Cell Culture Medium Guidance Using Time-Series Machine Learning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing cell culture methods rely heavily on operator experience for determining optimal component amounts in the medium, leading to a low probability of achieving good results, and existing technologies like WO2017/038887A do not provide a solution for this issue.
Innovation Solution
A program and apparatus utilizing machine learning to derive quantitative guidelines for component amounts in cell culture by analyzing time-series data, including basal, supply, and metabolic amounts, to enhance the likelihood of achieving good culture results.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If operator experience is used to determine component amounts, then ease of operation is maintained, but manufacturing precision deteriorates
Solution Approach 1:
The patent replaces the mechanical system of human operator judgment with an information processing system (computer) that executes machine learning algorithms. The computer acquires time-series data, performs machine learning to derive learned models, and outputs quantitative guidelines, substituting human experience-based decision making with automated data-driven analysis, thereby improving precision while maintaining ease of operation
Solution Approach 2:
The patent introduces a computer as an intermediary between the operator and the cell culture process. The computer acts as a mediator that acquires data, performs machine learning calculations, and provides quantitative guidelines to the operator, bridging the gap between simple operational input and precise scientific output
2Manufacturing precision
If machine learning analysis is implemented, then manufacturing precision is improved, but device complexity increases
Solution Approach 1:
The patent makes the computer serve multiple functions: acquiring time-series data, performing machine learning, deriving learned models, and outputting quantitative guidelines. By consolidating these functions into a single information processing system, the patent reduces overall device complexity while maintaining high manufacturing precision
Solution Approach 2:
The system performs self-service through automated machine learning processes. The computer automatically acquires data, performs learning calculations, and generates guidelines without requiring external expert intervention, thereby managing complexity internally while delivering precise results
3Manufacturing precision
If quantitative guidelines are provided, then manufacturing precision is improved, but loss of information is reduced
Solution Approach 1:
The patent implements feedback by using time-series data from cell culture processes to train machine learning models, which then generate quantitative guidelines. These guidelines can be applied to future experiments, creating a feedback loop where past information informs future decisions, reducing information loss and improving precision iteratively
Data Source
AI summary
A program for operating a cell culture support apparatus causes a computer to acquire a learned model, derived by performing machine learning on the basis of a set of time-series data for learning indicating a time transition of an amount of each of plural types of components constituting a medium used for cell culture and good/bad data indicating good or bad of a result of the cell culture in correspondence with the time-series data for learning, indicating a guideline of the amount, acquire time-series data for analysis indicating the time transition of the amount, derive quantitative guideline information of the amount for obtaining a good result in the cell culture, with respect to at least one of the plural types of components, from the learned model and input data of at least a part of the time-series data for analysis acquired, and output guideline information.