{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,14]],"date-time":"2026-11-14T12:45:37Z","timestamp":1794660337334,"version":"4.9.1"},"reference-count":89,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,12,6]],"date-time":"2024-12-06T00:00:00Z","timestamp":1733443200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,12,6]],"date-time":"2024-12-06T00:00:00Z","timestamp":1733443200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"UK Materials and Molecular Modelling Hub, which is partially funded by EPSRC"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Nat Commun"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>The generation of plausible crystal structures is often the first step in predicting the structure and properties of a material from its chemical composition. However, most current methods for crystal structure prediction are computationally expensive, slowing the pace of innovation. Seeding structure prediction algorithms with quality generated candidates can overcome a major bottleneck. Here, we introduce CrystaLLM, a methodology for the versatile generation of crystal structures, based on the autoregressive large language modeling (LLM) of the Crystallographic Information File (CIF) format. Trained on millions of CIF files, CrystaLLM focuses on modeling crystal structures through text. CrystaLLM can produce plausible crystal structures for a wide range of inorganic compounds unseen in training, as demonstrated by ab initio simulations. Our approach challenges conventional representations of crystals, and demonstrates the potential of LLMs for learning effective models of crystal chemistry, which will lead to accelerated discovery and innovation in materials science.<\/jats:p>","DOI":"10.1038\/s41467-024-54639-7","type":"journal-article","created":{"date-parts":[[2024,12,6]],"date-time":"2024-12-06T05:01:59Z","timestamp":1733461319000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":192,"title":["Crystal structure generation with autoregressive large language modeling"],"prefix":"10.1038","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4867-5635","authenticated-orcid":false,"given":"Luis M.","family":"Antunes","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5432-5597","authenticated-orcid":false,"given":"Keith T.","family":"Butler","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8845-1719","authenticated-orcid":false,"given":"Ricardo","family":"Grau-Crespo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,12,6]]},"reference":[{"key":"54639_CR1","doi-asserted-by":"publisher","first-page":"4562","DOI":"10.1021\/acs.chemmater.5b00716","volume":"27","author":"TF Cerqueira","year":"2015","unstructured":"Cerqueira, T. F. et al. Identification of novel Cu, Ag, and Au ternary oxides from global structural prediction. Chem. Mater. 27, 4562\u20134573 (2015).","journal-title":"Chem. Mater."},{"key":"54639_CR2","doi-asserted-by":"publisher","first-page":"575","DOI":"10.1021\/acsaem.1c03094","volume":"5","author":"B Zhu","year":"2022","unstructured":"Zhu, B. & Scanlon, D. O. Predicting lithium iron oxysulfides for battery cathodes. ACS Appl. Energy Mater. 5, 575\u2013584 (2022).","journal-title":"ACS Appl. Energy Mater."},{"key":"54639_CR3","doi-asserted-by":"publisher","first-page":"6629","DOI":"10.1021\/acs.chemmater.0c02054","volume":"32","author":"AF Harper","year":"2020","unstructured":"Harper, A. F., Evans, M. L. & Morris, A. J. Computational investigation of copper phosphides as conversion anodes for lithium-ion batteries. Chem. Mater. 32, 6629\u20136639 (2020).","journal-title":"Chem. Mater."},{"key":"54639_CR4","doi-asserted-by":"publisher","first-page":"331","DOI":"10.1038\/s41578-019-0101-8","volume":"4","author":"AR Oganov","year":"2019","unstructured":"Oganov, A. R., Pickard, C. J., Zhu, Q. & Needs, R. J. Structure prediction drives materials discovery. Nat. Rev. Mater. 