Cell culture scene prediction method and device, storage medium and electronic equipment

Abstract

The invention discloses a cell culture scene prediction method and device, a storage medium and electronic equipment. The method comprises the following steps: acquiring process data in a first time period in a current culture stage, wherein the process data in the first time period comprises detection data corresponding to a plurality of detection time points in the first time period of a target variable; determining an initial prediction model of the target variable based on detection data corresponding to a plurality of detection time points of the target variable in the first time period; fitting parameter values in the initial prediction model of the target variable to obtain a target prediction model corresponding to the target variable; and based on a target prediction model corresponding to the target variable, determining prediction data of the target variable at at least one prediction time point in the second time period in the current culture stage. The invention provides a universal prediction model of each culture stage in a cell culture scene, and realizes variable prediction of each culture stage.

Description

Technical Field

[0001] The present invention relates to the field of cell culture technology, and in particular to a prediction method, device, storage medium and electronic equipment for a cell culture scene. Background Art

[0002] During the cell culture process, parameters such as metabolite concentration are important influencing factors in the cell culture process. The prediction of parameters such as metabolite concentration provides a reference for the cell culture process and facilitates timely adjustment of the culture medium.

[0003] In the process of implementing the present invention, it was found that there are at least the following technical problems in the prior art: Currently, prediction can be achieved by constructing a model of cell growth metabolism, but since the model of cell growth metabolism is usually designed for specific processes and application scenarios, it has poor migration ability. Summary of the invention

[0004] The present invention provides a prediction method, device, storage medium and electronic device for a cell culture scenario, provides a universal prediction model for a cell culture scenario, and realizes variable prediction of a cell culture scenario.

[0005] According to one aspect of the present invention, a method for predicting a cell culture scenario is provided, comprising:

[0006] Acquiring process data in a first time period in a current culture stage, wherein the cell culture process includes at least one culture stage, each culture stage is divided based on a preset operation in the cell culture process, and the current culture stage is any culture stage in the at least one culture stage; the process data in the first time period includes detection data corresponding to a plurality of detection time points of a target variable in the first time period;

[0007] Determining an initial prediction model for the target variable based on detection data corresponding to a plurality of detection time points of the target variable within the first time period;

[0008] Performing fitting processing on the parameter values ​​in the initial prediction model of the target variable to obtain a target prediction model corresponding to the target variable;

[0009] Based on the target prediction model corresponding to the target variable, prediction data of at least one prediction time point of the target variable in a second time period in the current training stage is determined, wherein the second time period is after the first time period.

[0010] Optionally, the target variable includes one or more of a cell growth variable and a metabolite variable;

[0011] The initial prediction model of the cell growth variable is a change rate prediction model of the cell growth variable, wherein the change rate prediction model of the cell growth variable includes a product of a first coefficient group and the cell growth variable, wherein the first coefficient group includes a true specific growth rate and a true specific death rate;

[0012] The initial prediction model of the metabolite variable is a change rate prediction model of the metabolite variable, and the change rate prediction model of the metabolite variable includes the product of a second coefficient group and the cell growth variable, and the second coefficient group includes the true specific growth rate, the maintenance factor of the metabolite variable and the true yield factor of the metabolite variable.

[0013] Optionally, the process data in the first time period includes live cell density and live cell rate corresponding to a plurality of detection time points in the first time period;

[0014] The method of determining the initial prediction model of the target variable based on the detection data corresponding to multiple detection time points of the target variable in the first time period includes: determining the true specific growth rate and the true specific death rate at multiple detection time points in the first time period based on the live cell density and the live cell rate respectively corresponding to the multiple detection time points in the first time period; obtaining a first linear graph of the true specific growth rate changing with time based on the true specific growth rate at multiple detection time points in the first time period, determining a first parameter of the true specific growth rate relative to time based on the first linear graph, and determining a variation model of the true specific growth rate relative to time based on the first parameter; obtaining a second linear graph of the true specific death rate changing with time based on the true specific death rate at multiple detection time points in the first time period, determining a second parameter of the true specific death rate relative to time based on the second linear graph, and determining a variation model of the true specific death rate relative to time based on the second parameter; and determining the initial prediction model of the cell growth variable based on the variation model of the true specific growth rate relative to time and the variation model of the true specific death rate relative to time.

[0015] Optionally, the process data within the first time period further includes: the concentration values ​​of the metabolites corresponding to a plurality of detection time points within the first time period;

[0016] The method of determining the initial prediction model of the target variable based on the detection data corresponding to multiple detection time points of the target variable within the first time period includes: determining the concentration change of the metabolite based on the metabolite concentration values ​​corresponding to the multiple detection time points within the first time period; and determining the live cell density change based on the live cell density corresponding to the multiple detection time points within the first time period; determining the characterization yield factor of the metabolite variable based on the concentration change of the metabolite and the live cell density change; determining the characterization growth rate based on the live cell density and the interval time of adjacent detection time points; fitting a third linear graph based on the reciprocal of the characterization growth rate as the independent variable and the reciprocal of the characterization yield factor as the dependent variable; determining the maintenance factor of the metabolite variable and the true yield factor of the metabolite variable based on the third linear graph; determining the initial prediction model of the metabolite variable based on the change model of the true specific growth rate relative to time, the maintenance factor of the metabolite variable and the true yield factor of the metabolite variable.

