Shanghai Key Lab of Intelligent Information Processing, and School of Computer Science, Fudan University, Shanghai 200433, China.
Department of Computer Science and Technology, Tongji University, Shanghai 201804, China.
Bioinformatics. 2021 Sep 29;37(18):2981-2987. doi: 10.1093/bioinformatics/btab195.
Molecular property prediction is a hot topic in recent years. Existing graph-based models ignore the hierarchical structures of molecules. According to the knowledge of chemistry and pharmacy, the functional groups of molecules are closely related to its physio-chemical properties and binding affinities. So, it should be helpful to represent molecular graphs by fragments that contain functional groups for molecular property prediction.
In this article, to boost the performance of molecule property prediction, we first propose a definition of molecule graph fragments that may be or contain functional groups, which are relevant to molecular properties, then develop a fragment-oriented multi-scale graph attention network for molecular property prediction, which is called FraGAT. Experiments on several widely used benchmarks are conducted to evaluate FraGAT. Experimental results show that FraGAT achieves state-of-the-art predictive performance in most cases. Furthermore, our case studies show that when the fragments used to represent the molecule graphs contain functional groups, the model can make better predictions. This conforms to our expectation and demonstrates the interpretability of the proposed model.
The code and data underlying this work are available in GitHub, at https://github.com/ZiqiaoZhang/FraGAT.
Supplementary data are available at Bioinformatics online.
分子性质预测是近年来的热门话题。现有的基于图的模型忽略了分子的层次结构。根据化学和药学的知识，分子的官能团与其物理化学性质和结合亲和力密切相关。因此，通过包含与分子性质相关的官能团的片段来表示分子图，对于分子性质预测应该是有帮助的。
在本文中，为了提高分子性质预测的性能，我们首先提出了一种可能包含与分子性质相关的官能团的分子图片段的定义，然后开发了一种面向片段的多尺度图注意网络用于分子性质预测，称为 FraGAT。在几个广泛使用的基准上进行了 FraGAT 的实验评估。实验结果表明，FraGAT 在大多数情况下都达到了最先进的预测性能。此外，我们的案例研究表明，当用于表示分子图的片段包含官能团时，模型可以做出更好的预测。这符合我们的期望，并证明了所提出模型的可解释性。
这项工作的代码和数据可在 GitHub 上获得，网址为 https://github.com/ZiqiaoZhang/FraGAT。
补充数据可在生物信息学在线获得。
