Systems, methods, and computer program products that support the operation of cell culture.

Abstract

We provide systems, methods, and computer program products that support the operation of cell culture. [Solution] The system includes a processing circuit configured to acquire information related to cell culture, calculate predicted values ​​for the cell culture results over the culture time, and the possible range of each predicted value, and output the predicted values ​​and the possible range of each predicted value. The processing circuit calculates the predicted value at a first time point, and then, based on the predicted value at the first time point, calculates the predicted value at a second time point after the first time point, and repeats the calculation over the culture time. The processing circuit uses a statistical regression model to calculate the possible range of each predicted value.

Description

Technical Field

[0001] The present disclosure relates to a system, method, and computer program product for assisting in the operation of cell culture.

Background Art

[0002] In bioproduction, the behavior and productivity of cell culture vary depending on the cells used and the molecules produced. In recent years, efficient exploration of optimal culture conditions, such as the medium, culture method, and period, has been carried out using computers.

[0003] For example, U.S. Patent Application Publication No. 2022 / 0380717 discloses a method and device for exploring optimal culture conditions, a cell culture process exploration method for predicting cell culture results by overviewing the culture process, a culture result prediction program, and a culture result prediction device. A plurality of culture conditions for culturing cells are generated, and for each of the plurality of process conditions, a predicted culture result of the cells is obtained. Subsequently, based on the obtained predicted culture results, optimal process conditions are found.

[0004] U.S. Patent Application Publication No. 2024 / 0170098 discloses a method and apparatus for predicting cell culture results. A culture environment including a medium composition and culture conditions for culturing cells is received, a biological behavior amount is predicted based on the culture environment, and the cell environment is changed based on the predicted biological behavior amount. Prediction of the biological behavior amount and change of the cell environment are repeated, and the changed cell environment is output.

Summary of the Invention

Problems to be Solved by the Invention

[0005] However, due to biological variations and differences between batches of raw materials, it is difficult to accurately predict cell culture results. Additionally, since cell culture results are accompanied by various factors, it is highly difficult to identify the relationships between the factors that cause differences in the culture results.

[0006] Therefore, the object of this disclosure is to provide a system, method, and computer program product that can support cell culture operations and improve the accuracy of predicting cell culture results. [Means for solving the problem]

[0007] To achieve this objective, one aspect of this disclosure is a system that supports the operation of cell culture, We obtain information related to cell culture, We calculate the predicted values ​​for the cell culture results over the culture time, and the possible range of each predicted value. Outputs the predicted values ​​and the possible ranges for each predicted value. This system is equipped with a processing circuit configured in such a way.

[0008] As used herein, “cell culture” refers to the growth, maintenance, differentiation, transfection, or propagation of cells, tissues, or products thereof under controlled conditions (e.g., ex vivo).

[0009] In one embodiment, the processing circuit may calculate predicted values ​​for the cell culture results at several different time points. In this case, the processing circuit may calculate the predicted value at a first time point. Subsequently, based on the predicted value at the first time point, the processing circuit may further calculate the predicted value at a second time point later than the first time point, and repeat the calculation over the culture time. The processing circuit may calculate the predicted value at the first time point based on information related to the cell culture. Alternatively, the processing circuit may calculate the predicted value at the first time point based on predicted values ​​at a time point earlier than the first time point.

[0010] The processing circuit may estimate the change in the predicted value from the first time point to the second time point, add the estimated change to the predicted value at the first time point, and obtain the predicted value at the second time point.

[0011] The processing circuit may use a statistical regression model to calculate the possible range of each predicted value.

[0012] Information related to cell culture may include at least one measured value of the cell culture results.

[0013] Information related to cell culture may include culture conditions.

[0014] The culture conditions may include at least one selected from the group consisting of the type of culture medium, the capacity of the culture device, the volume of initial medium, the amount of cell seeding, the pH setting, the pH control range, the lower limit of dissolved oxygen, the temperature setting, the lower limit of glucose concentration, the gas flow rate, and the stirring speed.

[0015] The results of cell culture include at least one selected from the group consisting of cell viability, viable cell density, cell diameter, medium pH, dissolved oxygen level, dissolved carbon dioxide level, nutrients, metabolic components, and osmotic pressure concentration.

