公开(公告)号：US20230349886A1

公开(公告)日：2023-11-02

申请号：US17715796

申请日：2022-04-07

申请人： UTI Limited Partnership

发明人： Sergei NOSKOV ,  Soren WACKER ,  Henry DUFF ,  Jiqing GUO

IPC分类号： G01N33/50 ,  G06N20/00 ,  G16B15/00 ,  G16B35/00 ,  G16B40/00 ,  G16C20/60 ,  G01N33/68 ,  G16B20/00 ,  G16C20/30 ,  G06N20/20 ,  G16H50/00 ,  G16B15/30 ,  G16B40/20 ,  G16B35/20 ,  G06N5/01 ,  G06N7/01

CPC分类号： G01N33/5014 ,  G01N33/6872 ,  G06N5/01 ,  G06N7/01 ,  G06N20/00 ,  G06N20/20 ,  G16B15/00 ,  G16B15/30 ,  G16B20/00 ,  G16B35/00 ,  G16B35/20 ,  G16B40/00 ,  G16B40/20 ,  G16C20/30 ,  G16C20/60 ,  G16H50/00 ,  G16C20/70

摘要： Systems and methods are provided for predicting cardiotoxicity of molecular parameters of a compound. A computer can provide as input to a machine learning algorithm the molecular parameters of the compound. The molecular parameters can include at least structural information about the compound. The machine learning algorithm can have been trained using respective molecular parameters of compounds known to have cardiotoxicity and of compounds known not to have cardiotoxicity. The computer can receive as output from the machine learning algorithm a representation of the predicted cardiotoxicity of each molecular parameter of at least a subset of the molecular parameters of the compound.

公开(公告)号：US20180172667A1

公开(公告)日：2018-06-21

申请号：US15737246

申请日：2016-06-16

申请人： UTI Limited Partnership

发明人： Sergei NOSKOV ,  Soren WACKER ,  Henry DUFF ,  Jiqing GUO

IPC分类号： G01N33/50 ,  G01N33/68 ,  G06F15/18 ,  G06F19/24 ,  G06F19/16

CPC分类号： G01N33/5014 ,  G01N33/6872 ,  G06N5/003 ,  G06N7/005 ,  G06N20/00 ,  G06N20/20 ,  G16B15/00 ,  G16B20/00 ,  G16B35/00 ,  G16B40/00 ,  G16C20/30 ,  G16C20/60 ,  G16C20/70

摘要： Systems and methods are provided for predicting cardiotoxicity of molecular parameters of a compound. A computer can provide as input to a machine learning algorithm the molecular parameters of the compound. The molecular parameters can include at least structural information about the compound. The machine learning algorithm can have been trained using respective molecular parameters of compounds known to have cardiotoxicity and of compounds known not to have cardiotoxicity. The computer can receive as output from the machine learning algorithm a representation of the predicted cardiotoxicity of each molecular parameter of at least a subset of the molecular parameters of the compound.