{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T00:31:58Z","timestamp":1789432318625,"version":"build-2803163510"},"reference-count":83,"publisher":"American Chemical Society (ACS)","issue":"17","license":[{"start":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T00:00:00Z","timestamp":1787529600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T00:00:00Z","timestamp":1787529600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T00:00:00Z","timestamp":1787529600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-045"}],"funder":[{"DOI":"10.13039\/100006168","name":"National Nuclear Security Administration","doi-asserted-by":"publisher","award":["9233218CNA000001"],"award-info":[{"award-number":["9233218CNA000001"]}],"id":[{"id":"10.13039\/100006168","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100007000","name":"Laboratory Directed Research and Development","doi-asserted-by":"publisher","award":["20250006DR"],"award-info":[{"award-number":["20250006DR"]}],"id":[{"id":"10.13039\/100007000","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,9,14]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>The discovery of new energetic materials remains a pressing challenge, hindered by the limited availability of high-quality data. To address this, we have developed generative chemical language models that have been pretrained on extensive molecular data and then fine-tuned with curated energetic material data. This transfer learning strategy extends the chemical language model capabilities beyond the pharmacological space in which they have been predominantly developed, offering a framework that is applicable to other data-spare discovery problems. After fine-tuning, we observe modest distributional shifts in predicted detonation performance as benchmarked by density functional theory as well as the presence of chemical motifs associated with energetic materials. Furthermore, we discuss the benefits of fragment-based molecular encodings for chemical language models, in particular, in constructing synthetically accessible structures. Together, these advances provide a foundation for accelerating the design of next-generation energetic materials.<\/jats:p>","DOI":"10.1021\/acs.jcim.6c01013","type":"journal-article","created":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T21:08:24Z","timestamp":1788210504000},"page":"10648-10660","source":"Crossref","is-referenced-by-count":1,"title":["Generative Chemical\nLanguage Models for Energetic\nMaterials Discovery"],"prefix":"10.1021","volume":"66","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9507-3701","authenticated-orcid":true,"given":"Andrew","family":"Salij","sequence":"first","affiliation":[{"name":"Los Alamos National Laboratory , , , ,","place":["Los Alamos, New Mexico, United States, 87545"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5138-1833","authenticated-orcid":true,"given":"R. Seaton","family":"Ullberg","sequence":"additional","affiliation":[{"name":"Los Alamos National Laboratory , , , ,","place":["Los Alamos, New Mexico, United States, 87545"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4038-8615","authenticated-orcid":true,"given":"Megan C.","family":"Davis","sequence":"additional","affiliation":[{"name":"Los Alamos National Laboratory , , , ,","place":["Los Alamos, New Mexico, United States, 87545"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8919-3368","authenticated-orcid":true,"given":"Marc J.","family":"Cawkwell","sequence":"additional","affiliation":[{"name":"Los Alamos National Laboratory , , , ,","place":["Los Alamos, New Mexico, United States, 87545"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9610-9681","authenticated-orcid":true,"given":"Christopher J.","family":"Snyder","sequence":"additional","affiliation":[{"name":"Los Alamos National Laboratory , , , ,","place":["Los Alamos, New Mexico, United States, 87545"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cristina","family":"Garcia Cardona","sequence":"additional","affiliation":[{"name":"Los Alamos National Laboratory , , , ,","place":["Los Alamos, New Mexico, United States, 