[0017] Optionally, the parameter values ​​in the initial prediction model of the target variable are fitted to obtain the target prediction model corresponding to the target variable, including: obtaining parameter values ​​of set parameters in the initial prediction model, the numerical ranges of the set parameters, and feeding information during the cell culture process; calling a parameter fitting algorithm, and performing parameter fitting based on the parameter values ​​of the set parameters, the numerical ranges of the set parameters, and the feeding information during the cell culture process through the parameter fitting algorithm to obtain target parameter values ​​of the set parameters; and updating the initial prediction model based on the target parameter values ​​of the set parameters to obtain the target prediction model corresponding to the target variable.

[0018] Optionally, the target prediction model corresponding to the target variable is used to determine the prediction data of the target variable at at least one prediction time point in the second time period in the current training stage, including: taking the detection data of the last detection time point in the first time period as initial data, determining the rate of change of the target variable over time based on the target prediction model corresponding to the target variable, and determining the prediction data of the target variable at at least one prediction time point in the second time period based on the initial data and the rate of change of the target variable over time.

[0019] Optionally, the metabolites include one or more of glucose, glutamate, glutamine, ammonium ions, lactic acid and antibody products; each of the metabolite variables corresponds to one of the target prediction models.

[0020] According to another aspect of the present invention, a prediction device for a cell culture scenario is provided, comprising:

[0021] A data acquisition module, configured to acquire process data within a first time period in a current culture stage, wherein the cell culture process includes at least one culture stage, each culture stage is divided based on a preset operation in the cell culture process, and the current culture stage is any culture stage in the at least one culture stage; the process data within the first time period includes detection data corresponding to a plurality of detection time points of a target variable within the first time period;

[0022] An initial prediction model determination module, used to determine an initial prediction model of the target variable based on detection data corresponding to a plurality of detection time points of the target variable within the first time period;

[0023] A target prediction model determination module is used to perform fitting processing on the parameter values ​​in the initial prediction model of the target variable to obtain the target prediction model corresponding to the target variable;

[0024] A prediction module, for determining prediction data of the target variable at at least one prediction time point in a second time period in the current training stage based on the target prediction model corresponding to the target variable, wherein the second time period is after the first time period

[0025] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0026] at least one processor; and

[0027] a memory communicatively connected to the at least one processor; wherein,

[0028] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the method for predicting a cell culture scenario described in any embodiment of the present invention.

[0029] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for predicting a cell culture scenario described in any embodiment of the present invention when executed.

[0030] The technical solution of the embodiment of the present invention, in each culture stage of the cell culture process, determines the parameter value of the parameter set in the initial prediction model of the target variable through the process data of the first time period in each culture stage, so as to determine the target prediction model of the target variable in each culture stage. The target variable in any culture stage is predicted by the target prediction model of the target variable in the culture stage to determine the prediction data of the target variable at the prediction time point. The embodiment of this solution provides a target prediction model applicable to each culture stage of the cell culture process, which has strong applicability and realizes the variable prediction in each culture stage of the cell culture process.

[0031] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0033] Figure 1 is a flow chart of a method for predicting a cell culture scenario provided in Example 1 of the present invention;

[0034] Figure 2 is a schematic diagram of a first line graph provided in Embodiment 1 of the present invention;

[0035] Figure 3 is a schematic diagram of a third line graph provided in Embodiment 1 of the present invention;

[0036] Figure 4 is a schematic diagram of the structure of a prediction device for a cell culture scenario provided in the second embodiment of the present invention;

[0037] Figure 5 It is a structural schematic diagram of an electronic device provided in Embodiment 3 of the present invention. DETAILED DESCRIPTION

[0038] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0039] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0040] Embodiment 1

[0041] Figure 1 This is a flow chart of a prediction method for a cell culture scenario provided in Example 1 of the present invention. This embodiment can be applied to setting a target prediction model of a target variable in each culture stage of the cell culture scenario, and realizing the situation where the target variable is predicted by the target prediction model of the target variable in each culture stage. The target prediction model of the target variable has strong universality and can be applied to different cell culture scenarios. The method can be executed by a prediction device for a cell culture scenario, and the prediction device for the cell culture scenario can be implemented in the form of hardware and / or software. The prediction device for the cell culture scenario can be configured in an electronic device such as a mobile terminal, a server or a computer. The mobile terminal may include but is not limited to a mobile phone, a tablet computer, etc. Figure 1 As shown, the method includes:

[0042] S110. Obtain process data within a first time period in a current culture stage, wherein the cell culture process includes at least one culture stage, each culture stage is divided based on a preset operation in the cell culture process, and the current culture stage is any culture stage in the at least one culture stage; the process data within the first time period includes detection data corresponding to a target variable at multiple detection time points within the first time period.

[0043] S120. Determine an initial prediction model of the target variable based on the detection data corresponding to a plurality of detection time points of the target variable within the first time period.

[0044] S130: Fitting the parameter values ​​in the initial prediction model of the target variable to obtain a target prediction model corresponding to the target variable.

[0045] S140. Determine prediction data of the target variable at at least one prediction time point in a second time period in the current training stage based on the target prediction model corresponding to the target variable, wherein the second time period is after the first time period.

[0046] In this embodiment, the cell type targeted by the cell culture process is not limited, and optionally, the cells cultured in the cell culture process may be mammalian cells. The culture process of the cell culture process may include but is not limited to a Batch process and a Fed-Batch process.

