SFMMoE: A Semi-Empirical Descriptor-Augmented Multi-Expert Graph Neural Network for Accurate Prediction of Singlet Fission Properties
Source abstract
Abstract
Efficient identification of singlet fission (SF) candidates remains a significant challenge in the development of high-performance organic photovoltaic materials due to the high computational cost of accurately evaluating excited-state energetics. Here, we present SFMMoE, a graph neural network (GNN) that integrates a multiexpert multigating (MMoE) architecture with 2-HOP message passing. By integrating local topological information from molecular graphs with global molecular descriptors derived from semiempirical methods, SFMMoE enables simultaneous prediction of five key excited-state properties, including two thermodynamic criteria critical to SF: Δ E gap1 = Δ E S1 – 2Δ E T1 and Δ E gap2 = Δ E T2 – 2Δ E T1 . The model achieves a mean square error below 0.04 eV across all tasks, outperforming traditional machine learning and testing of GNN baselines. This work demonstrates that integrating multitask learning with expert specialization and graph–descriptor feature fusion substantially improves the prediction accuracy of excited-state energetics, enabling large-scale, low-cost virtual screening of SF materials with quantum-chemical accuracy. To facilitate broader access, a freely available and user-friendly online prediction server is provided at http://tech.iawnix.xyz/SFMMoE .
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Machine Learning in Materials Science · Organic Electronics and Photovoltaics · Advanced Graph Neural Networks
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Shanghai Engineering Research Center of Molecular Therapeutics and New Drug Development, Shanghai Frontiers Science Center of Molecule Intelligent Syntheses
School of Chemistry and Molecular Engineering, East China Normal University
Syngenta Jealott’s Hill International Research Centre Bracknell
Department of Chemistry, Hong Kong Branch of Chinese National Engineering Research Center for Tissue Restoration and Reconstruction
The Hong Kong University of Science and Technology
New York University−East China Normal University Center for Computational Chemistry
New York University Shanghai
Chongqing Key Laboratory of Precision Optics
Chongqing Institute of East China Normal University
Funding
Natural Science Foundation of Shanghai Municipality · East China Normal University · Natural Science Foundation of Chongqing Municipality · Shanghai Municipal Education Commission · Fundamental Research Funds for the Central Universities · National Natural Science Foundation of China · Syngenta International · Shanghai Future Discipline Program (Quantum Science and Technology)
References (64)
Show source-provided references
1. 10.1063/1.173391910.1063/1.1733919 ↗
2. 10.1039/D0CS01433H10.1039/D0CS01433H ↗
3. 10.1063/1.169569510.1063/1.1695695 ↗
4. 10.1016/0022-3697(78)90098-710.1016/0022-3697(78)90098-7 ↗
5. 10.1021/cr100261310.1021/cr1002613 ↗
6. 10.1038/ncomms201210.1038/ncomms2012 ↗
7. 10.1021/acsenergylett.1c0097210.1021/acsenergylett.1c00972 ↗
8. 10.1002/lpor.20240101510.1002/lpor.202401015 ↗
9. 10.1002/adma.20160165210.1002/adma.201601652 ↗
10. 10.1002/marc.20220032610.1002/marc.202200326 ↗
11. 10.1002/cjoc.20220070010.1002/cjoc.202200700 ↗
12. 10.1002/cjoc.20220068610.1002/cjoc.202200686 ↗
13. 10.1126/science.123299410.1126/science.1232994 ↗
14. 10.1063/1.173603410.1063/1.1736034 ↗
15. 10.1063/1.235679510.1063/1.2356795 ↗
16. 10.31635/ccschem.025.20250580210.31635/ccschem.025.202505802 ↗
