Organic crystal structure prediction via coupled generative adversarial networks and graph convolutional networks

Zhuyifan Ye; Nannan Wang; Jiantao Zhou; Defang Ouyang

doi:10.1016/j.xinn.2023.100562

The Innovation > 2024 Vol. 5 > No. 2

Next Article Previous Article

Article Open Access

Cite PDF

Organic crystal structure prediction via coupled generative adversarial networks and graph convolutional networks

1.
State Key Laboratory of Quality Research in Chinese Medicine, Institute of Chinese Medical Sciences, University of Macau, Macau 999078, China
2.
Faculty of Applied Sciences, Macao Polytechnic University, Macao 999078, China
3.
State Key Laboratory of Internet of Things for Smart City, University of Macau, Macau 999078, China
4.
Department of Computer and Information Science, Faculty of Science and Technology, University of Macau, Macau 999078, China
5.
Department of Public Health and Medicinal Administration, Faculty of Health Sciences, University of Macau, Macau 999078, China

More Information

Corresponding author: Defang Ouyang, defangouyang@um.edu.mo
Received Date: July 19, 2023

Accepted Date: December 29, 2023

Published Online: January 08, 2024

The Innovation 5(2), https://doi.org/10.1016/j.xinn.2023.100562 | Cite this article

GRAPHICAL ABSTRACT

GRAPHICAL ABSTRACT

DownLoad: Full size image

PUBLIC SUMMARY

PUBLIC SUMMARY
1. ■ The diverse crystal structures of organic compounds significantly influence their properties across fields, from optoelectronics to superconductors and from drugs to high-energy explosives.
2. ■ Traditionalmethods face limitations in efficiency due to incomplete experimental crystallization and time-consuming quantum mechanics calculations.
3. ■ DeepCSP leverages AI to achieve minute-scale predictions of organic crystal structures from two-dimensional molecular structures.

ABSTRACT

ABSTRACT

Organic crystal structures exert a profound impact on the physicochemical properties and biological effects of organic compounds. Quantum mechanics (QM)–based crystal structure predictions (CSPs) have somewhat alleviated the dilemma that experimental crystal structure investigations struggle to conduct complete polymorphism studies, but the high computing cost poses a challenge to its widespread application. The present study aims to construct DeepCSP, a feasible pure machine learning framework for minute-scale rapid organic CSP. Initially, based on 177,746 data entries from the Cambridge Crystal Structure Database, a generative adversarial network was built to conditionally generate trial crystal structures under selected feature constraints for the given molecule. Simultaneously, a graph convolutional attention network was used to predict the density of stable crystal structures for the input molecule. Subsequently, the distances between the predicted density and the definition-based calculated density would be considered to be the crystal structure screening and ranking basis, and finally, the density-based crystal structure ranking would be output. Two such distinct algorithms, performing the generation and ranking functionalities, respectively, collectively constitute the DeepCSP, which has demonstrated compelling performance in marketed drug validations, achieving an accuracy rate exceeding 80% and a hit rate surpassing 85%. Inspiringly, the computing speed of the pure machine learning methodology demonstrates the potential of artificial intelligence in advancing CSP research.

FullText(HTML)