87545"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9191-8620","authenticated-orcid":true,"given":"Ivana","family":"Matanovic","sequence":"additional","affiliation":[{"name":"Los Alamos National Laboratory , , , ,","place":["Los Alamos, New Mexico, United States, 87545"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0679-6690","authenticated-orcid":true,"given":"Wilton J. M.","family":"Kort-Kamp","sequence":"additional","affiliation":[{"name":"Los Alamos National Laboratory , , , ,","place":["Los Alamos, New Mexico, United States, 87545"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"316","published-online":{"date-parts":[[2026,8,24]]},"reference":[{"key":"2026091409064180300_cit1","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1016\/j.jhazmat.2007.10.039","article-title":"Advances in\nscience and technology of modern energetic materials: an overview","volume":"151","author":"Badgujar","year":"2008","journal-title":"J. Hazard. Mater."},{"key":"2026091409064180300_cit2","doi-asserted-by":"publisher","first-page":"731","DOI":"10.1016\/j.mencom.2021.11.001","article-title":"Advanced energetic materials: novel\nstrategies and\nversatile applications","volume":"31","author":"Zlotin","year":"2021","journal-title":"Mendeleev Commun."},{"key":"2026091409064180300_cit3","volume-title":"Energetic Materials:\nThermophysical Properties, Predictions, and Experimental Measurements","author":"Redner","year":"2010"},{"key":"2026091409064180300_cit4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/S0166-1280(01)00533-4","article-title":"Computational characterization of energetic materials","volume":"573","author":"Politzer","year":"2001","journal-title":"THEOCHEM"},{"key":"2026091409064180300_cit5","doi-asserted-by":"publisher","first-page":"692","DOI":"10.1021\/accountsmr.1c00063","article-title":"Materials-genome approach to energetic\nmaterials","volume":"2","author":"Yuan","year":"2021","journal-title":"Acc. Mater. Res."},{"key":"2026091409064180300_cit6","doi-asserted-by":"publisher","first-page":"322","DOI":"10.3390\/molecules28010322","article-title":"Prediction\nand construction\nof energetic materials based on machine learning methods","volume":"28","author":"Zang","year":"2023","journal-title":"Molecules"},{"key":"2026091409064180300_cit7","doi-asserted-by":"publisher","first-page":"8406","DOI":"10.1021\/acs.jctc.5c00865","article-title":"Machine learning densities,\ndetonation velocities, and formation enthalpies of energetic materials\nusing quantum chemistry descriptors","volume":"21","author":"Kimber","year":"2025","journal-title":"J. Chem.\nTheory Comput."},{"key":"2026091409064180300_cit8","doi-asserted-by":"publisher","first-page":"115764","DOI":"10.1016\/j.matdes.2026.115764","article-title":"From empirical\nformulas to machine learning: A comprehensive review of detonation\nvelocity prediction for advanced energetic materials","volume":"265","author":"Keshavarz","year":"2026","journal-title":"Mater. Des."},{"key":"2026091409064180300_cit9","doi-asserted-by":"publisher","first-page":"4873","DOI":"10.1021\/acs.jcim.2c00997","article-title":"Correlated RNN framework\nto quickly generate molecules with desired properties for energetic\nmaterials in the low data regime","volume":"62","author":"Li","year":"2022","journal-title":"J. Chem. Inf.\nModel."},{"key":"2026091409064180300_cit10","unstructured":"Barnes, B. C.; Elton, D. C.; Boukouvalas, Z.; Taylor, D. E.; Mattson, W. D.; Fuge, M. D.; Chung, P. W.\n          Machine Learning of\nEnergetic Material Properties. 2018; https:\/\/arxiv.org\/abs\/1807.06156."},{"key":"2026091409064180300_cit11","doi-asserted-by":"publisher","first-page":"11109","DOI":"10.1021\/acs.chemmater.4c01978","article-title":"Machine Learning\nModels for High Explosive Crystal Density and Performance","volume":"36","author":"Davis","year":"2024","journal-title":"Chem. Mater."},{"key":"2026091409064180300_cit12","doi-asserted-by":"publisher","first-page":"804","DOI":"10.1021\/ci950223m","article-title":"Prediction of the\nimpact sensitivity\nby neural networks","volume":"36","author":"Nefati","year":"1996","journal-title":"J. Chem. Inf. Comput. Sci."