AI-assisted rapid crystal structure generation towards a target local environment
Source abstract
Abstract
In material design, traditional crystal structure prediction approaches are expensive as they require extensive structural sampling through expensive energy minimization methods. Emerging artificial intelligence (AI) generative models have shown great promise in rapidly generating realistic crystals, but they typically handle only a few tens of atoms per unit cell. To overcome this limitation, we introduce a symmetry-informed approach, the Local Environment Geometry-Oriented Crystal Generator (LEGO-xtal). Our method generates initial structures using AI models trained on an augmented dataset, and then optimizes them using structure descriptors rather than energy-based optimization. We demonstrate its effectiveness by expanding from 25 known low-energy sp2 carbon allotropes to over 1700, all within 0.5 eV/atom of the ground-state energy of graphite. This framework offers a generalizable strategy for the targeted design of materials with modular building blocks, such as metal-organic frameworks and battery materials.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Machine Learning in Materials Science · Advanced Electron Microscopy Techniques and Applications · Enzyme Structure and Function
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (82)
Show source-provided references
1. Jumper, J. et al. Highly accurate protein structure prediction with alphafold. Nature 596, 583–589 (2021).10.1038/s41586-021-03819-2 ↗
2. Oganov, A. R., Pickard, C. J., Zhu, Q. & Needs, R. J. Structure prediction drives materials discovery. Nat. Rev. Mater. 4, 331–348 (2019).10.1038/s41578-019-0101-8 ↗
3. Pickard, C. J. & Needs, R. Ab initio random structure searching. J. Phys. 23, 053201 (2011).
4. Oganov, A. R. & Glass, C. W. Crystal structure prediction using ab initio evolutionary techniques: principles and applications. J. Chem. Phys. 124, 244704 (2006).10.1063/1.2210932 ↗
5. Oganov, A. R., Lyakhov, A. O. & Valle, M. How evolutionary crystal structure prediction works and why. Acc. Chem. Res. 44, 227–237 (2011).10.1021/ar1001318 ↗
6. Stillinger, F. H. Exponential multiplicity of inherent structures. Phys. Rev. E. 59, 48 (1999).10.1103/PhysRevE.59.48 ↗
7. Martiniani, S., Schrenk, K. J., Stevenson, J. D., Wales, D. J. & Frenkel, D. Structural analysis of high-dimensional basins of attraction. Phys. Rev. E 94, 031301 (2016).10.1103/PhysRevE.94.031301 ↗
8. Wang, Y., Lv, J., Zhu, L. & Ma, Y. Crystal structure prediction via particle-swarm optimization. Phys. Rev. B 82, 094116 (2010).10.1103/PhysRevB.82.094116 ↗
9. Lonie, D. C. & Zurek, E. Xtalopt: an open-source evolutionary algorithm for crystal structure prediction. Comput. Phys. Commun. 182, 372–387 (2011).10.1016/j.cpc.2010.07.048 ↗
10. Revard, B. C., Tipton, W. W. & Hennig, R. G. Genetic algorithm for structure and phase prediction https://github.com/henniggroup/GASP-python (2018).
