Equivariant Neural Networks Reveal How Host–Guest Interactions Shape 129 Xe NMR in Porous Liquids
Source abstract
Abstract
High Resolution Image Download MS PowerPoint Slide Understanding host–guest interactions in porous liquids (PLs) formed from porous organic cages (POCs) is pivotal in tailoring their physicochemical properties, therefore providing an avenue for engineering new PLs with enhanced functionalities. In this work, we demonstrate, for the first time, the use of an accurate and efficient machine-learning-based approach for atomistic modeling of host–guest interactions in large-scale PLs. The approach uses E (3)-equivariant graph neural networks (EGNNs) to construct a machine learning interatomic potential and a nuclear magnetic resonance machine learning model. The former enables machine learning molecular dynamics (MLMD) simulations, while the latter computes the 129 Xe isotropic chemical shift, δ iso, from MLMD snapshots. Applied to a PL composed of CC3- R POC in 4-(trifluoromethoxy)benzyl alcohol (TBA) solvent loaded with high Xe concentration, this dual-model approach shows that host(CC3)–guest(Xe) interactions are best described by a three-site binding model comprising the CC3 intrinsic cavity, CC3 openings, and TBA solvent, with exchange events occurring between these sites. Good agreement between computed and experimental 129 Xe δ iso validates our approach, demonstrating EGNN-based simulations as transformative tools for advancing the understanding of PLs.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Supramolecular Chemistry and Complexes · Covalent Organic Framework Applications · Supramolecular Self-Assembly in Materials
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
NMR Research Unit, Faculty of Science
University of Oulu
Funding
Luonnontieteiden ja Tekniikan Tutkimuksen Toimikunta
References (100+)
Show source-provided references
1. 10.1038/s41563-021-00957-w10.1038/s41563-021-00957-w ↗
2. 10.1038/nature0078510.1038/nature00785 ↗
3. 10.1126/science.aaa807510.1126/science.aaa8075 ↗
4. 10.1021/accountsmr.3c0010610.1021/accountsmr.3c00106 ↗
5. 10.1002/chem.20070009010.1002/chem.200700090 ↗
6. 10.1002/adfm.20210416210.1002/adfm.202104162 ↗
7. 10.1002/smll.20240846610.1002/smll.202408466 ↗
8. 10.1021/acsaem.5c0101510.1021/acsaem.5c01015 ↗
9. 10.1016/j.jece.2025.11929210.1016/j.jece.2025.119292 ↗
10. 10.1016/j.seppur.2025.13450210.1016/j.seppur.2025.134502 ↗
11. 10.1038/nmat254510.1038/nmat2545 ↗
12. 10.1038/nmat403510.1038/nmat4035 ↗
13. 10.1002/anie.20191403710.1002/anie.201914037 ↗
14. 10.1021/ja409594s10.1021/ja409594s ↗
15. 10.1039/C6SC05196K10.1039/C6SC05196K ↗
16. 10.1039/C9SC03316E10.1039/C9SC03316E ↗
17. 10.1021/jp711674y10.1021/jp711674y ↗
18. 10.1007/s00214-011-0930-z10.1007/s00214-011-0930-z ↗
19. 10.1021/ja513017610.1021/ja5130176 ↗
20. 10.1039/C7SC01990D10.1039/C7SC01990D ↗
21. 10.1038/s41598-018-25418-410.1038/s41598-018-25418-4 ↗
22. 10.1039/C9CP04379A10.1039/C9CP04379A ↗
23. 10.1038/s41467-022-29249-w10.1038/s41467-022-29249-w ↗
24. 10.1016/j.xcrp.2023.10128110.1016/j.xcrp.2023.101281 ↗
25. 10.1021/acs.jpclett.4c0022310.1021/acs.jpclett.4c00223 ↗
26. 10.1126/sciadv.aea185710.1126/sciadv.aea1857 ↗
27. 10.1103/PhysRevLett.98.14640110.1103/PhysRevLett.98.146401 ↗
28. 10.1103/PhysRevLett.104.13640310.1103/PhysRevLett.104.136403 ↗
29. 10.1021/acs.jpcc.6b1090810.1021/acs.jpcc.6b10908 ↗
30. 10.1021/acs.jctc.7b0052110.1021/acs.jctc.7b00521 ↗
31. 10.1038/s41467-018-06169-210.1038/s41467-018-06169-2 ↗
32. 10.1021/acs.chemrev.0c0111110.1021/acs.chemrev.0c01111 ↗
33. 10.1021/acs.jpclett.1c0120410.1021/acs.jpclett.1c01204 ↗
34. 10.1021/acs.chemrev.1c0002210.1021/acs.chemrev.1c00022 ↗
