公开(公告)号：US20230235410A1

公开(公告)日：2023-07-27

申请号：US18089565

申请日：2022-12-28

Applicant: Industrial Technology Research Institute

Inventor： Jian-Hao Li ,  Hui-Chu Hsieh ,  Po-Chang Chen ,  Pei-Shin Jiang ,  Chih-Lung Lin

IPC: C12Q1/6886

CPC classification number: C12Q1/6886 ,  C12Q2600/158

Abstract: An identification system of circulating biomarkers for cancer detection, a development method of circulating biomarkers for cancer detection, a cancer detection method and a kit are provided in the present disclosure, and the development method includes the following steps. Expression levels of multiple genes in normal tissue samples and tumor tissue samples are identified, and genes with high expression levels in the tumor tissue samples are selected. Afterwards, a weight of each human tissue’s contribution to plasma exosomes is calculated using tissue-specific genes and group-enriched genes. Next, expression levels of plasma exosome genes of healthy people and cancer patients are compared by an overlapping index, and circulating biomarkers and combinations thereof suitable for detection and evaluation of plasma exosomes are selected.

公开(公告)号：US20240311638A1

公开(公告)日：2024-09-19

申请号：US18398161

申请日：2023-12-28

Applicant: Industrial Technology Research Institute

Inventor： Nien-Tzu Chou ,  Yu-Yu Lin ,  Ching-Fang Lu ,  Jian-Hao Li ,  Ting-Hsuan Chen ,  Cheng-Tai Chen

IPC: G06N3/0895 ,  G01N33/50 ,  G16B40/20

CPC classification number: G06N3/0895 ,  G01N33/5023 ,  G16B40/20 ,  G01N2333/70503 ,  G01N2333/70596 ,  G01N2333/7155

Abstract: A method of predicting the efficacy of natural killer cells, including: generating a plurality of training data corresponding to a plurality of donors based on a characteristic factor and a corresponding killing result against the target cancer cells of a plurality of cultured natural killer cells from the donors; obtaining a trained neural network model by inputting the plurality of training data into a neural network model; inputting a to-be-tested input vector corresponding to at least one characteristic factor of a to-be-tested natural killer cell into the trained neural network model to obtain an outputted result vector of the trained neural network model, wherein the result vector indicates a predicted killing result corresponding to the target cancer cell after applying the to-be-tested natural killer cell; and determining a quality of the to-be-tested natural killer cell based on the predicted killing result.