Metabolite Identification via Non-Negative Matrix Factorization

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current metabolomic data analysis systems face challenges in accurately determining non-negative amounts of metabolite compounds across biological samples, especially when compounds co-elute, leading to ambiguous results and the need for extensive computational power and skill to interpret spectral data.

Innovation Solution

A system utilizing non-negative matrix factorization and independent component analysis to process spectrometry data from multiple samples, generating characteristic values that include the number, relative concentration, and spectra of metabolite compounds, while also correlating ion spectra to identify pure components and their concentrations.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If traditional spectral analysis methods are used to identify metabolite compounds, then the analysis can be performed with simpler computational tools, but the results become ambiguous and difficult to interpret when compounds co-elute

Engineering Contradiction:
Improveidentification accuracyVSAvoidcomputational complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent segments the complex spectral data into multiple pure component spectra through mathematical factorization. By decomposing the mixed spectral signals from co-eluting compounds into individual component spectra, the system enables accurate identification and quantification of each metabolite compound without requiring complex chromatographic separation

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces non-negative matrix factorization and independent component analysis as intermediary computational methods between raw spectral data and final compound identification. These mathematical tools act as mediators that transform ambiguous mixed spectra into distinct pure component spectra, making the data interpretable while maintaining computational feasibility

Inventive Principle:
Principle #24Intermediary (Mediator)

2Measurement precision

If chromatographic separation is improved to resolve co-eluting compounds, then compound identification becomes more accurate, but the analysis time and computational resources required increase significantly

Engineering Contradiction:
Improvequantification accuracyVSAvoiddata processing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent replaces mechanical chromatographic separation with mathematical factorization methods. Instead of relying on physical separation processes that require extended analysis time, the system uses non-negative matrix factorization and independent component analysis to computationally separate co-eluting compounds, achieving accurate quantification without increasing processing time

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

3Loss of information

If more sophisticated analysis methods are employed to handle co-elution, then the interpretability of spectral data improves, but the computational power and skill required increase

Engineering Contradiction:
Improvedata interpretabilityVSAvoidmethod complexity
Core Design Contradiction:
Loss of informationVSDevice complexity

Solution Approach 1:

The patent implements self-service through automated iterative algorithms that perform non-negative matrix factorization and independent component analysis without requiring manual intervention or expert interpretation. The system automatically processes spectral data, resolves co-eluting compounds, and produces interpretable results, reducing the need for specialized computational skill while maintaining high data interpretability

Inventive Principle:
Principle #25Self-service

Data Source

PatentEP1997049B1A system, method, and computer program product for analyzing spectrometry data to indentify and quantify individual components in a sample
Publication Date: 2019.03.13 METABOLON INC
  • EP1997049B1 patent drawingFigure 1
  • EP1997049B1 patent drawingFigure 2~3
  • EP1997049B1 patent drawingFigure 4

AI summary

A system is provided for analyzing metabolomics data received from an analytical device across a group of samples. The system automatically receives a data matrix corresponding to each of the samples, wherein the data matrix includes rows corresponding to each of the samples and columns corresponding to a group of ions present in the respective samples. A processor is provided for determining a characteristic value corresponding to at least one of a group of components present in the samples, wherein the components are made up of at least a portion of the group of ions, using at least one of a correlation function and a factorization function. A user interface is in communication with the processor for displaying a visual indication of the characteristic value such that a user may receive a visual indication of the types of components present in the samples.