[0047] At least one culture stage may be included in the cell culture process, and at least one culture stage in the cell culture process is divided based on a preset operation, and the culture duration of different culture stages may be different. Optionally, the preset operation includes but is not limited to a temperature adjustment operation. Optionally, the preset operation is a cooling operation. Among them, the temperature difference before and after the temperature adjustment operation is greater than a preset temperature threshold. Exemplarily, the preset temperature threshold may be, for example, 3 degrees Celsius. Exemplarily, different types of cells may correspond to different preset temperature thresholds, and the preset temperature thresholds corresponding to different types of cells may be determined according to the adaptability of the cells to temperature. In some embodiments, the cell culture process includes a cooling operation, and the cell culture process is divided into two culture stages.

[0048] It is understandable that some preset operations (here, it can be temperature adjustment operations) have a huge impact on cell growth and metabolism, and it is impossible to predict the cell culture process after the preset operation by executing the model before the preset operation. Therefore, a preset operation is used as a division node to obtain different culture stages. For each culture stage, the target prediction model corresponding to the target variable in each culture stage is determined to achieve the prediction of the target variable in each culture stage. In different culture stages, the construction process of the target prediction model corresponding to the target variable and the prediction process of the target variable are the same.

[0049] The current culture stage can be any culture stage of the cell culture process, and the sum of the duration of the first time period and the second time period of the current culture stage is the total duration of the current culture stage. For different culture stages, the durations corresponding to the first time period and the second time period may be different. A plurality of detection time points are set in the first time period of the current culture stage, and the cell culture fluid is sampled and tested at each detection time point to obtain process data in the first time period, that is, detection data at each detection time point in the first time period. Optionally, the detection data at each detection time point includes one or more of viable cell density, viable cell rate, and at least one metabolite concentration.

[0050] Among them, the detection time point can be a time point determined based on a preset time interval, for example, the preset time interval can be 4 hours to 6 hours. It can be understood that the preset time interval can be set according to needs, and this is only an example.

[0051] Optionally, when the current culture stage is after a preset operation, in order to avoid interference of the preset operation with the cell culture process and affecting the accuracy of the detection data, the first time period is after a transition period corresponding to the preset operation. For example, the transition period may be 24 hours. Accordingly, the first time period is the time period 24 hours after the preset operation.

[0052] Optionally, the number of detection time points in the first time period is greater than a preset number threshold, for example, the preset number threshold may be 5 or 6.

[0053] Optionally, the target variable includes one or more of a cell growth variable and a metabolite variable; wherein the cell growth variable includes viable cell density (VCD), and the metabolite variable includes metabolite concentration. wherein the metabolite includes one or more of glucose, glutamate, glutamine, ammonium ion, lactate, and antibody product, and correspondingly, the metabolite variable includes one or more of glucose concentration, glutamate concentration, glutamine concentration, ammonium ion concentration, lactate concentration, and antibody product concentration.

[0054] The cell growth variables and the metabolite variables correspond to initial prediction models respectively, and accordingly, one or more of the viable cell density, glucose concentration, glutamate concentration, glutamine concentration, ammonium ion concentration, lactate concentration and antibody product concentration correspond to an initial prediction model respectively.

[0055] Each of the above-mentioned initial prediction models includes setting parameters. For example, the parameter value of the setting parameter can be obtained by fitting based on the detection data of multiple detection time points in the first time period in the current cultivation stage.

[0056] The initial prediction model of the cell growth variable is a change rate prediction model of the cell growth variable, wherein the change rate prediction model of the cell growth variable includes the product of a first coefficient group and the cell growth variable, wherein the first coefficient group includes a true specific growth rate and a true specific death rate. The change rate prediction model of the cell growth variable can be used to determine the change rate of the current cell growth variable at each prediction time point. The cell growth variable can be a viable cell density, and accordingly, the change rate prediction model of the cell growth variable is used to predict the change rate of the viable cell density at each prediction time point.

[0057] The true specific growth rate can be understood as the amount of cells added per unit hour in the cell culture medium, and the true specific death rate can be understood as the amount of dead cells per unit hour in the cell culture medium. The first coefficient group can be the difference between the true specific growth rate and the true specific death rate. Accordingly, the initial prediction model of the cell growth variable can be expressed as:

[0058] Among them, μ g is the real specific growth rate, k d is the actual specific death rate. is the rate of change of viable cell density. Among them, the real specific growth rate μ g It can be expressed as μ g =μ g-init +μ g-slope *t, where μ g-init is the initial growth rate, μ g-slope is the growth rate of change. The real specific death rate k d It can be expressed as k d =k d-init +k d-slope *t, where k d-init is the initial mortality rate, k d-slope is the death change rate, and t is time. The set parameters in the initial prediction model of cell growth variables may include initial death rate, death change rate, initial growth rate, and growth change rate.

[0059] The real specific growth rate and the real specific death rate change with time. The real specific growth rate and the real specific death rate in the change rate prediction model of the cell growth variable can be represented by the real specific growth rate relative to time change model and the real specific death rate relative to time change model. Among them, the real specific growth rate relative to time change model includes a first parameter, and the first parameter includes an initial growth rate and a growth change rate; the real specific death rate relative to time change model includes a second parameter, and the second parameter includes an initial mortality rate and a mortality change rate. The first parameter and the second parameter here belong to set parameters.