4, 331\u2013348 (2019).","journal-title":"Nat. Rev. Mater."},{"key":"54639_CR5","doi-asserted-by":"crossref","unstructured":"Oganov, A. R. Modern Methods of Crystal Structure Prediction (John Wiley & Sons, 2011).","DOI":"10.1002\/9783527632831"},{"key":"54639_CR6","doi-asserted-by":"publisher","first-page":"045504","DOI":"10.1103\/PhysRevLett.97.045504","volume":"97","author":"CJ Pickard","year":"2006","unstructured":"Pickard, C. J. & Needs, R. High-pressure phases of silane. Phys. Rev. Lett. 97, 045504 (2006).","journal-title":"Phys. Rev. Lett."},{"key":"54639_CR7","doi-asserted-by":"publisher","first-page":"053201","DOI":"10.1088\/0953-8984\/23\/5\/053201","volume":"23","author":"CJ Pickard","year":"2011","unstructured":"Pickard, C. J. & Needs, R. Ab initio random structure searching. J. Phys. Condens. Matter 23, 053201 (2011).","journal-title":"J. Phys. Condens. Matter"},{"key":"54639_CR8","doi-asserted-by":"publisher","first-page":"244704","DOI":"10.1063\/1.2210932","volume":"124","author":"AR Oganov","year":"2006","unstructured":"Oganov, A. R. & Glass, C. W. Crystal structure prediction using ab initio evolutionary techniques: principles and applications. J. Chem. Phys. 124, 244704 (2006).","journal-title":"J. Chem. Phys."},{"key":"54639_CR9","doi-asserted-by":"publisher","first-page":"547","DOI":"10.1038\/s41586-018-0337-2","volume":"559","author":"KT Butler","year":"2018","unstructured":"Butler, K. T., Davies, D. W., Cartwright, H., Isayev, O. & Walsh, A. Machine learning for molecular and materials science. Nature 559, 547\u2013555 (2018).","journal-title":"Nature"},{"key":"54639_CR10","doi-asserted-by":"publisher","first-page":"064114","DOI":"10.1103\/PhysRevB.99.064114","volume":"99","author":"EV Podryabinkin","year":"2019","unstructured":"Podryabinkin, E. V., Tikhonov, E. V., Shapeev, A. V. & Oganov, A. R. Accelerating crystal structure prediction by machine-learning interatomic potentials with active learning. Phys. Rev. B 99, 064114 (2019).","journal-title":"Phys. Rev. B"},{"key":"54639_CR11","doi-asserted-by":"publisher","DOI":"10.1038\/s41524-022-00734-6","volume":"8","author":"K Choudhary","year":"2022","unstructured":"Choudhary, K. et al. Recent advances and applications of deep learning methods in materials science. npj Comput. Mater. 8, 59 (2022).","journal-title":"npj Comput. Mater."},{"key":"54639_CR12","unstructured":"Goodfellow, I. et al. Generative Adversarial Nets. In Advances in Neural Information Processing Systems vol. 27 (eds Ghahramani, Z., Welling, M., Cortes, C., Lawrence, N. & Weinberger, K.) (Curran Associates, Inc., 2014). https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2014\/file\/5ca3e9b122f61f8f06494c97b1afccf3-Paper.pdf."},{"key":"54639_CR13","doi-asserted-by":"publisher","first-page":"4518","DOI":"10.1021\/acs.jcim.0c00464","volume":"60","author":"CJ Court","year":"2020","unstructured":"Court, C. J., Yildirim, B., Jain, A. & Cole, J. M. 3-D inorganic crystal structure generation and property prediction via representation learning. J. Chem. Inf. Model. 60, 4518\u20134535 (2020).","journal-title":"J. Chem. Inf. Model."},{"key":"54639_CR14","unstructured":"Xie, T., Fu, X., Ganea, O.-E., Barzilay, R. & Jaakkola, T. Crystal diffusion variational autoencoder for periodic material generation. arXiv preprint arXiv:2110.06197 (2021)."},{"key":"54639_CR15","doi-asserted-by":"publisher","first-page":"572","DOI":"10.1038\/s43588-023-00471-w","volume":"3","author":"D Yan","year":"2023","unstructured":"Yan, D., Smith, A. D. & Chen, C.-C. Structure prediction and materials design with generative neural networks. Nat. Comput. Sci. 3, 572\u2013574 (2023).","journal-title":"Nat. Comput. Sci."