CN-121997609-A - Cell culture monitoring data management system and method

CN121997609ACN 121997609 ACN121997609 ACN 121997609ACN-121997609-A

Abstract

The invention relates to the technical field of cell culture monitoring data management, and particularly discloses a cell culture monitoring data management system and method, wherein a dynamic digital twin model is generated by constructing an initial digital twin model and combining real-time monitoring data, so that three-dimensional visual monitoring of a culture process is realized; the invention comprehensively and intuitively monitors the cell growth state, enhances the monitoring depth, reduces the actual adjustment risk through a virtual environment previewing strategy, establishes a closed loop feedback mechanism, supports cross-batch learning and self-optimization, simultaneously supports human-computer interaction, integrates the experience of an operator into a decision, improves the adaptability and the robustness, and finally improves the stability and the product quality of the culture process.

Inventors

WANG DIANYU
MA YU
WANG WENPENG
GAO SHUFENG

Assignees

赛尔高新(山东)生物科技有限公司

Dates

Publication Date: 20260508
Application Date: 20260206

Claims (10)

1. A cell culture monitoring data management system, comprising: The initial digital twin model construction module acquires the environmental parameters and the cell characteristic parameters of cell culture and constructs an initial digital twin model based on the environmental parameters and the cell characteristic parameters; the dynamic digital twin model generation module is used for acquiring real-time monitoring data and updating the initial digital twin model by combining the real-time monitoring data to generate a dynamic digital twin model; the fusion three-dimensional model generation module is used for acquiring three-dimensional imaging data, and carrying out data fusion on the three-dimensional imaging data and the dynamic digital twin model to generate a fusion three-dimensional model; and the cell culture optimization strategy generation module is used for generating a cell culture optimization strategy by applying an intelligent decision algorithm based on the fusion three-dimensional model and the dynamic digital twin model.
2. The system of claim 1, wherein the constructing the initial digital twin model based on the environmental parameters and the cell characteristic parameters comprises: collecting physicochemical information of the cell culture environment through a sensor network to obtain environmental parameters; extracting data matched with the current cultured cells from a database storing various cell biological characteristics to obtain cell characteristic parameters; The environmental parameters and cell characteristic parameters are input into a computer simulation algorithm to construct an initial digital twin model.
3. The system of claim 1, wherein the step of updating the initial digital twin model in combination with the real-time monitoring data to generate the dynamic digital twin model comprises: acquiring real-time monitoring data reflecting the state of cell populations and environmental changes through an online monitoring system; comparing the real-time monitoring data with the predicted data of the initial digital twin model to generate model error parameters; A model calibration algorithm is applied and internal parameters of the initial digital twin model are adjusted based on the generated model error parameters to generate a dynamic digital twin model.
4. The cell culture monitoring data management system of claim 1, wherein the specific step of data fusing the three-dimensional imaging data with the dynamic digital twin model to generate a fused three-dimensional model comprises: scanning the cell culture container through an optical scanning device to obtain three-dimensional imaging data; Performing alignment processing on the three-dimensional imaging data and the space coordinates of the dynamic digital twin model to generate space alignment data; And carrying out information dimension interpolation processing on the space alignment data to generate a fusion three-dimensional model.
5. The system of claim 4, wherein the step of interpolating the spatial alignment data in the information dimension to generate the fused three-dimensional model comprises: Identifying a dimensional difference between structural information provided by the three-dimensional imaging data and functional information provided by the dynamic digital twin model in the spatial alignment data to determine a data gap; Filling data gaps by using a data interpolation algorithm to generate a data set with uniform information dimension; and integrating the data sets with unified information dimension to generate a fusion three-dimensional model.
6. The cell culture monitoring data management system of claim 1, wherein the specific step of applying intelligent decision algorithms to generate cell culture optimization strategies comprises: Performing collaborative analysis on the fused three-dimensional model and the dynamic digital twin model to generate a recognition result about the growth state of the cells; inputting the recognition result about the cell growth state into a machine learning algorithm to generate a plurality of candidate optimization strategies; And carrying out virtual effect evaluation on the multiple candidate optimization strategies in the dynamic digital twin model, and selecting an optimal strategy as a cell culture optimization strategy according to an evaluation result.
7. The system of claim 6, wherein the step of inputting the recognition result regarding the growth state of the cells into a machine learning algorithm to generate a plurality of candidate optimization strategies comprises: training a predictive model for predicting cellular responses based on the historical culture data; the influence of various environmental parameter changes on the cell growth is rapidly simulated by using a prediction model, so that a large number of simulation results are generated; and screening out parameter change schemes with favorable prediction effects based on a large number of simulation results, and taking the parameter change schemes as a plurality of candidate optimization strategies.
8. The cell culture monitoring data management system of claim 1, further comprising: acquiring actual cell growth data obtained through offline analysis after the culture flow is finished; Comparing the full-period prediction result of the dynamic digital twin model with actual cell growth data to generate global model error parameters; a feedback algorithm is applied and biological parameters used to construct the initial digital twin model are adjusted based on the generated global model error parameters.
9. The cell culture monitoring data management system of claim 1, further comprising: receiving user input parameters input by an operator through a graphical user interface, wherein the user input parameters are used for defining a current cultivation target; Integrating the user input parameters into an intelligent decision algorithm to generate an adjusted optimization strategy embodying the intention of the operator; And updating the dynamic digital twin model based on the adjusted optimization strategy, and displaying the updated prediction result on the graphical user interface.
10. A method of cell culture monitoring data management comprising: S1, constructing an initial digital twin model, namely acquiring environmental parameters and cell characteristic parameters of cell culture, and constructing the initial digital twin model based on the environmental parameters and the cell characteristic parameters; S2, generating a dynamic digital twin model, namely acquiring real-time monitoring data, and updating an initial digital twin model by combining the real-time monitoring data to generate the dynamic digital twin model; S3, generating a fusion three-dimensional model, namely acquiring three-dimensional imaging data, and carrying out data fusion on the three-dimensional imaging data and the dynamic digital twin model to generate the fusion three-dimensional model; and S4, generating a cell culture optimization strategy by applying an intelligent decision algorithm based on the fusion three-dimensional model and the dynamic digital twin model.

