Neural Network for Predicting Proteasomal Cleavage

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current methods struggle to identify and utilize specific tumor antigens or neoantigens for personalized cancer treatments, as they require complex and inefficient processes to predict peptide cleavage sites and present them effectively to the immune system.

Innovation Solution

A neural network-based system that analyzes protein cleavage patterns, utilizing an immune epitope database to predict peptide cleavage probabilities and select target antigens for vaccine development, incorporating convolutional and fully connected layers for accurate prediction and separate modeling of N-terminal and C-terminal cleavage sites.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If complex methods are used to identify tumor antigens and predict peptide cleavage sites, then measurement precision may improve, but device complexity and ease of operation deteriorate

Engineering Contradiction:

Improveprediction accuracy of peptide cleavage sitesVSAvoidcomplexity of cleavage prediction system

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent replaces complex mechanical and manual analysis systems with an artificial intelligence-based neural network system. The neural network automatically predicts proteasomal cleavage sites and peptide binding affinity to MHC molecules, eliminating the need for complex manual experimental methods and simplifying the overall system while maintaining or improving prediction accuracy.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The neural network system performs self-learning and self-optimization through training on experimental data. The system automatically improves its prediction capabilities without requiring manual intervention or complex external control mechanisms, thereby reducing system complexity while enhancing measurement precision.

Inventive Principle:

Principle #25Self-service

2Productivity

If traditional methods are used for antigen identification, then ease of operation may be maintained, but productivity and measurement precision deteriorate

Engineering Contradiction:

Improvespeed of vaccine developmentVSAvoidaccuracy of antigen identification

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

The patent replaces traditional slow and labor-intensive antigen identification methods with an AI-based neural network system that can rapidly analyze protein sequences, predict cleavage sites, and identify potential tumor antigens. This substitution dramatically increases productivity while simultaneously improving measurement precision through the neural network's ability to learn from large datasets and identify patterns invisible to traditional methods.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The neural network performs preliminary screening and prediction of potential tumor antigens and cleavage sites before experimental validation. This preliminary action filters out unlikely candidates early in the process, increasing the efficiency and productivity of subsequent experimental steps while improving overall accuracy by focusing resources on the most promising candidates.

Inventive Principle:

Principle #10Preliminary action

3Adaptability or versatility

If personalized cancer treatment approaches are implemented, then adaptability improves, but device complexity and loss of time increase

Engineering Contradiction:

Improvepersonalization of cancer therapyVSAvoidtime for personalized antigen identification

Core Design Contradiction:

Adaptability or versatilityVSLoss of time

Solution Approach 1:

The patent replaces time-consuming manual processes for personalized antigen identification with an automated neural network system. The system can rapidly analyze patient-specific tumor data, predict individualized cleavage sites, and identify personalized tumor antigens, thereby enabling personalized cancer therapy while minimizing time loss through automated high-speed computation.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The neural network performs preliminary and rapid analysis of patient-specific data to identify potential tumor antigens before clinical implementation. This preliminary action enables personalized treatment planning to be completed quickly, allowing adaptability to individual patient needs without significant time loss.

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS20230326544A1Computerized Tool For Prediction of Proteasomal Cleavage

Publication Date: 2023.10.12 NANTCELL INC

AI summary

A method of preparing a vaccine includes providing an immune epitope database; providing a neural network; receiving data corresponding to at least one protein into the neural network; receiving data corresponding to one or more candidate peptides corresponding to potential cleavage products of the at least one protein, or determining, using the neural network, data corresponding to one or more candidate peptides corresponding to potential cleavage products of the at least one protein; calculating, using the neural network, a probability of cleavage of the protein to result in each of the one or more candidate peptides; and outputting a signal corresponding to the calculated probability. An architecture having two channel output, i.e., output of a C-terminal cleavage and an N-terminal cleavage, is described. Related devices, apparatuses, systems, techniques, articles and non-transitory computer-readable storage medium are also described.