},{"key":"54639_CR16","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1039\/D3DD00137G","volume":"3","author":"M Alverson","year":"2024","unstructured":"Alverson, M. et al. Generative adversarial networks and diffusion models in material discovery. Digit. Discov. 3, 62\u201380 (2024).","journal-title":"Digit. Discov."},{"key":"54639_CR17","first-page":"4","volume":"1","author":"L Chen","year":"2021","unstructured":"Chen, L., Zhang, W., Nie, Z., Li, S. & Pan, F. Generative models for inverse design of inorganic solid materials. J. Mater. Inf. 1, 4 (2021).","journal-title":"J. Mater. Inf."},{"key":"54639_CR18","unstructured":"Cao, Y. et al. A comprehensive survey of ai-generated content (AIGC): a history of generative AI from GAN to ChatGPT. arXiv preprint arXiv:2303.04226 (2023)."},{"key":"54639_CR19","unstructured":"Vaswani, A. et al. Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)."},{"key":"54639_CR20","unstructured":"Radford, A., Narasimhan, K., Salimans, T., Sutskever, I. et al. Improving Language Understanding by Generative Pre-Training. Technical Reports. OpenAI (2018). https:\/\/cdn.openai.com\/research-covers\/language-unsupervised\/language_understanding_paper.pdf."},{"key":"54639_CR21","unstructured":"Introducing ChatGPT. OpenAI Blog, accessed 07 October 2024. https:\/\/openai.com\/blog\/chatgpt."},{"key":"54639_CR22","doi-asserted-by":"publisher","first-page":"798","DOI":"10.1016\/j.jmat.2023.05.001","volume":"9","author":"Y Liu","year":"2023","unstructured":"Liu, Y. et al. Generative artificial intelligence and its applications in materials science: current situation and future perspectives. J. Materiomics 9, 798\u2013816 (2023).","journal-title":"J. Materiomics"},{"key":"54639_CR23","doi-asserted-by":"crossref","unstructured":"Bran, A. M., Cox, S., Schilter, O., Baldassari, C., White, A. D. & Schwaller, P. Augmenting large language models with chemistry tools. Nat. Mach. Intell. 6, 525\u2013535 (2024).","DOI":"10.1038\/s42256-024-00832-8"},{"key":"54639_CR24","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1038\/s42256-023-00788-1","volume":"6","author":"KM Jablonka","year":"2024","unstructured":"Jablonka, K. M., Schwaller, P., Ortega-Guerrero, A. & Smit, B. Leveraging large language models for predictive chemistry. Nat. Mach. Intell. 6, 161\u2013169 (2024).","journal-title":"Nat. Mach. Intell."},{"key":"54639_CR25","doi-asserted-by":"crossref","unstructured":"Xie, T. et al. Large language models as master key: unlocking the secrets of materials science with GPT. arXiv preprint arXiv:2304.02213 (2023).","DOI":"10.2139\/ssrn.4534137"},{"key":"54639_CR26","doi-asserted-by":"publisher","first-page":"015001","DOI":"10.1088\/2632-2153\/acadcd","volume":"4","author":"N Fu","year":"2023","unstructured":"Fu, N. et al. Material transformers: deep learning language models for generative materials design. Mach. Learn. Sci. Technol. 4, 015001 (2023).","journal-title":"Mach. Learn. Sci. Technol."},{"key":"54639_CR27","doi-asserted-by":"publisher","first-page":"1233","DOI":"10.1039\/D3DD00113J","volume":"2","author":"KM Jablonka","year":"2023","unstructured":"Jablonka, K. M. et al. 14 examples of how LLMs can transform materials science and chemistry: a reflection on a large language model hackathon. Digit. Discov. 2, 1233\u20131250 (2023).","journal-title":"Digit. Discov."},{"key":"54639_CR28","doi-asserted-by":"publisher","first-page":"570","DOI":"10.1038\/s41586-023-06792-0","volume":"624","author":"DA Boiko","year":"2023","unstructured":"Boiko, D. A., MacKnight, R., Kline, B. & Gomes, G. Autonomous chemical research with large language models. Nature 624, 570\u2013578 (2023).","journal-title":"Nature"},{"key":"54639_CR29","unstructured":"Flam-Shepherd, D. & Aspuru-Guzik, A. Language models can generate molecules, materials, and protein binding sites directly in three dimensions as XYZ, CIF, and PDB files. arXiv preprint arXiv:2305.05708 (2023)."