Citation: Zhiyuan Chen, Jinyu Song, Lai Hu, Peng Xu, Zhengyi Sun, Xiao-Chun Hang, Hongjun Zhu, Senqiang Zhu, Rui Liu. Structure-aware machine learning for predicting photophysical properties of MR-TADF materials[J]. Chinese Chemical Letters, ;2026, 37(7): 111967. doi: 10.1016/j.cclet.2025.111967 shu

Structure-aware machine learning for predicting photophysical properties of MR-TADF materials

Zhiyuan Chen ^a ,
Jinyu Song ^b ,
Lai Hu ^a ,
Peng Xu ^a ,
Zhengyi Sun ^b ,
Xiao-Chun Hang ^b ,
Hongjun Zhu ^a ,
Senqiang Zhu ^{a, *,} ,
Rui Liu ^{a, *,}

a.
School of Chemistry and Molecular Engineering, Nanjing Tech University, Nanjing 211816, China
b.
School of Flexible Electronics (Future Technologies) & Institute of Advanced Materials, Nanjing Tech University, Nanjing 211816, China

zhusenqiang1993@njtech.edu.cn

rui.liu@njtech.edu.cn

Received Date: 17 July 2025
Revised Date: 16 September 2025
Accepted Date: 14 October 2025
Available Online: 15 October 2025

Figures(6)

