclic structures containing carbon, hydrogen, oxygen, and nitrogen. J Am Chem Soc 91:2973\u20132976","journal-title":"J Am Chem Soc"},{"key":"1016_CR8","first-page":"296","volume":"8","author":"ME Elyashberg","year":"1968","unstructured":"Elyashberg ME, Gribov LA (1968) Formal logic method of infrared spectrum interpretation. Zh Prikl Spectrosk 8:296\u2013300","journal-title":"Zh Prikl Spectrosk"},{"key":"1016_CR9","doi-asserted-by":"publisher","first-page":"2220","DOI":"10.1021\/ac50158a061","volume":"40","author":"SI Sasaki","year":"1968","unstructured":"Sasaki SI, Abe H, Ouki T, Sakamoto M, Ochia SI (1968) Automated structure elucidation of several kinds of aliphatic and alicyclic compounds. Anal Chem 40:2220","journal-title":"Anal Chem"},{"key":"1016_CR10","doi-asserted-by":"publisher","first-page":"3800","DOI":"10.1021\/jo01264a014","volume":"34","author":"DB Nelson","year":"1969","unstructured":"Nelson DB, Munk ME, Gasli KB, Horald DL (1969) An application of computer techniques to structure elucidation. J Org Chem 34:3800","journal-title":"J Org Chem"},{"key":"1016_CR11","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1186\/1758-2946-1-3","volume":"1","author":"M Elyashberg","year":"2009","unstructured":"Elyashberg M, Blinov K, Molodtsov S, Smurnyy Y, Williams AJ, Churanova T (2009) Computer-assisted methods for molecular structure elucidation: realizing a spectroscopist\u2019s dream. J Cheminform 1:3","journal-title":"J Cheminform"},{"key":"1016_CR12","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1186\/1758-2946-4-5","volume":"4","author":"A Moser","year":"2012","unstructured":"Moser A, Elyashberg ME, Williams AJ, Blinov KA, Dimartino JC (2012) Blind trials of computer-assisted structure elucidation software. J Cheminform 4:5","journal-title":"J Cheminform"},{"key":"1016_CR13","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1186\/s13321-017-0244-9","volume":"9","author":"B-H Su","year":"2017","unstructured":"Su B-H, Shen M-Y, Harn Y-C, Wang S-Y, Schurz A, Lin C et al (2017) An efficient computer-aided structural elucidation strategy for mixtures using an iterative dynamic programming algorithm. J Cheminform 9:57","journal-title":"J Cheminform"},{"key":"1016_CR14","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1080\/14786419.2020.1777122","volume":"36","author":"Z-K Duan","year":"2022","unstructured":"Duan Z-K, Lv T-M, Song G-S, Wang Y-X, Lin B, Huang X-X (2022) Structure reassignment of two triterpenes with CASE algorithms and DFT chemical shift predictions. Nat Prod Res 36:229\u2013236","journal-title":"Nat Prod Res"},{"key":"1016_CR15","doi-asserted-by":"publisher","first-page":"3105","DOI":"10.1021\/acs.jnatprod.6b00799","volume":"79","author":"AV Buevich","year":"2016","unstructured":"Buevich AV, Elyashberg ME (2016) Synergistic combination of CASE algorithms and DFT chemical shift predictions: a powerful approach for structure elucidation, verification, and revision. J Nat Prod 79:3105\u20133116","journal-title":"J Nat Prod"},{"key":"1016_CR16","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-662-46402-1_1","volume-title":"Computer-based structure elucidation from spectral data: the art of solving problems","author":"ME Elyashberg","year":"2015","unstructured":"Elyashberg ME, Williams AJ (2015) Fundamentals of structure elucidator system. In: Elyashberg ME, Williams AJ (eds) Computer-based structure elucidation from spectral data: the art of solving problems. Springer, Berlin, pp 3\u201351"},{"key":"1016_CR17","doi-asserted-by":"publisher","first-page":"225","DOI":"10.1016\/0022-2860(92)80198-Q","volume":"275","author":"B Guzowska-Swider","year":"1992","unstructured":"Guzowska-Swider B, Hippe ZS (1992) Structure elucidation of organic compounds aided by the computer program system scannet. J Mol Struct 