[0016] The processing circuit includes a trained model obtained through machine learning.

[0017] Information related to cell culture may include at least one measured value of the cell culture results, and the processing circuit may use at least one measured value of the cell culture results to update the trained model.

[0018] The system may further include a display unit connected to the processing circuit that displays predicted values ​​and the possible range of each predicted value.

[0019] In one embodiment, the system may further include a culture device, and the processing circuit may be configured to output a predicted value and at least a part of the possible range of each predicted value to the culture device. Based on the output from the processing circuit, the culture device may control the culture conditions. In this case, the culture conditions may include at least one selected from the group consisting of a set value of temperature, a gas flow rate, and a stirring speed. The culture device may further control the culture conditions based on the predicted value in the immediate future and / or the possible range of the predicted value. Alternatively or additionally, the culture device may terminate the cell culture based on the output from the processing circuit.

[0020] In another embodiment, the system may further include a culture device and a nutrient component supply device. The processing circuit is configured to output a predicted value and at least a part of the possible range of each predicted value to the culture device, and the nutrient component supply device controls the amount of nutrient components supplied to the culture device based on the output from the processing circuit.

[0021] Another aspect of the present disclosure is a method for assisting in the operation of cell culture, comprising: acquiring information related to cell culture; calculating a predicted value of the result of cell culture over the culture time and the possible range of each predicted value; outputting the predicted value and the possible range of each predicted value and including the method.

[0022] In one embodiment, the predicted value of the result of cell culture may be calculated by using a cascade process, and the possible range of each predicted value may be calculated by using a continuous-time stochastic process.

[0023] The method may further include displaying the predicted value and the possible range of each predicted value.

[0024] Yet another aspect of the present disclosure is a computer program product for assisting in the operation of cell culture, comprising: A non - transient computer - readable medium that stores a program for causing a processor to execute an operation when executed on the processor, the operation comprising: acquiring information related to cell culture; calculating a predicted value of the result of cell culture over a culture time and a possible range of each predicted value; outputting the predicted value and the possible range of each predicted value; A computer program product comprising the non - transient computer - readable medium.

[0025] The predicted value of the result of cell culture may be calculated by using a cascade process, and the possible range of each predicted value is calculated by using a continuous - time stochastic process.

[0026] The predicted value and the possible range of each predicted value are calculated by using a trained model obtained by machine learning.

[0027] According to the system, method, and computer program product of the present disclosure, it is possible to improve the accuracy of predicting cell culture results regardless of biological variations and differences between batches of raw materials.

[0028] These and other aspects can be more readily understood from the following description and the accompanying drawings.

[0029] Various objects, features, and attendant advantages of the present disclosure other than those described above are fully understood when considered in conjunction with the accompanying drawings. In the drawings, like reference numerals refer to the same or similar parts throughout several views.

Brief Description of the Drawings

[0030] [Figure 1] A schematic diagram of a system for assisting an operation of cell culture according to an embodiment of the present disclosure. [Figure 2] A block diagram showing a schematic configuration of a processing circuit. [Figure 3] This flowchart shows the steps performed by a method for supporting the operation of cell culture according to one embodiment of the present disclosure. [Figure 4] This is a schematic diagram of the sequential prediction of cell culture results from day 0 to day n. [Figure 5] This figure shows an example of outputting predicted values ​​and the possible ranges for each predicted value. [Figure 6] This flowchart shows the steps performed by a method for assisting the operation of cell cultures according to another embodiment of the present disclosure. [Figure 7] This flowchart shows the steps performed by the culture device. [Figure 8A] This figure shows the distribution of supply patterns, predicted antibody titers, and predicted antibody titers on day 14 under a bolus supply pattern. [Figure 8B] This figure shows the distribution of supply patterns, predicted antibody titers, and predicted antibody titers on day 14 under a sustained supply pattern. [Modes for carrying out the invention]

[0031] Embodiments will be described with reference to the attached drawings. Figure 1 is a schematic diagram of a system that supports the operation of cell culture according to one embodiment of the present disclosure.

[0032] System 10 is designed to support cell culture operations and can be run using a computer. The system comprises an input unit 20, a processing circuit 30, a storage unit 50, a display unit 80, and a network interface 90 connected to a network NW.