11. Pannetier, J., Bassas-Alsina, J., Rodriguez-Carvajal, J. & Caignaert, V. Prediction of crystal structures from crystal chemistry rules by simulated annealing. Nature 346, 343 (1990).10.1038/346343a0 ↗
12. Banerjee, A., Jasrasaria, D., Niblett, S. P. & Wales, D. J. Crystal structure prediction for benzene using basin-hopping global optimization. J. Phys. Chem. A 125, 3776–3784 (2021).10.1021/acs.jpca.1c00903 ↗
13. Han, Y. et al. Efficient crystal structure prediction based on the symmetry principle. Nat. Comput. Sci. 5, 1–13 (2025).10.1038/s43588-025-00775-z ↗
14. Lyakhov, A. O., Oganov, A. R. & Valle, M. How to predict very large and complex crystal structures. Comput. Phys. Commun. 181, 1623–1632 (2010).10.1016/j.cpc.2010.06.007 ↗
15. Zhu, Q., Oganov, A. R. & Lyakhov, A. O. Evolutionary metadynamics: a novel method to predict crystal structures. CrystEngComm 14, 3596–3601 (2012).10.1039/c2ce06642d ↗
16. Zhu, Q., Oganov, A. R., Lyakhov, A. O. & Yu, X. Generalized evolutionary metadynamics for sampling the energy landscapes and its applications. Phys. Rev. B 92, 024106 (2015).10.1103/PhysRevB.92.024106 ↗
17. Kim, S., Noh, J., Gu, G. H., Aspuru-Guzik, A. & Jung, Y. Generative adversarial networks for crystal structure prediction. ACS Cent. Sci. 6, 1412–1420 (2020).10.1021/acscentsci.0c00426 ↗
18. Zhu, R., Nong, W., Yamazaki, S. & Hippalgaonkar, K. Wycryst: Wyckoff inorganic crystal generator framework. Matter 7, 3469–3488 (2024).10.1016/j.matt.2024.05.042 ↗
19. Noh, J. et al. Inverse design of solid-state materials via a continuous representation. Matter 1, 1370–1384 (2019).10.1016/j.matt.2019.08.017 ↗
20. Merchant, A. et al. Scaling deep learning for materials discovery. Nature 624, 80–85 (2023).10.1038/s41586-023-06735-9 ↗
21. Xie, T., Fu, X., Ganea, O.-E., Barzilay, R. & Jaakkola, T. Crystal diffusion variational autoencoder for periodic material generation. In International Conference on Learning Representations (2022).
22. Jiao, R. et al. Crystal structure prediction by joint equivariant diffusion. In Advances in Neural Information Processing Systems, Vol. 36, (eds, Oh, A. et al.) 17464–17497 (Curran Associates, Inc., 2023).
23. Zeni, C. et al. A generative model for inorganic materials design. Nature 639, 624–632 (2025).10.1038/s41586-025-08628-5 ↗
24. Levy, D. et al. SymmCD: Symmetry-preserving crystal generation with diffusion models. In AI for Accelerated Materials Design - NeurIPS https://openreview.net/forum?id=V7x2KZQn2v (2024).
25. Jiao, R., Huang, W., Liu, Y., Zhao, D. & Liu, Y. Space group constrained crystal generation. In The Twelfth International Conference on Learning Representations (2024).
26. Miller, B. K., Chen, R. T. Q., Sriram, A. & Wood, B. M. FlowMM: Generating materials with riemannian flow matching. In Forty-first International Conference on Machine Learning https://openreview.net/forum?id=W4pB7VbzZI (2024).
27. Zhong, P., Dai, X., Deng, B., Ceder, G. & Persson, K. A. Practical approaches for crystal structure predictions with inpainting generation and universal interatomic potentials. In AI4X 2025 International Conference (2025).
28. Antunes, L. M., Butler, K. T. & Grau-Crespo, R. Crystal structure generation with autoregressive large language modeling. Nat. Commun. 15, 1–16 (2024).10.1038/s41467-024-54639-7 ↗
29. Gruver, N. et al. Fine-tuned language models generate stable inorganic materials as text. In The Twelfth International Conference on Learning Representations (2024).
30. Cao, Z., Luo, X., Lv, J. & Wang, L. Space group informed transformer for crystalline materials generation. Sci. Bull. 70, 3522–3533 (2025).10.1016/j.scib.2025.09.035 ↗
31. Kazeev, N. et al. Wyckoff transformer: Generation of symmetric crystals. In Forty-second International Conference on Machine Learning (2025).