[0060] Optionally, the process data in the first time period includes live cell density and live cell rate corresponding to multiple detection time points in the first time period; the real specific growth rate and real specific death rate at multiple detection time points in the first time period can be determined by the live cell density and live cell rate corresponding to multiple detection time points in the first time period. The first parameter is obtained by fitting the real specific growth rate and the real specific death rate at multiple detection time points in the first time period to obtain a model of the change of the real specific growth rate relative to time; the second parameter is obtained by fitting the death specific growth rate and the real specific death growth rate at multiple detection time points in the first time period to obtain a model of the change of the real death specific growth rate relative to time.

[0061] Specifically, based on the detection data corresponding to multiple detection time points of the target variable in the first time period, determining the initial prediction model of the target variable includes: determining the true specific growth rate and the true specific death rate at multiple detection time points in the first time period based on the live cell density and the live cell rate respectively corresponding to the multiple detection time points in the first time period; fitting a first linear graph of the true specific growth rate changing with time based on the true specific growth rate at multiple detection time points in the first time period, determining a first parameter of the true specific growth rate relative to time based on the first linear graph, and determining a variation model of the true specific growth rate relative to time based on the first parameter; fitting a second linear graph of the true specific death rate changing with time based on the true specific death rate at multiple detection time points in the first time period, determining a second parameter of the true specific death rate relative to time based on the second linear graph, and determining a variation model of the true specific death rate relative to time based on the second parameter; determining the initial prediction model of the cell growth variable based on the variation model of the true specific growth rate relative to time and the variation model of the true specific death rate relative to time.

[0062] The process of determining the true specific growth rate and the true specific death rate may include: determining the representative specific growth rate representing the second detection time point based on the interval between the first detection time point and the second detection time point, the live cell density at the first detection time point and the live cell density at the second detection time point. Determining the total cell density based on the live cell density and the live cell rate at each detection time point. Determining the true specific growth rate corresponding to each detection time point based on the representative specific growth rate, the change in total cell density and the change in live cell density corresponding to each detection time point; determining the true specific death rate corresponding to each detection time point based on the true specific growth rate corresponding to each detection time point and the representative specific growth rate.

[0063] Exemplarily, the determination process of the true specific growth rate and the true specific death rate can be expressed as:

[0064] Among them, VCD t is the viable cell density at time point t, VCD t-1 is the viable cell density at time point t-1, and Δt is the interval between time point t and time point t-1. It can be understood that μ is a measurable characterization value, μ g With k d is an unknown true value.

[0065] Wherein, TCD is the total cell density, and viability% is the viable cell rate.

[0066] k d =μ g -μ; where ΔTCD is the change in total cell density and ΔVCD is the change in live cell density.

[0067] In the case where the true specific growth rate corresponding to each detection time point is determined based on the above method, a first linear graph of the true specific growth rate changing with time is drawn. For example, see Figure 2 , Figure 2 is a schematic diagram of the first linear graph provided by an embodiment of the present invention. The first parameter is determined based on the characteristic value of the first linear graph. Specifically, the characteristic value of the first linear graph includes an intercept and a slope. The intercept of the first linear graph is the initial growth rate in the first parameter, and the slope of the first linear graph is determined as the growth change rate in the first parameter. A variation model of the true specific growth rate relative to time is generated based on the initial growth rate and the growth change rate, that is, μ g =μ g-init +μ g-slope *t.

[0068] When the true relative mortality rate corresponding to each detection time point is determined, a second linear graph of the true relative mortality rate changing with time is plotted. The second parameter is determined based on the characteristic value of the second linear graph. Specifically, the characteristic value of the second linear graph includes an intercept and a slope. The intercept of the second linear graph is the initial mortality rate in the second parameter, and the slope of the second linear graph is determined as the mortality change rate in the second parameter. The variation model of the true relative mortality rate relative to time is determined based on the initial mortality rate and the mortality change rate, i.e., k d =k d-init +k d-slope *t.

[0069] The variation model of the real specific growth rate relative to time is used as the real specific growth rate in the initial prediction model of the cell growth variable, and the variation model of the real specific death rate relative to time is used as the real specific death rate to obtain the initial prediction model of the cell growth variable.

[0070] Based on the above embodiment, the initial prediction model of the metabolite variable is a change rate prediction model of the metabolite variable, and the change rate prediction model of the metabolite variable includes the product of a second coefficient group and the cell growth variable, and the second coefficient group includes the true specific growth rate, the maintenance factor of the metabolite variable and the true yield factor of the metabolite variable.

[0071] Wherein the second coefficient group can be determined based on the ratio of the true specific growth rate to the true yield factor of the metabolite variable, and the sum of the ratio and the maintenance factor of the metabolite variable. Exemplarily, the initial prediction model of the metabolite variable can be expressed as: in, Characterizes the concentration change rate of metabolite X, m X Y is the maintenance factor of metabolites, X is the true yield factor of metabolite X. The set parameters in the initial prediction model of the metabolite variable include the maintenance factor and the true yield factor of the metabolite.

[0072] For one or more of glucose, glutamate, glutamine, ammonium ion, lactate and antibody products, an initial prediction model is set respectively, wherein:

[0073] The initial prediction model for glucose is Among them, m Glc Y is the maintenance factor of glucose, Glc is the real yield factor of glucose;

[0074] The initial prediction model for glutamate is Among them, m Glu Y is the maintenance factor of glutamate. Glu is the true yield factor of glutamate;

[0075] The initial prediction model corresponding to glutamine is Among them, m Gln Y is the maintenance factor of glutamine. Gln is the true yield factor of glutamine;

[0076] The initial prediction model for ammonium ions is Among them, m Amm is the maintenance factor of ammonium ions, Y Amm is the true yield factor of ammonium ions;

[0077] The initial prediction model for lactate is Among them, m Lac Y is the maintenance factor of lactic acid. Lac is the true yield factor of lactic acid;

[0078] The initial prediction model corresponding to the antibody product is Among them, m IgG Y is the protective factor of antibody products. IgG is the actual yield factor of the antibody product.