[0033] The input unit 20 may be, for example, a keyboard, mouse, microphone, digital tablet, smartphone, or data logger. In this embodiment, the input unit 20 is isolated from the processing circuit 30 but is electrically connected to the processing circuit 30. However, the input unit 20 may be incorporated into the processing circuit 30.

[0034] The processing circuit 30 is connected to the culture apparatus 60 and / or the nutrient supply device 70. The culture apparatus 60 comprises a culture vessel for culturing cells and a controller configured to control culture conditions such as a temperature setpoint, gas flow rate, and stirring speed. The nutrient supply device 70 comprises a supply unit for supplying nutrients such as glucose or culture medium to the culture apparatus 60 and a controller configured to control the amount of nutrients supplied to the culture apparatus 60. In this embodiment, the processing circuit 30 is independent of the culture apparatus 60 and the nutrient supply device 70. However, the processing circuit 30 may be incorporated into the culture apparatus 60 and / or the nutrient supply device 70.

[0035] The storage unit 50 stores any information used to operate the system 10. For example, the storage unit 50 may store system programs, application programs, data from other units, data displayed on the display, data acquired from the input unit 20, data received from / sent to the network NW, trained models acquired by machine learning, etc. The information stored in the storage unit 50 may be updatable by the processing circuit 30. The storage unit 50 may be, for example, semiconductor memory, magnetic memory, or optical memory. The storage unit 50 is not particularly limited to these and may include any of the following types of memory: long-term storage, short-term storage, volatile, non-volatile, and other types of memory. Furthermore, there are no limitations on the number of memory modules that function as the storage unit 50, and on the type of medium in which the information is stored. Alternatively, the storage unit 50 may be incorporated into the processing circuit.

[0036] The display unit 80 may be equipped with a monitor such as an LCD and can display information input from the input unit 20, information stored in the storage unit 50, predicted values ​​of cell culture results, messages and / or warnings presented to the user, etc. The user can use the input unit 20 and the display unit 80 to manage the system and method that supports the operation of cell culture according to this embodiment.

[0037] The network interface 90 communicates with external devices via the network NW. The network NW may be an ad hoc network, a local area network (LAN), a metropolitan area network (MAN), a wireless personal area network (WPAN), a public switched telephone network (PSTN), a terrestrial wireless network, an optical network, or any combination thereof.

[0038] In this embodiment, the processing circuit 30, storage unit 50, display unit 80, and network interface 90 are located in one place and electrically connected to each other via the bus 40. However, these components may be located in separate places and connected to each other via a network NW.

[0039] In this embodiment, the culture device 60 and the nutrient supply device 70 are directly connected to the processing circuit, but the culture device 60 and the nutrient supply device 70 may be installed in a remote location and communicate with the processing circuit 30 via a network NW. Furthermore, the culture device 60 and the nutrient supply device 70 may be configured separately as shown in Figure 1, or they may be configured as a single integrated device.

[0040] Figure 2 is a block diagram showing the schematic configuration of the processing circuit 30. The processing circuit 30 comprises an input / output (I / O) unit 100, a prediction unit 110, a culture condition detection unit 120, a culture condition update unit 130, a culture condition storage unit 140, a central processing unit (CPU) 150, a random access memory (RAM) 160, and a read-only memory (ROM) 170.

[0041] The I / O unit 100 acquires information related to cell culture from the input unit 20.

[0042] The prediction unit 110 calculates predicted values ​​for cell culture results and possible ranges of predicted values ​​for cell culture results by using a trained model obtained by machine learning. Cell culture results may include, for example, cell viability, viable cell density, cell diameter, medium pH, dissolved oxygen level, dissolved carbon dioxide level, nutrients, metabolic components, and osmotic pressure.

[0043] The culture condition detection unit 120 compares the predicted values ​​of the cell culture results with their respective set upper and / or lower limits, and takes corrective action if at least one of the predicted values ​​of the cell culture results is less than its respective set lower limit and / or greater than its respective upper limit. The corrective action may be to highlight the predicted values ​​of the cell culture results or to display a warning on the display unit 80.