Multi-resonance thermally activated delayed fluorescence (MR-TADF) materials have attracted growing interest for their potential to achieve high color purity and efficiency in organic light-emitting diode (OLED) applications. However, their key performance parameters, including photoluminescence wavelength (PL), full width at half-maximum (FWHM), and photoluminescence quantum yield (PLQY), are highly structure-dependent, presenting challenges for high-throughput screening and efficient design. In this work, we propose a structure-aware ensemble learning model (BNML) that integrates molecular access system (MACCS) fingerprints, fingerprint2 (FP2) fingerprints, and molecular descriptors (MDs) to predict photophysical properties of MR-TADF materials. The model shows strong regression performance under small-data (415) conditions and achieves nearly 100% prediction accuracy (100%, 100%, and 96%, respectively) within a specific range of values. By incorporating SHapley Additive exPlanations (SHAP) analysis, the model reveals interpretable contributions of donor fragments and π-conjugation to the predicted properties. Guided by this analysis, fifteen novel MR-TADF compounds were designed, among which seven were successfully synthesized and validated, showing strong agreement with the predicted values (accuracy: predict/true, 21/20). This work provides a reliable strategy for intelligent design and rapid evaluation of MR-TADF compounds, offering a new approach for structure-property modeling in complex emission systems.
- MR-TADF,
- Machine learning,
- Photophysical properties,
- Structure-aware,
- SHAP analysis
1. [1]
  T. Hatakeyama, K. Shiren, K. Nakajima, et al., Adv. Mater. 28 (2016) 2777–2781. doi: 10.1002/adma.201505491
2. [2]
  X. Gong, W. Yang, H. Zhang, et al., Sci. China Mater. 67 (2024) 3537–3542. doi: 10.1007/s40843-024-3047-4
3. [3]
  J. Liu, X. Yin, M. Huang, et al., Adv. Mater. 37 (2025) 2411610. doi: 10.1002/adma.202411610
4. [4]
  H. Chen, M. Du, C. Qu, et al., Angew. Chem. Int. Ed. 64 (2025) e202415400. doi: 10.1002/anie.202415400
5. [5]
  H. Shi, Y. Shi, Z. Liang, et al., Chem. Eng. J. 494 (2024) 153150. doi: 10.1016/j.cej.2024.153150
6. [6]
  Z. Wu, Y. Xin, C. Lu, et al., Angew. Chem. Int. Ed. 63 (2024) e202318742. doi: 10.1002/anie.202318742
7. [7]
  W. Zhang, H. Zhuang, S. Chen, et al., Chem. Eng. J. 498 (2024) 155350. doi: 10.1016/j.cej.2024.155350
8. [8]
  P. Palanisamy, O.P. Kumar, H.U. Kim, et al., Chem. Eng. J. 481 (2024) 148781. doi: 10.1016/j.cej.2024.148781
9. [9]
  X. Zeng, X. Luo, G. Meng, et al., Angew. Chem. Int. Ed. 64 (2025) e202423670. doi: 10.1002/anie.202423670
10. [10]
  W. Yuan, Q. Jin, M. Du, L. Duan, Y. Zhang, Adv. Mater. 36 (2024) 2410096. doi: 10.1002/adma.202410096
11. [11]
  M. Mamada, M. Hayakawa, J. Ochi, T. Hatakeyama, Chem. Soc. Rev. 53 (2024) 1624–1692. doi: 10.1039/d3cs00837a
12. [12]
  L. Wan, Z. Cheng, F. Liu, P. Lu, Mater. Chem. Front. 7 (2023) 4420–4444. doi: 10.1039/d3qm00498h
13. [13]
  Q. He, M. Li, S. Su, ChemPhysChem 26 (2025) e202400955. doi: 10.1002/cphc.202400955
14. [14]
  R.K. Konidena, K.R. Naveen, Adv. Photonics Res. 3 (2022) 2200201. doi: 10.1002/adpr.202200201
15. [15]
  S. M. Suresh, D. Hall, D. Beljonne, Y. Olivier, Adv. Funct. Mater. 30 (2020) 1908677. doi: 10.1002/adfm.201908677
16. [16]
  H.J. Kim, T. Yasuda, Adv. Opt. Mater. 10 (2022) 2201714. doi: 10.1002/adom.202201714