32. Cheetham, A. K. & Seshadri, R. Artificial intelligence driving materials discovery? perspective on the article: scaling deep learning for materials discovery. Chem. Mater. 36, 3490–3495 (2024).10.1021/acs.chemmater.4c00643 ↗
33. Souvignier, B., Wondratschek, H., Aroyo, M. I., Chapuis, G. & Glazer, A. M. Space groups and their descriptions. In International Tables for Crystallography, Vol. A, 42–74 (Wiley-VCH, 2016).10.1107/97809553602060000922 ↗
34. Hall, S. R., Allen, F. H. & Brown, I. D. The crystallographic information file (CIF): a new standard archive file for crystallography. Acta Cryst. Sec. A 47, 655–685 (1991).10.1107/S010876739101067X ↗
35. Wondratschek, H. & Müller, U. Symmetry Relations Between Space Groups (International Union of Crystallography, 2006).10.1107/97809553602060000101 ↗
36. 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).10.1016/j.cpc.2020.107810 ↗
37. Steinhardt, P. J., Nelson, D. R. & Ronchetti, M. Bond-orientational order in liquids and glasses. Phys. Rev. B 28, 784–805 (1983).10.1103/PhysRevB.28.784 ↗
38. Kazhdan, M., Funkhouser, T. & Rusinkiewicz, S. Rotation invariant spherical harmonic representation of 3 d shape descriptors. Symp. Geometry Proces. 6, 156–164 (2003).
39. Bartók, A. P., Kondor, R. & Csányi, G. On representing chemical environments. Phys. Rev. B 87, 184115 (2013).10.1103/PhysRevB.87.184115 ↗
40. Zagaceta, D., Yanxon, H. & Zhu, Q. Spectral neural network potentials for binary alloys. J. Appl. Phys. 128, 045113 (2020).10.1063/5.0013208 ↗
41. Yanxon, H., Zagaceta, D., Tang, B., Matteson, D. S. & Zhu, Q. Pyxtal_ff: a python library for automated force field generation. Mach. Learn.: Sci. Tech. 2, 027001 (2020).
42. Tao, S., Shao, X. & Zhu, L. Accelerating structural optimization through fingerprinting space integration on the potential energy surface. J. Phys. Chem. Lett. 15, 3185–3190 (2024).10.1021/acs.jpclett.4c00275 ↗
43. Pickard, C. J. Beyond theory-driven discovery: introducing hot random search and datum-derived structures. Faraday Discuss. 256, 61–84 (2025).10.1039/D4FD00134F ↗
44. Hoffmann, R., Kabanov, A. A., Golov, A. A. & Proserpio, D. M. Homo citans and carbon allotropes: for an ethics of citation. Angew. Chem. Int. Ed. 55, 10962–10976 (2016).10.1002/anie.201600655 ↗
45. Lenosky, T., Gonze, X., Teter, M. & Elser, V. Energetics of negatively curved graphitic carbon. Nature 355, 333–335 (1992).10.1038/355333a0 ↗
46. Pun, S. H. & Miao, Q. Toward negatively curved carbons. Acc. Chem. Res. 51, 1630–1642 (2018).10.1021/acs.accounts.8b00140 ↗
47. Braun, E. et al. Generating carbon schwarzites via zeolite-templating. Proc. Nat. Acad. Sci. 115, E8116–E8124 (2018).10.1073/pnas.1805062115 ↗
48. Van Duin, A. C., Dasgupta, S., Lorant, F. & Goddard, W. A. Reaxff: a reactive force field for hydrocarbons. J. Phys. Chem. A 105, 9396–9409 (2001).10.1021/jp004368u ↗
49. Batatia, I., Kovacs, D. P., Simm, G. N. C., Ortner, C. & Csanyi, G. MACE: Higher order equivariant message passing neural networks for fast and accurate force fields. In Advances in Neural Information Processing Systems https://openreview.net/forum?id=YPpSngE-ZU (2022).