},{"key":"54639_CR30","doi-asserted-by":"publisher","first-page":"655","DOI":"10.1107\/S010876739101067X","volume":"47","author":"SR Hall","year":"1991","unstructured":"Hall, S. R., Allen, F. H. & Brown, I. D. The crystallographic information file (CIF): a new standard archive file for crystallography. Acta Crystallogr. Sect. A Found. Crystallogr. 47, 655\u2013685 (1991).","journal-title":"Acta Crystallogr. Sect. A Found. Crystallogr."},{"key":"54639_CR31","unstructured":"Chen, M. et al. Generative pretraining from pixels. In Proc. International Conference on Machine Learning 1691\u20131703 (PMLR, 2020)."},{"key":"54639_CR32","doi-asserted-by":"publisher","first-page":"3564","DOI":"10.1021\/acs.chemmater.9b01294","volume":"31","author":"C Chen","year":"2019","unstructured":"Chen, C., Ye, W., Zuo, Y., Zheng, C. & Ong, S. P. Graph networks as a universal machine learning framework for molecules and crystals. Chem. Mater. 31, 3564\u20133572 (2019).","journal-title":"Chem. Mater."},{"key":"54639_CR33","doi-asserted-by":"crossref","unstructured":"Toshniwal, S., Wiseman, S., Livescu, K. & Gimpel, K. Chess as a testbed for language model state tracking. In Proc. AAAI Conference on Artificial Intelligence Vol. 36, 11385\u201311393 (Association for the Advancement of Artificial Intelligence (AAAI), 2022).","DOI":"10.1609\/aaai.v36i10.21390"},{"key":"54639_CR34","unstructured":"Li, K. et al. Emergent world representations: exploring a sequence model trained on a synthetic task. In The Eleventh International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=DeG07_TcZvT (2023)."},{"key":"54639_CR35","doi-asserted-by":"crossref","unstructured":"Coulom, R. Efficient selectivity and backup operators in monte-carlo tree search. In International Conference on Computers and Games 72\u201383 (Springer, 2006).","DOI":"10.1007\/978-3-540-75538-8_7"},{"key":"54639_CR36","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TCIAIG.2012.2186810","volume":"4","author":"CB Browne","year":"2012","unstructured":"Browne, C. B. et al. A survey of Monte Carlo tree search methods. IEEE Trans. Comput. Intell. AI Games 4, 1\u201343 (2012).","journal-title":"IEEE Trans. Comput. Intell. AI Games"},{"key":"54639_CR37","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T. et al. Language models are few-shot learners. Adv. Neural Inf. Process. Syst. 33, 1877\u20131901 (2020).","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"54639_CR38","doi-asserted-by":"publisher","DOI":"10.1038\/s41524-022-00729-3","volume":"8","author":"LM Antunes","year":"2022","unstructured":"Antunes, L. M., Grau-Crespo, R. & Butler, K. T. Distributed representations of atoms and materials for machine learning. npj Comput. Mater. 8, 44 (2022).","journal-title":"npj Comput. Mater."},{"key":"54639_CR39","doi-asserted-by":"publisher","first-page":"1558","DOI":"10.1039\/D3DD00121K","volume":"2","author":"A Onwuli","year":"2023","unstructured":"Onwuli, A., Hegde, A. V., Nguyen, K. V., Butler, K. T. & Walsh, A. Element similarity in high-dimensional materials representations. Digit. Discov. 2, 1558\u20131564 (2023).","journal-title":"Digit. Discov."},{"key":"54639_CR40","unstructured":"Jiao, R. et al. Crystal structure prediction by joint equivariant diffusion. arXiv preprint arXiv:2309.04475 (2023)."},{"key":"54639_CR41","unstructured":"Jiao, R., Huang, W., Liu, Y., Zhao, D. & Liu, Y. Space group constrained crystal generation. arXiv preprint arXiv:2402.03992 (2024)."},{"key":"54639_CR42","unstructured":"Yang, M. et al. Scalable diffusion for materials generation. arXiv preprint arXiv:2311.09235 (2023)."},{"key":"54639_CR43","unstructured":"Gruver, N. et al. Fine-tuned language models generate stable inorganic materials as text. arXiv preprint arXiv:2402.04379 (2024)."},{"key":"54639_CR44","unstructured":"Touvron, H. et al. LLaMA: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)."