Department of Computer, Control and Management Engineering Antonio Ruberti (DIAG) Sapienza University of Rome, 00185 Rome, Italy; Department of Life Science Informatics and Data Science, B-IT, LIMES Program Unit Chemical Biology and Medicinal Chemistry, Rheinische Friedrich-Wilhelms-Universität, Friedrich-Hirzebruch-Allee 5/6, 53115 Bonn, Germany.
Department of Computer, Control and Management Engineering Antonio Ruberti (DIAG) Sapienza University of Rome, 00185 Rome, Italy.
STAR Protoc. 2022 Dec 16;3(4):101887. doi: 10.1016/j.xpro.2022.101887. Epub 2022 Nov 24.
Here we present EdgeSHAPer, a workflow for explaining graph neural networks by approximating Shapley values using Monte Carlo sampling. In this protocol, we describe steps to execute Python scripts for a chemical dataset from the original publication; however, this approach is also applicable to any user-provided dataset. We also detail steps encompassing neural network training, an explanation phase, and analysis via feature mapping. For complete details on the use and execution of this protocol, please refer to Mastropietro et al. (2022)..
在此，我们介绍了 EdgeSHAPer，这是一种通过使用蒙特卡罗抽样来近似 Shapley 值从而解释图神经网络的工作流程。在本方案中，我们描述了执行原始出版物中化学数据集的 Python 脚本的步骤；但是，这种方法也适用于任何用户提供的数据集。我们还详细介绍了涵盖神经网络训练、解释阶段以及通过特征映射进行分析的步骤。有关使用和执行本方案的完整详细信息，请参见 Mastropietro 等人（2022 年）。