},{"key":"2026091409064180300_cit13","doi-asserted-by":"publisher","first-page":"5397","DOI":"10.1021\/acs.jcim.2c00841","article-title":"Building chemical\nproperty models for energetic materials from small datasets using\na transfer learning approach","volume":"62","author":"Lansford","year":"2022","journal-title":"J. Chem. Inf.\nModel."},{"key":"2026091409064180300_cit14","doi-asserted-by":"publisher","first-page":"1811","DOI":"10.3390\/ma15051811","article-title":"Inverse design of materials by machine\nlearning","volume":"15","author":"Wang","year":"2022","journal-title":"Materials"},{"key":"2026091409064180300_cit15","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-12845-7","article-title":"Synthesizing controlled microstructures of porous media\nusing generative adversarial networks and reinforcement learning","volume":"12","author":"Nguyen","year":"2022","journal-title":"Sci. Rep."},{"key":"2026091409064180300_cit16","doi-asserted-by":"publisher","DOI":"10.1126\/sciadv.add6868","article-title":"PARC: Physics-aware\nrecurrent convolutional neural\nnetworks to assimilate meso scale reactive mechanics of energetic\nmaterials","volume":"9","author":"Nguyen","year":"2023","journal-title":"Sci. Adv."},{"key":"2026091409064180300_cit17","doi-asserted-by":"publisher","DOI":"10.1002\/prep.202200276","article-title":"Artificial intelligence approaches\nfor energetic materials by design:\nState of the art, challenges, and future directions","volume":"48","author":"Choi","year":"2023","journal-title":"Propellants, Explos., Pyrotech."},{"key":"2026091409064180300_cit18","doi-asserted-by":"publisher","DOI":"10.1038\/s41524-025-01845-6","article-title":"De novo multi-objective generation framework for energetic materials\nwith trading off energy and stability","volume":"11","author":"Liu","year":"2025","journal-title":"npj Comput.\nMater."},{"key":"2026091409064180300_cit19","doi-asserted-by":"publisher","DOI":"10.1002\/prep.202200264","article-title":"Application of machine\nlearning to the design of energetic\nmaterials: preliminary experience and comparison with alternative\ntechniques","volume":"48","author":"Wespiser","year":"2023","journal-title":"Propellants, Explos., Pyrotech."},{"key":"2026091409064180300_cit20","unstructured":"Jin, W.; Barzilay, R.; Jaakkola, T.\n          Junction\ntree variational\nautoencoder for molecular graph generation. In  International Conference on Machine Learning2018; pp 2323\u20132332."},{"key":"2026091409064180300_cit21","doi-asserted-by":"publisher","first-page":"172198","DOI":"10.1016\/j.cej.2025.172198","article-title":"Intelligent high-energy molecules\ndesign for solid propellants via interpretable machine learning and\nlatent space optimization","volume":"528","author":"Wang","year":"2026","journal-title":"Chem. Eng. J."},{"key":"2026091409064180300_cit22","unstructured":"Vaswani, A.; Shazeer, N.; Parmar, N.; Uszkoreit, J.; Jones, L.; Gomez, A. N.; Kaiser, \u0141.; Polosukhin, I.\n          Attention is all you need\n          Adv. Neural Inf. Process. Syst.\n          2017; Vol. 30."},{"key":"2026091409064180300_cit23","doi-asserted-by":"publisher","first-page":"102527","DOI":"10.1016\/j.sbi.2023.102527","article-title":"Chemical language\nmodels for de novo drug design: Challenges and opportunities","volume":"79","author":"Grisoni","year":"2023","journal-title":"Curr. Opin. Struct. Biol."},{"key":"2026091409064180300_cit24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3744746","article-title":"A comprehensive\noverview of large language models","volume":"16","author":"Naveed","year":"2025","journal-title":"ACM Trans.\nIntell. Systems Technol."},{"key":"2026091409064180300_cit25","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1021\/ci00057a005","article-title":"SMILES, a\nchemical language and information system. 1. Introduction to methodology\nand encoding rules","volume":"28","author":"Weininger","year":"1988","journal-title":"J. Chem. Inf. Comput. Sci."},{"key":"2026091409064180300_cit26","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/aba947","article-title":"Self-referencing\nembedded strings (SELFIES): A 100%\nrobust molecular string representation","volume":"1","author":"Krenn","year":"2020","journal-title":"Mach.\nLearn.: Sci. Technol."