Helmholtz Gemeinschaft


Graph neural networks for learning molecular excitation spectra

Item Type:Article
Title:Graph neural networks for learning molecular excitation spectra
Creators Name:Singh, K. and Münchmeyer, J. and Weber, L. and Leser, U. and Bande, A.
Abstract:Machine learning (ML) approaches have demonstrated the ability to predict molecular spectra at a fraction of the computational cost of traditional theoretical chemistry methods while maintaining high accuracy. Graph neural networks (GNNs) are particularly promising in this regard, but different types of GNNs have not yet been systematically compared. In this work, we benchmark and analyze five different GNNs for the prediction of excitation spectra from the QM9 dataset of organic molecules. We compare the GNN performance in the obvious runtime measurements, prediction accuracy, and analysis of outliers in the test set. Moreover, through TMAP clustering and statistical analysis, we are able to highlight clear hotspots of high prediction errors as well as optimal spectra prediction for molecules with certain functional groups. This in-depth benchmarking and subsequent analysis protocol lays down a recipe for comparing different ML methods and evaluating dataset quality.
Keywords:Machine Learning, Computer Neural Networks
Source:Journal of Chemical Theory and Computation
Publisher:American Chemical Society
Page Range:4408-4417
Date:12 July 2022
Official Publication:https://doi.org/10.1021/acs.jctc.2c00255
PubMed:View item in PubMed

Repository Staff Only: item control page

Open Access
MDC Library