METHOD FOR ACQUIRING LEARNING DATA, LEARNING DATA ACQUISITION SYSTEM, METHOD FOR CONSTRUCTING SOFT SENSOR, SOFT SENSOR, AND LEARNING DATA

    公开(公告)号:US20240232723A1

    公开(公告)日:2024-07-11

    申请号:US18612135

    申请日:2024-03-21

    IPC分类号: G06N20/00 G16B40/10

    CPC分类号: G06N20/00 G16B40/10

    摘要: A sample liquid in which a concentration of a specific component is known is prepared. The sample liquid and a diluent are mixed while a flow rate ratio of the sample liquid to the diluent is being continuously changed. First time-series data indicating a change in a mixing ratio and second time-series data indicating a change in spectral data are acquired for a mixed liquid obtained by the mixture while the sample liquid and the diluent are being mixed. Third time-series data indicating a change in the concentration of the specific component included in the mixed liquid is derived on the basis of the first time-series data. Learning data in which the spectral data and the concentration of the specific component are associated with each other is acquired from the second time-series data and the third time-series data.

    PROGRAM FOR OPERATING CELL CULTURE SUPPORT APPARATUS, CELL CULTURE SUPPORT APPARATUS, AND METHOD FOR OPERATING CELL CULTURE SUPPORT APPARATUS

    公开(公告)号:US20210081825A1

    公开(公告)日:2021-03-18

    申请号:US17102508

    申请日:2020-11-24

    IPC分类号: G06N5/04 G06N20/00

    摘要: A program for operating a cell culture support apparatus causes a computer to function as a first acquisition unit, a second acquisition unit, a first derivation unit, and an output control unit. The first acquisition unit acquires a learned model, derived by performing machine learning on the basis of a set of time-series data for learning indicating a time transition of an amount of each of plural types of components constituting a medium used for cell culture and good/bad data indicating good or bad of a result of the cell culture in correspondence with the time-series data for learning, indicating a guideline of the amount. The second acquisition unit acquires time-series data for analysis indicating the time transition of the amount. The first derivation unit derives quantitative guideline information of the amount for obtaining a good result in the cell culture, with respect to at least one of the plural types of components, from the learned model acquired in the first acquisition unit and input data of at least a part of the time-series data for analysis acquired in the second acquisition unit. The output control unit performs a control for outputting the guideline information.

    INFORMATION PROCESSING APPARATUS, INFORMATION PROCESSING METHOD, AND INFORMATION PROCESSING PROGRAM

    公开(公告)号:US20220199195A1

    公开(公告)日:2022-06-23

    申请号:US17690389

    申请日:2022-03-09

    IPC分类号: G16B5/00 G16B40/20

    摘要: An information processing apparatus acquires input information including at least one of a process condition, a culture medium component, or the number and diameters of cells in cell culture, and estimates a quality of an antibody produced from the cells and a quality of the cells after elapse of a predetermined period from a time point at which the input information is acquired, on the basis of the input information and a trained model which is trained in advance using the input information, the quality of the antibody, and the quality of the cells.

    METHOD FOR ESTIMATING PURIFIED STATE
    5.
    发明公开

    公开(公告)号:US20240018185A1

    公开(公告)日:2024-01-18

    申请号:US18474596

    申请日:2023-09-26

    IPC分类号: C07K1/36

    CPC分类号: C07K1/36

    摘要: A method for estimating a purified state includes quantifying a component that is included in a treatment liquid obtained by performing a purification treatment on a liquid including a specific protein and impurities other than the protein. The method for estimating a purified state includes acquiring an estimated value of a concentration of the impurities on the basis of spectral data indicating an intensity of electromagnetic waves, which have been emitted to the treatment liquid and have been subjected to an action of the treatment liquid, for each wave number or wavelength. The concentration of the impurities included in the treatment liquid is equal to or less than 20 mg/mL, and a weight ratio of the impurities to a mixture including the protein and the impurities is equal to or less than 15%.

    METHOD FOR ESTIMATING CULTURE STATE, INFORMATION PROCESSING DEVICE, AND PROGRAM

    公开(公告)号:US20230081615A1

    公开(公告)日:2023-03-16

    申请号:US18047384

    申请日:2022-10-18

    IPC分类号: C12M1/36 C12M1/34 G01N21/65

    摘要: Spectral data indicating an intensity of electromagnetic waves, which have been emitted to a cell suspension including a cell and a culture solution and have been subjected to an action of the cell suspension, for each wave number or wavelength is acquired. Preprocessing is performed on the spectral data. A soft sensor, which receives processed data obtained by the preprocessing as an input and outputs state data indicating a state of the cell or the culture solution, is constructed by machine learning using a plurality of combinations of the processed data and the state data as training data. The processed data for the spectral data acquired for a cell suspension including a cell which is being cultured is input to the soft sensor, and the state data output from the soft sensor is acquired.

    LEARNING APPARATUS, OPERATION METHOD OF LEARNING APPARATUS, OPERATION PROGRAM OF LEARNING APPARATUS, AND OPERATING APPARATUS

    公开(公告)号:US20220092435A1

    公开(公告)日:2022-03-24

    申请号:US17542869

    申请日:2021-12-06

    IPC分类号: G06N3/08 G01J3/28 G06T7/00

    摘要: There are provided a learning apparatus, an operation method of the learning apparatus, a non-transitory computer readable recording medium storing an operation program of the learning apparatus, and an operating apparatus capable of further improving accuracy of prediction of a quality of a product by a machine learning model in a case where learning is performed by inputting, as learning input data, multi-dimensional physical-property relevance data, which is derived from multi-dimensional physical-property data of the product, to the machine learning model. In the learning apparatus, a first processor is configured to extract a high-contribution item from the plurality of items of the multi-dimensional physical-property relevance data by using the temporary machine learning model; and selectively input the multi-dimensional physical-property relevance data of the high-contribution item to the machine learning model, perform learning, and output the machine learning model as a learned model to be provided for actual operation.