Exosome preparation method, device, terminal and medium based on digital twin
By using digital twin technology to predict the state of exosomes and adjust culture parameters, the problems of poor consistency and insufficient reliability in traditional exosome preparation are solved, and more efficient control of the exosome culture process is achieved.
Patent Information
- Application Number
- CN202611337768.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-08-31
- Publication Date
- 2026-11-17
AI Technical Summary
Traditional exosome preparation processes are highly dependent on operator experience, have poor batch-to-batch consistency, and lack real-time perception and prediction capabilities of the culture process, resulting in large quality fluctuations, resource waste, and insufficient reliability.
Digital twin technology is used to combine cell culture process parameters and environmental information for state prediction. The future state of exosomes is predicted through a digital twin model, and the culture process parameters are adjusted based on the prediction results to improve the perception capability and reliability of the culture process.
By predicting the state and adjusting parameters, the reliability and batch consistency of exosome culture were improved, resource waste was reduced, and the accuracy and efficiency of the preparation process were enhanced.
Smart Images

Figure CN123107918A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of interdisciplinary technology of biotechnology and artificial intelligence, specifically to a method, device, terminal and medium for preparing exosomes based on digital twins. Background Technology
[0002] Exosomes, as important mediators of intercellular communication, have shown great potential for application in fields such as skin care. Exosomes derived from mesenchymal stem cells (MSCs) are rich in bioactive molecules such as growth factors, mRNA (messenger ribonucleic acid), miRNA (micro ribonucleic acid), and proteins, which can promote tissue repair, regulate immune responses, reduce inflammation, and delay cellular aging. However, the preparation and quality control of exosomes are the core bottlenecks restricting their commercialization.
[0003] Traditional exosome preparation processes heavily rely on operator experience and subjective judgment, resulting in poor batch-to-batch consistency and significant fluctuations in critical quality attributes (CQA). Even minute environmental changes during cell culture (temperature, CO2 concentration, nutrient consumption, and metabolite accumulation) can significantly impact the final exosome yield, particle size distribution, surface marker expression, and bioactivity. Existing preparation systems lack the ability to sense and predict the culture process, often only identifying process deviations after product quality testing fails, leading to resource waste and batch rejection. Therefore, their reliability in exosome culture is insufficient. Summary of the Invention
[0004] This application provides a method, apparatus, terminal, and medium for preparing exosomes based on digital twins. It can combine the current culture process parameters and current culture environment information of exosomes to predict their state, adjust the culture process parameters based on the predicted state, and use the adjusted culture process parameters for culture processing. This can improve the perception of the culture process and enhance the reliability of exosome culture.
[0005] A first aspect of this application provides a method for preparing exosomes based on digital twins, characterized in that the method includes: Obtain the current culture process parameters of the exosomes to be predicted; Based on the current culture process parameters and the current culture environment information, a prediction process is performed to obtain the predicted state information of the exosomes to be predicted in the next time period; The current culture process parameters are adjusted based on the predicted state information to obtain the target culture process parameters; The exosomes to be predicted are cultured using the target culture process parameters.
[0006] In one possible implementation, the step of performing prediction processing based on the current culture process parameters and the current culture environment information to obtain the predicted state information of the exosome to be predicted in the next time period includes: The current state information of the exosomes to be predicted is determined based on the current culture process parameters. The specific consumption rate of glucose and the specific production rate of lactic acid are determined based on the current status information and the current culture environment information. Based on the current state information, the specific consumption rate of glucose, and the specific production rate of lactate, a prediction process is performed to obtain the predicted state information of the exosomes to be predicted in the next time period.
[0007] In one possible implementation, the prediction process based on the current state information, the specific consumption rate of glucose, and the specific production rate of lactate to obtain the predicted state information of the exosome in the next time period includes: Obtain a digital twin model of the cell culture process; Based on the digital twin model of the cell culture process, the current state information, the specific consumption rate of glucose, and the specific production rate of lactate are used for prediction to obtain the predicted state information of the exosomes to be predicted in the next time period.
[0008] In one possible implementation, the digital twin model of the cell culture process includes a cell growth kinetics model, a metabolite kinetics model, an exosome secretion kinetics model, and a culture environment-cell response coupling model. The prediction process, based on the digital twin model of the cell culture process, uses current state information, the specific consumption rate of glucose, and the specific production rate of lactate to obtain the predicted state information of the exosome to be predicted in the next time period, including: Based on the cell growth kinetics model and the cell density information in the current state information, a prediction process is performed to obtain the predicted exosome concentration in the next time period. Based on the metabolite kinetic model and the specific consumption rate of glucose and the specific production rate of lactate, the glucose concentration and lactate concentration of the exosome to be predicted in the next time period are obtained. Based on the exosome secretion dynamics model and cell density information in the current state information, the cell stress level of the exosome to be predicted in the next time period is obtained through prediction processing. Based on the culture environment-cell response coupling model and the current state information, prediction processing is performed to obtain the environment coupling response information of the exosome to be predicted in the next time period.
