Abstract
Artificial intelligence-driven materials development has emerged as a powerful alternative to traditional trial-and-error methods. Despite its promise, these methods often struggle to uncover novel materials or generate actionable insights in emerging fields due to limited data availability. This challenge is particularly pronounced in electronic materials, where the intricate interplay of physical mechanisms and structure-property relationships impede progress. Here, we report a methodology combining Physical-Knowledge-Undergirded Transfer Learning for accurate property prediction with limited data, coupled with physical knowledge and artificial intelligence-driven hypothesis generation to yield scientific insights. Using this approach, we successfully identify low-voltage, high-performance organic electrochemical transistor materials and yield material design knowledge. The approach is experimentally validated through the synthesis of n-type polymers, demonstrating accurate property prediction and revealing critical structure-property relationships. We believe this approach can be applied to other emerging material systems with limited data availability and complex physical mechanisms, and accelerates the development of materials in emerging fields.
Data availability
The organic field-effect transistor (OFET) performance data, organic electrochemical transistor (OECT) performance data, the generated polymer repeating units library, and the DFT-calculated energy and energy level libraries generated in this study have been deposited in the GitHub repository: https://github.com/Tina-starry/OECTs_prediction.git. All the other data supporting the findings of this study are available in the paper and its Supplementary Information. Source data are provided with this paper.
Code availability
The custom Python code used for dataset preprocessing, fine-tuning the Uni-Mol model, and training the XGBoost ensembles is publicly available in the following GitHub repository: https://github.com/Tina-starry/OECTs_prediction.git. The version of the code used in this study has been archived and can be cited using the reference58.
References
Peng, J. et al. Human- and machine-centred designs of molecules and materials for sustainability and decarbonization. Nat. Rev. Mater. 7, 991–1009 (2022).
Gromski, P. S., Henson, A. B., Granda, J. M. & Cronin, L. How to explore chemical space using algorithms and automation. Nat. Rev. Chem. 3, 119–128 (2019).
Sanchez-Lengeling, B. & Aspuru-Guzik, A. Inverse molecular design using machine learning: generative models for matter engineering. Science 361, 360–365 (2018).
Butler, K. T., Davies, D. W., Cartwright, H., Isayev, O. & Walsh, A. Machine learning for molecular and materials science. Nature 559, 547–555 (2018).
Gómez-Bombarelli, R. et al. Design of efficient molecular organic light-emitting diodes by a high-throughput virtual screening and experimental approach. Nat. Mater. 15, 1120–1127 (2016).
Merchant, A. et al. Scaling deep learning for materials discovery. Nature 624, 80–85 (2023).
Jordan, M. I. & Mitchell, T. M. Machine learning: trends, perspectives, and prospects. Science 349, 255–260 (2015).
Ding, R. et al. Unlocking the potential: machine learning applications in electrocatalyst design for electrochemical hydrogen energy transformation. Chem. Soc. Rev. 53, 11390–11461 (2024).
Hart, G. L. W., Mueller, T., Toher, C. & Curtarolo, S. Machine learning for alloys. Nat. Rev. Mater. 6, 730–755 (2021).
Batra, R., Song, L. & Ramprasad, R. Emerging materials intelligence ecosystems propelled by machine learning. Nat. Rev. Mater. 6, 655–678 (2021).
Angello, N. H. et al. Closed-loop transfer enables artificial intelligence to yield chemical knowledge. Nature 633, 351–358 (2024).
Yi, J., Zhang, G., Yu, H. & Yan, H. Advantages, challenges and molecular design of different material types used in organic solar cells. Nat. Rev. Mater. 9, 46–62 (2024).
Ostroverkhova, O. Organic optoelectronic materials: mechanisms and applications. Chem. Rev. 116, 13279–13412 (2016).
Mei, J., Diao, Y., Appleton, A. L., Fang, L. & Bao, Z. Integrated materials design of organic semiconductors for field-effect transistors. J. Am. Chem. Soc. 135, 6724–6746 (2013).
Rivnay, J. et al. Organic electrochemical transistors. Nat. Rev. Mater. 3, 17086 (2018).
Kroon, R. et al. Thermoelectric plastics: from design to synthesis, processing and structure–property relationships. Chem. Soc. Rev. 45, 6147–6164 (2016).
Wu, J. et al. Inverse design workflow discovers hole-transport materials tailored for perovskite solar cells. Science 386, 1256–1264 (2024).
