openadmet/pxr-challenge-train-test
收藏资源简介:
一个高质量的实验数据集,用于预测人类孕烷X受体(PXR)的诱导,包含超过11,000种通过高保真内部实验筛选的化合物。这是目前最大的公开PXR活性数据集,作为OpenADMET PXR Induction Blind Challenge的一部分发布。数据集包含多个配置:默认配置(主要实验训练集和513个化合物的盲测集)、反实验配置(PXR-null反实验训练数据)、结构配置(78个片段大小的分子,带有X射线晶体结构)和单浓度配置(单浓度筛选数据,log2 fold change)。
A high-quality experimental dataset for predicting human Pregnane-X Receptor (PXR) induction, comprising over 11,000 compounds screened using a high-fidelity in-house assay. This is the largest publicly available PXR activity dataset, released as part of the OpenADMET PXR Induction Blind Challenge. The dataset includes multiple configurations: default config (primary assay training set and a 513-compound blinded test set), counter_assay config (PXR-null counter-assay training data), structure config (78 fragment-sized molecules with X-ray crystal structures), and single_concentration config (single-concentration screening data, log2 fold change).