[0009] In one possible implementation, adjusting the current culture process parameters based on the predicted state information to obtain the target culture process parameters includes: The target correction parameters are determined based on the predicted state information and the preset exosome growth constraint information. The target culture process parameters are obtained by adjusting the current culture process parameters using the target correction parameters.
[0010] In one possible implementation, determining the target correction parameters based on the predicted state information and preset exosome growth constraint information includes: Extract the first lactate content information from the predicted state information, and extract the preset lactate content information from the preset exosome growth constraint information; Obtain the first offset between the first lactic acid content information and the preset lactic acid content information; Extract the first cell viability information from the predicted state information, and extract the preset cell viability information from the preset exosome growth constraint information; Obtain the second offset between the first cell viability information and the preset cell viability information; The target correction parameters are determined based on the first offset and the second offset.
[0011] A second aspect of this application provides an exosome preparation apparatus based on digital twins, the apparatus comprising: The acquisition unit is used to acquire the current culture process parameters of the exosomes to be predicted; The prediction unit is used to perform prediction processing based on the current culture process parameters and the current culture environment information to obtain the prediction status information of the exosome to be predicted in the next time period. The adjustment unit is used to adjust the current culture process parameters according to the predicted state information to obtain the target culture process parameters; The processing unit is used to culture the exosomes to be predicted using the target culture process parameters.
[0012] In one possible implementation, the prediction unit is specifically used for: The current state information of the exosomes to be predicted is determined based on the current culture process parameters. The specific consumption rate of glucose and the specific production rate of lactic acid are determined based on the current status information and the current culture environment information. Based on the current state information, the specific consumption rate of glucose, and the specific production rate of lactate, a prediction process is performed to obtain the predicted state information of the exosomes to be predicted in the next time period.
[0013] In one possible implementation, the prediction unit is specifically used to obtain the predicted state information of the exosome in the next time period by performing prediction processing based on the current state information, the specific consumption rate of glucose, and the specific production rate of lactate. Obtain a digital twin model of the cell culture process; Based on the digital twin model of the cell culture process, the current state information, the specific consumption rate of glucose, and the specific production rate of lactate are used for prediction to obtain the predicted state information of the exosomes to be predicted in the next time period.
[0014] In one possible implementation, the digital twin model of the cell culture process includes a cell growth kinetics model, a metabolite kinetics model, an exosome secretion kinetics model, and a culture environment-cell response coupling model. Specifically, regarding the prediction process based on the digital twin model of the cell culture process, using current state information, the specific consumption rate of glucose, and the specific production rate of lactate to obtain the predicted state information of the exosome in the next time period, the prediction unit is used for: Based on the cell growth kinetics model and the cell density information in the current state information, a prediction process is performed to obtain the predicted exosome concentration in the next time period. Based on the metabolite kinetic model and the specific consumption rate of glucose and the specific production rate of lactate, the glucose concentration and lactate concentration of the exosome to be predicted in the next time period are obtained. Based on the exosome secretion dynamics model and cell density information in the current state information, the cell stress level of the exosome to be predicted in the next time period is obtained through prediction processing. Based on the culture environment-cell response coupling model and the current state information, prediction processing is performed to obtain the environment coupling response information of the exosome to be predicted in the next time period.
[0015] In one possible implementation, the adjustment unit is specifically used for: The target correction parameters are determined based on the predicted state information and the preset exosome growth constraint information. The target culture process parameters are obtained by adjusting the current culture process parameters using the target correction parameters.
[0016] In one possible implementation, the adjustment unit is specifically used for determining the target correction parameters based on the predicted state information and the preset exosome growth constraint information, in which the adjustment unit is specifically configured to: Extract the first lactate content information from the predicted state information, and extract the preset lactate content information from the preset exosome growth constraint information; Obtain the first offset between the first lactic acid content information and the preset lactic acid content information; Extract the first cell viability information from the predicted state information, and extract the preset cell viability information from the preset exosome growth constraint information; Obtain the second offset between the first cell viability information and the preset cell viability information; The target correction parameters are determined based on the first offset and the second offset.
