journal article·2026

Machine-learning-guided high-throughput design of asymmetric A–DA′D–A acceptors toward efficient organic solar cells

Ziye Chen, Kuo Wang, Di Huang, Zhiyan Peng, Jiahao Deng, Zhimin Feng, Jiangtao Wu, Kang Zhang, Jiaojiao Liang, Ling Zhao, Jaemin Kong

Materials Horizons· Volume 13· Issue 6
Publisher page

Abstract

Asymmetric structure design in non-fullerene acceptors (NFAs) has driven a significant breakthrough in the power conversion efficiency (PCE) of organic solar cells (OSCs). However, finding high-performing moieties out of the vast amount of candidates and their potential combinations is a significant challenge. In this work, we propose a machine learning (ML)-guided high-throughput screening approach to identify optimal acceptor moieties for both symmetric and asymmetric A-DA'D-A type NFAs. By standardizing and splitting the NFA structures and using one-hot encoding to construct feature vectors, a reliable XGBoost model is established to predict structure-activity relationships. Combined with interpretability analysis, core contributors to solar cell performance, such as end groups, conjugated scaffolds, and central cores, were identified. From over a million virtually generated molecules, we screened the molecules to find the best acceptor matches with a donor polymer (e.g., PM6) exhibiting predicted PCEs greater than 18%. The Sankey diagram visualizes the best combined paths for NFAs, highlighting the great potential of asymmetric design. Furthermore, quantum chemical calculations verified that the picked-out acceptor molecules (K01-K12) with asymmetric structures and predicted PCEs of over 19% are potentially promising in terms of energy levels, electrostatic potentials, and charge transfer characteristics. Moreover, assessment of synthesis accessibility indicated their good experimental feasibility, and applicability to multiple donor systems. This work not only facilitates a transition from empirical trial-and-error to a data-driven approach, but also advances molecular engineering from symmetric simplicity to asymmetric function-oriented design.
Source: europepmc · Quality: candidate unverified · Source record ↗

Research context

OpenAlex topics: Organic Electronics and Photovoltaics · Machine Learning in Materials Science · Synthesis and Properties of Aromatic Compounds

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

Hunan University of Technology, Zhuzhou 412008, China

Department of Physics, Gyeongsang National University, Jinju 52828, Republic of Korea

Shandong Provincial Key Laboratory of Optical Communication Science and Technology, School of Physical Science and Information Technology, Liaocheng University, Liaocheng 252059, China

Funding

National Natural Science Foundation of China · Natural Science Foundation of Hunan Province · Education Department of Hunan Province · National Research Foundation of Korea

References (58)

