High-accuracy physical property prediction for pure organics via molecular representation learning: bridging data to discovery

作者：Qi Ou, Hongshuai Wang, Muni Zhuang, Shangqian Chen, Lele Liu, Ning Wang, Zhifeng Gao · 发表于：npj Computational Materials · 年份：2025 · DOI：10.1038/s41524-025-01720-4 · 被引用次数：4 · 研究领域：Computational Drug Discovery Methods、Machine Learning in Materials Science、Various Chemistry Research Topics

The escalating energy crisis has spurred extensive research into organic compounds for energy-efficient applications, taking advantage of their environmental friendliness, cost-effective synthesis, and adaptable molecular structures. Traditional trial-and-error methods for discovering highly functional organic compounds are expensive and time-consuming. We employed a 3D transformer-based molecular representation learning algorithm to create the Org-Mol pre-trained model, using 60 million semi-empirically optimized small organic molecule structures. After fine-tuning with public experimental data, the model can accurately predict various physical properties of pure organics, with test set R 2 values exceeding 0.92. These fine-tuned models are used in high-throughput screening among millions of ester molecules to identify novel immersion coolants, resulting in the experimental validation of two promising candidates. This work not only demonstrates the potential of Org-Mol in predicting bulk properties for pure organic compounds but also paves the way for the rational and efficient development of ideal candidates for energy-saving materials.