17. [17]
  Y. Li, X. Tan, B. Cai, C. Chan, Adv. Opt. Mater. 13 (2025) 2403556. doi: 10.1002/adom.202403556
18. [18]
  T.Y. Zhang, X.C. Fan, K. Wang, X.H. Zhang, Chem. Commun. 60 (2024) 14168–14179. doi: 10.1039/d4cc05040a
19. [19]
  J. Li, N. Wu, J. Zhang, et al., Nano-Micro Lett. 15 (2023) 227. doi: 10.1007/s40820-023-01192-5
20. [20]
  K.T. Butler, D.W. Davies, H. Cartwright, O. Isayev, A. Walsh, Nature 559 (2018) 547–555. doi: 10.1038/s41586-018-0337-2
21. [21]
  F. Strieth-Kalthoff, F. Sandfort, M. Kühnemund, et al., Angew. Chem. Int. Ed. 61 (2022) e202204647. doi: 10.1002/anie.202204647
22. [22]
  T. Zhang, Q. Ye, Y. Liu, et al., Nat. Commun. 16 (2025) 3644. doi: 10.1038/s41467-025-59053-1
23. [23]
  M. Suvarna, J. Pérez-Ramírez, Nat. Catal. 7 (2024) 624–635. doi: 10.1038/s41929-024-01150-3
24. [24]
  Z. Zhao, Y. Han, Q. Zhang, et al., ACS Appl. Nano Mater. 8 (2025) 579–588. doi: 10.1021/acsanm.4c05950
25. [25]
  L. Zhang, N. Li, D. Liu, et al., Angew. Chem. Int. Ed. 61 (2022) e202209337. doi: 10.1002/anie.202209337
26. [26]
  F. Lu, Y. Liang, N. Wang, et al., Adv. Photon. 6 (2024) 054001.
27. [27]
  Q. Tao, P. Xu, M. Li, W. Lu, Npj Comput. Mater. 7 (2021) 23. doi: 10.1038/s41524-021-00495-8
28. [28]
  X.Y. Ma, J.P. Lewis, Q.B. Yan, G. Su, J. Phys. Chem. Lett. 10 (2019) 6734–6740. doi: 10.1021/acs.jpclett.9b02420
29. [29]
  M. Wu, E. Tikhonov, A. Tudi, et al., Adv. Mater. 35 (2023) 2300848. doi: 10.1002/adma.202300848
30. [30]
  K.M. Eltohamy, M.G. Alashram, A.I. ElManawy, et al., Biochar 7 (2025) 57. doi: 10.1007/s42773-025-00442-6
31. [31]
  G.M. Landwehr, J.W. Bogart, C. Magalhaes, et al., Nat. Commun. 16 (2025) 865. doi: 10.1038/s41467-024-55399-0
32. [32]
  A. López Cortés, A. Cabrera Andrade, G.E. Garcés, et al., Sci. Rep. 14 (2024) 19359. doi: 10.1038/s41598-024-68565-7
33. [33]
  R. N, A. Mondal, J. Chem. Phys. 162 (2025) 144103. doi: 10.1063/5.0263384
34. [34]
  H. Shi, Y. Li, S. Zhao, et al., J. Phys. Chem. C 127 (2023) 23526–23535. doi: 10.1021/acs.jpcc.3c07392
35. [35]
  H. Shi, Y. Shi, Z. Liang, et al., Chem. Eng. J. 494 (2024) 153150. doi: 10.1016/j.cej.2024.153150
36. [36]
  H.S. Kim, H.J. Cheon, S.H. Lee, et al., Sci. Adv. 11 (2025) eadr1326. doi: 10.1126/sciadv.adr1326
37. [37]
  S. Wang, S. Liu, X. Che, et al., Spectrochim. Acta A 224 (2020) 117404. doi: 10.1016/j.saa.2019.117404
38. [38]
  T. Zhang, W. He, H. Zheng, et al., Chemosphere 268 (2021) 128801. doi: 10.1016/j.chemosphere.2020.128801
39. [39]
  Y. Zhang, S. Xing, L. Wei, et al., ACS Omega 9 (2024) 14368–14374. doi: 10.1021/acsomega.3c10469
40. [40]
  S. Wang, W. Bi, W. Gan, et al., Spectrochim. Acta A 268 (2022) 120711. doi: 10.1016/j.saa.2021.120711
41. [41]
  X. Lv, D. Gu, X. Liu, Y. Li, Sci. Rep. 14 (2024) 18834. doi: 10.1038/s41598-024-69876-5
42. [42]
  Q. Zhang, H. Liang, Y. Tao, J. Yang, et al., Small Methods 6 (2022) 2200208. doi: 10.1002/smtd.202200208
43. [43]
  H. Wang, C.M. Lee, R. Feng, C.S. Leung, Neural Comput. Appl. 29 (2018) 389–400. doi: 10.1007/s00521-017-2863-5
44. [44]
  H. Zou, T. Hastie, J. R. Stat. Soc. Ser. B 67 (2005) 301–320. doi: 10.1111/j.1467-9868.2005.00503.x
45. [45]
  D. Weininger, J. Chem. Inf. Comput. Sci. 28 (1988) 31–36. doi: 10.1021/ci00057a005
46. [46]
  F. Kruger, N. Stiefl, G.A. Landrum, J. Chem. Inf. Model. 60 (2020) 3331–3335. doi: 10.1021/acs.jcim.0c00296
47. [47]
