Published February 27, 2025 | Version v1

Pre-training molecular database and models of OCNet

Authors/Creators

Description

This record contains the pre-training molecular database and pretrained model files for OCNet, a domain-knowledge-enhanced representation learning framework for organic conjugated molecules and devices. The dataset and models are associated with the article “Virtual characterization via knowledge-enhanced representation learning: from organic conjugated molecules to devices” (npj Computational Materials, 2025; DOI: 10.1038/s41524-025-01788-y).

Files

Files (38.9 GB)

Name Size
md5:9c6ee67cf4ee51ee614526098d875acb
571.2 MB Download
md5:efd7a2649e1e1fa829114cad7d218954
25.4 GB Download
md5:6d51e6c62cfb35e8a7a4981364f40568
12.9 GB Download

Additional details

Related works

Is supplement to
Journal article: 10.1038/s41524-025-01788-y (DOI)

References

  • Zhao, G.; Ou, Q.; Zhao, Z.; Chen, S.; Lin, H.; Ji, X.; Wang, Z.; Wang, H.; Cai, H.; Wu, L.; Lu, S.; Yang, F.; Wen, Y.; Zhang, Y.; Ma, H.; Gao, Z.; Cheng, Z.; E, W. Virtual characterization via knowledge-enhanced representation learning: from organic conjugated molecules to devices. npj Computational Materials 2025, 11, 308. https://doi.org/10.1038/s41524-025-01788-y