},{"key":"2026091409064180300_cit27","unstructured":"Radford, A.; Narasimhan, K.; Salimans, T.; Sutskever, I.; et al.\n          Improving\nlanguage understanding by generative pre-training\n          2018, pp 1\u201312."},{"key":"2026091409064180300_cit28","doi-asserted-by":"publisher","first-page":"2064","DOI":"10.1021\/acs.jcim.1c00600","article-title":"MolGPT:\nmolecular generation using a transformer-decoder model","volume":"62","author":"Bagal","year":"2022","journal-title":"J. Chem. Inf. Model."},{"key":"2026091409064180300_cit29","doi-asserted-by":"publisher","first-page":"4430","DOI":"10.3390\/molecules28114430","article-title":"cMolGPT: a\nconditional\ngenerative pre-trained transformer for target-specific de novo molecular\ngeneration","volume":"28","author":"Wang","year":"2023","journal-title":"Molecules"},{"key":"2026091409064180300_cit30","doi-asserted-by":"publisher","DOI":"10.1002\/wcms.1395","article-title":"Advances and challenges\nin deep generative models for de novo molecule generation","volume":"9","author":"Xue","year":"2019","journal-title":"Wiley Interdiscip. Rev.: Comput. Mol. Sci."},{"key":"2026091409064180300_cit31","doi-asserted-by":"publisher","first-page":"2707","DOI":"10.1016\/j.drudis.2021.05.019","article-title":"De novo molecular design and generative\nmodels","volume":"26","author":"Meyers","year":"2021","journal-title":"Drug Discovery Today"},{"key":"2026091409064180300_cit32","doi-asserted-by":"publisher","first-page":"796","DOI":"10.1039\/D4DD00019F","article-title":"Gotta be SAFE:\na new framework for molecular design","volume":"3","author":"Noutahi","year":"2024","journal-title":"Digital\nDiscovery"},{"key":"2026091409064180300_cit33","doi-asserted-by":"publisher","first-page":"1297","DOI":"10.1038\/s42256-023-00740-3","article-title":"Neural scaling\nof deep chemical models","volume":"5","author":"Frey","year":"2023","journal-title":"Nat. Mach. Intell."},{"key":"2026091409064180300_cit34","doi-asserted-by":"publisher","DOI":"10.1016\/j.heliyon.2024.e39038","article-title":"Transformer-based\nmodels for chemical SMILES representation:\nA comprehensive literature review","volume":"10","author":"Mswahili","year":"2024","journal-title":"Heliyon"},{"key":"2026091409064180300_cit35","doi-asserted-by":"crossref","unstructured":"O\u2019Boyle, N.; Dalke, A.\n          DeepSMILES: an adaptation\nof SMILES for use in machine-learning of chemical structures\n          2018.","DOI":"10.26434\/chemrxiv.7097960.v1"},{"key":"2026091409064180300_cit36","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/acdb30","article-title":"SELFormer:\nmolecular representation learning via SELFIES language models","volume":"4","author":"Yu\u0308ksel","year":"2023","journal-title":"Mach. Learn. Sci. Technol."},{"key":"2026091409064180300_cit37","doi-asserted-by":"publisher","first-page":"748","DOI":"10.1039\/D3DD00012E","article-title":"Group SELFIES:\na robust fragment-based molecular string representation","volume":"2","author":"Cheng","year":"2023","journal-title":"Digital Discovery"},{"key":"2026091409064180300_cit38","doi-asserted-by":"publisher","DOI":"10.1186\/1758-2946-1-8","article-title":"Estimation of synthetic accessibility score of drug-like\nmolecules based on molecular complexity and fragment contributions","volume":"1","author":"Ertl","year":"2009","journal-title":"J. Cheminf."},{"key":"2026091409064180300_cit39","doi-asserted-by":"publisher","first-page":"3990","DOI":"10.1021\/acs.jcim.5c00051","article-title":"Unified Deep Learning of Molecular\nand Protein Language Representations with T5ProtChem","volume":"65","author":"Kelly","year":"2025","journal-title":"J. Chem. Inf. Model."},{"key":"2026091409064180300_cit40","doi-asserted-by":"publisher","DOI":"10.3389\/fphar.2020.565644","article-title":"Molecular\nsets (MOSES):\na benchmarking platform for molecular generation models","volume":"11","author":"Polykovskiy","year":"2020","journal-title":"Front. Pharmacol."},{"key":"2026091409064180300_cit41","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1038\/nchem.1243","article-title":"Quantifying\nthe chemical beauty of drugs","volume":"4","author":"Bickerton","year":"2012","journal-title":"Nat. Chem."