Biopolymer Sequencing via Structural Electronegativity Encoding

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing methods for sequencing biopolymers, such as DNA, through nanopore technology face challenges with statistical error and numerical effort, requiring improvements in accuracy and efficiency.

Innovation Solution

The method involves placing a biopolymer in an osmosis cell with a nanopore membrane, applying a voltage, and measuring the current as the biopolymer passes through the nanopores. This current is recorded over time and encoded using structural electronegativity encoding (SEN encoding), which identifies the biopolymer sequence using a neural network, specifically a transformer architecture.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If traditional statistical methods are used for nanopore sequencing, then the sequencing can be performed, but statistical errors increase and numerical effort increases

Engineering Contradiction:
Improvesequencing accuracyVSAvoidstatistical error
Core Design Contradiction:
Measurement precisionVSReliability

Solution Approach 1:

The patent replaces traditional statistical methods with a neural network-based machine learning system. The neural network is trained on simulated nanopore sequencing data and then used to predict base sequences from actual sequencing signals, substituting the mechanical statistical analysis process with an intelligent system that reduces both statistical errors and numerical computational effort while improving sequencing accuracy

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

2Productivity

If traditional methods are used to handle dynamic artifacts like slippage and sticking, then sequencing continues, but accuracy decreases

Engineering Contradiction:
Improvesequencing throughputVSAvoidsequencing accuracy
Core Design Contradiction:
ProductivityVSMeasurement precision

Solution Approach 1:

The patent applies preliminary action by pre-training the neural network on simulated nanopore sequencing data that includes various dynamic artifacts such as slippage and sticking events. This pre-training prepares the network to recognize and correctly interpret these artifacts during actual sequencing, allowing the system to maintain high throughput while achieving improved accuracy in distinguishing true biological signals from artifacts

Inventive Principle:
Principle #10Preliminary action

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 enhances the accuracy and efficiency of biopolymer sequencing by reducing statistical errors and improving the handling of dynamic artifacts such as slippage and sticking, while also providing a mechanism for recognizing biopolymer structural units and epigenetic markers.

Implementation Method 1

The passing of the biopolymer through the nanopores of the membrane may be driven by concentration gradients, by the applied voltage

Methodology Applied
Scientific EffectElectrophoresis: Electrophoresis

Implementation Method 2

measuring a current through the osmosis cell as the biopolymer passes the nanopores

Methodology Applied
Scientific EffectIonic conduction: Conduction (electrical)

Implementation Method 3

The passing of the biopolymer through the nanopores of the membrane may be driven by concentration gradients, by the applied voltage

Methodology Applied
Scientific EffectElectro-osmosis: Electro-Osmosis

Data Source

PatentEP4564354A1Method and system for biopolymer sequencing
Publication Date: 2025.06.04 DNA ME UG
  • EP4564354A1 patent drawingFigure 1~3
  • EP4564354A1 patent drawingFigure 4a~4c
  • EP4564354A1 patent drawingFigure 5

AI summary

The present invention provides sequencing of biopolymers by: putting a biopolymer in a first chamber of an osmosis cell, the osmosis cell comprising two chambers and a membrane with nanopores; applying a voltage across the osmosis cell; measuring a current through the osmosis cell as the biopolymer passes the nanopores; recording a time sequence of the current; encoding the monomers of the biopolymer via structural electronegativity encoding; and identifying the sequence of the biopolymer from the time sequence of the current using said SEN encoding. Herein, the biopolymer may be any one-dimensional biopolymer, for example, DNA, RNA, proteins, sugars, complex lipids, or artificially created biopolymers.