[0017] A third aspect of this application provides a terminal including a processor, an input device, an output device, and a memory, wherein the processor, input device, output device, and memory are interconnected, wherein the memory is used to store a computer program, the computer program including program instructions, and the processor is configured to invoke the program instructions to execute the step instructions as described in the first aspect of this application.
[0018] A fourth aspect of this application provides a computer-readable storage medium storing a computer program for electronic data interchange, wherein the computer program causes a computer to perform some or all of the steps described in the first aspect of this application.
[0019] A fifth aspect of this application provides a computer program product, wherein the computer program product includes a non-transitory computer-readable storage medium storing a computer program operable to cause a computer to perform some or all of the steps described in the first aspect of this application. The computer program product may be a software installation package.
[0020] Implementing the embodiments of this application has at least the following beneficial effects: By acquiring the current culture process parameters of the exosomes to be predicted, and performing prediction processing based on the current culture process parameters and the current culture environment information, the predicted state information of the exosomes to be predicted in the next time period is obtained. The current culture process parameters are adjusted based on the predicted state information to obtain the target culture process parameters. The exosomes to be predicted are then cultured using the target culture process parameters. Therefore, by combining the current culture process parameters and the current culture environment information of the exosomes to predict the state, and adjusting the culture process parameters based on the predicted state, and then using the adjusted culture process parameters for culture, the ability to perceive the culture process can be improved, thus enhancing the reliability of exosome culture. Attached Figure Description
[0021] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0022] Figure 1 This application provides a schematic flowchart of a method for preparing exosomes based on digital twins. Figure 2 This is a schematic diagram of the structure of a terminal provided in an embodiment of this application; Figure 3 This application provides a schematic diagram of the structure of an exosome preparation device based on digital twins. Detailed Implementation
[0023] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.
[0024] The terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or apparatuses.
[0025] In this application, the reference to "embodiment" means that a specific feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a mutually exclusive, independent, or alternative embodiment. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described in this application can be combined with other embodiments.
[0026] To better understand the exosome preparation method based on digital twins provided in this application, a brief introduction to existing digital twin-based exosome preparation methods is given below. In existing methods, traditional exosome preparation processes heavily rely on operator experience and subjective judgment, resulting in poor batch-to-batch consistency and large fluctuations in critical quality attributes (CQA). Even minor environmental changes during cell culture (temperature, CO2 concentration, nutrient consumption, and metabolite accumulation) significantly impact the final exosome yield, particle size distribution, surface marker expression, and bioactivity. Existing preparation systems lack real-time sensing and prediction capabilities for the culture process, often only discovering process deviations after product quality testing fails, leading to resource waste and batch rejection. Therefore, their reliability in exosome culture is insufficient.
[0027] Please see Figure 1 , Figure 1 This application provides a schematic flowchart of a method for preparing exosomes based on digital twins. For example... Figure 1 As shown, the method includes: 101. Obtain the current culture process parameters of the exosomes to be predicted.
[0028] The current culture process parameters may include temperature, dissolved oxygen, stirring speed, replenishment strategy, cell count, metabolites, exosome concentration, online Raman spectroscopy, etc., as well as the current culture environment information, including pH value, CO2, etc.
[0029] Specifically, when obtaining cell counts, metabolites, and exosome concentrations, the above parameters can be obtained through relevant cell technology sensors.
[0030] Exosomes to be predicted can be understood as exosomes currently in culture. Their status needs to be predicted periodically, and the relevant culture process parameters should be adjusted based on the prediction results to optimize the overall culture effect.
[0031] Specifically, a bioreactor sensor array is used for relevant data acquisition, such as collecting process parameters like temperature, pH, dissolved oxygen, CO2 partial pressure, stirring speed, and foam level; an online Raman spectroscopy submodule is used to monitor in situ concentration changes of key metabolites such as glucose, lactic acid, glutamine, and amino acids using Raman spectroscopy; an impedance sensing submodule is used to monitor cell density, cell viability, and cell morphology changes in real time using a microelectrode array; and an offline detection data interface is used to receive cell count, metabolite detection, exosome NTA (Nanoparticle Tracking Analysis) analysis, and flow cytometry results from the laboratory.
[0032] 102. Based on the current culture process parameters and the current culture environment information, perform prediction processing to obtain the predicted status information of the exosomes to be predicted in the next time period.
[0033] In this process, the current state information of the exosome to be predicted can be determined by combining the culture process parameters. Then, the current state information and the current culture environment information can be combined to perform prediction processing to obtain the predicted state information of the exosome to be predicted in the next time period.