  A. Treistman, D. Mughaz, A. Stulman, et al., Expert Syst. Appl. 208 (2022) 118157. doi: 10.1016/j.eswa.2022.118157
48. [48]
  R. Huang, M.F. Hanif, M.K. Siddiqui, et al., Sci. Rep. 14 (2024) 26552. doi: 10.1038/s41598-024-77838-0
49. [49]
  J.L. Durant, B.A. Leland, D.R. Henry, J.G. Nourse, J. Chem. Inf. Comput. Sci. 42 (2002) 1273–1280. doi: 10.1021/ci010132r
50. [50]
  B. Ji, X. He, Y. Zhang, et al., J. Chem. Inform. 13 (2021) 11.
51. [51]
  C.Z. Du, Y. Lv, H. Dai, et al., J. Mater. Chem. C 11 (2023) 2469–2474. doi: 10.1039/d2tc04952j
1. [1]
  Xiangyue Li , Dexin Zhu , Kunmin Pan , Xiaoye Zhou , Jiaming Zhu , Yingxue Wang , Yongpeng Ren , Hong-Hui Wu . Identifying key determinants of discharge capacity in ternary cathode materials of lithium-ion batteries. Chinese Chemical Letters, 2025, 36(5): 109870-. doi: 10.1016/j.cclet.2024.109870
2. [2]
  Honglin Chen , Rupeng Wang , Zixiang He , Shih-Hsin Ho . Data-driven insights into nonradical activation mechanisms for biochar inverse design: A synergistic approach using DFT and machine learning with meta-analysis. Chinese Chemical Letters, 2026, 37(2): 111372-. doi: 10.1016/j.cclet.2025.111372
3. [3]
  Lu Li , Jianing Shen , Qinkun Xiao , Chaozheng He , Jinzhou Zheng , Chaoqin Chu , Chen Chen . Stable crystal structure prediction using machine learning-based formation energy and empirical potential function. Chinese Chemical Letters, 2025, 36(11): 110421-. doi: 10.1016/j.cclet.2024.110421
4. [4]
  Shengwen Guan , Zhaotong Wei , Ningxu Han , Yude Wei , Bin Xu , Ming Wang , Junjuan Shi . Construction of metallo-complexes with 2,2′:6′,2″-terpyridine substituted triphenylamine in different modified positions and their photophysical properties. Chinese Chemical Letters, 2024, 35(7): 109348-. doi: 10.1016/j.cclet.2023.109348
5. [5]
  Yuting Wu , Haifeng Lv , Xiaojun Wu . Design of two-dimensional porous covalent organic framework semiconductors for visible-light-driven overall water splitting: A theoretical perspective. Chinese Journal of Structural Chemistry, 2024, 43(11): 100375-100375. doi: 10.1016/j.cjsc.2024.100375
6. [6]
  Zonglin Li , Shihua Zou , Zining Wang , Georgeta Postole , Liang Hu , Hongying Zhao . Machine learning in electrochemical oxidation process: A mini-review. Chinese Chemical Letters, 2025, 36(8): 110526-. doi: 10.1016/j.cclet.2024.110526
7. [7]
  Yunzhe Zheng , Si Sun , Jiali Liu , Qingyu Zhao , Heng Zhang , Jing Zhang , Peng Zhou , Zhaokun Xiong , Chuan-Shu He , Bo Lai . Application of machine learning for material prediction and design in the environmental remediation. Chinese Chemical Letters, 2025, 36(9): 110722-. doi: 10.1016/j.cclet.2024.110722
8. [8]
  Zixing Xu , Ruiying Chen , Chuanming Hao , Qionghong Xie , Chunhui Deng , Nianrong Sun . Peptidome data-driven comprehensive individualized monitoring of membranous nephropathy with machine learning. Chinese Chemical Letters, 2024, 35(5): 108975-. doi: 10.1016/j.cclet.2023.108975
9. [9]
  Han-Bin Liu , Xiaoyu Cheng , Zhou Guo , Juan Yang , Fuwen Tan , Donghui Lan , Jian-Ping Tan , Bing Yi , Weixin Zhai , Qing-Hui Guo . CrownBind-IA: A machine learning model predicting binding constants between crown ethers and alkali metal ions. Chinese Chemical Letters, 2025, 36(12): 111149-. doi: 10.1016/j.cclet.2025.111149
10. [10]
