Method for controlling culture device and method for controlling culture device including cell culture

Abstract

The purpose of the present invention is to provide a method for controlling a culture device capable of culturing in a more suitable culture environment. A method for controlling a culture device (1) for controlling a culture device for culturing by inputting a set value (SV) for setting a culture environment, the method comprising: a first step (S1) for acquiring, at a predetermined timing, a measured value (PV) of the culture environment at the set value (SV) and an analysis value (AV) of a culture solution (c) obtained by culturing; a second step (S2) of deriving, by machine learning, a function (F) for obtaining a new setting value (SV) for resetting the culture environment using the measured value (PV) and the analysis value (AV) acquired at a predetermined time; and a third step (S3) in which a new set value (SV) is obtained on the basis of the desired target value (TV) of the culture solution using the function (F), and the new set value (SV) is inputted for culturing. The function (F) used in the third step (S3) is a new function (F) derived at any time by machine learning, including the latest measured value (PV) and analysis value (AV) acquired at a predetermined time.

Description

Technical Field

[0001] The present invention relates to a control method of a culture device and a control method of a culture device accompanying cell culture. Prior art

[0002] Products produced by culture include cosmetics and pharmaceuticals such as antibodies, etc. For example, in the case of producing antibody pharmaceuticals, cells recombinant with genes producing antibodies are cultured, and antibodies secreted by the cultured cells are purified to produce the antibody pharmaceuticals.

[0003] Among such cultured products, there are also products such as vaccines that are required to be of high quality and are urgently needed to be supplied to the market.

[0004] As a method for controlling the quality of products produced by culture as described above, for example, a method has been proposed in which the quality characteristics of intermediate products in purification steps (downstream processes) such as purification and concentration processes of biological preparations are monitored while controlling purification, etc. (for example, refer to Patent Document 1).

[0005] By adopting such a control method, the downstream process is controlled based on the information of the refining and concentration process monitored in real time.

[0006] Prior art literature

[0007] Patent Literature

[0008] Patent Document 1: Japanese Patent Application No. 2019-522802 Summary of the invention

[0009] Problems to be solved by the invention

[0010] In the culture process (upstream process) of proliferating and culturing cells or microorganisms, there is still the possibility of achieving more appropriate control in accordance with the temporal changes in the culture state caused by the residence time of the cells.

[0011] The present invention has been made in view of the above circumstances, and an object of the present invention is to provide a control method of a culture device capable of performing culture in a more suitable culture environment, and a control method of a culture device accompanied with cell culture.

[0012] Technical solutions to the problem

[0013] One embodiment of the present invention is a method for controlling a culture device, which controls a culture device that performs culture by inputting a set value for setting a culture environment, the control method comprising:

[0014] The first step is to obtain the measured value of the culture environment under the above-mentioned set value and the analysis value of the culture solution obtained by the culture at a specified time;

[0015] The second step is to derive a function for obtaining a new setting value for resetting the culture environment by machine learning using the measured values ​​and analysis values ​​acquired at the predetermined time; and

[0016] The third step is to use the above function to find a new set value based on the target value of the desired culture solution, and input the new set value to perform the culture.

[0017] The function used in the third step is a new function derived from time to time through machine learning, including the latest measured values ​​and analysis values ​​acquired at a predetermined time.

[0018] Furthermore, the present invention includes a control method for a culture device accompanied by cell culture, and the control method is used for production of biopharmaceuticals accompanied by cell culture.

[0019] In this specification, "culture" means to multiply a single cell or microorganism (single-cell organism, multi-cell organism) in a culture medium. "Update at any time" includes both the concept of continuous update (real-time update) and the concept of intermittent update at specified intervals.

[0020] Effects of the Invention

[0021] The present invention provides a method for controlling a culture device capable of performing culture in a more suitable culture environment, and a method for controlling a culture device accompanied with cell culture. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 This is a schematic process diagram showing an example of a production process for producing an antibody pharmaceutical using a continuous cell culture apparatus.