[0044] Alternatively, the corrective action may involve sending the comparison results to the culture condition update unit 130. In this case, the culture condition update unit 130 modifies one or more of the culture conditions that are dominant factors in cell growth or cell culture and updates the culture condition settings. For example, the culture condition update unit 130 generates a command to increase the glucose dose. The predicted cell culture results are fed back to the prediction unit 110, which, based on the predicted cell culture results, calculates the predicted cell culture results for the next date. This cycle is repeated until a predetermined culture period has elapsed. In this way, the processing circuit calculates the predicted cell culture results at several different points in time.

[0045] The culture conditions storage unit 140 stores daily cell culture result values ​​and culture conditions. Alternatively or additionally, the daily cell culture result values ​​and culture conditions may be transmitted to other units via the I / O unit 100, such as the storage unit 50 or the display unit 80. How these functions of the processing circuit 30 can be used to support cell culture operations is described in detail below. Processing by these functions is performed under the control of the CPU 150.

[0046] The processing circuit 30 described above may include, but is not limited to, a general-purpose processor that runs software implementing various functions, a programmable logic circuit (PLD) such as a field-programmable gate array (FPGA) whose circuit configuration can be changed after manufacturing, and a dedicated electrical circuit which is a processor having a circuit configuration specifically designed to perform a particular process, such as an application-specific integrated circuit (ASIC).

[0047] The functions of the units described above may be performed by a single processor or a combination of multiple processors. Alternatively, multiple functions may be performed by a single processor. When the functions of the units described above are implemented by software, the computer-readable code of the software to be executed is stored on a non-temporary recording medium such as ROM 170, and CPU 150 refers to the software. The software stored in ROM 170 includes a program for executing a method to assist in the operation of cell culture, which will be described later. Alternatively, the code may be stored in a storage unit 50 and loaded into RAM 160 before executing the method.

[0048] Figure 3 is a flowchart showing the steps performed by a method for assisting the operation of cell culture according to one embodiment of the present disclosure. The method includes the steps of acquiring information related to cell culture, calculating predicted values ​​for the cell culture results over a culture time and the possible range of each predicted value, and outputting the predicted values ​​and the possible range of each predicted value.

[0049] Before production cell culture, cell seedlings are prepared (S10). At the start of cell culture (day 0), a sample of the cell seedlings is taken and initial information related to the cell seedlings is measured (S12). The measured (actual) information related to the cell seedlings includes, for example, the biovalue of the cell seedlings, such as cell viability, viable cell density, cell diameter, medium pH, dissolved oxygen level, dissolved carbon dioxide level, nutrient content, metabolic content, and osmotic pressure concentration.

[0050] Next, cell seeding is performed in the culture medium in the culture vessel of the culture device 60. The conditions for production cell culture are entered into system 10 along with the biovalue of the cell seeding on day 0 (S14). The culture conditions include, for example, the type of culture medium, the capacity of the culture device 60 (e.g., the internal volume of the culture vessel), the volume of the culture medium, the amount of cell seeding, the pH set value, the pH control range, the lower limit of dissolved oxygen, the temperature set value, the lower limit of glucose concentration, the gas flow rate, and the stirring speed. Preferably, the culture conditions include at least one of the temperature set value, the gas flow rate, and the stirring speed.

[0051] In step S16, the processing circuit 30 calculates predicted values ​​for the cell culture results and the possible range of each predicted value on day 1 of cell culture (the day after the start of cell culture), based on the conditions for production cell culture and the biological values ​​of cell seeding input in step S14. The calculation is performed using a machine learning-trained model. The creation of the machine learning-trained model is not particularly limited, but algorithms such as neural networks, decision trees, support vector machines, or clustering algorithms may be used. By adapting and optimizing these algorithms, the performance and accuracy in predicting the cell culture results can be improved. In this embodiment, the processing circuit 30 uses a statistical regression model to calculate the predicted values ​​for the cell culture and the possible range of each predicted value. Any statistical regression model may be used for the system and method according to this disclosure, but a Gaussian process regression model is preferably used. Unlike conventional machine learning models such as linear regression models and random forest models, the Gaussian process regression model can not only provide predictions for target variability but also return the potential variability of the prediction as a standard deviation. For each predicted cell culture result, a trained model is prepared. In this embodiment, since 10 outcomes of cell culture (i.e., cell viability, viable cell density, cell diameter, medium pH, dissolved oxygen level, dissolved carbon dioxide level, nutrient content, metabolic content, and osmotic pressure) are to be predicted, 10 trained models are prepared. Each of the trained models calculates (estimates) the change in each outcome of the cell culture from day 0 to day 1, adds that change to the input value, and obtains the predicted value for day 1.