  Xu He , Wenjie Gao , Jinglei Xu , Zhanjun Cheng , Wenchao Peng , Beibei Yan , Guanyi Chen , Ning Li . Machine learning-assisted construction of C=O and pyridinic N active sites in sludge-based catalysts. Chinese Chemical Letters, 2025, 36(12): 111019-. doi: 10.1016/j.cclet.2025.111019
11. [11]
  Shuang Li , Penghui Yuan , Xinyi Zhang , Meiru Liu , Dezhi Yang , Linglei Kong , Li Zhang , Yang Lu , Guanhua Du . Revolutionizing sepsis therapy: Machine learning-driven co-crystallization reveals emodin's therapeutic potential. Chinese Chemical Letters, 2026, 37(2): 111289-. doi: 10.1016/j.cclet.2025.111289
12. [12]
  Na Qin , Wenxin Guo , Fangxiu Li , Houfeng Zhang , Hong Liu , Chang Zhang , Lipiao Bao , Lei Liu , Muneerah Alomar , Siqi Zhao , Jian Zhang , Xing Lu . Recent advances in machine learning-driven discovery of alloy electrocatalysts for hydrogen evolution reaction. Chinese Chemical Letters, 2026, 37(3): 112021-. doi: 10.1016/j.cclet.2025.112021
13. [13]
  Dongshi Feng , Jiangdong Dai , Zhi Zhu , Pengwei Huo , Yongsheng Yan , Chunxiang Li . Molecularly imprinted electrochemical sensor arrays combined with machine learning for simultaneous determination of three neonicotinoid insecticides. Chinese Chemical Letters, 2026, 37(5): 111789-. doi: 10.1016/j.cclet.2025.111789
14. [14]
  Jieyu Liu , Junze Zhang , Haigang Deng , Shuoao Wang , Xingxing Jiang , Li Wang , Changhong Wang . Understanding the activity origin of Pd-anchored single-atom alloy catalysts for NO-to-NH₃ conversion by DFT studies and machine learning. Chinese Chemical Letters, 2025, 36(12): 110656-. doi: 10.1016/j.cclet.2024.110656
15. [15]
  Hao Chen , Haiyuan Liao , Qi Zhou , Yang Liu , Guojun Liu , Yuan Yao . Electronegativity-oriented coordination regulation of main-group metal single-atom catalysts for oxygen reduction to H₂O₂: A combined study of first-principles and machine learning. Chinese Chemical Letters, 2026, 37(3): 110711-. doi: 10.1016/j.cclet.2024.110711
16. [16]
  Qingyun Hu , Wei Wang , Junyuan Lu , He Zhu , Qi Liu , Yang Ren , Hong Wang , Jian Hui . High-throughput screening of high energy density LiMn_1-xFe_xPO₄ via active learning. Chinese Chemical Letters, 2025, 36(2): 110344-. doi: 10.1016/j.cclet.2024.110344
17. [17]
  Xi Xue , Kai Chen , Hanyu Sun , Xiangying Liu , Xue Liu , Shize Li , Jingjie Yan , Yu Peng , Mohammad S. Mubarak , Ahmed Al-Harrasi , Hai-Yu Hu , Yafeng Deng , Xiandao Pan , Xiaojian Wang . Bidirectional Chemical Intelligent Net: A unified deep learning–based framework for predicting chemical reaction. Chinese Chemical Letters, 2025, 36(11): 110968-. doi: 10.1016/j.cclet.2025.110968
18. [18]
  Jiaxiang Guo , Zeyi Li , Tianyu Zhang , Xinyu Tian , Yue Wang , Chuandong Dou . Thienothiophene-centered ladder-type π-systems that feature distinct quinoidal π-extension. Chinese Chemical Letters, 2024, 35(5): 109337-. doi: 10.1016/j.cclet.2023.109337
19. [19]
  Youxiang He , Yongfa Zhu , Ming Luo , Haiping Xia . A nonalternant analogue of pentacene incorporating a non-terminal azulene unit. Chinese Chemical Letters, 2025, 36(7): 110463-. doi: 10.1016/j.cclet.2024.110463
20. [20]
  Zijian Zhang , Fangxin Du , Lijia Liu , Yixiang Sun , Jie Xue , Hanshen Xin . 1-Azaazulene constructs: Overcoming the weak fluorescence of azulene derivatives via S₁-S₀ transitions. Chinese Chemical Letters, 2026, 37(6): 111987-. doi: 10.1016/j.cclet.2025.111987

Get Citation

PDF

XML

Metrics

PDF Downloads(0)
Abstract views(14)
HTML views(0)

通讯作者: 陈斌, bchen63@163.com

1.
沈阳化工大学材料科学与工程学院沈阳 110142