50. Furness, J. W., Kaplan, A. D., Ning, J., Perdew, J. P. & Sun, J. Accurate and numerically efficient r2scan meta-generalized gradient approximation. J. Phys. Chem. Lett. 11, 8208–8215 (2020).10.1021/acs.jpclett.0c02405 ↗
51. Furness, J. W., Kaplan, A. D., Ning, J., Perdew, J. P. & Sun, J. Correction to “accurate and numerically efficient r2scan meta-generalized gradient approximation”. J. Phys. Chem. Lett. 11, 9248–9248 (2020).10.1021/acs.jpclett.0c03077 ↗
52. Zoubritzky, L. & Coudert, F.-X. Crystalnets. jl: identification of crystal topologies. SciPost Chem. 1, 005 (2022).10.21468/SciPostChem.1.2.005 ↗
53. O’keeffe, M., Peskov, M. A., Ramsden, S. J. & Yaghi, O. M. The reticular chemistry structure resource (rcsr) database of, and symbols for, crystal nets. Acc. Chem. Res. 41, 1782–1789 (2008).10.1021/ar800124u ↗
54. Jang, E., Gu, S. & Poole, B. Categorical reparameterization with gumbel-softmax. In International Conference on Learning Representations https://arxiv.org/abs/1611.01144 (2017).
55. Higgins, I. et al. beta-vae: Learning basic visual concepts with a constrained variational framework. In International Conference on Learning Representations (ICLR, 2017).
56. Fu, H., Li, C., Liu, X., Gao, J., Celikyilmaz, A. & Carin, L. Cyclical annealing schedule: a simple approach to mitigating KL vanishing. Proc. 2019 Conf. North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) 1, 240–250 (2019).10.18653/v1/N19-1021 ↗
57. Lin, T.-Y., Goyal, P., Girshick, R., He, K. & Dollár, P. Focal loss for dense object detection. In Proceedings of the IEEE International Conference on Computer Vision, 2980–2988 (IEEE, 2017).10.1109/ICCV.2017.324 ↗
58. Bistritzer, R. & MacDonald, A. H. Moiré bands in twisted double-layer graphene. Proc. Nat. Acad. Sci. 108, 12233–12237 (2011).10.1073/pnas.1108174108 ↗
59. Cao, Y. et al. Unconventional superconductivity in magic-angle graphene superlattices. Nature 556, 43–50 (2018).10.1038/nature26160 ↗
60. Haymet, A. D. C120 and c60: Archimedean solids constructed from sp2 hybridized carbon atoms. Chem. Phys. Lett. 122, 421–424 (1985).10.1016/0009-2614(85)87239-0 ↗
61. Mackay, A. & Terrones, H. Diamond from graphite. Nature 352, 762–762 (1991).10.1038/352762a0 ↗
62. O’Keeffe, M., Adams, G. B. & Sankey, O. F. Predicted new low energy forms of carbon. Phys. Rev. Lett. 68, 2325–2328 (1992).10.1103/PhysRevLett.68.2325 ↗
63. Mackay, A. L. & Terrones, H. Hypothetical graphite structures with negative gaussian curvature. Philos. Trans. R. Soc. Lond. Ser. A 343, 113–127 (1993).10.1098/rsta.1993.0045 ↗
64. Townsend, S. J., Lenosky, T. J., Muller, D. A., Nichols, C. S. & Elser, V. Negatively curved graphitic sheet model of amorphous carbon. Phys. Rev. Lett. 69, 921–924 (1992).10.1103/PhysRevLett.69.921 ↗
65. Phillips, R., Drabold, D. A., Lenosky, T., Adams, G. B. & Sankey, O. F. Electronic structure of schwarzite. Phys. Rev. B 46, 1941–1943 (1992).10.1103/PhysRevB.46.1941 ↗
66. Tagami, M., Liang, Y., Naito, H., Kawazoe, Y. & Kotani, M. Negatively curved cubic carbon crystals with octahedral symmetry. Carbon 76, 266–274 (2014).10.1016/j.carbon.2014.04.077 ↗
67. Rombach, R., Blattmann, A., Lorenz, D., Esser, P. & Ommer, B. High-resolution image synthesis with latent diffusion models. In Proceedings of CVPR, 10684–10695 (IEEE, 2022).10.1109/CVPR52688.2022.01042 ↗
68. Yao, C.-H., Xie, Y., Voleti, V., Jiang, H. & Jampani, V. SV4D 2.0: Enhancing spatio-temporal consistency in multi-view video diffusion for high-quality 4D generation. In Proc. Int. Conf. Computer Vision (ICCV), 240–250 (2025).
