Page 99 - Read Online

Niu et al. J. Mater. Inf. 2025, 5, 45 Journal of
DOI: 10.20517/jmi.2025.22
Materials Informatics

Research Article Open Access

Data-driven OLED candidate design: a generative
model from independent-property domains to the

comprehensive performance enhancement

1
1
1,*
1
1
1
1,*
Xinxin Niu , Zhiyao Su , Luyu Wang , Wenbin Shi , Hengyue Zhang , Yanfeng Dang , Yuan Yuan , Yajing
1,*
Sun , Wenping Hu 1,2
1
Key Laboratory of Organic Integrated Circuits, Ministry of Education and Tianjin Key Laboratory of Molecular Optoelectronic
Sciences, Department of Chemistry, School of Science, Tianjin University, Tianjin 300072, China.
2
Joint School of National University of Singapore and Tianjin University, Fuzhou 350207, Fujian, China.
* Correspondence to: Dr. Yanfeng Dang, Dr. Yuan Yuan, Dr. Yajing Sun, Key Laboratory of Organic Integrated Circuits, Ministry of
Education and Tianjin Key Laboratory of Molecular Optoelectronic Sciences, Department of Chemistry, School of Science, Tianjin
University, No. 92 Weijin Road, Nankai District, Tianjin 300072, China. E-mail: yanfeng.dang@tju.edu.cn; yyuan@tju.edu.cn;
syj19@ tju.edu.cn
How to cite this article: Niu, X.; Su, Z.; Wang, L.; Shi, W.; Zhang, H.; Dang, Y.; Yuan, Y.; Sun, Y.; Hu, W. Data-driven OLED
candidate design: a generative model from independent-property domains to the comprehensive performance enhancement. J.
Mater. Inf. 2025, 5, 45. https://dx.doi.org/10.20517/jmi.2025.22
Received: 2 Apr 2025 First Decision: 23 May 2025 Revised: 7 Jun 2025 Accepted: 12 Jun 2025 Published: 23 Jul 2025

Academic Editors: Ming Hu, Bohayra Mortazavi Copy Editor: Pei-Yun Wang Production Editor: Pei-Yun Wang

Abstract
The discovery of high-performance organic light-emitting diode (OLED) materials is hindered by conventional
human-aware design methodologies and the scarcity of pure organic luminescent scaffolds. Although machine
learning models have improved the efficiency of high-throughput screening for OLED candidates, their
effectiveness is still limited by the small size and low quality of available experimental datasets. In this study, we
introduced LumiGen, an integrated framework for the de novo design of high-quality OLED candidate molecules
with targeted photophysical properties. A sampling-screening iterative process was designed to gradually refine
the molecular selection, enabling the transition from independent-property optimization to all-rounded OLED
candidates. Among the collected high-quality OLED candidate molecules, computational estimates indicate that
the optical properties of most molecules (approximately 80.2%) meet the required criteria. During the iterative
training process, the Sampling Augmentor enhances the proportion of OLED candidate molecules by over threefold
(from 6.56% to 21.13%). Additionally, we successfully synthesized a new molecular scaffold from the OLED
candidates, achieving a photoluminescence quantum yield of up to 88.6%. According to the statistics, only 0.33%
of the molecules in the dataset outperform our synthesized molecules in terms of overall optical performance.

© The Author(s) 2025. Open Access This article is licensed under a Creative Commons Attribution 4.0
International License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, sharing,
adaptation, distribution and reproduction in any medium or format, for any purpose, even commercially, as
long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and
indicate if changes were made.

www.oaepublish.com/jmi