[0079] The initial prediction model of metabolite variables provided in this example is universal and highly explanatory, and can be applied to different metabolites in different types of cell culture processes.

[0080] For any metabolite, when the model of change of the true specific growth rate relative to time has been determined, the maintenance factor and true yield factor of the metabolite are determined. Based on the model of change of the true specific growth rate relative to time, the maintenance factor and true yield factor of the metabolic parameters, the initial prediction model of the metabolite can be determined.

[0081] For any metabolite, the process data in the first time period in the current culture stage also includes: the concentration values ​​of the metabolite corresponding to a plurality of detection time points in the first time period;

[0082] Specifically, for each metabolite, the initial prediction model of the target variable is determined based on the detection data corresponding to the target variable at multiple detection time points within the first time period, including: determining the concentration change of the metabolite based on the metabolite concentration values ​​corresponding to the multiple detection time points within the first time period; and determining the live cell density change based on the live cell density corresponding to the multiple detection time points within the first time period; determining the characterization yield factor of the metabolite variable based on the concentration change of the metabolite and the live cell density change; determining the characterization growth rate based on the live cell density and the interval time of adjacent detection time points; fitting a third linear graph based on the reciprocal of the characterization growth rate as the independent variable and the reciprocal of the characterization yield factor as the dependent variable; determining the maintenance factor of the metabolite variable and the true yield factor of the metabolite variable based on the third linear graph; determining the initial prediction model of the metabolite variable based on the change model of the true specific growth rate relative to time, the maintenance factor of the metabolite variable and the true yield factor of the metabolite variable.

[0083] For the metabolite concentration values ​​corresponding to the multiple detection time points in the first time period, the concentration difference between any adjacent detection time points, i.e., the concentration change of the metabolite variable, is determined. For the viable cell density corresponding to the multiple detection time points in the first time period, the viable cell density difference between any adjacent detection time points, i.e., the viable cell density change, is determined, and the characteristic yield factor is determined based on the ratio of the viable cell density change to the concentration change of the metabolite variable. It can be understood that the characteristic yield factor is a measurable characteristic value, and the actual yield factor is an unknown theoretical true value.

[0084] Exemplarily, the actual yield factor of any metabolite X can be expressed as: app =ΔVCD / ΔX, where ΔVCD is the change in viable cell density and ΔX is the change in concentration of the metabolite variable. The characteristic yield factor corresponding to each detection time point can be determined based on the change in viable cell density and the change in concentration of the metabolite variable corresponding to each detection time point.

[0085] Based on the reciprocal of the growth rate as the independent variable and the reciprocal of the yield factor as the dependent variable, a third linear graph is fitted, for example, see Figure 3 , Figure 3 It is a schematic diagram of a third linear graph corresponding to a metabolite provided in an embodiment of the present invention. The maintenance factor and the true yield factor of the metabolite are determined by the characteristic value of the third linear graph. Specifically, the characteristic value of the third linear graph includes an intercept and a slope. The reciprocal of the intercept of the third linear graph is the true yield factor of the metabolite, and the slope of the third linear graph is determined as the maintenance factor of the metabolite.

[0086] In the above-mentioned situation, since the number of detection time points in the first time period in the current training stage is limited, that is, the detection data in the first time period is limited, the parameter values ​​of the set parameters in the initial prediction model determined based on the detection data in the first time period may have errors. In this embodiment, when the parameter values ​​of the set parameters are determined based on the above-mentioned method, the parameter values ​​of the set parameters in the initial prediction model are optimized, the target parameter values ​​of the set parameters are determined, and the target prediction model is obtained to improve the accuracy of the target prediction model.

[0087] Optionally, the parameter values ​​in the initial prediction model of the target variable are fitted to obtain the target prediction model corresponding to the target variable, including: obtaining the parameter values ​​of the set parameters in the initial prediction model, the numerical ranges of the set parameters, and the feeding information during the cell culture process; calling a parameter fitting algorithm, and performing parameter fitting based on the parameter values ​​of the set parameters, the numerical ranges of the set parameters, and the feeding information during the cell culture process through the parameter fitting algorithm to obtain the target parameter values ​​of the set parameters; updating the initial prediction model based on the target parameter values ​​of the set parameters to obtain the target prediction model corresponding to the target variable.

[0088] In this embodiment, an interactive page can be displayed, through which the parameter values ​​of the set parameters, the numerical range of the set parameters, and the feeding information during the cell culture process are collected. Optionally, the feeding information during the cell culture process can be the expected feeding information during the cell culture process; optionally, the feeding information during the cell culture process can be calculated based on the concentration of the material in the feed solution and the volume of the culture solution in the cell culture reactor through the principle of conservation of materials. Among them, the principle of conservation of materials can be reflected by the following formula: new concentration × new volume = original concentration × original volume + feed concentration × feed volume.