REFERENCES

[1]	Price, S.L. (2014). Predicting crystal structures of organic compounds. Chem. Soc. Rev. 43: 2098–2111. https://doi.org/10.1039/C3CS60279F. View in Article CrossRef Google Scholar
[2]	Hilfiker, R., and Von Raumer, M. (2019). Polymorphism in the Pharmaceutical Industry: Solid Form and Drug Development (John Wiley & Sons). https://doi.org/10.1002/9783527697847. View in Article Google Scholar
[3]	Wöhler, and Liebig. (1832). Untersuchungen über das Radikal der Benzoesäure. Ann. Pharm. (Poznan) 3: 249–282. https://doi.org/10.1002/jlac.18320030302. View in Article CrossRef Google Scholar
[4]	Brog, J.-P., Chanez, C.-L., Crochet, A., et al. (2013). Polymorphism, what it is and how to identify it: a systematic review. RSC Adv. 3: 16905–16931. https://doi.org/10.1039/c3ra41559g. View in Article CrossRef Google Scholar
[5]	Kersten, K., Kaur, R., and Matzger, A. (2018). Survey and analysis of crystal polymorphism in organic structures. IUCrJ 5: 124–129. https://doi.org/10.1107/S2052252518000660. View in Article CrossRef Google Scholar
[6]	Neumann, M.A., and van de Streek, J. (2018). How many ritonavir cases are there still out there? Faraday Discuss *211*: 441–458. https://doi.org/10.1039/C8FD00069G. View in Article CrossRef Google Scholar
[7]	Bauer, J., Spanton, S., Henry, R., et al. (2001). Ritonavir: An extraordinary example of conformational polymorphism. Pharm. Res. (N. Y.) 18: 859–866. https://doi.org/10.1023/A:1011052932607. View in Article CrossRef Google Scholar
[8]	Bernstein, J. (2020). Polymorphism in molecular crystals 2e (Oxford University Press). https://doi.org/10.1093/oso/9780199655441.001.0001. View in Article Google Scholar
[9]	Taylor, C.R., Mulvee, M.T., Perenyi, D.S., et al. (2020). Minimizing polymorphic risk through cooperative computational and experimental exploration. J. Appl. Comput. Sci. *142*: 16668–16680. https://doi.org/10.1021/jacs.0c06749. View in Article CrossRef Google Scholar
[10]	Liu, F., Chen, K., and Xue, D. (2023). How to fast grow large-size crystals? Innovation 4: 100458. https://doi.org/10.1016/j.xinn.2023.100458. View in Article CrossRef Google Scholar
[11]	Bučar, D.K., Lancaster, R.W., and Bernstein, J. (2015). Disappearing polymorphs revisited. Angew. Chem. Int. Ed. 54: 6972–6993. https://doi.org/10.1002/anie.201410356. View in Article CrossRef Google Scholar
[12]	Neumann, M.A., Van De Streek, J., Fabbiani, F.P.A., et al. (2015). Combined crystal structure prediction and high-pressure crystallization in rational pharmaceutical polymorph screening. Nat. Commun. 6: 7793–7797. https://doi.org/10.1038/ncomms8793. View in Article CrossRef Google Scholar
[13]	Magrasó, A., Frontera, C., Marrero-López, D., et al. (2009). New crystal structure and characterization of lanthanum tungstate "La6WO12" prepared by freeze-drying synthesis. Dalton Trans. 10273–10283. https://doi.org/10.1039/B916981B. View in Article CrossRef Google Scholar
[14]	Childs, S.L., Chyall, L.J., Dunlap, J.T., et al. (2004). A metastable polymorph of metformin hydrochloride: isolation and characterization using capillary crystallization and thermal microscopy techniques. Cryst. Growth Des. 4: 441–449. https://doi.org/10.1021/cg034243p. View in Article CrossRef Google Scholar
[15]	Zaccaro, J., Matic, J., Myerson, A.S., et al. (2001). Nonphotochemical, laser-induced nucleation of supersaturated aqueous glycine produces unexpected γ-polymorph. Cryst. Growth Des. 1: 5–8. https://doi.org/10.1021/cg0055171. View in Article CrossRef Google Scholar
[16]	Potticary, J., Terry, L.R., Bell, C., et al. (2016). An unforeseen polymorph of coronene by the application of magnetic fields during crystal growth. Nat. Commun. 7: 11555–11557. https://doi.org/10.1038/ncomms11555. View in Article CrossRef Google Scholar
[17]	Reverchon, E. (1999). Supercritical antisolvent precipitation of micro-and nano-particles. J. Supercrit. Fluids 15: 1–21. https://doi.org/10.1016/S0896-8446(98)00129-6. View in Article CrossRef Google Scholar
[18]	Price, S.L. (2008). From crystal structure prediction to polymorph prediction: interpreting the crystal energy landscape. Phys. Chem. Chem. Phys. 10: 1996–2009. https://doi.org/10.1039/b719351c. View in Article CrossRef Google Scholar
