Cleaned dataset for PubChem AID 1159555: qHTS assay of retinoic acid receptor (RAR) antagonists

This dataset is derived from PubChem BioAssay AID 1159555, titled "qHTS assay to identify small molecule antagonists of the retinoic acid receptor (RAR) signaling pathway". The original assay is part of the Tox21 program and evaluates inhibition of retinoic acid receptor (RAR) signaling using a luciferase reporter gene assay regulated by retinoic acid response elements (RARE) in a cell-based system. Original dataset statistics: - Tested compounds: 7,671 - Active (antagonists): 602 - Inactive: 5,114 Data preprocessing: - Removed duplicate entries based on compound identifiers. - Resolved conflicting labels by excluding compounds with inconsistent activity annotations. Final cleaned dataset: - Total compounds: 4,926 - Positive (antagonists): 503 - Negative (inactive): 4,423本数据集源自PubChem BioAssay数据库编号为AID 1159555的实验，该实验标题为「鉴定视黄酸受体（retinoic acid receptor, RAR）信号通路小分子拮抗剂的定量高通量筛选（quantitative high-throughput screening, qHTS）实验」。 该原始实验隶属于Tox21计划，采用基于细胞的实验体系，借助受视黄酸反应元件（retinoic acid response elements, RARE）调控的荧光素酶报告基因检测，评估视黄酸受体（RAR）信号通路的抑制活性。 原始数据集统计信息： - 受试化合物总数：7671种；活性化合物（拮抗剂）：602种；无活性化合物：5114种 数据预处理流程： - 基于化合物标识符去除重复条目； - 剔除活性注释存在冲突的化合物，以解决标签不一致问题。 最终清理后的数据集： - 总化合物数：4926种；阳性样本（拮抗剂）：503种；阴性样本（无活性）：4423种