69. Chang, H., Zhang, H., Jiang, L., Liu, C. & Freeman, W. T. Maskgit: Masked generative image transformer. In Proceedings of CVPR, 11315–11325 (IEEE, 2022).10.1109/CVPR52688.2022.01103 ↗
70. Patki, N., Wedge, R. & Veeramachaneni, K. The synthetic data vault. In IEEE International Conference on Data Science and Advanced Analytics (DSAA), 399–410 (IEEE, 2016).10.1109/DSAA.2016.49 ↗
71. Xu, L., Skoularidou, M., Cuesta-Infante, A. & Veeramachaneni, K. Modeling tabular data using conditional gan. In Advances in Neural Information Processing Systems (NIPS, 2019).
72. Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V. & Courville, A. C. Improved training of wasserstein gans. In Advances in Neural Information Processing Systems, Vol. 30 (eds, Guyon, I. et al.) https://proceedings.neurips.cc/paper_files/paper/2017/file/892c3b1c6dccd52936e27cbd0ff683d6-Paper.pdf (Curran Associates, Inc., 2017).
73. Kingma, D. P. & Welling, M. Auto-encoding variational Bayes. In Proc. Int. Conf. Learning Representations (ICLR) (2014).
74. Rezende, D. J., Mohamed, S. & Wierstra, D. Stochastic backpropagation and approximate inference in deep generative models. In Proceedings of ICML, vol. 32 of Proceedings of Machine Learning Research (eds, Xing, E. P. & Jebara, T.)1278–1286 (PMLR, 2014).
75. Virtanen, P. et al. SciPy 1.0-fundamental algorithms for scientific computing in Python. Nat. methods 17, 261–272 (2020).10.1038/s41592-019-0686-2 ↗
76. Nelder, J. A. & Mead, R. A simplex method for function minimization. Comput. J. 7, 308–313 (1965).10.1093/comjnl/7.4.308 ↗
77. Zhu, C., Byrd, R. H., Lu, P. & Nocedal, J. Algorithm 778: L-bfgs-b: Fortran subroutines for large-scale bound-constrained optimization. ACM Trans. Math. Softw. TOMS 23, 550–560 (1997).10.1145/279232.279236 ↗
78. Wales, D. J. & Doye, J. P. Global optimization by basin-hopping and the lowest energy structures of lennard-jones clusters containing up to 110 atoms. J. Phys. Chem. A 101, 5111–5116 (1997).10.1021/jp970984n ↗
79. Gale, J. D. Gulp: A computer program for the symmetry-adapted simulation of solids. J. Chem. Soc. Faraday Trans. 93, 629–637 (1997).10.1039/a606455h ↗
80. Larsen, A. H. et al. The atomic simulation environment–a python library for working with atoms. J. Phys. Condens. Matter 29, 273002 (2017).10.1088/1361-648X/aa680e ↗
81. Kresse, G. & Furthmüller, J. Efficient iterative schemes for ab initio total-energy calculations using a plane-wave basis set. Phys. Rev. B 54, 11169–11186 (1996).10.1103/PhysRevB.54.11169 ↗
82. Togo, A. & Tanaka, I. First principles phonon calculations in materials science. Scr. Mater. 108, 1–5 (2015).10.1016/j.scriptamat.2015.07.021 ↗