35. 10.1021/acs.chemrev.0c0086810.1021/acs.chemrev.0c00868 ↗
36. 10.1021/acs.jpca.2c0677810.1021/acs.jpca.2c06778 ↗
37. 10.1021/acs.jcim.3c0088910.1021/acs.jcim.3c00889 ↗
38. 10.1021/acs.chemrev.4c0057210.1021/acs.chemrev.4c00572 ↗
39. 10.48550/ARXIV.2401.0009610.48550/ARXIV.2401.00096 ↗
40. 10.1021/jacs.4c0709910.1021/jacs.4c07099 ↗
41. 10.1021/acs.jpclett.5c0060510.1021/acs.jpclett.5c00605 ↗
42. 10.48550/arXiv.2504.2128610.48550/arXiv.2504.21286 ↗
43. 10.1021/acs.jcim.1c0112410.1021/acs.jcim.1c01124 ↗
44. 10.1039/D1MA01152A10.1039/D1MA01152A ↗
45. 10.1038/s41524-023-00969-x10.1038/s41524-023-00969-x ↗
46. 10.1021/acs.jctc.3c0049510.1021/acs.jctc.3c00495 ↗
47. 10.1038/s41524-024-01205-w10.1038/s41524-024-01205-w ↗
48. 10.1021/acs.est.4c0385410.1021/acs.est.4c03854 ↗
49. 10.1021/acs.langmuir.4c0312610.1021/acs.langmuir.4c03126 ↗
50. 10.1021/acsnano.4c1236910.1021/acsnano.4c12369 ↗
51. 10.1021/acs.jpcc.4c0738610.1021/acs.jpcc.4c07386 ↗
52. 10.1016/j.matt.2025.10220310.1016/j.matt.2025.102203 ↗
53. 10.1021/acs.jpcc.5c0402010.1021/acs.jpcc.5c04020 ↗
54. 10.1021/acs.chemmater.7b0253210.1021/acs.chemmater.7b02532 ↗
55. 10.1021/acs.chemmater.0c0043410.1021/acs.chemmater.0c00434 ↗
56. 10.1021/acs.jpcc.1c0973710.1021/acs.jpcc.1c09737 ↗
57. 10.1039/D2SC01225A10.1039/D2SC01225A ↗
58. 10.1016/j.molliq.2022.11891310.1016/j.molliq.2022.118913 ↗
59. 10.1021/acs.jpcc.2c0842910.1021/acs.jpcc.2c08429 ↗
60. 10.1038/s41467-023-36666-y10.1038/s41467-023-36666-y ↗
61. 10.1021/acs.jpcc.4c0736510.1021/acs.jpcc.4c07365 ↗
62. 10.1016/j.mtcomm.2024.11092210.1016/j.mtcomm.2024.110922 ↗
63. 10.1021/acs.chemrev.1c0090410.1021/acs.chemrev.1c00904 ↗
64. 10.1021/acs.jpcb.2c0374610.1021/acs.jpcb.2c03746 ↗
65. 10.1039/D5DD00025D10.1039/D5DD00025D ↗
66. 10.1038/s42256-025-01009-710.1038/s42256-025-01009-7 ↗
67. 10.1021/acs.jpcb.5c0230610.1021/acs.jpcb.5c02306 ↗
68. 10.1021/acs.jpclett.1c0114010.1021/acs.jpclett.1c01140 ↗
69. 10.1021/acs.jpcb.2c0635410.1021/acs.jpcb.2c06354 ↗
70. 10.1038/s41598-023-43804-510.1038/s41598-023-43804-5 ↗
71. 10.1016/j.polymer.2024.12741610.1016/j.polymer.2024.127416 ↗
72. 10.1126/sciadv.adn439710.1126/sciadv.adn4397 ↗
73. 10.1016/j.bpj.2025.06.01910.1016/j.bpj.2025.06.019 ↗
74. 10.1021/acsnano.3c0460210.1021/acsnano.3c04602 ↗
75. 10.1021/acs.jctc.3c0111510.1021/acs.jctc.3c01115 ↗
76. 10.1016/j.commatsci.2024.11298310.1016/j.commatsci.2024.112983 ↗
77. 10.1111/jace.1993410.1111/jace.19934 ↗
78. 10.1111/jace.2005610.1111/jace.20056 ↗
79. 10.1021/acs.jctc.5c0021810.1021/acs.jctc.5c00218 ↗
80. 10.1002/adma.20230575810.1002/adma.202305758 ↗
81. 10.1002/chem.20240137310.1002/chem.202401373 ↗
82. 10.1021/acsami.4c0381510.1021/acsami.4c03815 ↗
83. 10.1063/5.024417510.1063/5.0244175 ↗
84. 10.1021/acs.jctc.9b0018110.1021/acs.jctc.9b00181 ↗
85. 10.48550/arXiv.2007.1444410.48550/arXiv.2007.14444 ↗
86. 10.48550/arXiv.2003.0312310.48550/arXiv.2003.03123 ↗
87. Schütt K. · Adv. Neural Inf. Process. Syst. · 2017 · 30 · 992
88. 10.1063/1.501977910.1063/1.5019779 ↗
89. 10.1021/acs.jctc.8b0090810.1021/acs.jctc.8b00908 ↗
90. Schütt K. · Proceedings of the 38th International Conference on Machine Learning · 2021 · 139 · 9377
91. 10.48550/arXiv.2202.0254110.48550/arXiv.2202.02541 ↗
92. 10.1038/s41467-022-29939-510.1038/s41467-022-29939-5 ↗
93. Batatia I. · Adv. Neural Inf. Process. Syst. · 2022 · 35 · 11423
94. 10.1038/s41467-023-36329-y10.1038/s41467-023-36329-y ↗
95. 10.1063/5.013836710.1063/5.0138367 ↗
96. 10.1021/acs.jpca.2c0753010.1021/acs.jpca.2c07530 ↗
97. 10.1039/D3DD00233K10.1039/D3DD00233K ↗
98. 10.1039/D4DD00027G10.1039/D4DD00027G ↗
99. 10.1038/s42256-024-00956-x10.1038/s42256-024-00956-x ↗
100. 10.1038/s41524-025-01535-310.1038/s41524-025-01535-3 ↗