[0089] Wherein, the feed solution may include glucose and glutamic acid. Exemplarily, the feeding information may include time information, material name and concentration increase. The setting parameters may include the initial growth rate and growth growth rate corresponding to the true specific growth rate, the initial mortality rate and mortality growth rate corresponding to the true specific death rate, the maintenance factor of the metabolite and the true yield factor. The numerical range of each setting parameter may include a maximum value and a minimum value, and the maximum value and the minimum value of each setting parameter may be obtained through the interactive page collection.

[0090] The parameter values ​​of the set parameters, the numerical ranges of the set parameters, and the feeding information during the cell culture process are parameter-fitted by a parameter fitting algorithm to obtain the parameter values ​​of the optimized set parameters, i.e., the target parameter values ​​of the set parameters. Optionally, the parameter fitting algorithm may be, for example, a machine learning algorithm or a deep learning algorithm. Optionally, a program package is obtained in advance, and the program package may include multiple parameter fitting algorithms, for example, the parameter fitting algorithm may include the least squares algorithm of Levenberg-Marquardt.

[0091] The initial prediction model is replaced by the target parameter value based on the set parameters to obtain the target prediction model, thereby improving the prediction performance of the target prediction model.

[0092] Based on the target prediction model corresponding to the target variable, the prediction data of at least one prediction time point of the target variable in the second time period in the current training stage is determined, wherein the prediction time point can be any time point in the second time period and can be set according to the prediction requirements. Exemplarily, at least one prediction time point can be collected through an interactive page, or the time interval of the prediction time points can be collected through an interactive page, and multiple prediction time points in the second time period are determined based on the time interval of the prediction time points. The prediction task is performed based on the target prediction model of the target variable to obtain the prediction data of the target variable at each prediction time point.

[0093] Taking the detection data of the last detection time point in the first time period as the initial data, determine the rate of change of the target variable over time based on the target prediction model corresponding to the target variable, and determine the predicted data of the target variable at at least one prediction time point in the second time period based on the initial data and the rate of change of the target variable over time.

[0094] The detection data of the last detection time point of the first time period includes the live cell density and the concentration value of each metabolite at the last detection time point, which are used as the initial data of the second time period, that is, the live cell density and the concentration value of each metabolite at the starting time of the second time point. The live cell density change rate at the prediction time point is determined based on the target prediction model of the cell growth variable and the live cell density, the live cell density change amount is determined based on the live cell density change rate and the interval duration corresponding to the prediction time point, and the live cell density prediction data corresponding to the prediction time point is determined based on the live cell density at the starting time of the second time point and the live cell density change amount.

[0095] Similarly, for any metabolite, the metabolite concentration change rate at the prediction time point is determined based on the target prediction model of the metabolite variable and the live cell density, the metabolite concentration change amount is determined based on the interval duration corresponding to the prediction time point of the metabolite change concentration rate, and the metabolite concentration prediction data corresponding to the prediction time point is determined based on the metabolite concentration value at the starting time of the second time point and the metabolite concentration change amount.

[0096] When there are multiple prediction time points, the initial data is predicted by the target prediction model of the target variable to obtain the prediction data of the target variable at multiple prediction time points.

[0097] The technical solution of this embodiment is to determine the target prediction model of the target variable in each culture stage in each culture stage of the cell culture process through the process data of the first time period in each culture stage. The target variable in any culture stage is predicted by the target prediction model of the target variable, and the prediction data of the target variable at the prediction time point is determined. This embodiment of the solution provides a target prediction model applicable to each culture stage in the cell culture process, which has strong applicability and realizes the variable prediction in each culture stage of the cell culture process.

[0098] Embodiment 2

[0099] Figure 4 FIG. 1 is a schematic diagram of a cell culture scenario prediction device provided in Example 2 of the present invention. Figure 4 As shown, the method includes:

[0100] The data acquisition module 210 is used to acquire process data in a first time period in the current culture stage, wherein the cell culture process includes at least one culture stage, each culture stage is divided based on a preset operation in the cell culture process, and the current culture stage is any culture stage in the at least one culture stage; the process data in the first time period includes detection data corresponding to multiple detection time points of the target variable in the first time period;

[0101] An initial prediction model determination module 220, configured to determine an initial prediction model of the target variable based on detection data corresponding to a plurality of detection time points of the target variable within the first time period;

[0102] A target prediction model determination module 230 is used to perform fitting processing on the parameter values ​​in the initial prediction model of the target variable to obtain a target prediction model corresponding to the target variable;

[0103] The prediction module 240 is used to determine the prediction data of the target variable at at least one prediction time point in a second time period in the current training stage based on the target prediction model corresponding to the target variable, wherein the second time period is after the first time period.

[0104] The technical solution of this embodiment is to determine the target prediction model of the target variable in each culture stage in each culture stage of the cell culture process through the process data of the first time period in each culture stage. The target variable in any culture stage is predicted by the target prediction model of the target variable, and the prediction data of the target variable at the prediction time point is determined. This embodiment of the solution provides a target prediction model applicable to each culture stage in the cell culture process, which has strong applicability and realizes the variable prediction in each culture stage of the cell culture process.

[0105] Based on the above embodiment, optionally, the target variable includes one or more of a cell growth variable and a metabolite variable;

[0106] The initial prediction model of the cell growth variable is a change rate prediction model of the cell growth variable, wherein the change rate prediction model of the cell growth variable includes a product of a first coefficient group and the cell growth variable, wherein the first coefficient group includes a true specific growth rate and a true specific death rate;

[0107] The initial prediction model of the metabolite variable is a change rate prediction model of the metabolite variable, and the change rate prediction model of the metabolite variable includes the product of a second coefficient group and the cell growth variable, and the second coefficient group includes the true specific growth rate, the maintenance factor of the metabolite variable and the true yield factor of the metabolite variable.

