论文标题
分子性质预测图神经网络中原子表示的比较
Comparison of Atom Representations in Graph Neural Networks for Molecular Property Prediction
论文作者
论文摘要
图神经网络最近已成为分析化合物的标准方法。在分子财产预测领域，现在重点是设计新的模型体系结构，并且原子特征的重要性通常被贬低。当对比两个图神经网络时，使用不同原子的使用可能会导致结果对网络体系结构的不正确归因。为了更好地理解此问题，我们比较图形模型的多个原子表示，并根据自由能，溶解度和代谢稳定性进行评估。据我们所知，这是第一个重点是原子表示与图神经网络的预测性能的相关性的方法论研究。
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.
