%0 Generic %1 huang2021therapeutics %A Huang, Kexin %A Fu, Tianfan %A Gao, Wenhao %A Zhao, Yue %A Roohani, Yusuf %A Leskovec, Jure %A Coley, Connor W. %A Xiao, Cao %A Sun, Jimeng %A Zitnik, Marinka %D 2021 %K Medizin datasets medical ml %T Therapeutics Data Commons: Machine Learning Datasets and Tasks for Therapeutics %U http://arxiv.org/abs/2102.09548 %X Machine learning for therapeutics is an emerging field with incredible opportunities for innovation and expansion. Despite the initial success, many key challenges remain open. Here, we introduce Therapeutics Data Commons (TDC), the first unifying framework to systematically access and evaluate machine learning across the entire range of therapeutics. At its core, TDC is a collection of curated datasets and learning tasks that can translate algorithmic innovation into biomedical and clinical implementation. To date, TDC includes 66 machine learning-ready datasets from 22 learning tasks, spanning the discovery and development of safe and effective medicines. TDC also provides an ecosystem of tools, libraries, leaderboards, and community resources, including data functions, strategies for systematic model evaluation, meaningful data splits, data processors, and molecule generation oracles. All datasets and learning tasks are integrated and accessible via an open-source library. We envision that TDC can facilitate algorithmic and scientific advances and accelerate development, validation, and transition into production and clinical implementation. TDC is a continuous, open-source initiative, and we invite contributions from the research community. TDC is publicly available at https://tdcommons.ai.

@misc{huang2021therapeutics, abstract = {Machine learning for therapeutics is an emerging field with incredible opportunities for innovation and expansion. Despite the initial success, many key challenges remain open. Here, we introduce Therapeutics Data Commons (TDC), the first unifying framework to systematically access and evaluate machine learning across the entire range of therapeutics. At its core, TDC is a collection of curated datasets and learning tasks that can translate algorithmic innovation into biomedical and clinical implementation. To date, TDC includes 66 machine learning-ready datasets from 22 learning tasks, spanning the discovery and development of safe and effective medicines. TDC also provides an ecosystem of tools, libraries, leaderboards, and community resources, including data functions, strategies for systematic model evaluation, meaningful data splits, data processors, and molecule generation oracles. All datasets and learning tasks are integrated and accessible via an open-source library. We envision that TDC can facilitate algorithmic and scientific advances and accelerate development, validation, and transition into production and clinical implementation. TDC is a continuous, open-source initiative, and we invite contributions from the research community. TDC is publicly available at https://tdcommons.ai.}, added-at = {2021-02-24T08:34:36.000+0100}, author = {Huang, Kexin and Fu, Tianfan and Gao, Wenhao and Zhao, Yue and Roohani, Yusuf and Leskovec, Jure and Coley, Connor W. and Xiao, Cao and Sun, Jimeng and Zitnik, Marinka}, biburl = {https://www.bibsonomy.org/bibtex/2b0fe0388a5a724533e160bcd218d7881/hotho}, description = {Therapeutics Data Commons: Machine Learning Datasets and Tasks for Therapeutics}, interhash = {afb5f492c8f509b0cc9a753c390c96bd}, intrahash = {b0fe0388a5a724533e160bcd218d7881}, keywords = {Medizin datasets medical ml}, note = {cite arxiv:2102.09548}, timestamp = {2021-02-24T08:34:36.000+0100}, title = {Therapeutics Data Commons: Machine Learning Datasets and Tasks for Therapeutics}, url = {http://arxiv.org/abs/2102.09548}, year = 2021 }