MvGraphDTA: Multi-view-based graph deep model for drug-target affinity prediction by introducing the graphs and line graphs
收藏资源简介：
MvGraphDTA MvGraphDTA:通过引入图形和折线图,基于多视图的图形深度模型用于药物-靶点亲和力预测 要求 numpy==1.23.5 pandas==1.5.2 biopython==1.79 scipy==1.9.3 torch==2.0.1 torch_geometric==2.3.1 示例用法 1. 使用我们的预训练模型 在本节中,我们提供了 pdbbindv2016 的核心集数据和 Li 的数据(过滤后的 casf2013 和 casf2016),您可以直接执行以下命令来运行我们的预训练模型并在核心集上获取结果。 # Run the following command.python test_pretrain.py 2. 在数据集上运行 在本节中,您必须提供药物的 .sdf 文件以及靶标的 .pdb 文件。 # 您可以通过运行以下命令获取药物和靶点的图形和折线图。Python data_process.py # 当所有数据都准备好后,您可以通过运行以下命令来训练自己的模型。Python training.py
MvGraphDTA: Multi-view Graph-based Deep Model for Drug-Target Affinity Prediction via Integrating Graphs and Line Graphs ## Requirements numpy==1.23.5 pandas==1.5.2 biopython==1.79 scipy==1.9.3 torch==2.0.1 torch_geometric==2.3.1 ## Example Usage 1. Using Pre-trained Models In this section, we provide the core set data of pdbbindv2016 and Li's dataset (filtered casf2013 and casf2016). You can directly execute the following command to run our pre-trained model and obtain results on the core set: bash python test_pretrain.py 2. Running on Custom Datasets In this section, you must provide the .sdf file of the drug and the .pdb file of the target. You can obtain the graphs and line graphs of drugs and targets by running the following command: bash python data_process.py After all data are prepared, you can train your own model by executing the following command: bash python training.py