17. 10.1039/C9EE01508F10.1039/C9EE01508F ↗
18. 10.1021/ja104246210.1021/ja1042462 ↗
19. 10.1063/1.349576410.1063/1.3495764 ↗
20. 10.1038/s41467-021-21719-x10.1038/s41467-021-21719-x ↗
21. 10.1038/nchem.180110.1038/nchem.1801 ↗
22. 10.1021/jacs.8b0951010.1021/jacs.8b09510 ↗
23. 10.1002/adfm.20150153710.1002/adfm.201501537 ↗
24. 10.1021/ja501337b10.1021/ja501337b ↗
25. 10.1021/acs.jpclett.5b0019810.1021/acs.jpclett.5b00198 ↗
26. 10.1039/C7CP08313K10.1039/C7CP08313K ↗
27. 10.1063/1.318278710.1063/1.3182787 ↗
28. 10.1016/0009-2614(71)80289-010.1016/0009-2614(71)80289-0 ↗
29. 10.22203/eCM.v052a0410.22203/eCM.v052a04 ↗
30. 10.22203/eCM.v052a0610.22203/eCM.v052a06 ↗
31. 10.1021/ja073173y10.1021/ja073173y ↗
32. 10.1021/acs.jpcc.0c0621510.1021/acs.jpcc.0c06215 ↗
33. 10.1021/jp407426q10.1021/jp407426q ↗
34. 10.1038/nmat356810.1038/nmat3568 ↗
35. 10.1038/s41598-023-50860-410.1038/s41598-023-50860-4 ↗
36. 10.1038/s41586-021-03819-210.1038/s41586-021-03819-2 ↗
37. 10.48550/arXiv.2507.0144410.48550/arXiv.2507.01444 ↗
38. 10.1038/s41586-025-08628-510.1038/s41586-025-08628-5 ↗
39. 10.1021/acs.jctc.9b0018110.1021/acs.jctc.9b00181 ↗
40. 10.1021/acs.jcim.3c0170810.1021/acs.jcim.3c01708 ↗
41. 10.1021/acs.jpclett.3c0001410.1021/acs.jpclett.3c00014 ↗
42. 10.1021/jacs.3c0776610.1021/jacs.3c07766 ↗
43. 10.1038/s41524-022-00860-110.1038/s41524-022-00860-1 ↗
44. 10.1038/s41467-025-56480-y10.1038/s41467-025-56480-y ↗
45. 10.1002/anie.20221395310.1002/anie.202213953 ↗
46. 10.1021/acs.jctc.8b0117610.1021/acs.jctc.8b01176 ↗
47. 10.1038/s41524-022-00758-y10.1038/s41524-022-00758-y ↗
48. 10.1023/A:101093340432410.1023/A:1010933404324 ↗
49. 10.48550/arXiv.1603.0275410.48550/arXiv.1603.02754 ↗
50. 10.1007/s10994-006-6226-110.1007/s10994-006-6226-1 ↗
51. 10.1214/aos/101320345110.1214/aos/1013203451 ↗
52. 10.1021/acs.jcim.3c0125010.1021/acs.jcim.3c01250 ↗
53. 10.48550/arXiv.2105.1449110.48550/arXiv.2105.14491 ↗
54. 10.48550/arXiv.1609.0290710.48550/arXiv.1609.02907 ↗
55. 10.1002/wcms.149310.1002/wcms.1493 ↗
56. 10.48550/arXiv.1907.1090210.48550/arXiv.1907.10902 ↗
57. 10.48550/arXiv.2205.1332810.48550/arXiv.2205.13328 ↗
58. Ma J. · Proc. 24th ACM SIGKDD Int. Conf. Knowledge Discovery & Data Mining (KDD) · 2018 · 193010.1145/3219819.3220007 ↗
59. 10.1021/acs.jcim.1c0146710.1021/acs.jcim.1c01467 ↗
60. 10.1021/acs.jcim.5c0045610.1021/acs.jcim.5c00456 ↗
61. 10.3390/molecules2802084410.3390/molecules28020844 ↗
62. Maaten L. v. d. · J. Mach. Learn. Res. · 2008 · 9 · 2579
63. 10.5281/zenodo.1699601710.5281/zenodo.16996017 ↗
64. Frisch, M. J.; Trucks, G. W.; Schlegel, H. B.; Scuseria, G. E.; Robb, M. A.; Cheeseman, J. R.; Scalmani, G.; Barone, V.; Petersson, G. A.; Nakatsuji, H.; Li, X.; Caricato, M.; Marenich, A. V.; Bloino, J.; Janesko, B. G.; Gomperts, R.; Mennucci, B.; Hratchian, H. P.; Ortiz, J. V.; Izmaylov, A. F.; Sonnenberg, J. L.; Williams; Ding, F.; Lipparini, F.; Egidi, F.; Goings, J.; Peng, B.; Petrone, A.; Henderson, T.; Ranasinghe, D.; Zakrzewski, V. G.; Gao, J.; Rega, N.; Zheng, G.; Liang, W.; Hada, M.; Ehara, M.; Toyota, K.; Fukuda, R.; Hasegawa, J.; Ishida, M.; Nakajima, T.; Honda, Y.; Kitao, O.; Nakai, H.; Vreven, T.; Throssell, K.; Montgomery, J. A., Jr.; Peralta, J. E.; Ogliaro, F.; Bearpark, M. J.; Heyd, J. J.; Brothers, E. N.; Kudin, K. N.; Staroverov, V. N.; Keith, T. A.; Kobayashi, R.; Normand, J.; Raghavachari, K.; Rendell, A. P.; Burant, J. C.; Iyengar, S. S.; Tomasi, J.; Cossi, M.; Millam, J. M.; Klene, M.; Adamo, C.; Cammi, R.; Ochterski, J. W.; Martin, R. L.; Morokuma, K.; Farkas, O.; Foresman, J. B.; Fox, D. J. Gaussian 16 , Rev. C.01; Gaussian, Inc.: Wallingford, CT, 2016.