Methods of treating glioblastomas
    41.
    发明授权

    公开(公告)号:US12090170B2

    公开(公告)日:2024-09-17

    申请号:US17042032

    申请日:2019-04-04

    IPC分类号: A61K35/17 A61K38/17

    CPC分类号: A61K35/17 A61K38/1793

    摘要: Methods are provided for treating a subject for glioblastoma, including e.g., an EGFRvIII negative glioblastoma. The methods of the present disclosure involve administering to a subject a molecular circuit that includes a binding triggered transcriptional switch (BTTS) that binds to a priming antigen expressed by the subjects glioblastoma multiforme (GBM) that, when bound to the priming antigen, induces one or more encoded therapeutics specific for one or more antigens expressed by the GBM. Nucleic acids containing sequences encoding all or portions of such circuits are also provided, as well as cells, expression cassettes and vectors that contain such nucleic acids. Also provided are kits for practicing the described methods.

    GRAPH DATABASE TECHNIQUES FOR MACHINE LEARNING

    公开(公告)号:US20240303544A1

    公开(公告)日:2024-09-12

    申请号:US18551483

    申请日:2022-03-29

    IPC分类号: G06N20/00

    CPC分类号: G06N20/00

    摘要: A process is provided for using a graph database (e.g., SPOKE) to generate training vectors (SPOKEsigs) and train a machine learning model to classify biological entities. A cohort's input data records (EHRs) are compared to graph database nodes to identify overlapping concepts. Entry nodes (SEPs) associated with these overlapping concepts are used to generate propagated entry vectors (PSEVs) that encode the importance of each database node for a particular cohort, which helps train the model with only relevant information. Further, the propagated entry vectors for a given entity with a known classification can be aggregated to create training vectors. The training vectors are used as inputs to train a machine learning model. Biological entities with an unknown classification can be classified with a trained machine learning model. Entity signature vectors are generated for entities without a classification and input into the trained machine learning model to obtain a classification.

    System and method for high-throughput radio thin layer chromatography analysis

    公开(公告)号:US12078625B2

    公开(公告)日:2024-09-03

    申请号:US17605213

    申请日:2020-04-15

    IPC分类号: G01N30/95 G01N35/10 H04N25/71

    CPC分类号: G01N30/95 G01N35/10 H04N25/71

    摘要: A method of performing high-throughput radio thin layer chromatography (radio-TLC) includes spotting a plurality of locations on one or more TLC plates with samples containing a radiochemical or a radiopharmaceutical, each location defining an individual lane on the one or more TLC plates for the respective samples. The one or more TLC plates are developed with a developing solution and dried. The TLC plates are imaged with an imaging device comprising a camera, wherein the image obtained from the camera comprises a field of view that contains regions of interest (ROIs) from the plurality of lanes. The ROIs in the images obtained from the camera may then be analyzed by the user. The ROIs may be used, for example, reaction optimization or for quality control check of the production of radiotracers.