[0034] The next time period can be understood as a preset time cycle following the current moment. When culturing exosomes, it is necessary to periodically detect and predict the state of the exosomes in order to dynamically adjust the relevant culture process parameters.
[0035] Predicted status information may include cell concentration, exosome density, lactate content, and glucose content. Since exosome culture needs to be completed after reaching a preset density, lactate and glucose levels directly affect cell viability during the culture process. Therefore, dynamic adjustments are necessary to ensure cells grow in the optimal culture environment, thereby improving overall culture efficiency and accuracy.
[0036] 103. Adjust the current culture process parameters according to the predicted state information to obtain the target culture process parameters.
[0037] When using predicted state information to adjust culture process parameters, the specific steps can be as follows: determine the correction parameters based on preset state information and preset exosome growth constraint information, use the correction parameters for correction processing, and obtain the target culture process parameters.
[0038] The preset exosome growth constraint information can be: preset exosome concentration, preset lactate content, preset glucose content, exosome concentration, etc. For example, the exosome concentration should reach a preset target value, which is set according to the culture stage.
[0039] Target culture process parameters may include temperature, dissolved oxygen, stirring speed, and liquid replenishment strategy. By adjusting the target culture process parameters, the exosome culture process can be directly intervened to improve fit and thus improve accuracy.
[0040] Although the current culture process parameters include cell count, metabolites, exosome concentration, and online Raman spectroscopy, these data are parameters for characterizing the state of exosomes and cannot be actively adjusted. Therefore, when generating target correction parameters, no adjustment information related to the above parameters will be generated.
[0041] 104. The exosomes to be predicted are cultured using the target culture process parameters.
[0042] Specifically, exosomes can be cultured using target culture process parameters, such as stirring at the stirring speed specified in the target culture process parameters and setting a culture temperature consistent with the target culture process parameters.
[0043] In this example, by obtaining the current culture process parameters of the exosome to be predicted, and performing prediction processing based on the current culture process parameters and the current culture environment information, the predicted state information of the exosome to be predicted in the next time period is obtained. The current culture process parameters are adjusted based on the predicted state information to obtain the target culture process parameters. The exosome to be predicted is then cultured using the target culture process parameters. Therefore, by combining the current culture process parameters and the current culture environment information of the exosome, the state prediction can be performed, and the culture process parameters can be adjusted using the predicted state. The adjusted culture process parameters can then be used for culture processing, which can improve the perception of the culture process and enhance the reliability of exosome culture.
[0044] In one possible implementation, a method for predicting the state information of the exosome to be predicted in the next time period by performing predictive processing based on the current culture process parameters and the current culture environment information includes: A1. Determine the current state information of the exosomes to be predicted based on the current culture process parameters; A2. Determine the specific consumption rate of glucose and the specific production rate of lactic acid based on the current status information and the current culture environment information; A3. Based on the current status information, the specific consumption rate of glucose, and the specific production rate of lactate, a prediction process is performed to obtain the predicted status information of the exosomes to be predicted in the next time period.
[0045] The current culture process parameters may include temperature, dissolved oxygen, stirring speed, replenishment strategy, cell count, metabolites, exosome concentration, online Raman spectroscopy, etc., and the current culture environment information includes pH value, CO2, etc.
[0046] Specifically, when determining the current state information, cell concentration can be determined through cell counting. Based on cell density and current culture environment information, the specific rate of glucose consumption and the specific rate of lactate production can be determined. Specifically, the specific rate of glucose consumption and the specific rate of lactate production can be determined using the following formula: dGlu / dt = -qs·X; dLac / dt=qL·X; Where qs and qL are the specific consumption rate and specific production rate, respectively, X is the cell concentration, dGlu / dt is the rate of change of glucose concentration over time (consumption rate), and dLac / dt is the rate of change of lactate concentration over time (growth rate).
[0047] Specifically, the predictive processing can be performed using a digital twin model of the cell culture process. This digital twin model includes a cell growth kinetics model, a metabolite kinetics model, an exosome secretion kinetics model, and a culture environment-cell response coupling model. Specifically, the cell growth kinetics model predicts exosome concentration, the metabolite kinetics model predicts glucose and lactate concentrations, and the exosome secretion kinetics model predicts cell stress levels. When cell stress levels exceed a threshold, exosome secretion is activated. Based on the culture environment-cell response coupling model and the current state information, the environmental coupling response information of the exosome to be predicted in the next time period is obtained.