[0052] In step S18, the predicted values ​​of the cell culture results for day 1 and the possible range of each predicted value are sent to the culture condition detection unit 120, where the predicted values ​​are compared with their respective set upper and / or lower limits. The set lower and upper limits may be stored in the ROM 170 in step S20, or stored in the storage unit 50 and loaded into the RAM 160, or entered by the user at the start of cell culture using the input unit 20. If at least one of the predicted values ​​of the cell culture results is less than its respective set lower limit and / or greater than its respective upper limit, predetermined corrective measures are taken, such as modifying the major culture conditions that are dominant factors in cell growth or cell culture (S28). For example, if the predicted glucose concentration is less than the set lower limit of 3.0 g / L, the glucose dose is increased by 0.1 ml. The modification of the major culture conditions is performed automatically by the processing circuit 30. Alternatively, cell culture may be temporarily paused, and a warning notifying the user of the deviation from the set limits may be displayed in a pop-up on the display unit 80, allowing the user to decide on corrective measures. The process returns to step S16, where the predicted values ​​for the cell culture results on day 1 and the possible ranges for each predicted value are recalculated based on the modified primary culture conditions.

[0053] Optionally, in step S22, it may be determined whether it is necessary to change any of the culture conditions other than the primary culture conditions. This may be done automatically or manually. If it is necessary to change other conditions, the other conditions are modified in step S30, and the process returns to step S16. Based on the modified other conditions, the predicted values ​​for the cell culture results on day 1 of the cell culture and the possible range of each predicted value are recalculated.

[0054] In step S24, a decision is made as to whether or not to continue the calculation. This may be done automatically or manually. If it is decided to continue the calculation, the process returns to step S14, and the predicted values ​​of the cell culture results on day 1 are used as input values. In step S16, the processing circuit 30 calculates the predicted values ​​of the cell culture results on day 2 and the possible range of each predicted value. Specifically, the predicted values ​​of the cell culture results on day 1 (first time point) and the possible range of each predicted value are input to the trained model, and the trained model predicts the difference between each cell culture result on day 2 (second time point) and the predicted value of the result on day 1. The calculation is performed in the same way as when the predicted values ​​for day 1 were obtained. Each of the trained models calculates (estimates) the change in each cell culture result from day 1 to day 2, adds that change to the predicted value for day 1, and obtains the predicted value for day 2.

[0055] Steps 18, 20, 22, and 24 are performed in the same manner as described above for day 1. This is repeated for day 3 (third time point) based on the predicted value for day 2, for day 4 (fourth time point) based on the predicted value for day 3, and so on, until it is decided in step S24 to terminate the calculation on day n, as shown in Figure 4. In step S24, it is determined that the cell culture will terminate when certain conditions are met. For example, the calculation will terminate after a predetermined culture period has elapsed.

[0056] In step S26, the processing circuit 30 outputs the calculated predicted values ​​and the possible ranges for each predicted value. For example, the predicted values ​​and the possible ranges for each predicted value are sent to the display unit 80, where the predicted values ​​and possible ranges are displayed in the form of, for example, raw data, a table, or a graph as shown in Figure 5. In the example shown in Figure 5, only the antibody titer is shown from the cell culture results. However, two or more results may be displayed. Alternatively or additionally, the predicted values ​​and the possible ranges for each predicted value may be stored in the storage unit 50, and these results may be used later.

[0057] The predicted values ​​and the possible ranges for each predicted value may be output to the nutrient supply device 70, which controls the amount of nutrients supplied to the culture device 60 based on the output from the processing circuit 30. Alternatively, the processing circuit 30 may directly control the nutrient supply device 70 to adjust the amount of nutrients supplied to the culture device 60.