},{"key":"2026091409064180300_cit42","unstructured":"Lee, S.; Kreis, K.; Veccham, S. P.; Liu, M.; Reidenbach, D.; Peng, Y.; Paliwal, S.; Nie, W.; Vahdat, A.\n          GenMol: A Drug Discovery Generalist\nwith Discrete Diffusion. 2025; https:\/\/arxiv.org\/abs\/2501.06158."},{"key":"2026091409064180300_cit43","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1021\/ci049714+","article-title":"ZINC- a free database\nof commercially available compounds\nfor virtual screening","volume":"45","author":"Irwin","year":"2005","journal-title":"J. Chem. Inf. Model."},{"key":"2026091409064180300_cit44","doi-asserted-by":"publisher","first-page":"1166","DOI":"10.1021\/acs.jcim.2c01253","article-title":"ZINC-22\n- A free multi-billion-scale database of tangible compounds for ligand\ndiscovery","volume":"63","author":"Tingle","year":"2023","journal-title":"J. Chem. Inf. Model."},{"issue":"4","key":"2026091409064180300_cit45","doi-asserted-by":"publisher","first-page":"267","DOI":"10.1016\/j.enmf.2023.09.002","article-title":"EM Database\nv1. 0: A benchmark informatics platform for data-driven discovery\nof energetic materials","volume":"5","author":"Huang","year":"2023","journal-title":"Energ. Mater. Front."},{"key":"2026091409064180300_cit46","first-page":"1877","article-title":"Language\nmodels are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Adv. Neural Inf.\nProcess. Syst."},{"key":"2026091409064180300_cit47","unstructured":"Xiong, R.; Yang, Y.; He, D.; Zheng, K.; Zheng, S.; Xing, C.; Zhang, H.; Lan, Y.; Wang, L.; Liu, T.\n          On layer normalization in the transformer\narchitecture. In  International Conference\non Machine Learning2020; pp 10524\u201310533."},{"key":"2026091409064180300_cit48","unstructured":"OLMo, T.; et al.\n          2 OLMo\n2 Furious. 2025; https:\/\/arxiv.org\/abs\/2501.00656."},{"key":"2026091409064180300_cit49","unstructured":"SELFIES development team.\n          \n          SELFIES (v 2.2.0). 2025; https:\/\/github.com\/aspuru-guzik-group\/selfies."},{"key":"2026091409064180300_cit50","unstructured":"Group SELFIES development team.\n          \n          Group SELFIES. 2025; https:\/\/github.com\/aspuru-guzik-group\/group-selfies."},{"key":"2026091409064180300_cit51","doi-asserted-by":"publisher","DOI":"10.1186\/1758-2946-5-3","article-title":"UniChem: a unified chemical structure cross-referencing\nand identifier tracking system","volume":"5","author":"Chambers","year":"2013","journal-title":"J. Cheminf."},{"key":"2026091409064180300_cit52","unstructured":"Shibata, Y.; Kida, T.; Fukamachi, S.; Takeda, M.; Shinohara, A.; Shinohara, T.; Arikawa, S.\n          Byte pair encoding: A text compression\nscheme that accelerates pattern matching\n          1999, pp 1\u201313."},{"key":"2026091409064180300_cit53","doi-asserted-by":"publisher","first-page":"380","DOI":"10.1107\/S0108768102003890","article-title":"The Cambridge\nStructural Database: a quarter of a million crystal structures and\nrising","volume":"58","author":"Allen","year":"2002","journal-title":"Acta Crystallogr., B"},{"key":"2026091409064180300_cit54","unstructured":"Fried, L. E.\n          \n          Cheetah 1.0 users\nmanual, 1994."},{"key":"2026091409064180300_cit55","doi-asserted-by":"publisher","first-page":"6615","DOI":"10.1039\/b810189b","article-title":"Long-range corrected hybrid density functionals with\ndamped atom-atom dispersion corrections","volume":"10","author":"Chai","year":"2008","journal-title":"Phys.\nChem. Chem. Phys."},{"key":"2026091409064180300_cit56","doi-asserted-by":"publisher","first-page":"13856","DOI":"10.1021\/acs.iecr.8b03001","article-title":"Accurate or\nfast prediction of solid-state formation enthalpies using standard\nsublimation enthalpies derived from geometrical fragments","volume":"57","author":"Mathieu","year":"2018","journal-title":"Ind. Eng. Chem. Res."},{"key":"2026091409064180300_cit57","unstructured":"Ullberg, R. S.; Davis, M. C.; Schroeder, J. N.; Cawkwell, M. J.; Snyder, C. J.; Kort-Kamp, W. J. M.; Matanovic, I.\n          High-throughput\nprediction of energetic materials performance with chemical insights\nfrom machine learning methods, in preparation."