[0023] Figure 2 This is a schematic diagram showing an example of a continuous cell culture apparatus.

[0024] Figure 3 It is a schematic diagram showing a control method of a culture apparatus in one embodiment.

[0025] Figure 4 This is a schematic diagram showing an example of a continuous cell culture apparatus.

[0026] Figure 5 This is a schematic process diagram showing an example of a production process for producing an antibody pharmaceutical using a batch culture apparatus. DETAILED DESCRIPTION

[0027] <Control method of culture device>

[0028] The control method of the culture device of the present invention is a control method of the culture device for controlling the culture device for culture by inputting the set value of the culture environment, which comprises: a first step of obtaining the measured value of the culture environment under the set value and the analysis value of the culture solution obtained by culture at a specified time; a second step of deriving a function for obtaining a new set value for resetting the culture environment by machine learning using the measured value and the analysis value obtained at the specified time; and a third step of using the function to obtain a new set value based on the target value of the desired culture solution, and inputting the new set value for culture. The function used in the third step is a new function derived at any time by machine learning, including the latest measured value and analysis value obtained at the specified time.

[0029] Hereinafter, the control method of the cell culture device of the present invention will be described by taking the control method of the cell culture device for culturing cells as an example. The control method of the cell culture device can be used, for example, to control a cell culture device for culturing cells to produce pharmaceuticals such as antibodies. In this specification, a continuous cell culture device is exemplified as a cell culture device. In a continuous cell culture device, a culture medium is continuously supplied to a culture system, and an equal amount of culture fluid is simultaneously extracted from the culture system.

[0030] However, the control method of the culture device described below is not limited to the control of the cell culture device. In addition, one embodiment of the present invention is described with reference to the drawings, but the present invention is not limited to the embodiment described in the drawings.

[0031] Figure 1 FIG. 1 is a schematic diagram showing an example of a process for producing an antibody pharmaceutical using a continuous cell culture apparatus. Figure 1 As shown, the antibody pharmaceutical original drug can be produced, for example, by sequentially performing the culture step P1 and the purification step P2.

[0032] The culture step P1 is a step of culturing (proliferating) cells. The culture step P1 of this embodiment is performed by controlling the continuous cell culture apparatus. Figure 2 As shown, the continuous cell culture apparatus 1 may be composed of, for example, a continuous cell culture tank 100 , a medium adding device 200 , a cell separation device 300 , a culture environment adjusting device 400 , a control device 500 , and a culture solution analyzing device 600 .

[0033] The continuous cell culture tank 100 cultures cells in a culture solution c under a specific culture environment. The sensors 101, 102 and the culture solution analyzer 600 provided in the continuous cell culture tank 100 measure the measured value PV (Process Variable) and the analysis value AV (Analytical Variable) described later. The culture medium addition device 200 stores fresh culture medium and supplies the culture medium to the continuous cell culture tank 100. The cell separation device 300 separates the culture solution from the cells using a membrane and extracts only the culture solution. The culture environment adjustment device 400 adjusts the culture environment such as the temperature, pH value, and dissolved oxygen concentration of the culture solution c. The control device 500 controls the continuous cell culture tank 100, the culture medium addition device 200, the cell separation device 300, the culture environment adjustment device 400, etc. The details of the control device 500 are as follows.

[0034] The set value SV (Set Variable) is a variable for setting the culture environment of the continuous cell culture tank 100. The set value SV includes one or more parameters. Examples of the parameters include the supply rate of the culture medium, the temperature of the culture solution in the continuous cell culture tank 100, the pH value, the dissolved oxygen concentration, the stirring speed of the culture solution, the perfusion rate, etc. In order to realize the desired culture environment using the set value SV, the continuous cell culture device 1 is provided with a temperature regulator for adjusting the temperature of the culture solution c, a pH regulator for adjusting the pH value of the culture solution c, an oxygen concentration regulator for adjusting the dissolved oxygen concentration in the culture solution c, a stirrer for uniformly stirring the culture solution c, a perfusion device for perfusing the culture solution c, etc., which are not shown in the figure.