[0058] In this embodiment, the calculation is performed every other day. However, the interval may be longer or shorter, such as one week, one month, one year, 12 hours, one hour, or 30 minutes. The calculation also begins at the start of the cell culture (day 0). However, the calculation may be started at any time during the cell culture (day 1, day 2, ...), and actual cell culture-related information measured one or several days prior to the calculation may be used as initial information.

[0059] Figure 6 is a flowchart showing the steps performed by a method for assisting the operation of cell culture according to another embodiment of the present disclosure. In this embodiment, cell culture preparation (S110), cell seeding sampling and measurement (S112), and prediction of cell culture results by a trained model (S116) are performed in the same manner as steps S10 to S16 described above. Predicted values ​​and the possible range of each predicted value are calculated until a predetermined culture period has elapsed. At least one measured value of the cell culture result is measured during cell culture and input into system 10 (S140). Optionally, in step S122, the need to change any of the culture conditions other than the main culture conditions may be determined based on at least one measured value of the cell culture result. This may be done automatically or manually. If it is necessary to change other conditions, the other conditions are modified in step S130. For example, if the measured value of antibody titer deviates from the predicted value of antibody titer, at least one of the temperature setpoint, gas flow rate, and stirring speed may be changed. In step S124, a decision is made as to whether or not to continue the cell culture. This may be done automatically or manually. For example, if the measured antibody titer deviates from the predicted antibody titer, the deviation from the predicted value is treated as an indication of an abnormality in the cell culture, and it is decided to terminate the cell culture (S126). If it is decided to continue the calculation, the process returns to step S116, and the predicted value of the cell culture result on day 1 is used as the input value. Subsequently, based on the other modified culture conditions and at least one measured value of the cell culture result, the processing circuit 30 recalculates the predicted value of the cell culture result after the measurement day and the possible range of each predicted value. In this way, a more accurate predicted value of the result can be obtained at the end of the cell culture. The processing circuit 30 may update the trained model using at least one measured value of the cell culture result as teaching data (S132). The update of the trained model may be performed dynamically while the cell culture is continuing.Alternatively or additionally, at least one measured value of the cell culture results may be measured at one or more time points during the cell culture, and at least one measured value of the cell culture results may be input to system 10 as teaching data to update the trained model after the cell culture is complete.

[0060] The operation of the culture apparatus will be explained below with reference to Figure 7.

[0061] The preparation of the cell culture (S210) and the prediction of the cell culture results using the trained model (S216) are carried out in the same manner as steps S10 to S16 described above, and the processing circuit 30 outputs the predicted values ​​and at least a portion of the possible range of each predicted value, which are sent to and input to the culture device 60 (S226).

[0062] Next, the culture device 60 controls one or more culture conditions based on the output from the processing circuit. Specifically, in step S222, it is determined whether it is necessary to change any of the culture conditions. If it is necessary to change the culture conditions, the culture device 60 changes the culture conditions in step S250 based on the output from the processing circuit 30. The culture conditions may include a set temperature, gas flow rate, stirring speed, or a combination thereof. The culture device 60 may automatically control the culture conditions within a predetermined optimal range so that the antibody titer can be increased at the end of cell culture. In one embodiment, when the predicted value or predictable range of viable cell density falls outside the set range or set value, the temperature of the culture vessel is controlled to fall within a predetermined range. For example, if the predicted value of viable cell density is 10 × 10 6 cells / mL~200×10 6 cells / mL, preferably 10 × 10 6 cells / mL~150×10 6 Cells / mL, more preferably 15 × 10 6 cells / mL~150×10 6When the cells / mL range is outside the specified range, the culture apparatus 60 controls the temperature of the culture vessel to be within the range of 30°C to 35°C, preferably 30°C to 33°C, and more preferably 30°C to 32°C. In another embodiment, when the predicted value or predictable range of the carbon dioxide level is outside the set range or set value, the stirring of the culture medium is controlled to be within a predetermined range. For example, when the predicted value of the carbon dioxide level is outside the range of 5% to 20%, preferably 5% to 15%, and more preferably 5% to 10%, the culture apparatus 60 controls the stirring speed to be within the range of 101% to 150% of the initial stirring speed, preferably 101% to 120% of the initial stirring speed. In another embodiment, when the predicted value or predictable range of the internal pressure of the culture vessel is outside the set range or set value, the gas flow rate is controlled to be within a predetermined range. For example, when the predicted internal pressure of the culture vessel falls outside the range of 0.1 psi (0.69 kPa) to 0.6 psi (4.14 kPa), preferably 0.1 psi (0.69 kPa) to 0.5 psi (3.45 kPa), and more preferably 0.2 psi (1.38 kPa) to 0.5 psi (3.45 kPa), the culture apparatus 60 controls the gas flow rate to be within the range of 50% to 90% of the initial gas flow rate, preferably 50% to 80%, and more preferably 50% to 70%. In another embodiment, when the predicted value or predictable range of carbon dioxide levels falls outside a set range or set value, the gas flow rate is controlled to be within a predetermined range. For example, when the predicted carbon dioxide level falls outside the range of 5% to 20%, preferably 5% to 15%, and more preferably 5% to 10%, the culture apparatus 60 controls the gas flow rate to be within the range of 101% to 200%, preferably 120% to 180%, of the initial gas flow rate.