},{"key":"2026091409064180300_cit58","doi-asserted-by":"publisher","first-page":"1096","DOI":"10.1021\/acs.jcim.8b00839","article-title":"GuacaMol:\nbenchmarking\nmodels for de novo molecular design","volume":"59","author":"Brown","year":"2019","journal-title":"J. Chem.\nInf. Model."},{"key":"2026091409064180300_cit59","unstructured":"Kingma, D. P.; Ba, J.\n          Adam: A Method for Stochastic Optimization. 2017; https:\/\/arxiv.org\/abs\/1412.6980."},{"key":"2026091409064180300_cit60","unstructured":"PyTorch development team.\n          \n          CrossEntropyLoss. 2025; https:\/\/docs.pytorch.org\/docs\/stable\/generated\/torch.nn.CrossEntropyLoss.html."},{"key":"2026091409064180300_cit61","unstructured":"Hu, E. J.; Shen, Y.; Wallis, P.; Allen-Zhu, Z.; Li, Y.; Wang, S.; Wang, L.; Chen, W.; et al.\n          Lora: Low-rank adaptation of large language\nmodels\n          ICLR\n          2022; Vol. 1, p 3."},{"key":"2026091409064180300_cit62","doi-asserted-by":"crossref","unstructured":"Yu, Y.; Yang, C.-H. H.; Kolehmainen, J.; Shivakumar, P. G.; Gu, Y.; Ren, S. R. R.; Luo, Q.; Gourav, A.; Chen, I.-F.; Liu, Y.-C.; et al.\n          Low-rank adaptation of\nlarge language model rescoring for parameter-efficient speech recognition. In  2023 IEEE Automatic Speech Recognition and Understanding\nWorkshop (ASRU), 2023; pp 1\u20138.","DOI":"10.1109\/ASRU57964.2023.10389632"},{"key":"2026091409064180300_cit63","unstructured":"Wang, L.; Pulugurta, R.; Vure, P.; Zhang, Y.; Pal, A.; Chatterjee, P.\n          PepDoRA: A Unified Peptide Language Model via Weight-Decomposed\nLow-Rank Adaptation. 2024; https:\/\/arxiv.org\/abs\/2410.20667."},{"key":"2026091409064180300_cit64","doi-asserted-by":"crossref","unstructured":"Buehler, E. L.; Buehler, M. J.\n          X-LoRA: Mixture\nof low-rank adapter experts, a flexible framework for large language\nmodels with applications in protein mechanics and molecular design\n          APL Mach. Learn.\n          2024; Vol. 210.1063\/5.0203126.","DOI":"10.1063\/5.0203126"},{"key":"2026091409064180300_cit65","unstructured":"RDKit development team.\n          \n          RDKit (v 2025.3.12). 2025; https:\/\/github.com\/rdkit\/rdkit."},{"key":"2026091409064180300_cit66","doi-asserted-by":"crossref","unstructured":"Benhenda, M.\n          \n          ChemGAN challenge for\ndrug discovery: can AI reproduce natural chemical diversity. 2017; https:\/\/arxiv.org\/abs\/1708.08227.","DOI":"10.1101\/292177"},{"key":"2026091409064180300_cit67","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1111\/j.1469-8137.1912.tb05611.x","article-title":"The distribution\nof the flora in the alpine zone. 1","volume":"11","author":"Jaccard","year":"1912","journal-title":"New Phytol."},{"key":"2026091409064180300_cit68","doi-asserted-by":"publisher","first-page":"1115","DOI":"10.1126\/science.132.3434.1115","article-title":"A Computer Program\nfor Classifying Plants: The computer\nis programmed to simulate the taxonomic process of comparing each\ncase with every other case","volume":"132","author":"Rogers","year":"1960","journal-title":"Science"},{"key":"2026091409064180300_cit69","unstructured":"RDKit development team.\n          \n          RDKit (v Q3 2014). 2014; https:\/\/github.com\/rdkit\/rdkit\/releases\/tag\/Release_2014_09_1."},{"key":"2026091409064180300_cit70","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1214\/aoms\/1177729694","article-title":"On information and\nsufficiency","volume":"22","author":"Kullback","year":"1951","journal-title":"Ann. Math. Stat."},{"key":"2026091409064180300_cit71","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1021\/acs.jcim.3c01250","article-title":"Chemprop:\na machine learning package for chemical property prediction","volume":"64","author":"Heid","year":"2024","journal-title":"J. Chem. Inf. Model."},{"key":"2026091409064180300_cit72","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1063\/1.1667908","article-title":"Chemistry of detonations. I. A simple\nmethod for calculating\ndetonation properties of C-H-N-O explosives","volume":"48","author":"Kamlet","year":"1968","journal-title":"J. Chem. Phys."