[19]	Han, Y., Ali, I., Wang, Z., et al. (2021). Machine learning accelerates quantum mechanics predictions of molecular crystals. Phys. Rep. *934*: 1–71. https://doi.org/10.1016/j.physrep.2021.08.002. View in Article CrossRef Google Scholar
[20]	Wang, W., Ye, Z., Gao, H., et al. (2021). Computational pharmaceutics-A new paradigm of drug delivery. J. Contr. Release *338*: 119–136. https://doi.org/10.1016/j.jconrel.2021.08.030. View in Article CrossRef Google Scholar
[21]	Xu, Y., Liu, X., Cao, X., et al. (2021). Artificial intelligence: A powerful paradigm for scientific research. Innovation 2: 100179. https://doi.org/10.1016/j.xinn.2021.100179. View in Article CrossRef Google Scholar
[22]	Xu, Y., Wang, F., An, Z., et al. (2023). Artificial intelligence for science—bridging data to wisdom. Innovation 4: 100525. https://doi.org/10.1016/j.xinn.2023.100525. View in Article CrossRef Google Scholar
[23]	Taylor, R., and Wood, P.A. (2019). A million crystal structures: The whole is greater than the sum of its parts. Chem. Rev. *119*: 9427–9477. https://doi.org/10.1021/acs.chemrev.9b00155. View in Article CrossRef Google Scholar
[24]	Long, T., Fortunato, N.M., et al. (2021). Constrained crystals deep convolutional generative adversarial network for the inverse design of crystal structures. npj Comput. Mater. 7: 66–67. https://doi.org/10.1038/s41524-021-00526-4. View in Article CrossRef Google Scholar
[25]	Noh, J., Kim, J., Stein, H.S., et al. (2019). Inverse design of solid-state materials via a continuous representation. Matter 1: 1370–1384. https://doi.org/10.1016/j.matt.2019.08.017. View in Article CrossRef Google Scholar
[26]	Cheng, G., Gong, X.-G., and Yin, W.-J. (2022). Crystal structure prediction by combining graph network and optimization algorithm. Nat. Commun. 13: 1492–1498. https://doi.org/10.1038/s41467-022-29241-4. View in Article CrossRef Google Scholar
[27]	Kim, S., Noh, J., Gu, G.H., et al. (2020). Generative adversarial networks for crystal structure prediction. ACS Cent. Sci. 6: 1412–1420. https://doi.org/10.1021/acscentsci.0c00426. View in Article CrossRef Google Scholar
[28]	Radford, A., Metz, L., and Chintala, S. (2015). Unsupervised representation learning with deep convolutional generative adversarial networks. Preprint at arXiv. https://doi.org/10.48550/arXiv.1511.06434. View in Article Google Scholar
[29]	Burger, A., and Ramberger, R. (1979). On the polymorphism of pharmaceuticals and other molecular crystals. Mikrochim. Acta 72: 259–271. https://doi.org/10.1007/BF01197379. View in Article CrossRef Google Scholar
[30]	Burger, A., and Ramberger, R. (1979). On the polymorphism of pharmaceuticals and other molecular crystals. Ⅱ. Mikrochim. Acta 72: 273–316. https://doi.org/10.1007/BF01197380. View in Article CrossRef Google Scholar
[31]	Bruno, I.J., Cole, J.C., Edgington, P.R., et al. (2002). New software for searching the Cambridge Structural Database and visualizing crystal structures. Acta Crystallogr. B 58: 389–397. https://doi.org/10.1107/S0108768102003324. View in Article CrossRef Google Scholar
[32]	Weininger, D. (1988). SMILES, a chemical language and information system. 1. Introduction to methodology and encoding rules. J. Chem. Inf. Comput. Sci. 28: 31–36. https://doi.org/10.1021/ci00057a005. View in Article CrossRef Google Scholar
[33]	Landrum, G. (2006). RDKit: Open-source cheminformatics. https://doi.org/10.5281/zenodo.591637. View in Article Google Scholar
[34]	O'Boyle, N.M., Banck, M., James, C.A., et al. (2011). Open Babel: An open chemical toolbox. J. Cheminf. 3: 1–14. https://doi.org/10.1186/1758-2946-3-33. View in Article CrossRef Google Scholar
[35]	Fábián, L. (2009). Cambridge structural database analysis of molecular complementarity in cocrystals. Cryst. Growth Des. 9: 1436–1443. https://doi.org/10.1021/cg800861m. View in Article CrossRef Google Scholar
[36]	Reilly, A.M., Cooper, R.I., Adjiman, C.S., et al. (2016). Report on the sixth blind test of organic crystal structure prediction methods. Acta Crystallogr. B 72: 439–459. https://doi.org/10.1107/S2052520616007447. View in Article CrossRef Google Scholar
