Downstream molecular models and properties of OCNet

The dataset for the optoelectronic properties in the gas phase is derived from the OCELOT chromophore dataset [1,2] created by Qianxiang Ai, Vinayak Bhat et al. , while the dataset for the optoelectronic properties in solution is sourced from Deep4Chem [3] created by Joonyoung F. Joung et al. We additionally provide the neural network weights finetuned by OCNet based on these datasets. [1] Bhat, V.; Sornberger, P.; Pokuri, B. S. S.; Duke, R.; Ganapathysubramanian, B.; Risko, C. Electronic, redox, and optical property prediction of organic π-conjugated molecules through a hierarchy of machine learning approaches. Chemical Science 2023, 14, 203–213. [2] Ai, Q.; Bhat, V.; Ryno, S. M.; Jarolimek, K.; Sornberger, P.; Smith, A.; Haley, M. M.; Anthony, J. E.; Risko, C. OCELOT: An infrastructure for data-driven research to discover and design crystalline organic semiconductors. The Journal of Chemical Physics 2021, 154 . [3] Joung, J. F.; Han, M.; Jeong, M.; Park, S. Experimental database of optical properties of organic compounds. Scientific data 2020, 7, 295.