Nucleic Acid Sequence Modeling for Organism and Host Estimation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Inaccurate nucleic acid sequence information in public databases leads to unreliable oligonucleotide design and reduced accuracy in molecular diagnostic reagents, particularly when incorrect host entity information is registered, causing inefficiencies and increased consumption of oligonucleotides.

Innovation Solution

A computer-implemented method using a fine-tuned pre-learned model to accurately assume an organism or host from a given nucleic acid sequence, employing semi-supervised learning and tokenization to improve accuracy and reliability.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If nucleic acid sequence information from public databases is used for oligonucleotide design, then the design process can be performed, but inaccurate sequence information leads to reduced detection accuracy and reliability

Engineering Contradiction:
Improveoligonucleotide design efficiencyVSAvoiddetection accuracy
Core Design Contradiction:
ProductivityVSReliability

Solution Approach 1:

The patent applies preliminary action by verifying the accuracy of nucleic acid sequence information before using it for oligonucleotide design. The system checks sequence information against multiple criteria including database reliability, sequence quality metrics, and consistency verification before the design process begins, preventing propagation of errors through the workflow

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent implements feedback mechanisms by continuously monitoring and validating sequence information during the oligonucleotide design process. The system provides feedback on sequence quality, alerts potential errors, and adjusts design parameters based on verified information, creating a closed-loop system that maintains both efficiency and accuracy

Inventive Principle:
Principle #23Feedback

2Loss of time

If inaccurate nucleic acid sequence information is used, then oligonucleotide design can proceed quickly, but the accuracy of molecular diagnostic reagents is reduced

Engineering Contradiction:
Improvedesign timeVSAvoidreagent accuracy
Core Design Contradiction:
Loss of timeVSManufacturing precision

Solution Approach 1:

The system performs preliminary verification of sequence information quality before the oligonucleotide design process. By checking sequence accuracy, database reliability, and information consistency in advance, the system identifies and flags potential errors before they impact design outcomes, maintaining both speed and precision

Inventive Principle:
Principle #10Preliminary action

3Device complexity

If host entity information is not verified, then the design process is simpler and faster, but incorrect information causes inefficiencies and increased oligonucleotide consumption

Engineering Contradiction:
Improvedesign process complexityVSAvoidoligonucleotide consumption
Core Design Contradiction:
Device complexityVSLoss of substance

Solution Approach 1:

The system applies self-service by automatically verifying host entity information through integrated databases and validation algorithms. The verification process is performed autonomously without requiring manual intervention, checking host information against multiple sources and flagsging inconsistencies, thereby preventing wasted oligonucleotide synthesis while maintaining process simplicity

Inventive Principle:
Principle #25Self-service

Data Source

PatentEP4641574A1Method for estimating organism or host, method for acquiring model for estimating organism or host, and computer device for performing same
Publication Date: 2025.10.29 SEEGENE INC
  • EP4641574A1 patent drawingFigure 1
  • EP4641574A1 patent drawingFigure 2
  • EP4641574A1 patent drawingFigure 3

AI summary

According to an embodiment, disclosed is a computer-implemented method performed by a computer device using a memory, a processor, and one or more programs stored in the memory and configured to be executed by the processor, the method comprising: accessing an assumption model obtained by fine-tuning a pre-learned model; providing a nucleic acid sequence to the assumption model; and assuming an organism carrying the nucleic acid sequence or a host of the organism from the assumption model. A representative figure may be FIG. 1.