[0035] The purification step P2 is a step of purifying specific products secreted by cells (physiologically active substances, useful proteins such as antibodies, etc.) and other useless substances (cell shells, viruses, products such as lactic acid or ammonia secreted by cells, etc.) so that the product has a specified quality.

[0036] In the refining step P2, the refining device (method) used is not particularly limited as long as a specific product can be separated. Examples of the refining device include: Figure 1 The continuous collection device, virus inactivation device, filtration sterilization device shown in the figure and the gravity sedimentation device, ultrasonic coagulation device, filtration separation device, etc., which are not shown in the figure, can be used alone or in combination in the purification step P2.

[0037] Furthermore, in the above-mentioned purification step P2, known methods and apparatuses can be used.

[0038] Here, refer to Figure 3 , Figure 4One embodiment of a method for controlling the continuous cell culture apparatus 1 used in the culture step P1 in the above-mentioned steps will be described in detail.

[0039] In the control method of the continuous cell culture apparatus 1, a set value SV for setting the culture environment is input and the continuous cell culture apparatus 1 is controlled. Figure 3 As shown, the control method of the continuous cell culture apparatus 1 of this embodiment includes a first step S1, a second step S2 and a third step S3.

[0040] [First step]

[0041] The first step S1 is a step of acquiring the actual value PV of the culture environment and the analysis value AV of the culture solution c obtained by the culture at a predetermined time. The first step S1 is performed by measuring the actual value PV and the analysis value AV using the sensors 101, 102, the culture solution analyzer 600, and the like.

[0042] In the first step S1, specifically, the measured value PV related to the culture environment (temperature, pH value, pressure, dissolved oxygen concentration, dissolved carbon dioxide concentration, culture solution volume, etc.) in the continuous cell culture apparatus 1 operating under the culture environment at the preset setting value SV (hereinafter also referred to as "preset setting value SV") is acquired using the sensor 101, etc. In addition, in the first step S1, the analysis value AV is acquired using the sensor 102, the culture solution analyzer 600, etc., which is an index of quality or productivity (viable cell count, antibody concentration, inclusion concentration, etc.) related to the culture solution c cultured using the preset setting value SV. The time (hereinafter also referred to as "predetermined time") at which the measured value PV and the analysis value AV are acquired (measured) respectively can be continuous "regular time" or intermittent "timely". In addition, the measured value PV and the analysis value AV can be acquired at the same time or at different times.

[0043] [Step 2]

[0044] The second step S2 is a step of deriving a function F for obtaining a new setting value SV for resetting the culture environment by machine learning using the measured value PV and the analysis value AV acquired at a predetermined time. The second step S2 is executed by the database 501, the data extraction unit 502, and the machine learning unit 503 of the control device 500 described later.

[0045] Specifically, in the second step S2 , a function F for calculating a new setting value SV is derived while machine learning is performed using the actual measurement value PV and the analysis value AV acquired in the first step S1 as teaching data.

[0046] Examples of learning methods used in machine learning include Bayesian inference, support vector regression, random forest regression, and neural networks.

[0047] Among these, machine learning is preferably performed using Bayesian inference or support vector regression. By applying Bayesian inference or support vector regression to machine learning, a more accurate function F can be derived from less data of measured values ​​PV and analytical values ​​AV as teaching data. Such a learning method using Bayesian inference or support vector regression is particularly effective when there are limited samples during process development and when it is urgent to supply pharmaceuticals to the market.

[0048] [Third step]

[0049] The third step S3 is a step of using the function F to obtain a new set value SV based on the target value TV (Target Variable) of the desired culture solution c, and inputting the new set value SV into the continuous cell culture apparatus 1 for culture. The third step S3 is executed by the set value calculation unit 504 (described later) of the control device 500, the continuous cell culture tank 100, the culture medium adding device 200, the cell separation device 300, and the culture environment adjustment device 400.