[0063] The predicted values ​​and / or possible ranges of predicted values ​​used by the culture device 60 may be for the most recent future time. For example, assuming a calculation interval of one day and cell culture has been performed for three days, the culture device 60 controls the culture conditions by referring to the predicted values ​​and / or possible ranges of predicted values ​​for day four (i.e., the most recent future time).

[0064] Optionally, in step S224, a decision is made as to whether or not to continue the cell culture. If it is decided to continue the cell culture, the process returns to step S210. Otherwise, the cell culture is temporarily paused in step S226, allowing the user to decide on corrective measures. In this way, more ideal results can be obtained at the end of the cell culture.

[0065] The systems and methods described above may be used to simulate cell culture under different culture conditions. For example, different patterns of nutrient supply can be evaluated. Figures 8A and 8B show the distribution of supply patterns, predicted antibody titers, and predicted antibody titers on day 14 under bolus supply patterns and continuous supply patterns, respectively. In the simulation, nutrients A and B are supplied to the culture medium every other day (Figure 8A) or daily (Figure 8B), and the predicted antibody titers are calculated by system 10. A comparison of the distribution of predicted values ​​on day 14 shows that the bolus supply pattern yields a higher yield with a 97% probability.

[0066] With the configuration described above, system 10 can provide predictive information that can be used to facilitate operator decision-making. System 10 allows users to input measured results during cell culture, improving the accuracy of predicting cell culture results regardless of biological variability and batch-to-batch differences in raw materials. It also makes it possible to evaluate the contribution of each culture condition and determine the optimal culture conditions. Furthermore, a trained model can be built for each culture batch without relying on mathematical models based on existing information.

[0067] While this disclosure has been described with reference to drawings and examples, it should be noted that various modifications and amendments can be made based on this disclosure by those skilled in the art. Such modifications and amendments are therefore included within the scope of this disclosure. For example, configurations, functions, etc., included in each embodiment can be reconfigured without logical inconsistency. In addition, configurations or functions included in each embodiment can be used in combination with other embodiments. Furthermore, multiple configurations or functions can be combined, divided, or partially omitted.

[0068] For example, an embodiment is also possible in which a general-purpose computer functions as the processing circuit 30 according to the above-described embodiment. Specifically, a program containing a process for realizing the functions of the processing circuit 30 according to the above-described embodiment may be stored in the memory of the general-purpose computer, and the program may be read and executed by the processor of the general-purpose computer. Therefore, this disclosure can also be implemented as a program executable by a processor or by a non-temporary computer-readable storage medium on which the program is stored. Examples of non-temporary computer-readable storage mediums include magnetic storage devices, optical discs, magneto-optical storage devices, and semiconductor memories. A non-temporary computer-readable storage medium on which a program is stored is also called a computer program product.

[0069] For example, in the embodiments described above, the processing circuit 30 is described as performing all of the operations and processing in the steps shown in Figures 3, 6, and 7, but the disclosure is not limited to this configuration. An external server and / or user terminal may perform some or all of the operations and processing performed by the processing circuit 30. In such a case, the processing circuit 30 may be configured to communicate with the external server and / or user terminal via a network NW.