[37]	Case, D.H., Campbell, J.E., Bygrave, P.J., et al. (2016). Convergence properties of crystal structure prediction by quasi-random sampling. J. Chem. Theor. Comput. 12: 910–924. https://doi.org/10.1021/acs.jctc.5b01112. View in Article CrossRef Google Scholar
[38]	Pillardy, J., Arnautova, Y.A., Czaplewski, C., et al. (2001). Conformation-family Monte Carlo: A new method for crystal structure prediction. Proc. Natl. Acad. Sci. USA 98: 12351–12356. https://doi.org/10.1073/pnas.231479298. View in Article CrossRef Google Scholar
[39]	Karfunkel, H.R., and Gdanitz, R.J. (1992). Ab Initio prediction of possible crystal structures for general organic molecules. J. Comput. Chem. 13: 1171–1183. https://doi.org/10.1002/jcc.540131002. View in Article CrossRef Google Scholar
[40]	Kim, S., Orendt, A.M., Ferraro, M.B., et al. (2009). Crystal structure prediction of flexible molecules using parallel genetic algorithms with a standard force field. J. Comput. Chem. 30: 1973–1985. https://doi.org/10.1002/jcc.21189. View in Article CrossRef Google Scholar
[41]	Lund, A.M., Pagola, G.I., Orendt, A.M., et al. (2015). Crystal structure prediction from first principles: The crystal structures of glycine. Chem. Phys. Lett. *626*: 20–24. https://doi.org/10.1016/j.cplett.2015.03.015. View in Article CrossRef Google Scholar
[42]	Pyzer-Knapp, E.O., Thompson, H.P.G., Schiffmann, F., et al. (2014). Predicted crystal energy landscapes of porous organic cages. Chem. Sci. 5: 2235–2245. https://doi.org/10.1039/c4sc00095a. View in Article CrossRef Google Scholar
[43]	Kendrick, J., Stephenson, G.A., Neumann, M.A., et al. (2013). Crystal structure prediction of a flexible molecule of pharmaceutical interest with unusual polymorphic behavior. Cryst. Growth Des. 13: 581–589. https://doi.org/10.1021/cg301222m. View in Article CrossRef Google Scholar
[44]	Price, S.L., Leslie, M., Welch, G.W.A., et al. (2010). Modelling organic crystal structures using distributed multipole and polarizability-based model intermolecular potentials. Phys. Chem. Chem. Phys. 12: 8478–8490. https://doi.org/10.1039/c004164e. View in Article CrossRef Google Scholar
[45]	Gavezzotti, A., and Filippini, G. (1995). Polymorphic forms of organic crystals at room conditions: thermodynamic and structural implications. J. Appl. Comput. Sci. *117*: 12299–12305. https://doi.org/10.1021/ja00154a032. View in Article CrossRef Google Scholar
[46]	Yu, T.-Q., and Tuckerman, M.E. (2011). Temperature-accelerated method for exploring polymorphism in molecular crystals based on free energy. Phys. Rev. Lett. *107*: 015701. https://doi.org/10.1103/PhysRevLett.107.015701. View in Article CrossRef Google Scholar
[47]	Frenkel, D., and Ladd, A.J.C. (1984). New Monte Carlo method to compute the free energy of arbitrary solids. Application to the fcc and hcp phases of hard spheres. J. Chem. Phys. 81: 3188–3193. https://doi.org/10.1063/1.448024. View in Article CrossRef Google Scholar
[48]	Uzoh, O.G., Galek, P.T.A., and Price, S.L. (2015). Analysis of the conformational profiles of fenamates shows route towards novel, higher accuracy, force-fields for pharmaceuticals. Phys. Chem. Chem. Phys. 17: 7936–7948. https://doi.org/10.1039/c4cp05525j. View in Article CrossRef Google Scholar
[49]	Broo, A., and Nilsson Lill, S.O. (2016). Transferable force field for crystal structure predictions, investigation of performance and exploration of different rescoring strategies using DFT-D methods. Acta Crystallogr. B 72: 460–476. https://doi.org/10.1107/S2052520616006831. View in Article CrossRef Google Scholar
[50]	Cutini, M., Civalleri, B., Corno, M., et al. (2016). Assessment of different quantum mechanical methods for the prediction of structure and cohesive energy of molecular crystals. J. Chem. Theor. Comput. 12: 3340–3352. https://doi.org/10.1021/acs.jctc.6b00304. View in Article CrossRef Google Scholar
[51]	Price, S.L. (2018). Is zeroth order crystal structure prediction (CSP_0) coming to maturity? What should we aim for in an ideal crystal structure prediction code? Faraday Discuss *211*: 9–30. https://doi.org/10.1039/C8FD00121A. View in Article CrossRef Google Scholar
[52]	McCrone, W. (1965). Physics and Chemistry of the Organic Solid State (Wiley-Interscience). View in Article Google Scholar

