Cell culture process searching method, cell culture process searching program, and cell culture process searching device

The method and device simulate and predict optimal cell culture conditions using metabolic flux analysis and machine learning, addressing inefficiencies in existing methods by reducing experimental repetition and improving the search for optimal conditions.

JP7749065B2Active Publication Date: 2025-10-03FUJIFILM CORP
9 Cites 0 Cited by

Patent Information

Application Number
JP2024093167
Authority / Receiving Office
JP · JP
Patent Type
Patents
Current Assignee / Owner
Priority Date
2020-02-19
Filing Date
2024-06-07
Publication Date
2025-10-03
Estimated Expiration
2041-02-15

AI Technical Summary

Technical Problem

Existing methods for searching optimal cell culture conditions for bioproduction are inefficient and costly due to the need for repeated experiments and lack of consideration for medium composition, culture method, and culture period, especially for organisms beyond small-scale microorganisms.

Method used

A method and device that generate and simulate various culture conditions using a computer, incorporating metabolic flux analysis and machine learning to predict optimal conditions without experimental repetition, including medium composition and culture conditions for both small and large scales.

Benefits of technology

Enables efficient exploration of optimal medium and culture conditions for cell culture processes, reducing the need for experimental repetition and enhancing the search for optimal conditions.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

To provide a cell culture process exploring method, a cell culture process exploring program, and a cell culture process exploring apparatus that can explore optimal culture conditions.SOLUTION: The cell culture process exploration method includes the following steps: a process condition generation step of generating a plurality of process conditions; a culture result prediction step of obtaining a cell culture prediction result for each generated process condition, which includes a simulation method including metabolic flux analysis using a cell mechanism or a genome-scale metabolic model, or flux balance analysis, thereby finding optimal process conditions from the predicted culture result; and an optimal process conditions obtaining step of selecting an optimal medium composition and culture conditions based on the cell growth amount and antibody bioproduction yield, in which the optimal process is calculated by inputting the generated process conditions and the predicted culture result and using a regression model that is a model trained by machine learning.SELECTED DRAWING: Figure 7
Need to check novelty before this filing date? Find Prior Art