# Comparison of Atom Representations in Graph Neural Networks for Molecular Property Prediction

arXiv: https://arxiv.org/abs/2012.04444 · HTML: https://mlsanity.com/paper/2012.04444/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Nov 2020.

## Built on by (most cited first, 5 of 5)

- [Graph neural networks for materials science and chemistry](https://mlsanity.com/paper/2208.09481/) (2022)
- [Learning to Extend Molecular Scaffolds with Structural Motifs](https://mlsanity.com/paper/2103.03864/) (2021)
- [Relative Molecule Self-Attention Transformer](https://mlsanity.com/paper/2110.05841/) (2021)
- [ProGReST: Prototypical Graph Regression Soft Trees for Molecular Property Prediction](https://mlsanity.com/paper/2210.03745/) (2022)
- [Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction](https://mlsanity.com/paper/2411.13688/) (2024)

## Abstract (arXiv)

Graph neural networks have recently become a standard method for analysing chemical compounds. In the field of molecular property prediction, the emphasis is now put on designing new model architectures, and the importance of atom featurisation is oftentimes belittled. When contrasting two graph neural networks, the use of different atom features possibly leads to the incorrect attribution of the results to the network architecture. To provide a better understanding of this issue, we compare multiple atom representations for graph models and evaluate them on the prediction of free energy, solubility, and metabolic stability. To the best of our knowledge, this is the first methodological study that focuses on the relevance of atom representation to the predictive performance of graph neural networks.