# On Improving Graph Neural Networks for QSAR by Pre-training on Extended-Connectivity Fingerprints

arXiv: https://arxiv.org/abs/2605.10722 · HTML: https://mlsanity.com/paper/2605.10722/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 4 of its 124 references that are in the map.
- First posted on arXiv 11 May 2026.

## Builds on (most cited first, 4 of 4)

- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [Fast Graph Representation Learning with PyTorch Geometric](https://mlsanity.com/paper/1903.02428/) (2019)
- [Strategies for Pre-training Graph Neural Networks](https://mlsanity.com/paper/1905.12265/) (2019)
- [Deep Learning Foundation Models from Classical Molecular Descriptors](https://mlsanity.com/paper/2506.15792/) (2025)

## Abstract (arXiv)

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-training to predict Extended-Connectivity Fingerprints (ECFP). We validate our approach with statistical tests and challenging out-of-distribution (OOD) splits. Across five out of six Biogen benchmarks, we observed a statistically significant improvement in standard performance metrics over all evaluated baselines when using ECFP pre-trained GNNs. However, for more heterogeneous datasets and more complex endpoints, such as binding affinity prediction, pre-trained GNNs underperformed in OOD settings. Importantly, we investigated the impact of substructure-level data leakage during pre-training on downstream performance. While we identified scenarios where pre-training on ECFPs was less effective, our findings show that ECFP-based pre-training can enhance downstream OOD performance on a diverse set of practically relevant QSAR tasks.