275:225\u2013234","journal-title":"J Mol Struct"},{"key":"1016_CR18","doi-asserted-by":"publisher","first-page":"133","DOI":"10.1002\/9783527806539.ch5","volume-title":"Applied chemoinformatics","author":"J de Aires Sousa","year":"2018","unstructured":"de Aires Sousa J (2018) Structure-spectrum correlations and computer-assisted structure elucidation. In: Engel T, Gasteiger J (eds) Applied chemoinformatics. Wiley-VCH Verlag GmbH & Co. KGaA, Weinheim, pp 133\u2013163"},{"key":"1016_CR19","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1080\/10408347908085714","volume":"8","author":"LA Gribov","year":"1979","unstructured":"Gribov LA, Elyashberg ME, Clerc JT (1979) Computer-aided identification of organic molecules by their molecular spectra. CRC Crit Rev Anal Chem 8:111\u2013220","journal-title":"CRC Crit Rev Anal Chem"},{"key":"1016_CR20","doi-asserted-by":"publisher","first-page":"924","DOI":"10.1007\/BF00664596","volume":"51","author":"ME \u00c9lyashberg","year":"1989","unstructured":"Lyashberg ME, Gribov LA (1989) Expert systems in molecular spectroscopy (Review). J Appl Spectrosc 51:924\u2013936","journal-title":"J Appl Spectrosc"},{"key":"1016_CR21","first-page":"91","volume-title":"Fortschritte der chemischen forschung","author":"T Clerc","year":"2006","unstructured":"Clerc T, Erni F (2006) Identification of organic compounds by computer-aided interpretation of spectra. In: Clerc T, Erni F (eds) Fortschritte der chemischen forschung. Springer-Verlag, Berlin, pp 91\u2013107"},{"key":"1016_CR22","doi-asserted-by":"publisher","first-page":"669","DOI":"10.1002\/mrc.5115","volume":"59","author":"M Elyashberg","year":"2021","unstructured":"Elyashberg M, Argyropoulos D (2021) Computer assisted structure elucidation (CASE): current and future perspectives. Magn Reson Chem 59:669\u2013690","journal-title":"Magn Reson Chem"},{"key":"1016_CR23","doi-asserted-by":"publisher","first-page":"919","DOI":"10.1039\/C9NP00007K","volume":"36","author":"DC Burns","year":"2019","unstructured":"Burns DC, Mazzola EP, Reynolds WF (2019) The role of computer-assisted structure elucidation (CASE) programs in the structure elucidation of complex natural products. Nat Prod Rep 36:919\u2013933","journal-title":"Nat Prod Rep"},{"key":"1016_CR24","doi-asserted-by":"publisher","first-page":"997","DOI":"10.1021\/ci980083r","volume":"38","author":"ME Munk","year":"1998","unstructured":"Munk ME (1998) Computer-based structure determination: then and now. J Chem Inf Comput Sci 38:997\u20131009","journal-title":"J Chem Inf Comput Sci"},{"key":"1016_CR25","doi-asserted-by":"publisher","DOI":"10.3390\/molecules26216623","author":"M Elyashberg","year":"2021","unstructured":"Elyashberg M, Williams A (2021) ACD\/structure elucidator: 20 years in the history of development. Molecules. https:\/\/doi.org\/10.3390\/molecules26216623","journal-title":"Molecules"},{"key":"1016_CR26","doi-asserted-by":"publisher","first-page":"4351","DOI":"10.1039\/D0SC00442A","volume":"11","author":"A Howarth","year":"2020","unstructured":"Howarth A, Ermanis K, Goodman JM (2020) DP4-AI automated NMR data analysis: straight from spectrometer to structure. Chem Sci 11:4351\u20134359","journal-title":"Chem Sci"},{"key":"1016_CR27","doi-asserted-by":"publisher","first-page":"489","DOI":"10.1021\/ci034132y","volume":"44","author":"Y Han","year":"2004","unstructured":"Han Y, Steinbeck C (2004) Evolutionary-algorithm-based strategy for computer-assisted structure elucidation. J Chem Inf Comput Sci 44:489\u2013498","journal-title":"J Chem Inf Comput Sci"},{"key":"1016_CR28","doi-asserted-by":"publisher","DOI":"10.1021\/ja0109388","author":"J Meiler","year":"2002","unstructured":"Meiler J, Genius WM (2002) A genetic algorithm for automated structure elucidation from 13C NMR spectra. J Am Chem