},{"key":"54639_CR45","doi-asserted-by":"crossref","unstructured":"\u00c7i\u00e7ek, \u00d6., Abdulkadir, A., Lienkamp, S. S., Brox, T. & Ronneberger, O. 3D U-Net: Learning dense volumetric segmentation from sparse annotation. In Medical Image Computing and Computer-Assisted Intervention\u2013MICCAI 2016: 19th International Conference, Athens, Greece, October 17-21, 2016, Proceedings, Part II 19, 424\u2013432 (Springer, 2016).","DOI":"10.1007\/978-3-319-46723-8_49"},{"key":"54639_CR46","first-page":"8633","volume":"35","author":"J Ho","year":"2022","unstructured":"Ho, J. et al. Video diffusion models. Adv. Neural Inf. Process. Syst. 35, 8633\u20138646 (2022).","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"54639_CR47","doi-asserted-by":"publisher","first-page":"9034","DOI":"10.1039\/c2ee22341d","volume":"5","author":"IE Castelli","year":"2012","unstructured":"Castelli, I. E. et al. New cubic perovskites for one- and two-photonwater splitting using the computational materials repository. Energy Environ. Sci. 5, 9034\u20139043 (2012).","journal-title":"Energy Environ. Sci."},{"key":"54639_CR48","doi-asserted-by":"publisher","first-page":"5814","DOI":"10.1039\/C1EE02717D","volume":"5","author":"IE Castelli","year":"2012","unstructured":"Castelli, I. E. et al. Computational screening of perovskite metal oxides for optimal solar light capture. Energy Environ. Sci. 5, 5814\u20135819 (2012).","journal-title":"Energy Environ. Sci."},{"key":"54639_CR49","unstructured":"Pickard, C. J. AIRSS Data for Carbon at 10GPa and the C+N+H+O System at 1GPa. https:\/\/archive.materialscloud.org\/record\/2020.0026\/v1 (2020)."},{"key":"54639_CR50","doi-asserted-by":"publisher","first-page":"011002","DOI":"10.1063\/1.4812323","volume":"1","author":"A Jain","year":"2013","unstructured":"Jain, A. et al. Commentary: the materials project: a materials genome approach to accelerating materials innovation. APL Mater. 1, 011002 (2013).","journal-title":"APL Mater."},{"key":"54639_CR51","unstructured":"Baird, S. mp-time-split, accessed in 2024. https:\/\/github.com\/sparks-baird\/mp-time-split (2023)."},{"key":"54639_CR52","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1016\/S0304-8853(99)00452-7","volume":"204","author":"T Mazet","year":"1999","unstructured":"Mazet, T., Welter, R. & Malaman, B. A study of the new ferromagnetic YbMn6Sn6 compound by magnetization and neutron diffraction measurements. J. Magn. Magn. Mater. 204, 11\u201319 (1999).","journal-title":"J. Magn. Magn. Mater."},{"key":"54639_CR53","doi-asserted-by":"publisher","first-page":"675","DOI":"10.1016\/0022-3697(64)90176-3","volume":"25","author":"B Pamplin","year":"1964","unstructured":"Pamplin, B. A systematic method of deriving new semiconducting compounds by structural analogy. J. Phys. Chem. Solids 25, 675\u2013684 (1964).","journal-title":"J. Phys. Chem. Solids"},{"key":"54639_CR54","doi-asserted-by":"publisher","first-page":"617","DOI":"10.1016\/j.chempr.2016.09.010","volume":"1","author":"DW Davies","year":"2016","unstructured":"Davies, D. W. et al. Computational screening of all stoichiometric inorganic materials. Chem 1, 617\u2013627 (2016).","journal-title":"Chem"},{"key":"54639_CR55","doi-asserted-by":"publisher","first-page":"918","DOI":"10.1107\/S160057671900997X","volume":"52","author":"D Zagorac","year":"2019","unstructured":"Zagorac, D., M\u00fcller, H., Ruehl, S., Zagorac, J. & Rehme, S. Recent developments in the inorganic crystal structure database: theoretical crystal structure data and related features. J. Appl. Crystallogr. 52, 918\u2013925 (2019).","journal-title":"J. Appl. Crystallogr."},{"key":"54639_CR56","doi-asserted-by":"publisher","first-page":"8519","DOI":"10.1021\/acs.inorgchem.2c04312","volume":"62","author":"S Ponou","year":"2023","unstructured":"Ponou, S., Lidin, S. & Mudring, A.