AI RESEARCH
On Improving Graph Neural Networks for QSAR by Pre-training on Extended-Connectivity Fingerprints
arXiv CS.LG
•
ArXi:2605.10722v1 Announce Type: new Molecular Graph Neural Networks (GNNs) are increasingly common in drug discovery, particularly for Quantitative Structure-Activity Relationship (QSAR) studies; yet, their superiority compared to classical molecular featurisation approaches is disputed. We report a general strategy for improving GNNs for QSAR by pre-