[0048] A digital twin model of the cell culture process is also provided, constructed in the following manner: (1) Data collection: Collect process data of historical culture batches, including temperature, pH, dissolved oxygen, CO2 partial pressure, stirring speed, cell density, glucose concentration, lactate concentration, exosome concentration and cell viability data. The data collection interval is a preset time period to form a time series dataset. (2) Model framework construction: The digital twin model of the cell culture process includes four sub-models: cell growth kinetics model, metabolite kinetics model, exosome secretion kinetics model and culture environment-cell response coupling model; (3) Parameter identification: The dynamic parameters of the above four sub-models are estimated by nonlinear least squares method to minimize the root mean square error between the model prediction and the historical measured values. (4) Model validation: Leave-one-out cross-validation is used. The historical data is divided into training set and validation set. When the prediction error on the validation set is less than the preset threshold, the model is validated. (5) Model update: After the new batch of culture data is generated, the model parameters are updated in a rolling manner using the Bayesian online learning method so that the model can continuously adapt to the changes in the actual culture process.
[0049] In one possible implementation, a method for predicting the state information of the exosome in the next time period by performing predictive processing based on the current state information, the specific consumption rate of glucose, and the specific production rate of lactate includes: B1. Obtain a digital twin model of the cell culture process; B2. Based on the digital twin model of the cell culture process, the current state information, the specific consumption rate of glucose, and the specific production rate of lactate are used for prediction processing to obtain the predicted state information of the exosomes to be predicted in the next time period.
[0050] Among them, the digital twin model of the cell culture process includes a cell growth kinetic model, a metabolite kinetic model, an exosome secretion kinetic model, and a culture environment-cell response coupling model, which are pre-constructed digital twin models.
[0051] It is important to note that the four sub-models mentioned above do not operate independently, but are coupled and linked through state variables: the cell density X output by the cell growth kinetics model simultaneously serves as the driving variable for the substrate consumption rate in the metabolite kinetics model and the secretion rate in the exosome secretion kinetics model; the lactate concentration output by the metabolite kinetics model, after being corrected by the culture environment-cell response coupling model, feeds back to correct the value of the environmental condition correction function f(T, pH, DO) in the cell growth kinetics model; and the trigger threshold of the cell stress level H in the exosome secretion kinetics model is dynamically adjusted based on the environmental coupling response information output by the culture environment-cell response coupling model. Therefore, any perturbation of the current culture process parameters propagates along the four dimensions of 'growth—metabolism—secretion—environment,' ensuring that the predicted state information reflects the overall dynamics of the culture system, rather than the independent extrapolation of a single variable. This coupling structure, unlike the independent application of classical equations, is key to improving the prediction accuracy and batch consistency of the exosome culture process.
[0052] Specifically, the cell growth kinetics model uses a modified Logistic equation to describe the change in cell density over time: dX / dt = mumax·X·(1-X / Xmax)·f(T,pH,DO), where mumax is the maximum specific growth rate, Xmax is the maximum cell density, f(T,pH,DO) is the environmental condition correction function, X is the cell density, T is the temperature, pH is the pH value, DO is the oxygen solubility, and dX / dt is the change in cell density over time. Metabolite kinetic model: Based on the Monod equation (a kinetic equation describing the relationship between microbial growth and substrate concentration), glucose consumption and lactate production are described: dGlu / dt = -qs·X, dLac / dt = qL·X, where qs and qL are the specific consumption rate and specific production rate, respectively, which are related to environmental conditions and cell state. The consumption amount can be determined according to the above formula, and then the actual predicted amount can be calculated by combining the glucose concentration and lactate concentration in the current culture process parameters (using a common variable calculation method).
[0053] Exosome secretion kinetics model: An inducible secretion model is adopted, dE / dt=k1·X·H(cellular stress level)-k2·E, where H is the Heaviside step function, which activates exosome secretion when the cellular stress level exceeds the threshold, dE / dt is the rate of change of secretion concentration over time, k1 is the inducible secretion rate constant, k2 is the effector degradation / clearance rate constant, E is the secretion concentration, and X is the cell concentration.
[0054] Predictive state information includes cell concentration, specific consumption rate and specific production rate, and cellular stress level. In one possible implementation, a method for predicting the state information of the exosome to be predicted in the next time period by using current state information, specific glucose consumption rate, and specific lactate production rate based on a digital twin model of the cell culture process includes: C1. Based on the cell growth kinetics model and the cell density information in the current state information, perform prediction processing to obtain the predicted exosome concentration in the next time period; C2. Based on the metabolite kinetic model and the specific consumption rate of glucose and the specific production rate of lactate, the glucose concentration and lactate concentration of the exosome to be predicted in the next time period are obtained. C3. Based on the exosome secretion dynamics model and the cell density information in the current state information, predictive processing is performed to obtain the cell stress level of the exosome to be predicted in the next time period; C4. Based on the culture environment-cell response coupling model and the current state information, perform prediction processing to obtain the environment coupling response information of the exosome to be predicted in the next time period.