Description

Cell culture monitoring data management system and method Technical Field The invention belongs to the technical field of cell culture monitoring data management, and relates to a cell culture monitoring data management system and method. Background Cell culture technology is a key element of modern biopharmaceutical, cell therapy and basic life science research, and the stability of the process and the quality of the product directly determine the success or failure of the final product. The monitoring and management system for cell culture process is a key technical guarantee for ensuring that cells obtain proper growth environment in bioreactor and other devices, and the system realizes efficient proliferation of cells and high-level expression of target products by monitoring and regulating key parameters in culture process in real time. Currently, existing cell culture monitoring means mainly rely on various sensors deployed in a culture device for acquiring macroscopic physicochemical parameters such as temperature, pH, dissolved oxygen, etc., and evaluating cell density and viability in combination with off-line sampling analysis or on-line two-dimensional microscopic imaging techniques. Process management is typically based on these discrete, two-dimensional monitoring data by manually intervening through preset programmed control logic or by experience by an operator to adjust process parameters such as feed rate, gas flow, etc. However, the above prior art has obvious technical drawbacks in practical applications. Firstly, monitoring based on discrete sensors cannot reflect heterogeneity of microenvironments inside the culture vessel, and two-dimensional imaging cannot comprehensively capture real distribution and interaction states of cells in a three-dimensional space. Secondly, the diversity and unstructured data sources result in severe information islanding, which makes it difficult to develop an overall knowledge of the culture process. Finally, control decisions are seriously dependent on experience of operators, look-ahead and optimality are lacking, hysteresis response is often only carried out on the problems which have occurred, complex biological process fluctuation is difficult to effectively cope with, batch-to-batch differences are large, and process stability and repeatability are poor. Disclosure of Invention In view of this, in order to solve the above-mentioned problems in the background art, a system and a method for managing cell culture monitoring data are proposed. The invention provides a cell culture monitoring data management system, which comprises an initial digital twin model construction module, a cell culture monitoring data management module and a cell culture monitoring data management module, wherein the initial digital twin model construction module is used for acquiring environmental parameters and cell characteristic parameters of cell culture and constructing an initial digital twin model based on the environmental parameters and the cell characteristic parameters. The dynamic digital twin model generation module acquires real-time monitoring data and updates the initial digital twin model by combining the real-time monitoring data to generate a dynamic digital twin model. The fusion three-dimensional model generation module is used for acquiring three-dimensional imaging data, and carrying out data fusion on the three-dimensional imaging data and the dynamic digital twin model to generate a fusion three-dimensional model. And the cell culture optimization strategy generation module is used for generating a cell culture optimization strategy by applying an intelligent decision algorithm based on the fusion three-dimensional model and the dynamic digital twin model. The invention provides a cell culture monitoring data management method, which comprises the following steps of S1, constructing an initial digital twin model, namely acquiring environmental parameters and cell characteristic parameters of cell culture, and constructing the initial digital twin model based on the environmental parameters and the cell characteristic parameters. S2, generating a dynamic digital twin model, namely acquiring real-time monitoring data, and updating the initial digital twin model by combining the real-time monitoring data to generate the dynamic digital twin model. And S3, generating a fusion three-dimensional model, namely acquiring three-dimensional imaging data, and carrying out data fusion on the three-dimensional imaging data and the dynamic digital twin model to generate the fusion three-dimensional model. And S4, generating a cell culture optimization strategy by applying an intelligent decision algorithm based on the fusion three-dimensional model and the dynamic digital twin model. Compared with the prior art, the embodiment of the invention has at least the following advantages or beneficial effects that (1) the method realizes the comprehensive and visual monit