[0070] The actual scope of the protection required, when viewed correctly based on the prior art, is intended to be defined by the following claims:

Claims

1. A system that supports the operation of cell culture, Obtaining information related to the aforementioned cell culture, The predicted values ​​of the cell culture results over the culture time, and the possible range of each predicted value are calculated. Output the predicted value and the possible range of each of the predicted values. A system equipped with a processing circuit configured in such a way.

2. The system according to claim 1, wherein the processing circuit calculates the predicted value of the cell culture result at multiple different time points.

3. The system according to claim 2, wherein the processing circuit calculates the predicted value at a first time point, and then, based on the predicted value at the first time point, calculates the predicted value at a second time point after the first time point, and repeats the calculation over the culture time.

4. The system according to claim 3, wherein the processing circuit calculates the predicted value at the first time point based on the information related to the cell culture.

5. The system according to claim 2, wherein the processing circuit estimates the change in the predicted value from the first time point to the second time point, adds the estimated change to the predicted value at the first time point, and obtains the predicted value at the second time point.

6. The system according to claim 1, wherein the processing circuit calculates the possible range of each of the predicted values ​​using a statistical regression model.

7. The system according to claim 1, wherein the information relating to the cell culture includes at least one measured value of the results of the cell culture.

8. The system according to claim 1, wherein the information related to the cell culture includes culture conditions.

9. The system according to claim 8, wherein the culture conditions include at least one selected from the group consisting of the type of culture medium, the capacity of the culture apparatus, the volume of initial culture medium, the amount of cell seeding, the pH setting, the pH control range, the lower limit of dissolved oxygen, the temperature setting, the lower limit of glucose concentration, the gas flow rate, and the stirring speed.

10. The system according to claim 1, wherein the results of the cell culture include at least one selected from the group consisting of cell viability, viable cell density, cell diameter, pH of the culture medium, dissolved oxygen level, dissolved carbon dioxide level, nutrients, metabolic components, and osmotic pressure concentration.

11. The system according to claim 1, wherein the processing circuit includes a trained model obtained by machine learning.

12. The system according to claim 11, wherein the information relating to the cell culture includes at least one measured value of the results of the cell culture, and the processing circuit updates the trained model using the at least one measured value of the results of the cell culture.

13. The system according to claim 1, further comprising a display unit connected to the processing circuit for displaying the predicted values ​​and the possible range of each of the predicted values.

14. Further equipped with a culture device, The processing circuit is configured to output the predicted value and at least a portion of the possible range of each of the predicted values ​​to the culture device. The culture apparatus controls the culture conditions based on the output from the processing circuit, according to claim 1.

15. The system according to claim 14, wherein the culture conditions include at least one selected from the group consisting of a temperature set value, a gas flow rate, and a stirring speed.

16. The system according to claim 14, wherein the culture apparatus controls the culture conditions based on the predicted value for the immediate future and / or the possible range of the predicted value.

17. Further equipped with a culture device, The processing circuit is configured to output the predicted value and at least a portion of the possible range of each of the predicted values ​​to the culture device. The system according to claim 1, wherein the culture apparatus terminates the cell culture based on the output from the processing circuit.

18. The system further includes a culture device and a nutrient supply device. The processing circuit is configured to output the predicted value and at least a portion of the possible range of each of the predicted values ​​to the culture device. The system according to claim 1, wherein the nutrient supply device controls the amount of nutrients supplied to the culture device based on the output from the processing circuit.

19. A method to support the operation of cell culture, To obtain information related to the aforementioned cell culture, To calculate the predicted values ​​of the cell culture results over the culture time, and the possible range of each predicted value, Outputting the predicted values ​​and the possible ranges for each of the predicted values. A method that includes this.

20. A computer program product that supports the operation of cell culture, A non-temporary computer-readable medium that stores a program that causes the processor to perform an operation when executed on the processor, wherein the operation is To obtain information related to the aforementioned cell culture, To calculate the predicted values ​​of the cell culture results over the culture time, and the possible range of each predicted value, Outputting the predicted values ​​and the possible ranges for each of the predicted values. Non-temporary computer-readable media A computer program product that includes the following features.

Images