Protein Graph Prediction for Alternative Protein Screening

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

The process of identifying suitable plant-based or microbial-based protein materials that mimic the functional features of conventional animal-based proteins is time-consuming, costly, and labor-intensive, necessitating an efficient screening and prediction technology.

Innovation Solution

An alternative protein material prediction device and method using an artificial intelligence model that converts composite features of proteins into protein graph data, incorporating sequence, physicochemical, and structural features, to predict suitable alternative protein materials.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If traditional methods are used to search for new plant-based protein materials, then comprehensive analysis of protein features can be achieved, but the process becomes time-consuming, costly, and labor-intensive

Engineering Contradiction:

Improveprotein feature analysis accuracyVSAvoidscreening time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent replaces traditional mechanical and manual protein analysis methods with an artificial intelligence model that processes protein graph data. The system automatically extracts composite features (sequence, structural, and physicochemical) and performs predictions through computational algorithms, eliminating the need for time-consuming laboratory experiments and manual analysis while maintaining high accuracy in protein feature assessment

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent transforms protein data into a graph-based representation where proteins are modeled as graphs with nodes representing amino acids and edges representing interactions. This parameter transformation enables the AI model to efficiently process and analyze protein features through graph neural networks, significantly reducing analysis time while preserving comprehensive protein characteristic information

Inventive Principle:

Principle #35Parameter changes

2Reliability

If traditional methods are used to search for new plant-based protein materials, then thorough evaluation can be performed, but the cost and labor requirements increase significantly

Engineering Contradiction:

Improveprediction reliabilityVSAvoidimplementation cost

Core Design Contradiction:

ReliabilityVSEase of manufacture

Solution Approach 1:

The patent replaces expensive and labor-intensive traditional protein evaluation methods with an AI-based computational system. The model processes protein graph data to predict functional features and identify alternative protein materials, providing reliable predictions without the need for extensive physical experimentation, thereby significantly reducing implementation costs while maintaining high evaluation reliability

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent performs preliminary filtering and evaluation of potential alternative protein materials using the AI model before conducting any physical experiments. The system predicts which plant-based or microbial-based proteins are most likely to mimic animal-based protein functionalities, allowing researchers to focus resources on only the most promising candidates, thus reducing overall implementation costs while maintaining reliable assessment

Inventive Principle:

Principle #10Preliminary action

3Loss of information

If composite features of protein are converted into protein graph data, then comprehensive learning of protein features is achieved, but the device complexity increases

Engineering Contradiction:

Improveprotein feature information completenessVSAvoidprediction system complexity

Core Design Contradiction:

Loss of informationVSDevice complexity

Solution Approach 1:

The patent segments protein features into three distinct composite categories: sequence features, structural features, and physicochemical features. Each feature type is extracted and processed separately by the AI model, which then integrates them into a comprehensive protein graph representation. This segmentation approach enables complete information retention while organizing the complex data processing into manageable, modular components that reduce system complexity

Inventive Principle:

Principle #1Segmentation

Data Source

PatentUS20260045318A1Alternative protein material prediction device and method

Publication Date: 2026.02.12 KOOKMIN UNIV IND ACAD COOP FOUND

AI summary

The present disclosure relates to an alternative protein material prediction device. The device includes a protein feature extractor configured to composite features of protein as sequence features, structural features, and physicochemical features; a protein graph data generator configured to generate nodes based on the sequence features and physicochemical features of the protein and generate edges between the nodes based on the structural features of the protein, thereby generating protein graph network data, and an alternative material protein predictor configured to generate an alternative protein material prediction model for predicting an alternative protein material by learning the protein graph data that reflects the composite features of the protein.