[0108] Optionally, the process data in the first time period includes live cell density and live cell rate corresponding to a plurality of detection time points in the first time period;

[0109] The initial prediction model determination module 220 is also used to: determine the true specific growth rate and the true specific death rate at multiple detection time points in the first time period based on the live cell density and the live cell rate respectively corresponding to the multiple detection time points in the first time period; obtain a first linear graph of the true specific growth rate changing with time based on the true specific growth rate at multiple detection time points in the first time period, determine a first parameter of the true specific growth rate relative to time based on the first linear graph, and determine a variation model of the true specific growth rate relative to time based on the first parameter; obtain a second linear graph of the true specific death rate changing with time based on the true specific death rate at multiple detection time points in the first time period, determine a second parameter of the true specific death rate relative to time based on the second linear graph, and determine a variation model of the true specific death rate relative to time based on the second parameter; determine the initial prediction model of the cell growth variable based on the variation model of the true specific growth rate relative to time and the variation model of the true specific death rate relative to time.

[0110] Optionally, the process data within the first time period further includes: the concentration values ​​of the metabolites corresponding to a plurality of detection time points within the first time period;

[0111] The initial prediction model determination module 220 is also used to: determine the concentration change of the metabolite based on the metabolite concentration values ​​corresponding to multiple detection time points within the first time period; and determine the live cell density change based on the live cell density corresponding to multiple detection time points within the first time period; determine the characterization yield factor of the metabolite variable based on the concentration change of the metabolite and the live cell density change; determine the characterization growth rate based on the live cell density and the interval time of adjacent detection time points; fit a third linear graph based on the reciprocal of the characterization growth rate as the independent variable and the reciprocal of the characterization yield factor as the dependent variable; determine the maintenance factor of the metabolite variable and the true yield factor of the metabolite variable based on the third linear graph; determine the initial prediction model of the metabolite variable based on the change model of the true specific growth rate relative to time, the maintenance factor of the metabolite variable and the true yield factor of the metabolite variable.

[0112] Optionally, the target prediction model determination module 230 is also used to: obtain the parameter value of the set parameter in the initial prediction model, the numerical range of the set parameter and the feeding information in the cell culture process; call the parameter fitting algorithm, and perform parameter fitting based on the parameter value of the set parameter, the numerical range of the set parameter and the feeding information in the cell culture process through the parameter fitting algorithm to obtain the target parameter value of the set parameter; update the initial prediction model based on the target parameter value of the set parameter to obtain the target prediction model corresponding to the target variable.

[0113] Optionally, the prediction module 240 is also used to: take the detection data at the last detection time point in the first time period as initial data, determine the rate of change of the target variable over time based on the target prediction model corresponding to the target variable, and determine the predicted data of the target variable at at least one prediction time point in the second time period based on the initial data and the rate of change of the target variable over time.

[0114] Optionally, the metabolites include one or more of glucose, glutamate, glutamine, ammonium ions, lactic acid and antibody products; each of the metabolite variables corresponds to one of the target prediction models.

[0115] The prediction device for cell culture scenes provided in the embodiment of the present invention can execute the prediction method for cell culture scenes provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0116] Embodiment 3

[0117] Figure 5 1 is a schematic diagram of the structure of an electronic device provided in Embodiment 3 of the present invention. The electronic device 10 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0118] like Figure 5As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0119] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0120] The processor 11 may be a variety of general and / or dedicated processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the prediction method of the cell culture scenario.

[0121] In some embodiments, the prediction method of the cell culture scenario can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the prediction method of the cell culture scenario described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to execute the prediction method of the cell culture scenario in any other appropriate manner (for example, by means of firmware).

[0122] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0123] The computer program for implementing the prediction method of the cell culture scenario of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program can be executed entirely on the machine, partially on the machine, partially on the machine as a stand-alone software package and partially on a remote machine, or entirely on a remote machine or server.

[0124] Embodiment 4

[0125] Embodiment 4 of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to execute a method for predicting a cell culture scenario, the method comprising:

[0126] Obtain process data within a first time period in a current culture stage, wherein the cell culture process includes at least one culture stage, each of the culture stages is divided based on preset operations in the cell culture process, and the current culture stage is any culture stage in the at least one culture stage; the process data within the first time period includes detection data corresponding to a plurality of detection time points of a target variable within the first time period; based on the detection data corresponding to a plurality of detection time points of the target variable within the first time period, determine an initial prediction model of the target variable; perform fitting processing on parameter values ​​in the initial prediction model of the target variable to obtain a target prediction model corresponding to the target variable; based on the target prediction model corresponding to the target variable, determine prediction data of the target variable at at least one prediction time point within a second time period in the current culture stage, wherein the second time period is located after the first time period.

[0127] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0128] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0129] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0130] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0131] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0132] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for predicting a cell culture scenario, characterized in that: include: Acquiring process data in a first time period in a current culture stage, wherein the cell culture process includes at least one culture stage, each culture stage is divided based on a preset operation in the cell culture process, and the current culture stage is any culture stage in the at least one culture stage; the process data in the first time period includes detection data corresponding to a plurality of detection time points of a target variable in the first time period; Determining an initial prediction model for the target variable based on detection data corresponding to a plurality of detection time points of the target variable within the first time period; Performing fitting processing on the parameter values ​​in the initial prediction model of the target variable to obtain a target prediction model corresponding to the target variable; Based on the target prediction model corresponding to the target variable, prediction data of at least one prediction time point of the target variable in a second time period in the current training stage is determined, wherein the second time period is after the first time period.

