Antibody Fragment Pair Scoring for Reliable Candidate Selection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing methods for selecting antibody fragments struggle to identify promising candidates efficiently due to the high diversity and complexity of antibody libraries, as the number of VH genes in the final pool is not a reliable criterion for determining the binding strength and therapeutic potential.

Innovation Solution

A method and system that generate score values for pairs of VL and VH genes by analyzing enrichment patterns across multiple selection cycles, using feature vectors and multivariate data analysis to rank antibody fragments based on their binding strength and enrichment patterns.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If the number of VH genes in the final pool is used as a criterion to select antibody fragments, then the selection process is simple, but the reliability of identifying promising candidates is poor

Engineering Contradiction:

Improvesimplicity of selection processVSAvoidaccuracy of candidate identification

Core Design Contradiction:

Ease of operationVSReliability

Solution Approach 1:

The patent transforms the selection criterion from a single parameter (number of VH genes in final pool) to multiple parameters including enrichment patterns across multiple pools, binding strength measurements, and therapeutic potential assessments. This multi-parameter approach resolves the contradiction by maintaining operational simplicity through automated scoring while significantly improving reliability through comprehensive evaluation metrics.

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The patent replaces manual evaluation of antibody candidates with an automated computational system that processes enrichment patterns and generates score values. This substitution of mechanical/manual evaluation with automated information processing maintains ease of operation while enhancing reliability through objective, data-driven candidate selection based on multiple criteria rather than single-parameter heuristics.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Adaptability or versatility

If antibody libraries with high diversity are used to ensure comprehensive coverage, then the potential for finding promising candidates increases, but the complexity of analyzing and selecting candidates increases

Engineering Contradiction:

Improvecomprehensive coverage of antibody libraryVSAvoidcomplexity of analysis and selection

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent segments the complex analysis process into distinct manageable components: (1) tracking enrichment patterns across multiple pools, (2) measuring binding strength, (3) assessing therapeutic potential, and (4) generating composite score values. This segmentation allows comprehensive analysis of diverse antibody libraries while reducing overall complexity by breaking down the selection process into systematic steps that can be automated and standardized.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent introduces an intermediary scoring system that mediates between the complexity of diverse antibody library analysis and the need for straightforward candidate selection. The score value acts as a condensed representation that encapsulates multiple evaluation dimensions (enrichment patterns, binding strength, therapeutic potential), transforming complex multi-dimensional data into a single actionable metric that simplifies the selection process while maintaining comprehensive coverage.

Inventive Principle:

Principle #24Intermediary (Mediator)

3Reliability

If multiple selection cycles are performed to improve binding strength, then the quality of selected antibodies improves, but the time required for selection increases

Engineering Contradiction:

Improvebinding strength of selected antibodiesVSAvoidtime for selection process

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The patent performs preliminary tracking and analysis of enrichment patterns across multiple pools during the selection process, rather than conducting comprehensive analysis only after all selection cycles are complete. This preliminary action allows the system to identify and prioritize promising candidates earlier, reducing the time required for subsequent analysis while maintaining the quality improvement benefits of multiple selection cycles.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent implements feedback mechanisms that continuously monitor enrichment patterns and binding strength measurements throughout the selection process. This feedback allows for dynamic adjustment of the selection strategy, identifying high-value candidates earlier and reducing the number of additional cycles needed, thereby shortening overall selection time while maintaining high reliability of the selected antibodies.

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS12573485B2Selection of antibodies / antibody fragments

Publication Date: 2026.03.10 BAYER AG

AI summary

The present invention deals with the selection of antibodies and/or antibody fragments in a selection method. Subjects of the present invention are a method, a system and a computer program product for generating score values for pairs of genes which encode the variable domains of light and heavy chains of antibodies and/or antibody fragments. Antibodies and/or antibody fragments can be selected on the basis of the score values.