[0055] Specifically, the calculation methods of the relevant models in the aforementioned embodiments can be used to calculate the parameters to obtain the predicted exosome concentration, glucose concentration and lactate concentration in the next time period, and cellular stress level in the next time period.
[0056] In one possible implementation, a method for adjusting current culture process parameters based on the predicted state information to obtain target culture process parameters includes: D1. Determine the target correction parameters based on the predicted state information and the preset exosome growth constraint information; D2. Adjust the current culture process parameters using the target correction parameters to obtain the target culture process parameters.
[0057] The preset exosome growth constraint information can be: preset exosome concentration, preset lactate content, preset glucose content, etc.
[0058] Specifically, the method for determining the target correction parameters based on the predicted state information and preset exosome growth constraint information includes: E1. Extract the first lactate content information from the predicted state information, and extract the preset lactate content information from the preset exosome growth constraint information; E2. Obtain the first offset between the first lactic acid content information and the preset lactic acid content information; E3. Extract the first cell viability information from the predicted state information, and extract the preset cell viability information from the preset exosome growth constraint information; E4. Obtain the second offset between the first cell viability information and the preset cell viability information; E5. Determine the target correction parameters based on the first offset and the second offset.
[0059] The first offset can be understood as the difference between the first lactic acid content in the first lactic acid content information and the preset lactic acid content information (the endpoint of the content range). For example, if the first lactic acid content is greater than the value corresponding to the right endpoint of the range, it indicates that the lactic acid content exceeds the standard, and the lactic acid content needs to be reduced.
[0060] If the cell viability corresponding to the cell viability information is less than the left endpoint of the preset cell viability information interval, it indicates that the cell viability is insufficient and needs to be increased. If the cell viability corresponding to the cell viability information is greater than or equal to the right endpoint of the preset cell viability information interval, it indicates that the cell viability is high and needs to be reduced or controlled.
[0061] Specifically, the preset multiples of the first and second offsets can be determined as values in the target correction parameters. For example, if the first offset indicates excessive lactic acid, then the lactic acid content needs to be reduced by the preset multiple of the first offset.
[0062] In one specific implementation, a quality feedback closed-loop optimization is also provided: In vitro quality attribute detection data (including exosome concentration, particle size distribution, and surface marker expression levels) of exosome products from different culture batches are summarized, and a causal association model (such as a causal forest model) is used to analyze the contribution of each quality attribute to the preset quality target. For example, the analysis found that exosome concentration contributes significantly to the quality target, particle size contributes moderately (smaller particle size is better than larger particle size), and surface marker expression level contributes relatively little. Based on the causal analysis results, the process optimization module adjusts the optimization target of the digital twin model: increasing the weight of exosome concentration by a preset percentage and adding constraints on particle size control (target particle size ≤ preset particle size). After the optimization target adjustment, subsequent culture batches show a significant increase in average exosome concentration, a significant decrease in average particle size, and improved batch-to-batch consistency. For examples consistent with the above embodiments, please refer to... Figure 2 , Figure 2 This is a schematic diagram of the structure of a terminal provided in an embodiment of this application, such as... Figure 2 As shown, it includes a processor, an input device, an output device, and a memory, which are interconnected. The memory is used to store a computer program, which includes program instructions. The processor is configured to call the program instructions. The program includes instructions for performing the following steps. Obtain the current culture process parameters of the exosomes to be predicted; Based on the current culture process parameters and the current culture environment information, a prediction process is performed to obtain the predicted state information of the exosomes to be predicted in the next time period; The current culture process parameters are adjusted based on the predicted state information to obtain the target culture process parameters; The exosomes to be predicted are cultured using the target culture process parameters.
[0063] The above mainly describes the solutions of the embodiments of this application from the perspective of the method execution process. It is understood that, in order to achieve the above functions, the terminal includes the corresponding hardware structure and / or software modules for executing each function. Those skilled in the art should readily recognize that, in conjunction with the units and algorithm steps of the various examples described in the embodiments provided herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.
[0064] This application embodiment can divide the terminal into functional units according to the above method example. For example, each function can be divided into a separate functional unit, or two or more functions can be integrated into one processing unit. The integrated unit can be implemented in hardware or as a software functional unit. It should be noted that the unit division in this application embodiment is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods.
