NCI Anti-cancer activity prediction data (NCI)
收藏资源简介:
NCI图数据集常被用作图分类的基准。每个NCI数据集属于一个抗癌活性预测的生物测定任务,其中每个化学化合物被表示为一个图,原子代表节点,键作为边。如果化学化合物对相应的癌症有活性,则标记为正,否则为负。表1总结了从PubChem下载的NCI图数据。我们已经移除了原始图中的不连通图和含有异常原子(某些图中的原子表示为`*`)的图。第2-3列显示了每个数据集中正例和总图的数量,第4-5列分别表示每个数据集的平均节点数和边数。
The NCI graph dataset is frequently utilized as a benchmark for graph classification. Each NCI dataset pertains to a bioassay task aimed at predicting anticancer activity, where each chemical compound is represented as a graph with atoms as nodes and bonds as edges. A chemical compound is labeled as positive if it exhibits activity against the corresponding cancer, otherwise, it is labeled as negative. Table 1 summarizes the NCI graph data downloaded from PubChem. We have removed disconnected graphs and graphs containing anomalous atoms (where certain atoms are represented as `*`) from the original dataset. Columns 2-3 display the number of positive instances and the total number of graphs in each dataset, while columns 4-5 represent the average number of nodes and edges per dataset, respectively.