Soc. https:\/\/doi.org\/10.1021\/ja0109388","journal-title":"J Am Chem Soc"},{"key":"1016_CR29","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1145\/3065386","volume":"60","author":"A Krizhevsky","year":"2017","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2017) ImageNet classification with deep convolutional neural networks. Commun ACM 60:84\u201390","journal-title":"Commun ACM"},{"key":"1016_CR30","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas, NV, USA: IEEE; 2016.","DOI":"10.1109\/CVPR.2016.90"},{"key":"1016_CR31","unstructured":"Vaswani A, Shazeer NM, Parmar N, Uszkoreit J, Jones L, Gomez AN, et al. Attention is All you Need. Neural Information Processing Systems. 2017."},{"key":"1016_CR32","unstructured":"Devlin J, Chang M-W, Lee K, Toutanova K. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In: Burstein J, Doran C, Solorio T, editors. 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). Minneapolis, Minnesota: Association for Computational Linguistics; 2019. pp. 4171\u20134186."},{"key":"1016_CR33","unstructured":"Brown TB, Mann B, Ryder N, Subbiah M, Kaplan J, Dhariwal P, et al. Language Models are Few-Shot Learners. ArXiv. 2020;abs\/2005.14165."},{"key":"1016_CR34","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-024-07487-w","author":"J Abramson","year":"2024","unstructured":"Abramson J, Adler J, Dunger J, Evans R, Green T, Pritzel A et al (2024) Accurate structure prediction of biomolecular interactions with AlphaFold 3. Nature. https:\/\/doi.org\/10.1038\/s41586-024-07487-w","journal-title":"Nature"},{"key":"1016_CR35","doi-asserted-by":"publisher","first-page":"2590","DOI":"10.1093\/bioinformatics\/bty134","volume":"34","author":"P Klukowski","year":"2018","unstructured":"Klukowski P, Augoff M, Zieba M, Drwal M, Gonczarek A, Walczak MJ (2018) NMRNet: a deep learning approach to automated peak picking of protein NMR spectra. Bioinformatics 34:2590\u20132597","journal-title":"Bioinformatics"},{"key":"1016_CR36","doi-asserted-by":"publisher","DOI":"10.3389\/fntpr.2023.1122426","author":"I Cort\u00e9s","year":"2023","unstructured":"Cort\u00e9s I, Cuadrado C, Hern\u00e1ndez Daranas A, Sarotti AM (2023) Machine learning in computational NMR-aided structural elucidation. Front Nat Produc. https:\/\/doi.org\/10.3389\/fntpr.2023.1122426","journal-title":"Front Nat Produc"},{"key":"1016_CR37","doi-asserted-by":"publisher","first-page":"128","DOI":"10.1021\/ci700256n","volume":"48","author":"YD Smurnyy","year":"2008","unstructured":"Smurnyy YD, Blinov KA, Churanova TS, Elyashberg ME, Williams AJ (2008) Toward more reliable 13C and 1H chemical shift prediction: a systematic comparison of neural-network and least-squares regression based approaches. J Chem Inf Model 48:128\u2013134","journal-title":"J Chem Inf Model"},{"key":"1016_CR38","doi-asserted-by":"publisher","first-page":"550","DOI":"10.1021\/ci700363r","volume":"48","author":"KA Blinov","year":"2008","unstructured":"Blinov KA, Smurnyy YD, Elyashberg ME, Churanova TS, Kvasha M, Steinbeck C et al (2008) Performance validation of neural network based (13)c NMR prediction using a publicly available data source. J Chem Inf Model 48:550\u2013555","journal-title":"J Chem Inf Model"},{"key":"1016_CR39","doi-asserted-by":"publisher","first-page":"973","DOI":"10.1038\/s42256-021-00407-x","volume":"3","author":"MA Skinnider","year":"2021","unstructured":"Skinnider MA, Wang F, Pasin D, Greiner R, Foster LJ, Dalsgaard PW et al (2021) A deep generative model enables automated structure elucidation of novel psychoactive substances. Nat Mach Intell 3:973\u2013984","journal-title":"Nat Mach Intell"},{"key":"1016_CR40","doi-asserted-by":"publisher","first-page":"5624","DOI":"10.1021\/acs.jcim.4c00522","volume":"64","author":"Z Tian","year":"2024","unstructured":"Tian Z, Dai Y, Hu F, Shen Z, Xu