PyTorch-native graph neural networks for molecules and proteins. Use when building custom GNN architectures for drug discovery, protein modeling, or knowledge graph reasoning. Best for custom model development, protein property prediction, retrosynthesis. For pre-trained models and diverse featurizers use deepchem; for benchmark datasets use pytdc.

用于分子和蛋白质的PyTorch原生图神经网络。适用于构建自定义GNN架构以进行药物发现、蛋白质建模或知识图谱推理，特别适合自定义模型开发、蛋白质性质预测和逆合成分析。如需预训练模型和多种特征化工具，请使用DeepChem；如需基准数据集，请使用PyTDC。