-V. Optimization of chemical bonding through defect formation and ordering\u2013the case of Mg7Pt4Ge4. Inorg. Chem. 62, 8519\u20138529 (2023).","journal-title":"Inorg. Chem."},{"key":"54639_CR57","doi-asserted-by":"publisher","first-page":"868","DOI":"10.1107\/S2052520617007983","volume":"73","author":"J Gonz\u00e1lez-L\u00f3pez","year":"2017","unstructured":"Gonz\u00e1lez-L\u00f3pez, J., Cockcroft, J. K., Fern\u00e1ndez-Gonz\u00e1lez, A., Jimenez, A. & Grau-Crespo, R. Crystal structure of cobalt hydroxide carbonate Co2CO3(OH)2: density functional theory and X-ray diffraction investigation. Acta Crystallogr. Sect. B Struct. Sci. Cryst. Eng. Mater. 73, 868\u2013873 (2017).","journal-title":"Acta Crystallogr. Sect. B Struct. Sci. Cryst. Eng. Mater."},{"key":"54639_CR58","unstructured":"Speech Understanding Systems. Summary of Results of the Five-Year Research Effort at Carnegie-Mellon University Technical Reports 1529, Carnegie-Mellon Univ Pittsburgh PA Dept Of Computer Science (1977)."},{"key":"54639_CR59","doi-asserted-by":"crossref","unstructured":"Chaffin, A., Claveau, V. & Kijak, E. PPL-MCTS: Constrained Textual Generation Through Discriminator-Guided MCTS Decoding. In Carpuat, M., de Marneffe, M. & Ru\u00edz, I. V. M. (eds.) Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL 2022, Seattle, WA, United States, July 10-15, 2022, 2953\u20132967 (Association for Computational Linguistics, 2022).","DOI":"10.18653\/v1\/2022.naacl-main.215"},{"key":"54639_CR60","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1007\/s10472-011-9258-6","volume":"61","author":"CD Rosin","year":"2011","unstructured":"Rosin, C. D. Multi-armed bandits with episode context. Ann. Math. Artif. Intell. 61, 203\u2013230 (2011).","journal-title":"Ann. Math. Artif. Intell."},{"key":"54639_CR61","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1038\/nature16961","volume":"529","author":"D Silver","year":"2016","unstructured":"Silver, D. et al. Mastering the game of Go with deep neural networks and tree search. Nature 529, 484\u2013489 (2016).","journal-title":"Nature"},{"key":"54639_CR62","doi-asserted-by":"publisher","DOI":"10.1038\/s41524-021-00650-1","volume":"7","author":"K Choudhary","year":"2021","unstructured":"Choudhary, K. & DeCost, B. Atomistic line graph neural network for improved materials property predictions. npj Comput. Mater. 7, 185 (2021).","journal-title":"npj Comput. Mater."},{"key":"54639_CR63","doi-asserted-by":"publisher","first-page":"12027","DOI":"10.1021\/acs.inorgchem.3c01510","volume":"62","author":"P Hyde","year":"2023","unstructured":"Hyde, P. et al. Lithium intercalation into the excitonic insulator candidate Ta2NiSe5. Inorg. Chem. 62, 12027\u201312037 (2023).","journal-title":"Inorg. Chem."},{"key":"54639_CR64","doi-asserted-by":"publisher","first-page":"111496","DOI":"10.1016\/j.commatsci.2022.111496","volume":"211","author":"M Kusaba","year":"2022","unstructured":"Kusaba, M., Liu, C. & Yoshida, R. Crystal structure prediction with machine learning-based element substitution. Comput. Mater. Sci. 211, 111496 (2022).","journal-title":"Comput. Mater. Sci."},{"key":"54639_CR65","doi-asserted-by":"publisher","first-page":"8431","DOI":"10.1021\/acs.inorgchem.1c03879","volume":"61","author":"L Wei","year":"2022","unstructured":"Wei, L. et al. TCSP: a template-based crystal structure prediction algorithm for materials discovery. Inorg. Chem. 61, 8431\u20138439 (2022).","journal-title":"Inorg. Chem."},{"key":"54639_CR66","doi-asserted-by":"publisher","first-page":"107810","DOI":"10.1016\/j.cpc.2020.107810","volume":"261","author":"S Fredericks","year":"2021","unstructured":"Fredericks, S., Parrish, K., Sayre, D. & Zhu, Q. PyXtal: a python library for crystal structure generation and symmetry analysis. Comput. Phys. Commun. 261, 107810 (2021).","journal-title":"Comput. Phys. Commun."