introvoyz041/MolData

MolData是一个基于疾病和靶点的综合数据集，收集自PubChem。该数据集包含约1.7亿个药物筛选结果，来自140万个独特分子和600个测定，旨在加速分子机器学习，以促进更好的药物发现。数据集经过预处理，包括分子消毒、格式化、列重命名和数据集分割。MolData is a comprehensive disease and target-based dataset collected from PubChem. The dataset contains roughly 170 million drug screening results from 1.4 million unique molecules and 600 assays, which are collected to accelerate molecular machine learning for better drug discovery. The dataset has been preprocessed, including molecule sanitization, formatting, column renaming, and dataset splitting.