KinaseDocker² Database

Database The .sqlite file in this dataset is released as part of the KinaseDocker² research. It serves as a ML-ready dataset of small molecule docked poses in a curated set of kinases. Please refer to the publication for more information. The .knwf file provides an easy to use graphical interface to query the dataset released. Follow the instructions below to get started. KNIME GUI Installation KNIME can be downloaded free of charge from KNIME.com. When installed, the workflow downloaded from this repository can be imported through Local Space ->Import workflow. The software will warn that there are missing dependencies (KNIME Base Chemistry nodes, KNIME-CDK, KNIME Python Integration) and propose to search and install these. Approve, and after a restart of KNIME the workflow should load. Usage To use, the location of the downloaded .sqlite file needs to be configured by double clicking the gray node in the green box. Browse to the .sqlite file and click OK. Execute the node by clicking the Execute button in the top bar. Now, either use the red-boxed part of the workflow to browse based on a kinase of choice or use the blue-boxed portion of the workflow to query based on compounds. The instructions per node are in the workflow, but typically it requires execution of the node (shortcut: F7 or click Execute in the top bar) and opening the View it generates (shortcut: F10 or hover over node and click magnifying glass). Some nodes require configuration: either the choice of docking engine (Vina / DiffDock) or the folder to write files into.数据集说明 本数据集内含的.sqlite文件为KinaseDocker²研究的公开成果之一，是一份经过人工精选的激酶集合中包含小分子对接构象的、可直接用于机器学习（Machine Learning）的数据集。如需获取更多详细信息，请参阅相关研究论文。 本数据集附带的.knwf文件提供了便捷易用的图形用户界面，用于查询上述公开数据集。请遵循下文指引完成使用配置。 ### KNIME图形界面安装指南 可从KNIME.com免费下载KNIME软件。安装完成后，可通过「本地空间 -> 导入工作流」路径导入本仓库下载的工作流。软件会提示存在缺失的依赖项（KNIME基础化学节点、KNIME-CDK、KNIME Python集成工具）并自动检索并安装这些依赖。确认安装并重启KNIME后，工作流即可正常加载。 ### 使用方法 使用前，请双击绿色框中的灰色节点以配置已下载的.sqlite文件路径，浏览至目标.sqlite文件后点击「确定」。点击顶部菜单栏的「执行」按钮以运行该节点。 此时，你既可以通过工作流中红色框选区域，基于选定的激酶进行数据浏览；也可以通过蓝色框选区域，基于化合物进行数据查询。各节点的操作说明已内嵌于工作流中，通常只需执行节点（快捷键：F7，或点击顶部菜单栏的「执行」按钮）并打开其生成的视图（快捷键：F10，或将鼠标悬停在节点上并点击放大镜图标）即可。部分节点需额外配置：包括选择对接引擎（Vina / DiffDock）或指定文件输出目录。