Culture Medium Parameter Prediction for Faster Condition Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods do not effectively maximize the gain during medium culture, leading to increased costs in searching for optimal production conditions due to varying composition and conditions required for different cell types and culture objectives.
Innovation Solution
A method involving creating a prediction model based on past medium manufacturing parameters, using a medium optimizing engine to determine optimal parameters for medium manufacturing, and performing successive optimization through a series of evaluations and adjustments.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If traditional trial-and-error methods are used to search for optimal medium manufacturing conditions, then the composition can be adjusted for different cell types and culture objectives, but the time and cost required for experimentation increase significantly
Solution Approach 1:
The system performs preliminary actions by creating a prediction model from past medium manufacturing data before actual medium production. The medium optimization engine pre-calculates optimal parameters by analyzing historical data and culture results, so when new medium manufacturing is needed, the system can quickly determine optimal conditions without extensive trial-and-error experimentation.
Solution Approach 2:
The system creates a virtual model (prediction model) that copies and simulates the complex relationships between medium composition, manufacturing conditions, and culture outcomes. Instead of physically testing numerous medium formulations, the system uses this copied model to predict optimal conditions, thereby reducing the need for physical trial-and-error experiments while maintaining adaptability to different cell types and culture objectives.
2Manufacturing precision
If extensive experimentation is conducted to find optimal medium conditions, then the accuracy of culture results can be improved, but the manufacturing cost increases
Solution Approach 1:
The system implements feedback by continuously analyzing past medium manufacturing data and culture results to refine the prediction model. The medium optimization engine uses this feedback loop to learn from previous experiments and improve its predictions, thereby achieving high manufacturing precision without requiring extensive new experimentation. Each cycle of data collection and model refinement reduces the need for additional costly trials.
Solution Approach 2:
The prediction model serves as a virtual copy of the complex biological and chemical interactions that occur during medium-manufacturing and culture processes. This copied model allows the system to simulate and evaluate numerous medium formulations computationally, achieving accurate predictions of culture results without the need for expensive physical experimentation for each formulation.
3Reliability
If multiple parameters are adjusted to optimize medium for specific culture objectives, then the effectiveness of the medium can be maximized, but the complexity of the manufacturing process increases
Solution Approach 1:
The medium optimization engine serves as a universal system that handles multiple parameters and different culture objectives through a single integrated platform. Rather than requiring separate complex manufacturing processes for each parameter adjustment, the system uses the prediction model to simultaneously evaluate and optimize multiple parameters for various culture objectives (proliferation, differentiation, production, etc.), thereby maintaining reliability while reducing overall process complexity.
Solution Approach 2:
The system manages parameter complexity by using the prediction model to evaluate and optimize multiple medium parameters computationally. The medium optimization engine can adjust numerous parameters (composition, concentration, pH, temperature, etc.) and predict their combined effects on culture outcomes, allowing for effective medium optimization without requiring complex manual adjustment of each parameter during manufacturing.
Data Source
AI summary
A method of determining a value of a parameter related to manufacturing of a medium includes: a step of creating a prediction model based on values of parameters related to manufacturing of a plurality of other media manufactured in the past and being different in at least any one among an object of culture, an index of the culture, and a manufacturing condition of the medium manufacturing; a step of creating a value of the parameter using the prediction model; and a step of determining the created value of the parameter as a value of the parameter that is used for the manufacturing of the medium.