},{"key":"54639_CR67","doi-asserted-by":"publisher","first-page":"208","DOI":"10.1016\/j.cpc.2016.12.005","volume":"213","author":"P Avery","year":"2017","unstructured":"Avery, P. & Zurek, E. RandSpg: an open-source program for generating atomistic crystal structures with specific spacegroups. Comput. Phys. Commun. 213, 208\u2013216 (2017).","journal-title":"Comput. Phys. Commun."},{"key":"54639_CR68","doi-asserted-by":"publisher","first-page":"80","DOI":"10.1038\/s41586-023-06735-9","volume":"624","author":"A Merchant","year":"2023","unstructured":"Merchant, A. et al. Scaling deep learning for materials discovery. Nature 624, 80\u201385 (2023).","journal-title":"Nature"},{"key":"54639_CR69","unstructured":"Sutton, R. S. & Barto, A. G. Reinforcement Learning: An Introduction (MIT Press, 2018)."},{"key":"54639_CR70","unstructured":"Ziegler, D. M. et al. Fine-tuning language models from human preferences. arXiv preprint arXiv:1909.08593 (2019)."},{"key":"54639_CR71","unstructured":"Illustrating Reinforcement Learning from Human Feedback (RLHF). Accessed: 2023-07-05. https:\/\/huggingface.co\/blog\/rlhf."},{"key":"54639_CR72","doi-asserted-by":"publisher","DOI":"10.1038\/s41524-022-00792-w","volume":"8","author":"S Kang","year":"2022","unstructured":"Kang, S. et al. Accelerated identification of equilibrium structures of multicomponent inorganic crystals using machine learning potentials. npj Comput. Mater. 8, 108 (2022).","journal-title":"npj Comput. Mater."},{"key":"54639_CR73","doi-asserted-by":"publisher","first-page":"718","DOI":"10.1038\/s43588-022-00349-3","volume":"2","author":"C Chen","year":"2022","unstructured":"Chen, C. & Ong, S. P. A universal graph deep learning interatomic potential for the periodic table. Nat. Comput. Sci. 2, 718\u2013728 (2022).","journal-title":"Nat. Comput. Sci."},{"key":"54639_CR74","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1002\/zaac.19693640107","volume":"364","author":"G Pausewang","year":"1969","unstructured":"Pausewang, G. & R\u00fcdorff, W. \u00dcber alkali-oxofluorometallate der \u00dcbergangsmetalle. $${{{\\rm{A}}}}_{3}^{{\\prime} }$$MeOxF6\u2212x-Verbindungen mit x = 1, 2, 3. Z. Anorg. Allg. Chem. 364, 69\u201387 (1969).","journal-title":"Z. Anorg. Allg. Chem."},{"key":"54639_CR75","doi-asserted-by":"publisher","first-page":"053805","DOI":"10.1103\/PhysRevMaterials.7.053805","volume":"7","author":"VI Hegde","year":"2023","unstructured":"Hegde, V. I. et al. Quantifying uncertainty in high-throughput density functional theory: a comparison of AFLOW, materials project, and OQMD. Phys. Rev. Mater. 7, 053805 (2023).","journal-title":"Phys. Rev. Mater."},{"key":"54639_CR76","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-022-01438-8","volume":"9","author":"W Ye","year":"2022","unstructured":"Ye, W., Lei, X., Aykol, M. & Montoya, J. H. Novel inorganic crystal structures predicted using autonomous simulation agents. Sci. Data 9, 302 (2022).","journal-title":"Sci. Data"},{"key":"54639_CR77","doi-asserted-by":"crossref","unstructured":"Antunes, L. M. et al. Machine learning approaches for accelerating the discovery of thermoelectric materials. In Machine Learning in Materials Informatics: Methods and Applications, 1\u201332 (ACS Publications, 2022).","DOI":"10.1021\/bk-2022-1416.ch001"},{"key":"54639_CR78","doi-asserted-by":"publisher","first-page":"1501","DOI":"10.1007\/s11837-013-0755-4","volume":"65","author":"JE Saal","year":"2013","unstructured":"Saal, J. E., Kirklin, S., Aykol, M., Meredig, B. & Wolverton, C. Materials design and discovery with high-throughput density functional theory: the open quantum materials database (OQMD). JOM 65, 1501\u20131509 (2013).","journal-title":"JOM"},{"key":"54639_CR79","doi-asserted-by":"publisher","first-page":"036001","DOI":"10.1088\/2515-7639\/ab13bb","volume":"2","author":"C Draxl","year":"2019","unstructured":"Draxl, C. & Scheffler, M. The NOMAD laboratory: from data sharing to artificial intelligence. J. Phys. Mater. 