Cited by

ABOUT THIS ARTICLE

Cite this article:

Zhuyifan Ye, Nannan Wang, Jiantao Zhou, Defang Ouyang. Organic crystal structure prediction via coupled generative adversarial networks and graph convolutional networks[J]. The Innovation, 2024, 5(2). https://doi.org/10.1016/j.xinn.2023.100562

Zhuyifan Ye, Nannan Wang, Jiantao Zhou, Defang Ouyang. Organic crystal structure prediction via coupled generative adversarial networks and graph convolutional networks[J]. The Innovation, 2024, 5(2). https://doi.org/10.1016/j.xinn.2023.100562

Welcome!

To request copyright permission to republish or share portions of our works, please visit Copyright Clearance Center's (CCC) Marketplace website at marketplace.copyright.com.

PDF

Figures(5) Tables(3)

Article Metrics

Article views(4650) PDF downloads(757)

Organic crystal structure prediction via coupled generative adversarial networks and graph convolutional networks

GRAPHICAL ABSTRACT

PUBLIC SUMMARY

ABSTRACT

REFERENCES

ABOUT THIS ARTICLE

Cite this article:

Welcome!

Share

Article Metrics

Relative Articles

Cited by

Catalog

{{newsColumn.name}}

Journal links

{{newsColumn.name}}

Collections

Stay connected

Organic crystal structure prediction via coupled generative adversarial networks and graph convolutional networks

GRAPHICAL ABSTRACT

PUBLIC SUMMARY

ABSTRACT

REFERENCES

ABOUT THIS ARTICLE

Cite this article:

Welcome!

Share

Article Metrics

Relative Articles

Cited by

Catalog

Export File

Citation

Format

Content

{{newsColumn.name}}

Journal links

{{newsColumn.name}}

Collections

Stay connected