H, Zhang H et al (2024) Enhancing chemical reaction monitoring with a deep learning model for NMR spectra image matching to target compounds. J Chem Inf Model 64:5624\u20135633","journal-title":"J Chem Inf Model"},{"key":"1016_CR41","doi-asserted-by":"publisher","DOI":"10.26434\/chemrxiv-2023-8wxcz","author":"M Alberts","year":"2023","unstructured":"Alberts M, Zipoli F, Vaucher AC (2023) Learning the language of NMR: structure elucidation from NMR spectra using transformer models. ChemRxiv. https:\/\/doi.org\/10.26434\/chemrxiv-2023-8wxcz","journal-title":"ChemRxiv"},{"key":"1016_CR42","doi-asserted-by":"publisher","DOI":"10.26434\/chemrxiv-2023-5v27f","author":"M Alberts","year":"2023","unstructured":"Alberts M, Laino T, Vaucher AC (2023) Leveraging Infrared spectroscopy for automated structure elucidation. ChemRxiv. https:\/\/doi.org\/10.26434\/chemrxiv-2023-5v27f","journal-title":"ChemRxiv"},{"key":"1016_CR43","doi-asserted-by":"publisher","first-page":"34219","DOI":"10.1007\/s11042-024-18307-8","volume":"83","author":"AS Al-Shamayleh","year":"2024","unstructured":"Al-Shamayleh AS, Adwan O, Alsharaiah MA, Hussein AH, Kharma QM, Eke CI (2024) A comprehensive literature review on image captioning methods and metrics based on deep learning technique. Multimed Tools Appl 83:34219\u201334268","journal-title":"Multimed Tools Appl"},{"key":"1016_CR44","doi-asserted-by":"crossref","unstructured":"Rasyad F, Kongguasa HA, Onggususilo NC, Anderies, Kurniawan A, Gunawan AAS. A Systematic Literature Review of Generative Adversarial Network Potential In AI Artwork. 2023 International Conference on Computer Science, Information Technology and Engineering (ICCoSITE). IEEE; 2023. pp. 853\u2013857.","DOI":"10.1109\/ICCoSITE57641.2023.10127706"},{"key":"1016_CR45","doi-asserted-by":"publisher","first-page":"4609","DOI":"10.1007\/s11063-022-10777-x","volume":"54","author":"M Elasri","year":"2022","unstructured":"Elasri M, Elharrouss O, Al-Maadeed S, Tairi H (2022) Image generation: a review. Neural Process Lett 54:4609\u20134646","journal-title":"Neural Process Lett"},{"key":"1016_CR46","doi-asserted-by":"publisher","DOI":"10.4855\/arXiv.2403.05131","author":"J Cho","year":"2024","unstructured":"Cho J, Puspitasari FD, Zheng S, Zheng J, Lee L-H, Kim T-H et al (2024) Sora as an AGI world model? A complete survey on text-to-video generation. arXiv. https:\/\/doi.org\/10.4855\/arXiv.2403.05131","journal-title":"arXiv"},{"key":"1016_CR47","doi-asserted-by":"publisher","unstructured":"Pavlidis N, Nikolaidis CC, Perifanis V, Papadopoulou A, Efraimidis P, Arampatzis A. An extensive overview of feature representation techniques for molecule classification. Proceedings of the 27th Pan-Hellenic Conference on Progress in Computing and Informatics. New York, NY, USA: ACM; 2023. https:\/\/doi.org\/10.1145\/3635059.3635083","DOI":"10.1145\/3635059.3635083"},{"key":"1016_CR48","doi-asserted-by":"publisher","DOI":"10.1515\/jib-2022-0006","author":"D Baptista","year":"2022","unstructured":"Baptista D, Correia J, Pereira B, Rocha M (2022) Evaluating molecular representations in machine learning models for drug response prediction and interpretability. J Integr Bioinform. https:\/\/doi.org\/10.1515\/jib-2022-0006","journal-title":"J Integr Bioinform"},{"key":"1016_CR49","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. 1. Introduction to methodology and encoding rules. J Chem Inf Comput Sci 28:31\u201336","journal-title":"J Chem Inf Comput Sci"},{"key":"1016_CR50","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1021\/ci00062a008","volume":"29","author":"D Weininger","year":"1989","unstructured":"Weininger D, Weininger A, Weininger JL (1989) SMILES. 