openadmet/openadmet-expansionrx-challenge-data

这是OpenADMET-ExpansionRx盲测挑战赛中使用的完整数据集，该挑战赛于2026年1月19日结束。数据集最初分为训练集和盲测测试集，现在发布了完整数据集，其中包含Expansion Therapeutics公司在RNA介导疾病药物研发活动中收集的真实ADMET数据。在优化候选分子的临床前项目中，Expansion收集了各种ADMET数据，用于研究脱靶效应和感兴趣的属性。数据集包含两个版本：一个是“ML-ready”格式，仅包含范围内测量值；另一个是“原始”数据集，包含带有超出范围修饰符的测量值（如“>”或“<”）。数据集涵盖九个关键端点：LogD、动力学溶解度（KSOL）、小鼠肝微粒体清除率（MLM CLint）、人肝微粒体清除率（HLM CLint）、Caco-2外排比、Caco-2 Papp A>B、小鼠血浆蛋白结合率（MPPB）、小鼠脑蛋白结合率（MBPB）和小鼠腓肠肌蛋白结合率（MGMB）。此外，原始数据集中还包含一个额外端点：大鼠肝微粒体稳定性CLint。

This is the full dataset used in the OpenADMET-ExpansionRx blind challenge, which finalized in January 19th, 2026. Originally split in a train and blinded test set, we now release the full dataset, which contains real-work ADMET data from a recently prosecuted series of drug discovery campaigns by Expansion Therapeutics on RNA mediated diseases. While optimising candidate molecules for their preclinical programs Expansion collected a variety of ADMET data for off-targets and properties of interest. The dataset comes in two versions: One is the dataset in "ML-ready" format where only in-range measurements are included. The "raw" dataset is also available that includes measurements with out of range modifiers e.g ">" or "<". The dataset encompasses nine (9) crucial endpoints: LogD, Kinetic Solubility (KSOL), Mouse Liver Microsomal (MLM) CLint, Human Liver Microsomal (HLM) Clint, Caco-2 Efflux Ratio, Caco-2 Papp A>B, Mouse Plasma Protein Binding (MPPB), Mouse Brain Protein Binding (MBPB), and Mouse Gastrocnemius Muscle Binding (MGMB). An additional endpoint Rat Liver Microsomal (RLM) stability CLint, which was not part of the challenge, is included in the raw dataset.