Chromatography Protocol Development Using Predictive Modeling

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional methods for developing chromatography protocols for biopharmaceutical production are time and labor intensive, leading to high costs and inefficiencies, and often result in non-optimized protocols that waste reagents and products, particularly in the production of biopharmaceuticals like antibody-drug conjugates.

Innovation Solution

A method is developed to generate chromatography protocols by identifying loading parameters and performance criteria, creating predictive models, and conducting chromatography runs to optimize parameters such as loading buffer salt concentration, density, and high molecular weight species content, using techniques like hydrophobic interaction chromatography to reduce impurities and increase yield.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If conventional methods are used to develop chromatography protocols, then the protocols can be established, but the process is time and labor intensive and results in high costs

Engineering Contradiction:

Improvechromatography protocol effectivenessVSAvoidprotocol development time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system performs preliminary computational analysis and predictive modeling before actual chromatography experiments. By using machine learning models to predict optimal parameters and rank potential protocols, the system prepares development paths in advance, reducing the time and labor needed for actual protocol development and implementation.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system creates virtual models and simulations of chromatography protocols through computational algorithms. These digital twins allow for protocol development, testing, and optimization in a virtual environment before physical implementation, significantly reducing the time and resources required for conventional trial-and-error approaches.

Inventive Principle:

Principle #26Copying

2Reliability

If conventional methods are used to develop chromatography protocols, then the protocols can be established, but the process is labor intensive and results in high costs

Engineering Contradiction:

Improvechromatography protocol effectivenessVSAvoidprotocol development cost

Core Design Contradiction:

ReliabilityVSEase of manufacture

Solution Approach 1:

The system replaces manual, mechanical chromatography development processes with automated computational algorithms and machine learning models. The computer system automatically analyzes parameters, predicts outcomes, and optimizes protocols, eliminating the need for extensive manual experimentation and reducing both labor intensity and development costs.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system enables self-optimizing chromatography protocol development through automated computational analysis. The machine learning models continuously learn from experimental data and automatically adjust parameter recommendations, allowing the system to improve its own performance without increasing human labor or costs.

Inventive Principle:

Principle #25Self-service

3Productivity

If non-optimized chromatography protocols are used, then the production process can proceed, but reagents and products are wasted

Engineering Contradiction:

Improveproduction throughputVSAvoidreagent and product waste

Core Design Contradiction:

ProductivityVSLoss of substance

Solution Approach 1:

The system implements continuous feedback loops where chromatography experimental results are fed back into the machine learning models. This feedback mechanism allows the system to learn from actual outcomes, refine its predictions, and continuously improve parameter optimization, ensuring that production protocols minimize waste while maintaining productivity.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The system dynamically adjusts chromatography parameters based on real-time data and predictive modeling. By continuously optimizing parameters such as flow rate, gradient profiles, and column conditions, the system maximizes product recovery and minimizes reagent consumption and waste during production operations.

Inventive Principle:

Principle #35Parameter changes

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

This approach significantly reduces the time and labor required for protocol development, optimizes chromatography conditions, and enhances the efficiency and cost-effectiveness of biopharmaceutical production by improving yield and reducing high molecular weight species content in the final product.

Implementation Method 1

hydrophobic interaction chromatography

Methodology Applied

Scientific EffectHydrophobic interaction: Hydrophobe

Data Source

PatentUS20250095773A1Methods and systems for developing chromatography protocols

Publication Date: 2025.03.20 REGENERON PHARMACEUTICALS INC

AI summary

A method of purifying a target molecule may include introducing a load including a high molecular weight species concentration (% HMW) to a chromatography apparatus comprising sartobind phenyl chromatography media. A method of generating a chromatography protocol, may include identifying chromatography loading parameters, identifying chromatography performance criteria. The method of generating the chromatography protocol may include selecting combinations of test values of the loading parameters, and conducting a chromatography run for each combination of the set of test values combinations, thereby generating actual performance criteria values corresponding to each combination of the set of test value combinations.