Show source-provided references
1. Yi · Nat. Rev. Mater. · 2023 · 9 · 4610.1038/s41578-023-00618-1 ↗
2. Wang · Nat. Rev. Phys. · 2024 · 6 · 36510.1038/s42254-024-00719-y ↗
3. Tian · Sci. China: Chem. · 2023 · 1674
4. Lee · Chem. Soc. Rev. · 2024 · 53 · 467410.1039/D3CS00895A ↗
5. Yuan · Joule · 2019 · 3 · 114010.1016/j.joule.2019.01.004 ↗
6. Lin · Adv. Mater. · 2015 · 27 · 117010.1002/adma.201404317 ↗
7. Yuan · Joule · 2019 · 3 · 114010.1016/j.joule.2019.01.004 ↗
8. Wang · Energy Environ. Sci. · 2022 · 15 · 32010.1039/D1EE01832A ↗
9. Xu · Sci. Adv. · 2025 · 11 · 602410.1126/sciadv.adt6024 ↗
10. Luo · Energy Environ. Sci. · 2023 · 16 · 273210.1039/D3EE00908D ↗
11. Meng · Nano Res. · 2025 · 1998
12. Li · Adv. Energy Mater. · 2019 · 9 · 1614
13. Li · Nat. Mater. · 2025 · 24 · 43310.1038/s41563-024-02087-5 ↗
14. Yu · Energy Environ. Sci. · 2025 · 18 · 609410.1039/D5EE01604E ↗
15. Liu · Adv. Mater. · 2024 · 36 · 240466010.1002/adma.202404660 ↗
16. Xie · Chem. Sci. · 2024 · 15 · 826510.1039/D4SC01481B ↗
17. Pyzer-Knapp · npj Comput. Mater. · 2022 · 8 · 0076510.1038/s41524-022-00765-z ↗
18. Zhang · Sol. RRL · 2025 · 9 · 240084610.1002/solr.202400846 ↗
19. Sun · npj Comput. Mater. · 2024 · 10 · 2057
20. Zhang · Adv. Mater. · 2024 · 37 · 240761310.1002/adma.202407613 ↗
21. Wang · Mol. Syst. Des. Eng. · 2023 · 8 · 79910.1039/D2ME00265E ↗
22. Nie · ACS Appl. Mater. Interfaces · 2024 · 16 · 6631610.1021/acsami.4c15835 ↗
23. Wang · FlexMat · 2024 · 1 · 23410.1002/flm2.34 ↗
24. Wu · npj Comput. Mater. · 2019 · 5 · 6610.1038/s41524-019-0203-2 ↗
25. T.Akiba , S.Sano , T.Yanase , T.Ohta and M.Koyama , editors. Optuna: A next-generation hyperparameter optimization framework. Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining; 2019
26. T.Chen and C.Guestrin , editors. Xgboost: A scalable tree boosting system. Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining; 2016
27. Xu · npj Comput. Mater. · 2023 · 9 · 4210.1038/s41524-023-01000-z ↗
28. Cui · Nat. Commun. · 2019 · 10 · 251510.1038/s41467-019-10351-5 ↗
29. Zou · Energy Environ. Sci. · 2022 · 15 · 351910.1039/D2EE01340A ↗
30. Zhao · Adv. Sci. · 2020 · 7 · 200050910.1002/advs.202000509 ↗
31. Aloufi · ACS Omega · 2023 · 8 · 2142510.1021/acsomega.2c07975 ↗
32. Yang · Angew. Chem., Int. Ed. · 2021 · 133 · 1939010.1002/ange.202104766 ↗
33. Tian · Sci. China: Chem. · 2024 · 67 · 78810.1007/s11426-023-1774-6 ↗
34. Li · Nat. Energy · 2021 · 6 · 60510.1038/s41560-021-00820-x ↗
35. Guo · Nat. Commun. · 2025 · 16 · 150310.1038/s41467-025-56799-6 ↗
36. Bei · Chin. Chem. Lett. · 2024 · 35 · 10843810.1016/j.cclet.2023.108438 ↗
37. Crociani · Molecules · 2024 · 29 · 362510.3390/molecules29153625 ↗
38. Sun · Nat. Commun. · 2018 · 9 · 74310.1038/s41467-018-03207-x ↗
39. Zhang · Adv. Mater. · 2024 · 36 · 240516310.1002/adma.202405163 ↗
40. Machala · Nat. Commun. · 2025 · 16 · 98810.1038/s41467-025-56063-x ↗
41. Stephens · J. Phys. Chem. · 1994 · 98 · 1162310.1021/j100096a001 ↗
42. Rassolov · J. Comput. Chem. · 2001 · 22 · 97610.1002/jcc.1058 ↗
43. Andrea · EPJ Photovoltaics · 2022 · 13 · 1510.1051/epjpv/2022012 ↗
44. Yao · Acc. Chem. Res. · 2020 · 53 · 82210.1021/acs.accounts.0c00009 ↗
45. Grüne · Adv. Funct. Mater. · 2023 · 33 · 221264010.1002/adfm.202212640 ↗
46. He · Adv. Funct. Mater. · 2022 · 32 · 211185510.1002/adfm.202111855 ↗
47. Huang · Chem. Eng. J. · 2023 · 475 · 14595810.1016/j.cej.2023.145958 ↗
48. Song · Angew. Chem., Int. Ed. · 2025 · 137 · e20250635710.1002/ange.202506357 ↗
49. Yang · Adv. Mater. · 2025 · e1098010.1002/adma.202510980 ↗
50. Mulliken · J. Chem. Phys. · 1955 · 23 · 183310.1063/1.1740588 ↗
51. Wang · ACS Appl. Mater. Interfaces · 2024 · 16 · 6684610.1021/acsami.3c15365 ↗
52. Runge · Phys. Rev. Lett. · 1984 · 52 · 99710.1103/PhysRevLett.52.997 ↗
53. M. E.Casida , Time-dependent density functional response theory for molecules , Recent Advances In Density Functional Methods: (Part I) , World Scientific , 1995 , pp. 155–9210.1142/9789812830586_0005 ↗
54. Wang · J. Am. Chem. Soc. · 2023 · 145 · 1368610.1021/jacs.3c01634 ↗
55. Cui · Angew. Chem., Int. Ed. · 2023 · 62 · e20230493110.1002/anie.202304931 ↗
56. Leblebici · ACS Appl. Mater. Interfaces · 2013 · 5 · 1010510.1021/am402744k ↗
57. Sun · npj Comput. Mater. · 2024 · 10 · 18110.1038/s41524-024-01367-7 ↗
58. Cao · J. Mater. Chem. C · 2025 · 13 · 1215010.1039/D5TC02014J ↗