利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

6 条记录 (耗时 0.016 秒)

    Distributed Machine Learning Systems, Apparatus, And Methods
    2.
    发明申请
    Distributed Machine Learning Systems, Apparatus, And Methods 有权

    公开(公告)号：US20220405644A1

    公开(公告)日：2022-12-22

    申请号：US17890953

    申请日：2022-08-18

    申请人： NantOmics, LLC ,  Nant Holdings IP, LLC

    发明人： Christopher W. SZETO ,  Stephen Charles BENZ ,  Nicholas J. WITCHEY

    IPC分类号： G06N20/00 ,  G16H50/50 ,  G06N20/10 ,  G16H50/20 ,  G16H10/60 ,  G16H40/20 ,  G06F21/62

    摘要： A distributed, online machine learning system is presented. Contemplated systems include many private data servers, each having local private data. Researchers can request that relevant private data servers train implementations of machine learning algorithms on their local private data without requiring de-identification of the private data or without exposing the private data to unauthorized computing systems. The private data servers also generate synthetic or proxy data according to the data distributions of the actual data. The servers then use the proxy data to train proxy models. When the proxy models are sufficiently similar to the trained actual models, the proxy data, proxy model parameters, or other learned knowledge can be transmitted to one or more non-private computing devices. The learned knowledge from many private data servers can then be aggregated into one or more trained global models without exposing private data.

    VALIDATION OF INFERRED ANTICANCER PATHWAYS
    4.
    发明公开
    VALIDATION OF INFERRED ANTICANCER PATHWAYS 审中-公开

    公开(公告)号：US20230230654A1

    公开(公告)日：2023-07-20

    申请号：US18185105

    申请日：2023-03-16

    申请人： NantBio, Inc. ,  Nant Holdings IP, LLC

    发明人： Kayvan NIAZI ,  Shahrooz RABIZADEH ,  Nicholas J. WITCHEY

    IPC分类号： G16B5/20 ,  G16B40/20 ,  G16H20/10

    CPC分类号： G16B5/20 ,  G16B40/20 ,  G16H20/10

    摘要： The invention provides a method of validating a predicted pathway activity of a pathway in a solid tumor of a subject, with a digital computer, the method including:

    a) obtaining a tumor associated sample from the subject;
    b) obtaining omics data from the tumor associated sample obtained in (a);
    c) applying the omics data obtained in (b) to a digital computer programmed with a pathway analysis engine configured to generate predicted tumor cell pathway activities in silico, to provide a prediction of one or more pharmaceutically active anticancer compounds effective for treating the subject’s tumor; and
    d) obtaining enriched viable tumor cells from the subject, and interrogating the enriched viable tumor cells with at least one pharmaceutically active compound known to interact with a pathway element of one or more of the pathways predicted by (c), to measure anticancer activity of the at least one pharmaceutically active compound with respect to the subject’s enriched viable tumor cells.