[0065] For those consistent with the above, please refer to Figure 3 , Figure 3 This application provides a schematic diagram of an exosome preparation device based on digital twins. For example... Figure 3 As shown, the device includes: Acquisition unit 301 is used to acquire the current culture process parameters of the exosomes to be predicted; The prediction unit 302 is used to perform prediction processing based on the current culture process parameters and the current culture environment information to obtain the prediction status information of the exosome to be predicted in the next time period. The adjustment unit 303 is used to adjust the current culture process parameters according to the predicted state information to obtain the target culture process parameters; Processing unit 304 is used to culture the exosomes to be predicted using the target culture process parameters.
[0066] In one possible implementation, the prediction unit 302 is specifically used for: The current state information of the exosomes to be predicted is determined based on the current culture process parameters. The specific consumption rate of glucose and the specific production rate of lactic acid are determined based on the current status information and the current culture environment information. Based on the current state information, the specific consumption rate of glucose, and the specific production rate of lactate, a prediction process is performed to obtain the predicted state information of the exosomes to be predicted in the next time period.
[0067] In one possible implementation, the prediction unit 302 is specifically used to: perform prediction processing based on the current state information, the specific consumption rate of glucose, and the specific production rate of lactate to obtain the predicted state information of the exosome in the next time period; Obtain a digital twin model of the cell culture process; Based on the digital twin model of the cell culture process, the current state information, the specific consumption rate of glucose, and the specific production rate of lactate are used for prediction to obtain the predicted state information of the exosomes to be predicted in the next time period.
[0068] In one possible implementation, the digital twin model of the cell culture process includes a cell growth kinetics model, a metabolite kinetics model, an exosome secretion kinetics model, and a culture environment-cell response coupling model. Regarding the prediction process based on the digital twin model of the cell culture process, using current state information, the specific consumption rate of glucose, and the specific production rate of lactate to obtain the predicted state information of the exosome in the next time period, the prediction unit 302 is specifically used for: Based on the cell growth kinetics model and the cell density information in the current state information, a prediction process is performed to obtain the predicted exosome concentration in the next time period. Based on the metabolite kinetic model and the specific consumption rate of glucose and the specific production rate of lactate, the glucose concentration and lactate concentration of the exosome to be predicted in the next time period are obtained. Based on the exosome secretion dynamics model and cell density information in the current state information, the cell stress level of the exosome to be predicted in the next time period is obtained through prediction processing. Based on the culture environment-cell response coupling model and the current state information, prediction processing is performed to obtain the environment coupling response information of the exosome to be predicted in the next time period.
[0069] In one possible implementation, the adjustment unit 303 is specifically used for: The target correction parameters are determined based on the predicted state information and the preset exosome growth constraint information. The target culture process parameters are obtained by adjusting the current culture process parameters using the target correction parameters.
[0070] In one possible implementation, in determining the target correction parameters based on the predicted state information and the preset exosome growth constraint information, the adjustment unit 303 is specifically used for: Extract the first lactate content information from the predicted state information, and extract the preset lactate content information from the preset exosome growth constraint information; Obtain the first offset between the first lactic acid content information and the preset lactic acid content information; Extract the first cell viability information from the predicted state information, and extract the preset cell viability information from the preset exosome growth constraint information; Obtain the second offset between the first cell viability information and the preset cell viability information; The target correction parameters are determined based on the first offset and the second offset.
[0071] This application also provides a computer storage medium storing a computer program for electronic data interchange, which causes a computer to perform some or all of the steps of any of the digital twin-based exosome preparation methods described in the above method embodiments.
[0072] This application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program that causes a computer to perform some or all of the steps of any of the digital twin-based exosome preparation methods described in the above method embodiments.
[0073] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.
[0074] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.
[0075] In the several embodiments provided in this application, it should be understood that the disclosed apparatus can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical or other forms.
[0076] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.
[0077] Furthermore, the functional units in the various embodiments of the application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software program module.
[0078] If the integrated unit is implemented as a software program module and sold or used as an independent product, it can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned memory includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.
[0079] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage device, which may include: a flash drive, a read-only memory, a random access memory, a magnetic disk, or an optical disk, etc.
[0080] The embodiments of this application have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this application. The description of the above embodiments is only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.
Claims
1. A method for preparing exosomes based on digital twins, characterized in that, The method includes: Obtain the current culture process parameters of the exosomes to be predicted; Based on the current culture process parameters and current culture environment information, a prediction process is performed to obtain the predicted state information of the exosomes to be predicted in the next time period; The current culture process parameters are adjusted based on the predicted state information to obtain the target culture process parameters; The exosomes to be predicted are cultured using the target culture process parameters.