2. Algorithm for generation of unique SMILES notation. J Chem Inf Comput Sci 29:97\u2013101","journal-title":"J Chem Inf Comput Sci"},{"key":"1016_CR51","doi-asserted-by":"publisher","first-page":"237","DOI":"10.1021\/ci00067a005","volume":"30","author":"D Weininger","year":"1990","unstructured":"Weininger D (1990) SMILES. 3. DEPICT. Graphical depiction of chemical structures. J Chem Inf Comput Sci 30:237\u2013243","journal-title":"J Chem Inf Comput Sci"},{"key":"1016_CR52","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1109\/TPAMI.2022.3152247","volume":"45","author":"K Han","year":"2023","unstructured":"Han K, Wang Y, Chen H, Chen X, Guo J, Liu Z et al (2023) A survey on vision transformer. IEEE Trans Pattern Anal Mach Intell 45:87\u2013110","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"1016_CR53","doi-asserted-by":"publisher","DOI":"10.4855\/arXiv.1907.11692","author":"Y Liu","year":"2019","unstructured":"Liu Y, Ott M, Goyal N, Du J, Joshi M, Chen D et al (2019) RoBERTa: a robustly optimized BERT pretraining approach. arXiv. https:\/\/doi.org\/10.4855\/arXiv.1907.11692","journal-title":"arXiv"},{"key":"1016_CR54","doi-asserted-by":"publisher","DOI":"10.4855\/arXiv.2209.01712","author":"W Ahmad","year":"2022","unstructured":"Ahmad W, Simon E, Chithrananda S, Grand G, Ramsundar B (2022) ChemBERTa-2: towards chemical foundation models. arXiv. https:\/\/doi.org\/10.4855\/arXiv.2209.01712","journal-title":"arXiv"},{"key":"1016_CR55","doi-asserted-by":"publisher","DOI":"10.4855\/arXiv.2010.09885","author":"S Chithrananda","year":"2020","unstructured":"Chithrananda S, Grand G, Ramsundar B (2020) ChemBERTa: large-scale self-supervised pretraining for molecular property prediction. arXiv. https:\/\/doi.org\/10.4855\/arXiv.2010.09885","journal-title":"arXiv"},{"key":"1016_CR56","doi-asserted-by":"publisher","first-page":"D1102","DOI":"10.1093\/nar\/gky1033","volume":"47","author":"S Kim","year":"2019","unstructured":"Kim S, Chen J, Cheng T, Gindulyte A, He J, He S et al (2019) PubChem 2019 update: improved access to chemical data. Nucleic Acids Res 47:D1102\u2013D1109","journal-title":"Nucleic Acids Res"},{"key":"1016_CR57","doi-asserted-by":"publisher","first-page":"957","DOI":"10.1038\/s43588-023-00550-y","volume":"3","author":"Z Zou","year":"2023","unstructured":"Zou Z, Zhang Y, Liang L, Wei M, Leng J, Jiang J et al (2023) A deep learning model for predicting selected organic molecular spectra. Nat Comput Sci 3:957\u2013964","journal-title":"Nat Comput Sci"},{"key":"1016_CR58","doi-asserted-by":"publisher","first-page":"2864","DOI":"10.1021\/ci300415d","volume":"52","author":"L Ruddigkeit","year":"2012","unstructured":"Ruddigkeit L, van Deursen R, Blum LC, Reymond J-L (2012) Enumeration of 166 billion organic small molecules in the chemical universe database GDB-17. J Chem Inf Model 52:2864\u20132875","journal-title":"J Chem Inf Model"},{"key":"1016_CR59","doi-asserted-by":"publisher","first-page":"140022","DOI":"10.1038\/sdata.2014.22","volume":"1","author":"R Ramakrishnan","year":"2014","unstructured":"Ramakrishnan R, Dral PO, Rupp M, von Lilienfeld OA (2014) Quantum chemistry structures and properties of 134 kilo molecules. Sci Data 1:140022","journal-title":"Sci Data"},{"key":"1016_CR60","doi-asserted-by":"publisher","DOI":"10.4855\/ARXIV.2405.00099","author":"G Franceschelli","year":"2024","unstructured":"Franceschelli G, Musolesi M (2024) Creative beam search: LLM-as-a-Judge for improving response generation. arXiv. https:\/\/doi.org\/10.4855\/ARXIV.2405.00099","journal-title":"arXiv"},{"key":"1016_CR61","doi-asserted-by":"publisher","first-page":"2887","DOI":"10.1021\/jm9602928","volume":"39","author":"GW Bemis","year":"1996","unstructured":"Bemis GW, Murcko MA (1996) The properties of known drugs. 