2. The method according to claim 1, characterized in that The target variables include one or more of a cell growth variable and a metabolite variable; The initial prediction model of the cell growth variable is a change rate prediction model of the cell growth variable, wherein the change rate prediction model of the cell growth variable includes a product of a first coefficient group and the cell growth variable, wherein the first coefficient group includes a true specific growth rate and a true specific death rate; The initial prediction model of the metabolite variable is a change rate prediction model of the metabolite variable, and the change rate prediction model of the metabolite variable includes the product of a second coefficient group and the cell growth variable, and the second coefficient group includes the true specific growth rate, the maintenance factor of the metabolite variable and the true yield factor of the metabolite variable.

3. The method according to claim 2, characterized in that The process data in the first time period includes live cell density and live cell rate corresponding to a plurality of detection time points in the first time period; The determining the initial prediction model of the target variable based on the detection data corresponding to the plurality of detection time points of the target variable within the first time period includes: Determine the true specific growth rate and the true specific death rate at multiple detection time points in the first time period based on the live cell density and the live cell rate respectively corresponding to the multiple detection time points in the first time period; Based on the true specific growth rate at multiple detection time points in the first time period, a first linear graph of the true specific growth rate changing with time is obtained by fitting, based on the first linear graph, a first parameter of the true specific growth rate relative to time is determined, and based on the first parameter, a variation model of the true specific growth rate relative to time is determined; Based on the true specific death rate at multiple detection time points in the first time period, a second linear graph of the true specific death rate changing with time is obtained by fitting, based on the second linear graph, a second parameter of the true specific death rate relative to time is determined, and based on the second parameter, a variation model of the true specific death rate relative to time is determined; An initial prediction model for the cell growth variable is determined based on the variation model of the true specific growth rate with respect to time and the variation model of the true specific death rate with respect to time.

4. The method according to claim 3, characterized in that The process data within the first time period also includes: metabolite concentration values ​​corresponding to a plurality of detection time points within the first time period; The determining the initial prediction model of the target variable based on the detection data corresponding to the plurality of detection time points of the target variable within the first time period includes: Determine the concentration change of the metabolite based on the concentration values ​​of the metabolite corresponding to the multiple detection time points in the first time period; and determine the live cell density change based on the live cell density corresponding to the multiple detection time points in the first time period; Determining a characteristic yield factor of the metabolite variable based on the change in concentration of the metabolite and the change in viable cell density; Determining the growth rate based on the viable cell density and the interval time between adjacent detection time points; Fitting a third linear graph based on the reciprocal of the growth rate as an independent variable and the reciprocal of the yield factor as a dependent variable; determining a maintenance factor for the metabolite variable and a true yield factor for the metabolite variable based on the third linear plot; An initial prediction model for the metabolite variable is determined based on the model of the change of the true specific growth rate with respect to time, the maintenance factor of the metabolite variable and the true yield factor of the metabolite variable.

5. The method according to claim 1, characterized in that The fitting process is performed on the parameter values ​​in the initial prediction model of the target variable to obtain the target prediction model corresponding to the target variable, including: Obtaining parameter values ​​of set parameters in the initial prediction model, numerical ranges of the set parameters, and feeding information during cell culture; Calling a parameter fitting algorithm, and performing parameter fitting based on the parameter value of the set parameter, the numerical range of the set parameter, and the feeding information during the cell culture process through the parameter fitting algorithm to obtain a target parameter value of the set parameter; The initial prediction model is updated based on the target parameter value of the set parameter to obtain a target prediction model corresponding to the target variable.

6. The method according to claim 2, characterized in that The determining, based on the target prediction model corresponding to the target variable, prediction data of at least one prediction time point of the target variable in the second time period in the current training stage comprises: Taking the detection data of the last detection time point in the first time period as the initial data, determine the rate of change of the target variable over time based on the target prediction model corresponding to the target variable, and determine the predicted data of the target variable at at least one prediction time point in the second time period based on the initial data and the rate of change of the target variable over time.

7. The method according to claim 2, characterized in that The metabolites include one or more of glucose, glutamate, glutamine, ammonium ions, lactic acid, and antibody products; Each of the metabolite variables corresponds to a target prediction model.

8. A prediction device for a cell culture scenario, characterized in that: include: A data acquisition module, configured to acquire process data within a first time period in a current culture stage, wherein the cell culture process includes at least one culture stage, each culture stage is divided based on a preset operation in the cell culture process, and the current culture stage is any culture stage in the at least one culture stage; the process data within the first time period includes detection data corresponding to a plurality of detection time points of a target variable within the first time period; An initial prediction model determination module, used to determine an initial prediction model of the target variable based on detection data corresponding to a plurality of detection time points of the target variable within the first time period; A target prediction model determination module is used to perform fitting processing on the parameter values ​​in the initial prediction model of the target variable to obtain the target prediction model corresponding to the target variable; A prediction module is used to determine prediction data of the target variable at at least one prediction time point in a second time period in the current training stage based on a target prediction model corresponding to the target variable, wherein the second time period is after the first time period.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can perform the method for predicting a cell culture scenario according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for predicting a cell culture scenario according to any one of claims 1 to 7 when executed.

Images