2, 036001 (2019).","journal-title":"J. Phys. Mater."},{"key":"54639_CR80","doi-asserted-by":"publisher","first-page":"314","DOI":"10.1016\/j.commatsci.2012.10.028","volume":"68","author":"SP Ong","year":"2013","unstructured":"Ong, S. P. et al. Python materials genomics (pymatgen): a robust, open-source Python library for materials analysis. Comput. Mater. Sci. 68, 314\u2013319 (2013).","journal-title":"Comput. Mater. Sci."},{"key":"54639_CR81","unstructured":"Liu, P. J. et al. Generating Wikipedia by Summarizing Long Sequences. In 6th International Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada, April 30 - May 3, 2018, Conference Track Proceedings (2018)."},{"key":"54639_CR82","doi-asserted-by":"crossref","unstructured":"Togo, A. & Tanaka, I. Spglib: a software library for crystal symmetry search. Sci. Technol. Adv. Mater. Methods 31, 2384822 (2024).","DOI":"10.1080\/27660400.2024.2384822"},{"key":"54639_CR83","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1016\/j.commatsci.2018.05.018","volume":"152","author":"L Ward","year":"2018","unstructured":"Ward, L. et al. Matminer: an open source toolkit for materials data mining. Comput. Mater. Sci. 152, 60\u201369 (2018).","journal-title":"Comput. Mater. Sci."},{"key":"54639_CR84","doi-asserted-by":"publisher","first-page":"3865","DOI":"10.1103\/PhysRevLett.77.3865","volume":"77","author":"JP Perdew","year":"1996","unstructured":"Perdew, J. P., Burke, K. & Ernzerhof, M. Generalized gradient approximation made simple. Phys. Rev. Lett. 77, 3865 (1996).","journal-title":"Phys. Rev. Lett."},{"key":"54639_CR85","doi-asserted-by":"publisher","first-page":"2295","DOI":"10.1016\/j.commatsci.2011.02.023","volume":"50","author":"A Jain","year":"2011","unstructured":"Jain, A. et al. A high-throughput infrastructure for density functional theory calculations. Comput. Mater. Sci. 50, 2295\u20132310 (2011).","journal-title":"Comput. Mater. Sci."},{"key":"54639_CR86","unstructured":"Horton, M. et al. Crystal toolkit: a web app framework to improve usability and accessibility of materials science research algorithms. arXiv preprint arXiv:2302.06147 (2023)."},{"key":"54639_CR87","doi-asserted-by":"publisher","unstructured":"Antunes, L., Butler, K. & Grau-Crespo, R. Supporting data for: crystal structure generation with autoregressive large language modeling. https:\/\/doi.org\/10.5281\/zenodo.10642388 (2024).","DOI":"10.5281\/zenodo.10642388"},{"key":"54639_CR88","unstructured":"Creative Commons Attribution 4.0 License, accessed 26 June 2023. https:\/\/creativecommons.org\/licenses\/by\/4.0\/."},{"key":"54639_CR89","doi-asserted-by":"publisher","unstructured":"Antunes, L. lantunes\/CrystaLLM: CrystaLLM v1.0. https:\/\/doi.org\/10.5281\/zenodo.13883399 (2024).","DOI":"10.5281\/zenodo.13883399"}],"container-title":["Nature Communications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41467-024-54639-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41467-024-54639-7","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41467-024-54639-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,6]],"date-time":"2024-12-06T06:02:46Z","timestamp":1733464966000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41467-024-54639-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,6]]},"references-count":89,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2024,12]]}},"alternative-id":["54639"],"URL":"https:\/\/doi.org\/10.1038\/s41467-024-54639-7","relation":{},"ISSN":["2041-1723"],"issn-type":[{"value":"2041-1723","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,6]]},"assertion":[{"value":"22 December 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 November 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 December 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"10570"}}