Wu, Y. et al. Autonomous synthesis and inverse design of electrochromic polymers with high efficiency and accuracy. J. Am. Chem. Soc. 147, 44101–44113 (2025).
Russ, B., Glaudell, A., Urban, J. J., Chabinyc, M. L. & Segalman, R. A. Organic thermoelectric materials for energy harvesting and temperature control. Nat. Rev. Mater. 1, 16050 (2016).
Wang, Y. et al. Designing organic mixed conductors for electrochemical transistor applications. Nat. Rev. Mater. 9, 249–265 (2024).
Liu, C., Wang, K., Gong, X. & Heeger, A. J. Low bandgap semiconducting polymers for polymeric photovoltaics. Chem. Soc. Rev. 45, 4825–4846 (2016).
Heeger, A. J. Semiconducting polymers: the Third Generation. Chem. Soc. Rev. 39, 2354–2371 (2010).
Ding, L. et al. Polymer semiconductors: synthesis, processing, and applications. Chem. Rev. 123, 7421–7497 (2023).
Tran, H. et al. Design of functional and sustainable polymers assisted by artificial intelligence. Nat. Rev. Mater. 9, 866–886 (2024).
Yuvaraja, S. et al. Organic field-effect transistor-based flexible sensors. Chem. Soc. Rev. 49, 3423–3460 (2020).
Chen, H., Zhang, W., Li, M., He, G. & Guo, X. Interface engineering in organic field-effect transistors: principles, applications, and perspectives. Chem. Rev. 120, 2879–2949 (2020).
Zhang, C., Chen, P. & Hu, W. Organic field-effect transistor-based gas sensors. Chem. Soc. Rev. 44, 2087–2107 (2015).
Yang, J., Zhao, Z., Wang, S., Guo, Y. & Liu, Y. Insight into high-performance conjugated polymers for organic field-effect transistors. Chem. 4, 2748–2785 (2018).
Nketia-Yawson, B. et al. A highly planar fluorinated benzothiadiazole-based conjugated polymer for high-performance organic thin-film transistors. Adv. Mater. 27, 3045–3052 (2015).
Chen, H. et al. Highly π-extended copolymers with diketopyrrolopyrrole moieties for high-performance field-effect transistors. Adv. Mater. 24, 4618–4622 (2012).
Yan, X. et al. Approaching disorder-tolerant semiconducting polymers. Nat. Commun. 12, 5723 (2021).
Che, Y. & Perepichka, D. F. Quantifying planarity in the design of organic electronic materials. Angew. Chem. Int. Ed. 60, 1364–1373 (2021).
Tsao, H. N. et al. Ultrahigh mobility in polymer field-effect transistors by design. J. Am. Chem. Soc. 133, 2605–2612 (2011).
Jiang, Y. et al. Fast deposition of aligning edge-on polymers for high-mobility ambipolar transistors. Adv. Mater. 31, 1805761 (2019).
Yang, Y., Liu, Z., Zhang, G., Zhang, X. & Zhang, D. The effects of side chains on the charge mobilities and functionalities of semiconducting conjugated polymers beyond solubilities. Adv. Mater. 31, 1903104 (2019).
Gengmo, Z. et al. Uni-Mol: a universal 3D molecular representation learning framework. In The Eleventh International Conference on Learning Representations. https://openreview.net/forum?id=6K2RM6wVqKu (2023).
Gao, Z. et al. Uni-QSAR: an Auto-ML Tool for Molecular Property Prediction. Preprint at https://arxiv.org/abs/2304.12239 (2023).
Lee, M.-H. Machine learning for understanding the relationship between the charge transport mobility and electronic energy levels for n-type organic field-effect transistors. Adv. Electron. Mater. 5, 1900573 (2019).
Chen, T. & Guestrin, C. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 785–794 (Association for Computing Machinery, San Francisco, California, USA, 2016).
Pedregosa, F. et al. Scikit-learn: machine learning in python. J. Mach. Learn. Res. 12, 2825–2830 (2011).
Wu, Y., Zhao, Y. & Liu, Y. Toward efficient charge transport of polymer-based organic field-effect transistors: molecular design, processing, and functional utilization. Acc. Mater. Res. 2, 1047–1058 (2021).
Chen, Z. et al. π-conjugated polymers for high-performance organic electrochemical transistors: molecular design strategies, applications and perspectives. Angew. Chem. Int. Ed. 64, e202423013 (2025).
Ding, R. et al. Donor engineering for high performance n-type oect materials with exceptional operational stability. Angew. Chem. Int. Ed. 64, e202513182 (2025).