},{"key":"2026091409064180300_cit73","doi-asserted-by":"publisher","first-page":"437","DOI":"10.1038\/s42256-024-00821-x","article-title":"Invalid\nSMILES are beneficial rather than detrimental to chemical language\nmodels","volume":"6","author":"Skinnider","year":"2024","journal-title":"Nat. Mach. Intell."},{"key":"2026091409064180300_cit74","doi-asserted-by":"publisher","first-page":"2075","DOI":"10.1145\/3660799","article-title":"Glitch tokens\nin large language models: Categorization taxonomy and effective detection","volume":"1","author":"Li","year":"2024","journal-title":"Proc. ACM Software Eng.g"},{"key":"2026091409064180300_cit75","doi-asserted-by":"publisher","first-page":"7079","DOI":"10.1039\/D1SC00231G","article-title":"Beyond generative models: superfast\ntraversal, optimization,\nnovelty, exploration and discovery (STONED) algorithm for molecules\nusing SELFIES","volume":"12","author":"Nigam","year":"2021","journal-title":"Chem. Sci."},{"key":"2026091409064180300_cit76","unstructured":"Schulman, J.; Wolski, F.; Dhariwal, P.; Radford, A.; Klimov, O.\n          Proximal Policy Optimization\nAlgorithms. 2017; https:\/\/arxiv.org\/abs\/1707.06347."},{"key":"2026091409064180300_cit77","doi-asserted-by":"crossref","first-page":"53728","DOI":"10.52202\/075280-2338","article-title":"Direct preference optimization:\nYour language model is secretly a\nreward model","volume":"36","author":"Rafailov","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"2026091409064180300_cit78","unstructured":"Wang, Z.; Bi, B.; Pentyala, S. K.; Ramnath, K.; Chaudhuri, S.; Mehrotra, S.; Zixu; ; Zhu; ; Mao, X.-B.; Asur, S.; Na; ; Cheng\n          A\nComprehensive Survey of LLM Alignment\nTechniques: RLHF, RLAIF, PPO, DPO and More. 2024; https:\/\/arxiv.org\/abs\/2407.16216."},{"key":"2026091409064180300_cit79","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1007\/s10822-024-00559-z","article-title":"De novo drug\ndesign as GPT language modeling: large chemistry models with supervised\nand reinforcement learning","volume":"38","author":"Ye","year":"2024","journal-title":"J. Comput.-Aided\nMol. Des."},{"key":"2026091409064180300_cit80","doi-asserted-by":"publisher","first-page":"33712","DOI":"10.1021\/jacs.4c11504","article-title":"Generative Pretrained\nTransformer for Heterogeneous Catalysts","volume":"146","author":"Mok","year":"2024","journal-title":"J.\nAm. Chem. Soc."},{"key":"2026091409064180300_cit81","doi-asserted-by":"crossref","unstructured":"Soares, E.; Sharma, V.; Brazil, E. V.; Cerqueira, R.; Na, Y.-H.\n          Capturing formulation design\nof battery electrolytes with chemical large language model.  AI for Accelerated Materials Design-NeurIPS 2023 Workshop, 2023.","DOI":"10.21203\/rs.3.rs-3593035\/v1"},{"key":"2026091409064180300_cit82","unstructured":"Salij, A.\n          \n          \u03c7hem-GPT Series\nof Models. 2026; 10.5281\/zenodo.19374557."},{"key":"2026091409064180300_cit83","doi-asserted-by":"crossref","unstructured":"Salij, A.; Ullberg, R. S.\n          Generative\nChemical\nLanguage Models for Energetic Materials Discovery (Dataset). 2026; 10.5281\/zenodo.20041207.","DOI":"10.1021\/acs.jcim.6c01013"}],"container-title":["Journal of Chemical Information\nand Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.acs.org\/doi\/pdf\/10.1021\/acs.jcim.6c01013","content-type":"application\/pdf","content-version":"vor","intended-application":"unspecified"},{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article-pdf\/66\/17\/10648\/67392313\/acs.jcim.6c01013.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article-pdf\/66\/17\/10648\/67392313\/acs.jcim.6c01013.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T13:15:18Z","timestamp":1789391718000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article\/66\/17\/10648\/5328185\/Generative-Chemical-Language-Models-for-Energetic"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,24]]},"references-count":83,"journal-issue":{"issue":"17","published-online":{"date-parts":[[2026,8,24]]},"published-print":{"date-parts":[[2026,9,14]]}},"URL":"https:\/\/doi.org\/10.1021\/acs.jcim.6c01013","relation":{},"ISSN":["1549-9596","1549-960X"],"issn-type":[{"value":"1549-9596","type":"print"},{"value":"1549-960X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,24]]}}}