Deeply learning molecular structure-property relationships using graph attention neural network
Seongok Ryu, Jaechang Lim and Woo Youn Kim
Received: 29th May 18
Molecular structure-property relationships are the key to molecular design for materials and drug discovery. The rise of deep learning offers a new viable solution to elucidate the structure-property relationships directly from chemical data. Here we show that graph attention networks can greatly improve performance of the deep learning for chemistry. The attention mechanism enables to distinguish atoms in different environments and thus to extract important structural features determining target properties. We demonstrated that our model can detect appropriate features for molecular polarity, solubility, and energy. Interestingly, it identified two distinct parts of molecules as essential structural features for high photovoltaic efficiency, each of which coincided with the area of donor and acceptor orbitals in charge-transfer excitations, respectively. As a result, it could accurately predict molecular properties. Moreover, the resultant latent space was well-organized such that molecules with similar properties were closely located, which is critical for successful molecular design.
Read in full at arXiv.
This is an abstract of a preprint hosted on an independent third party site. It has not been peer reviewed but is currently under consideration at Nature Communications.