How Important Are GNN Architectures For QSAR Modelling?

28 March 2025, Version 1
This content is a preprint and has not undergone peer review at the time of posting.

Abstract

This work investigates Graph Neural Networks and molecular descriptors average performance across a range of realistic QSAR problems. Using 9 GSK internal QSAR datasets, 9 Graph Neural Network layer architectures and their hyperparameters were evaluated on a default set of descriptors. Following this, 5 descriptor classes were evaluated across datasets using a common baseline model architecture. We show that no architecture performed better than any other, and that hyperparameters such as the learning rate, dropout, and message-passing layers are crucial for performance. We likewise show that the choice of molecular descriptors is impactful across datasets. Finally, the impact of tautomers on descriptors showed consistent deviations for expected descriptors, such as the number of hydrogens and graph centrality measures. Our recommendations are to direct modelling efforts towards hyperparameter optimization and feature selection rather than focusing on network architecture.

Keywords

QSAR
GNN
Cheminformatics
Hyperparameter

Supplementary materials

Title
Description
Actions
Title
Supplementary Information
Description
Details of descriptors studied, statistical tests, and information and analysis on hyperparameters optimisation runs
Actions

Supplementary weblinks

Comments

Comments are not moderated before they are posted, but they can be removed by the site moderators if they are found to be in contravention of our Commenting Policy [opens in a new tab] - please read this policy before you post. Comments should be used for scholarly discussion of the content in question. You can find more information about how to use the commenting feature here [opens in a new tab] .
This site is protected by reCAPTCHA and the Google Privacy Policy [opens in a new tab] and Terms of Service [opens in a new tab] apply.