[0050] In the third step S3, first, a new set value SV is calculated using the target value TV of the desired culture solution c and the function F derived in the second step S2.

[0051] The desired target value TV of the culture solution c is an index related to quality or productivity (number of viable cells, antibody concentration, impurity concentration, etc.).

[0052] In addition, the new set value SV can be obtained in such a way that it becomes a value within a prescribed range. Specifically, for example, there is a case where the conditions (setting ranges of various parameters to be followed) of the culture environment for operating the continuous cell culture apparatus 1 are predetermined. In this case, if the new set value SV calculated using the function F is a value outside the above setting range, the new set value SV calculated using the function F is corrected so that it falls within the above setting range, and the corrected value is used as the new set value SV. In this way, for example, cells can be cultured under the manufacturing conditions of approved pharmaceuticals.

[0053] Next, the calculated new set value SV is input to the continuous cell culture apparatus 1, and the culture solution c is cultured in the culture environment of the continuous cell culture apparatus 1 operated using the new set value SV. That is, the culture solution c is cultured in the new culture environment by replacing the existing set value SV with the new set value SV. However, when the value of the parameter constituting the existing set value SV is the same as the value of the parameter constituting the new set value SV, the parameter is kept at the same value.

[0054] In the control method of the continuous cell culture apparatus 1, as the function F used in the third step S3, a new function F derived from time to time by machine learning including the latest measured value PV and the latest analysis value AV acquired at a predetermined time is used. That is, in the third step S3, the new function F updated from time to time based on the latest information related to the culture solution c is used, and the new set value SV is calculated using the latest function F.

[0055] The time when the function F is updated to a new function may be the same as the prescribed time when the measured value PV and the analyzed value AV are obtained (continuous "constantly" or intermittent "timely"), or may be different from the prescribed time. When the function F is updated at the same time as the prescribed time, the culture solution c can be cultured under the culture environment of the new set value SV obtained using the latest measured value PV and the latest analyzed value AV.

[0056] Next, a control device capable of executing the control method of the above-mentioned continuous cell culture device is described. Figure 4 As shown, the control device 500 of the continuous cell culture apparatus 1 may include, for example, a database 501 , a data extraction unit 502 , a machine learning unit 503 , and a set value calculation unit 504 .

[0057] The database 501 stores data such as set values ​​SV, actual measurement values ​​PV and analysis values ​​AV acquired at a predetermined time, and other batch or process information.

[0058] The data extraction unit 502 extracts data used in the machine learning unit 503 and the setting value calculation unit 504 described later from the data stored in the database 501 at an appropriate time.

[0059] The machine learning unit 503 is a part that executes step S2. The machine learning unit 503 performs machine learning for deriving a function F, which is used to obtain a new setting value SV for resetting the culture environment using the measured value PV and the analysis value AV obtained from the database 501 via the data extraction unit 502. The measured value PV and the analysis value AV that become the teaching data when machine learning is performed may also include the latest measured value PV and the latest analysis value AV. By including the latest measured value PV and the latest analysis value AV, a more accurate function F can be derived through machine learning using more teaching data including the latest information.

[0060] The set value calculation unit 504 is a part that obtains the new set value SV in step S3. The set value calculation unit 504 uses the function F derived by the machine learning unit 503 to obtain the new set value SV based on the target value TV of the desired culture solution c. The information (value) of each parameter included in the new set value SV obtained by the set value calculation unit 504 is output to the continuous cell culture tank 100, the culture medium addition device 200, the cell separation device 300, and the culture environment adjustment device 400.

[0061] The control device 500 may be composed of the following hardware, for example. That is, the database 501 may be composed of a storage device for storing various data. The storage device may be composed of any type of storage medium, for example, a semiconductor memory, a hard disk drive, etc. The data extraction unit 502, the machine learning unit 503, and the set value calculation unit 504 may be composed of a central processing unit (CPU) capable of executing the above-mentioned processing.