2. The method for preparing exosomes based on digital twins according to claim 1, characterized in that, The step of performing prediction processing based on the current culture process parameters and the current culture environment information to obtain the predicted state information of the exosomes to be predicted in the next time period includes: The current state information of the exosomes to be predicted is determined based on the current culture process parameters. The specific consumption rate of glucose and the specific production rate of lactic acid are determined based on the current status information and the current culture environment information. Based on the current state information, the specific consumption rate of glucose, and the specific production rate of lactate, a prediction process is performed to obtain the predicted state information of the exosomes to be predicted in the next time period.
3. The method for preparing exosomes based on digital twins according to claim 2, characterized in that, The prediction process, based on the current state information, the specific consumption rate of glucose, and the specific production rate of lactate, yields the predicted state information of the exosomes to be predicted in the next time period, including: Obtain a digital twin model of the cell culture process; Based on the digital twin model of the cell culture process, the current state information, the specific consumption rate of glucose, and the specific production rate of lactate are used for prediction to obtain the predicted state information of the exosomes to be predicted in the next time period.
4. The method for preparing exosomes based on digital twins according to claim 3, characterized in that, The digital twin model of the cell culture process includes a cell growth kinetics model, a metabolite kinetics model, an exosome secretion kinetics model, and a culture environment-cell response coupling model. The process involves using the current state information, the specific glucose consumption rate, and the specific lactate production rate from the digital twin model to predict the state information of the exosomes to be predicted in the next time period, including: Based on the cell growth kinetics model and the cell density information in the current state information, a prediction process is performed to obtain the predicted exosome concentration in the next time period. Based on the metabolite kinetic model and the specific consumption rate of glucose and the specific production rate of lactate, the glucose concentration and lactate concentration of the exosome to be predicted in the next time period are obtained. Based on the exosome secretion dynamics model and cell density information in the current state information, the cell stress level of the exosome to be predicted in the next time period is obtained through prediction processing. Based on the culture environment-cell response coupling model and the current state information, prediction processing is performed to obtain the environment coupling response information of the exosome to be predicted in the next time period.
5. The method for preparing exosomes based on digital twins according to any one of claims 1-4, characterized in that, The step of adjusting the current culture process parameters based on the predicted state information to obtain the target culture process parameters includes: The target correction parameters are determined based on the predicted state information and the preset exosome growth constraint information. The target culture process parameters are obtained by adjusting the current culture process parameters using the target correction parameters.
6. The method for preparing exosomes based on digital twins according to claim 5, characterized in that, The step of determining the target correction parameters based on the predicted state information and the preset exosome growth constraint information includes: Extract the first lactate content information from the predicted state information, and extract the preset lactate content information from the preset exosome growth constraint information; Obtain the first offset between the first lactic acid content information and the preset lactic acid content information; Extract the first cell viability information from the predicted state information, and extract the preset cell viability information from the preset exosome growth constraint information; Obtain the second offset between the first cell viability information and the preset cell viability information; The target correction parameters are determined based on the first offset and the second offset.
7. An exosome preparation device based on digital twins, characterized in that, The device includes: The acquisition unit is used to acquire the current culture process parameters of the exosomes to be predicted; The prediction unit is used to perform prediction processing based on the current culture process parameters and the current culture environment information to obtain the prediction status information of the exosome to be predicted in the next time period. The adjustment unit is used to adjust the current culture process parameters according to the predicted state information to obtain the target culture process parameters; The processing unit is used to culture the exosomes to be predicted using the target culture process parameters.
8. The exosome preparation apparatus based on digital twins according to claim 7, characterized in that, The prediction unit is specifically used for: The current state information of the exosomes to be predicted is determined based on the current culture process parameters. The specific consumption rate of glucose and the specific production rate of lactic acid are determined based on the current status information and the current culture environment information. Based on the current state information, the specific consumption rate of glucose, and the specific production rate of lactate, a prediction process is performed to obtain the predicted state information of the exosomes to be predicted in the next time period.
9. A terminal, characterized in that, The device includes a processor, an input device, an output device, and a memory, which are interconnected. The memory is used to store a computer program, which includes program instructions. The processor is configured to invoke the program instructions to execute the exosome preparation method based on digital twins as described in any one of claims 1-5.
10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, the computer program including program instructions that, when executed by a processor, cause the processor to perform the exosome preparation method based on digital twins as described in any one of claims 1-5.