Li, P., Shi, J., Lei, Y., Huang, Z. & Lei, T. Switching p-type to high-performance n-type organic electrochemical transistors via doped state engineering. Nat. Commun. 13, 5970 (2022).
Lei, Y., Li, P., Zheng, Y. & Lei, T. Materials design and applications of n-type and ambipolar organic electrochemical transistors. Mater. Chem. Front. 8, 133–158 (2024).
Ge, G.-Y. et al. On-site biosignal amplification using a single high-spin conjugated polymer. Nat. Commun. 16, 396 (2025).
Gonthier, J. F. et al. π-depletion as a criterion to predict π-stacking ability. Chem. Commun. 48, 9239–9241 (2012).
Alsufyani, M. et al. The effect of organic semiconductor electron affinity on preventing parasitic oxidation reactions limiting performance of n-type organic electrochemical transistors. Adv. Mater. 36, 2403911 (2024).
Moser, M. et al. Polaron delocalization in donor–acceptor polymers and its impact on organic electrochemical transistor performance. Angew. Chem. Int. Ed. 60, 7777–7785 (2021).
Shi, J. et al. Revealing the role of polaron distribution on the performance of n-type organic electrochemical transistors. Chem. Mater. 34, 864–872 (2022).
Ding, R. et al. Ultra-low threshold voltage in n-type organic electrochemical transistors enabled by organic mixed ionic-electronic conductors with dual electron-withdrawing substitutions. Adv. Funct. Mater. 35, 2412181 (2025).
Mei, J., Graham, K. R., Stalder, R. & Reynolds, J. R. Synthesis of isoindigo-based oligothiophenes for molecular bulk heterojunction solar cells. Org. Lett. 12, 660–663 (2010).
Hong, W. et al. Is a polymer semiconductor having a “perfect” regular structure desirable for organic thin film transistors? Chem. Sci. 6, 3225–3235 (2015).
Lu, T. & Chen, F. Multiwfn: a multifunctional wavefunction analyzer. J. Comput. Chem. 33, 580–592 (2012).
Lu, T. A comprehensive electron wavefunction analysis toolbox for chemists, Multiwfn. J. Chem. Phys. 161, 082503 (2024).
Humphrey, W., Dalke, A. & Schulten, K. VMD: visual molecular dynamics. Journal of Molecular Graphics 14, 33–38 (1996).
Pan, Y. et al. An insight into the role of side chains in the microstructure and carrier mobility of high-performance conjugated polymers. Polym. Chem. 12, 2471–2480 (2021).
Tian, S.-Y. Transfer-learning guided design of high-performance conjugated polymers for low-voltage electrochemical transistors. Zenodo https://doi.org/10.5281/zenodo.18883965 (2026).
Perea, J. A., Deckard, A., Haase, S. B. & Harer, J. SW1PerS: sliding windows and 1-persistence scoring; discovering periodicity in gene expression time series data. BMC Bioinformatics 16, 257 (2015).
Acknowledgments
This work is supported by the National Natural Science Foundation of China (T2425010 and T2521001) and the National Key R&D Program of China (2025YFF0518301). We acknowledge the Molecular Materials and Nanofabrication Laboratory, the Materials Processing and Analysis Center and the Electron Microscopy Laboratory of Peking University for instrument use. The computational part is supported by the High-Performance Computing Platform of Peking University.
Author information
Authors and Affiliations
Contributions
S.-Y.T., F.M. and T.L. conceived the idea and designed the experiments. S.-Y.T. constructed the polymer field effect transistors (OFETs) and polymer electrochemical transistors (OECTs) database. S.-Y.T. performed AI prediction studies, polymer characterization and device fabrication. Z.R. synthesized the polymers. Y.Z., J.W., X.-Y.D. and Q.L provided experimental help and advice. S.-Y.T., F.M. and T.L. wrote the manuscript. All the authors revised and approved the manuscript.
Corresponding authors
Ethics declarations
Competing interests
The authors declare no competing interests.
Peer review
Peer review information
Nature Communications thanks Kui Feng, Akinori Saeki, Suhao Wang, and the other anonymous reviewer(s) for their contribution to the peer review of this work. A peer review file is available.
Additional information
Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary information
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
About this article
Cite this article
Tian, SY., Ren, Z., Zheng, Y. et al. Transfer-learning guided design of high-performance conjugated polymers for low-voltage electrochemical transistors. Nat Commun (2026). https://doi.org/10.1038/s41467-026-71381-4
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41467-026-71381-4
