Dataset Groups Activity Stream ChEMBL The ChEMBL dataset is a large collection of bioactive molecules, with over 10 million molecules, that can be used for various machine learning tasks, including molecular design. BibTex: @dataset{Chenghui_Zhou_and_Barnabás_Póczos_2024, abstract = {The ChEMBL dataset is a large collection of bioactive molecules, with over 10 million molecules, that can be used for various machine learning tasks, including molecular design.}, author = {Chenghui Zhou and Barnabás Póczos}, doi = {10.57702/6ffppl4i}, institution = {No Organization}, keyword = {'Bioactive molecules', 'ChEMBL', 'Drug-like properties', 'bioactivity data', 'chemical database', 'drug discovery', 'drug-like molecules', 'molecular database', 'molecular dataset', 'molecular space'}, month = {dec}, publisher = {TIB}, title = {ChEMBL}, url = {https://service.tib.eu/ldmservice/dataset/chembl}, year = {2024} }