Bioprocess Predictive Modeling for Processing Time and Quality

Solution Overview

Problem

Conventional chromatography processes for purifying biomolecules do not account for unexpected processing time delays, leading to increased failure rates and non-conformance with regulatory quality standards, which complicates production transferability and increases resource waste.

Innovation Solution

A predictive model is trained using historical bioprocess data to evaluate the impact of processing time on product quality, allowing for the determination of predicted product quality parameters or processing times based on input values, thereby providing insights for optimizing bioprocess operations.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If conventional chromatography processes are used without accounting for processing time delays, then the process is simple and easy to operate, but product quality deteriorates and compliance with quality standards decreases

Engineering Contradiction:

Improveproduct quality complianceVSAvoidprocess complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The system performs preliminary actions by training a predictive model on historical bioprocess data before actual production. The model learns the relationship between processing time and product quality in advance, enabling predictions about how delays will affect quality outcomes. This preliminary modeling allows operators to anticipate quality issues before they occur, rather than reacting after delays happen.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system implements feedback by continuously monitoring actual processing times and comparing predicted quality outcomes with actual quality measurements. This feedback loop allows the model to be retrained and refined over time, improving its accuracy in predicting how processing time variations affect product quality. The feedback mechanism enables the system to adapt to changing process conditions and improve compliance through learned insights.

Inventive Principle:

Principle #23Feedback

2Duration of action of moving object

If processing time is extended due to unexpected delays, then more time is available for operations, but product quality deteriorates due to increased exposure to unforgiving chemical conditions

Engineering Contradiction:

Improveprocessing time flexibilityVSAvoidproduct quality

Core Design Contradiction:

Duration of action of moving objectVSManufacturing precision

Solution Approach 1:

The system performs preliminary actions by training a predictive model on historical bioprocess data before actual production. The model learns the relationship between processing time and product quality in advance, enabling predictions about how delays will affect quality outcomes. This preliminary modeling allows operators to anticipate quality issues before they occur, rather than reacting after delays happen.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system implements feedback by continuously monitoring actual processing times and comparing predicted quality outcomes with actual quality measurements. This feedback loop allows the model to be retrained and refined over time, improving its accuracy in predicting how processing time variations affect product quality. The feedback mechanism enables the system to adapt to changing process conditions and improve compliance through learned insights.

Inventive Principle:

Principle #23Feedback

3Productivity

If conventional processes without predictive modeling are used, then resource efficiency is lower and waste is higher, but the system is simpler to implement

Engineering Contradiction:

Improveresource efficiencyVSAvoidsystem complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The system performs preliminary actions by training a predictive model on historical bioprocess data before actual production. The model learns the relationship between processing time and product quality in advance, enabling predictions about how delays will affect quality outcomes. This preliminary modeling allows operators to anticipate quality issues before they occur, rather than reacting after delays happen.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system implements feedback by continuously monitoring actual processing times and comparing predicted quality outcomes with actual quality measurements. This feedback loop allows the model to be retrained and refined over time, improving its accuracy in predicting how processing time variations affect product quality. The feedback mechanism enables the system to adapt to changing process conditions and improve compliance through learned insights.

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS20260080272A1Predictive model to evaluate processing time impacts

Publication Date: 2026.03.19 AMGEN INC

AI summary

Systems and methods for evaluating impacts of processing time of a process (such as a bioprocess) can include (a) obtaining a model trained using historical bioprocess data, (b) determining, by applying input to the model, predicted output that would result when operating the bioprocess in accordance with the input, wherein either: (i) the input includes a processing time and the predicted output includes a product quality, or (ii) the input includes a product quality parameter and the predicted output includes a processing time, and (c) displaying or storing the values of the predicted output. Further aspects include receiving the input as user input from a user. Still further aspects include presenting the predicted output to the user via a graphical user interface.