用几何散射变换提升分子图像预测致突变性的精度。
GeoScatt-GNN: A Geometric Scattering Transform-Based Graph Neural Network Model for Ames Mutagenicity Prediction
- 结合分子图像的2D散射系数与几何图散射特征
- 在ZINC数据集上显著优于传统方法
- 适合药物发现与化学品安全评估研究者
本文针对致突变性预测这一紧迫挑战，提出三项创新方法。首先，展示从分子图像提取的2D散射系数相比传统分子描述符具有更优性能。其次，提出一种混合方法，融合几何图散射（GGS）、图同构网络（GIN）与机器学习模型，在致突变性预测中表现优异。第三，提出新型图神经网络架构MOLG3-SAGE，将GGS节点特征整合至全连接图结构，实现卓越预测准确率。在ZINC数据集上的实验结果表明，结合2D与几何散射技术与GNN可显著提升性能。本研究揭示了GNN与GGS在致突变性预测中的潜力，对药物发现与化学安全评估具有广泛意义。
原文摘要 · Abstract (English)
This paper tackles the pressing challenge of mutagenicity prediction by introducing three ground-breaking approaches. First, it showcases the superior performance of 2D scattering coefficients extracted from molecular images, compared to traditional molecular descriptors. Second, it presents a hybrid approach that combines geometric graph scattering (GGS), Graph Isomorphism Networks (GIN), and machine learning models, achieving strong results in mutagenicity prediction. Third, it introduces a novel graph neural network architecture, MOLG3-SAGE, which integrates GGS node features into a fully connected graph structure, delivering outstanding predictive accuracy. Experimental results on the ZINC dataset demonstrate significant improvements, emphasizing the effectiveness of blending 2D and geometric scattering techniques with graph neural networks. This study illustrates the potential of GNNs and GGS for mutagenicity prediction, with broad implications for drug discovery and chemical safety assessment.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。