[0062] As described above, according to the control method of the continuous cell culture apparatus 1, the function F used in the third step S3 is a new function F derived at any time by machine learning including the latest measured value PV and analysis value AV acquired at a predetermined time, so that a more accurate new set value SV can be obtained by machine learning of more teaching data including the latest information, and culture can be performed under a more suitable culture environment. As a result, a product with desired quality and productivity can be reliably manufactured.

[0063] <Control method of culture device accompanying cell culture>

[0064] The method for controlling a culture device accompanying cell culture of the present invention is characterized in that the method for controlling a culture device described in the above-mentioned <Method for controlling a culture device> is used for production of a biopharmaceutical accompanying cell culture.

[0065] As in the control method of the continuous cell culture apparatus 1 illustrated in the above embodiment, according to the control method of the culture apparatus of the present invention, cells can be cultured in a more suitable culture environment, and biopharmaceuticals such as antibody drugs can be manufactured with high quality and high productivity. Therefore, the control method of the culture apparatus of the present invention can be applied to the control method of the culture apparatus accompanied by cell culture used in the manufacture of biopharmaceuticals accompanied by cell culture.

[0066] However, the present invention is not limited to the configuration of the above-mentioned embodiment, but is represented by the scope of the protection requested, including all changes within the meaning and scope of the scope of the protection requested. Part of the configuration of the above-mentioned embodiment may be deleted or replaced with other configurations, and other configurations may be added to the configuration of the above-mentioned embodiment.

[0067] For example, in the above embodiment, as a control method for a culture device, a control method for a continuous cell culture device 1 for manufacturing antibody pharmaceuticals (biopharmaceuticals) is described. However, the control method for a culture device of the present invention can also be applied to cultures other than cells, as long as they can be proliferated by culture. The control method for a culture device of the present invention can also be applied to a control method for a culture device for manufacturing cosmetics, etc., by culturing microorganisms such as unicellular organisms or multicellular organisms.

[0068] In the above embodiment, the continuous culture device 1 is described as an example of a culture device to which the control method of the culture device is applied. However, the control method of the culture device of the present invention can also be applied to Figure 5 The control method of the culture device (batch culture device) for performing batch processing shown in Figure 5 , which illustrates a process for producing a biopharmaceutical raw material using a batch cell culture apparatus. In the control method of a batch culture apparatus, set values, measured values, analysis values, target values, and functions can also be processed in the same manner as in a continuous culture apparatus.

[0069] Description of Reference Numerals

[0070] 1: continuous cell culture device (culture device); SV: set value; PV: measured value; AV: analysis value; TV: target value; S1: first step; S2: second step; S3: third step; P1: culture process; P2: purification process.

Claims

1. A method for controlling a culture device, which controls a culture device that performs culture by inputting a set value of a culture environment, the method comprising: The first step is to obtain the measured value of the culture environment under the set value and the analysis value of the culture solution obtained by the culture at a specified time; The second step is to derive a function for obtaining a new setting value for resetting the culture environment by machine learning using the measured value and the analysis value acquired at the specified time; and The third step is to use the function to find a new setting value based on the target value of the desired culture solution, and input the new setting value to perform the culture. The function used in the third step is a new function derived at any time through machine learning including the latest measured values ​​and analysis values ​​acquired at a predetermined time.

2. The control method according to claim 1, characterized in that: The function is updated to the new function at the same time as the prescribed time.

3. The control method according to claim 1, characterized in that: The machine learning is performed using Bayesian inference or support vector regression.

4. The control method according to claim 1, characterized in that: The new set value is obtained so as to be a value within a predetermined range.

5. A method for controlling a culture device for accompanying cell culture, characterized in that: The control method according to any one of claims 1 to 4 is used for production of biopharmaceuticals accompanied by cell culture.

Images