Effect of molecular representation on deep learning performance for prediction of molecular electronic properties

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 55
  • Download : 0
Deep learning (DL) can be a useful approach to molecular applications such as the organic light-emitting diode (OLED) development via high-throughput virtual screening. Various representations have been proposed to incorporate molecular structures in DL methods. However, it is yet to be clear which one would be better for accurate prediction of molecular electronic properties. Here, we carried out a comparative study on the performance of four widely used molecular representations to elucidate an optimal solution for DL applications to OLED materials. We implemented six DL models based on the four representations and assessed their accuracies in the prediction of the electronic properties of thermally activated delayed fluorescence (TADF) molecules. The attention gated graph neural network based on molecular graphs showed the highest accuracy for test sets and TADF candidates. Therefore, the molecular graph can be used as an optimal representation to predict the TADF-related molecular properties.
Publisher
WILEY-V C H VERLAG GMBH
Issue Date
2022-05
Language
English
Article Type
Article
Citation

BULLETIN OF THE KOREAN CHEMICAL SOCIETY, v.43, no.5, pp.645 - 649

ISSN
0253-2964
DOI
10.1002/bkcs.12516
URI
http://hdl.handle.net/10203/296596
Appears in Collection
CH-Journal Papers(저널논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0