Detailed Information

A benchmark study of machine learning methods for molecular electronic transition: Tree-based ensemble learning versus graph neural network

Cited 8 time in Web of Science Cited 9 time in Scopus

Kang, Beomchang; Seok, Chaok; Lee, Ju Yong

Issue Date
Bulletin of the Korean Chemical Society, Vol.43 No.3, pp.328-335
Fluorophores play crucial roles in chemical and biological imaging. An efficient computational model that evaluates the electronic properties of molecules accurately would be a useful tool for discovering novel fluorophores. Tree-based ensemble and graph neural network (GNN) methods have been regarded as attractive models for predicting molecular properties. Here, we present a benchmark test using three tree-based ensemble methods (Random Forest, LightGBM, and XGBoost) and three GNNs (directed message passing neural network [D-MPNN], attention message passing neural network [AMPNN], and DimeNet++) for predicting electronic transition properties such as excitation energies and oscillator strengths. From our benchmark, DimeNet++ was identified as the most accurate model to predict electronic transition properties. The average root mean square error of DimeNet++ for predicting the HOMO-LUMO gap was 0.11 eV whereas those of the other methods exceeded 0.3 eV. D-MPNN predicted fastest without sacrificing accuracy. Our results show that DimeNet++ and D-MPNN may serve as helpful evaluators for novel fluorophore design when combined with molecular generation methods.
Files in This Item:
There are no files associated with this item.
Appears in Collections:

Related Researcher

  • Graduate School of Convergence Science & Technology
  • Dept. of Molecular and Biopharmaceutical Sciences
Research Area AI models for drug discovery, Free energy calculation, Molecular dynamics, 분자동역학, 신약개발을 위한 AI 모델, 자유에너지 계산


Item View & Download Count

  • mendeley

Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.