1. Molecular frameworks. J Med Chem 39:2887\u20132893","journal-title":"J Med Chem"},{"key":"1016_CR62","doi-asserted-by":"publisher","first-page":"3600","DOI":"10.1039\/D2SC05892H","volume":"14","author":"G Jung","year":"2023","unstructured":"Jung G, Jung SG, Cole JM (2023) Automatic materials characterization from infrared spectra using convolutional neural networks. Chem Sci 14:3600\u20133609","journal-title":"Chem Sci"},{"key":"1016_CR63","doi-asserted-by":"publisher","first-page":"105395","DOI":"10.1016\/j.microc.2020.105395","volume":"159","author":"Z Wang","year":"2020","unstructured":"Wang Z, Feng X, Liu J, Lu M, Li M (2020) Functional groups prediction from infrared spectra based on computer-assist approaches. Microchem J 159:105395","journal-title":"Microchem J"},{"key":"1016_CR64","doi-asserted-by":"publisher","first-page":"4618","DOI":"10.1039\/C9SC06240H","volume":"11","author":"JA Fine","year":"2020","unstructured":"Fine JA, Rajasekar AA, Jethava KP, Chopra G (2020) Spectral deep learning for prediction and prospective validation of functional groups. Chem Sci 11:4618\u20134630","journal-title":"Chem Sci"},{"key":"1016_CR65","doi-asserted-by":"publisher","DOI":"10.4855\/ARXIV.2010.11929","author":"A Dosovitskiy","year":"2020","unstructured":"Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner T et al (2020) An image is worth 16x16 words: transformers for image recognition at scale. arXiv. https:\/\/doi.org\/10.4855\/ARXIV.2010.11929","journal-title":"arXiv"},{"key":"1016_CR66","doi-asserted-by":"publisher","DOI":"10.4855\/ARXIV.2108.08810","author":"M Raghu","year":"2021","unstructured":"Raghu M, Unterthiner T, Kornblith S, Zhang C, Dosovitskiy A (2021) Do vision transformers see like convolutional neural networks? arXiv. https:\/\/doi.org\/10.4855\/ARXIV.2108.08810","journal-title":"arXiv"},{"key":"1016_CR67","doi-asserted-by":"publisher","DOI":"10.4855\/ARXIV.2106.04560","author":"X Zhai","year":"2021","unstructured":"Zhai X, Kolesnikov A, Houlsby N, Beyer L (2021) Scaling vision transformers. arXiv. https:\/\/doi.org\/10.4855\/ARXIV.2106.04560","journal-title":"arXiv"}],"updated-by":[{"DOI":"10.1186\/s13321-025-01065-6","type":"correction","label":"Correction","source":"publisher","updated":{"date-parts":[[2025,8,4]],"date-time":"2025-08-04T00:00:00Z","timestamp":1754265600000}}],"container-title":["Journal of Cheminformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13321-025-01016-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13321-025-01016-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13321-025-01016-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,7]],"date-time":"2025-09-07T06:27:08Z","timestamp":1757226428000},"score":1,"resource":{"primary":{"URL":"https:\/\/jcheminf.biomedcentral.com\/articles\/10.1186\/s13321-025-01016-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,12]]},"references-count":67,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["1016"],"URL":"https:\/\/doi.org\/10.1186\/s13321-025-01016-1","relation":{"correction":[{"id-type":"doi","id":"10.1186\/s13321-025-01065-6","asserted-by":"object"}]},"ISSN":["1758-2946"],"issn-type":[{"value":"1758-2946","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,12]]},"assertion":[{"value":"20 January 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 April 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 July 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 August 2025","order":4,"name":"change_date","label":"Change Date","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Correction","order":5,"name":"change_type","label":"Change Type","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"A Correction to this paper has been published:","order":6,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"https:\/\/doi.org\/10.1186\/s13321-025-01065-6","URL":"https:\/\/doi.org\/10.1186\/s13321-025-01065-6","order":7,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"103"}}