Enhanced Predictions for the Experimental Photophysical Data Using the Featurized Schnet-Bondstep Approach

Sheng Hsuan Hung, Zong Rong Ye, Chi Feng Cheng, Berlin Chen*, Ming Kang Tsai*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

1 Citation (Scopus)

Abstract

An assessment of modifying the SchNET model for the predictions of experimental molecular photophysical properties, including absorption energy (ΔEabs), emission energy (ΔEemi), and photoluminescence quantum yield (PLQY), was reported. The solution environment was properly introduced outside the interaction layers of SchNET for not overly amplifying the solute-solvent interactions, particularly being supported by the changes of prediction errors between the presence and absence of the solvent effect. Two featurization schemes under the framework of the Schnet-bondstep approach, with featuring the concepts of reduced-atomic-number and reduced-atomic-neighbor, were demonstrated. These featurized models can consequently provide fine predictions for ΔEabs and ΔEemi with errors less than 0.1 eV. The corresponding predictions of PLQY were shown to be comparable to the previous graph convolution network model.

Original languageEnglish
Pages (from-to)4559-4567
Number of pages9
JournalJournal of Chemical Theory and Computation
Volume19
Issue number14
DOIs
Publication statusPublished - 2023 Jul 25

ASJC Scopus subject areas

  • Computer Science Applications
  • Physical and Theoretical Chemistry

Fingerprint

Dive into the research topics of 'Enhanced Predictions for the Experimental Photophysical Data Using the Featurized Schnet-Bondstep Approach'. Together they form a unique fingerprint.

Cite this