LC Peak Shape Modeling for Standard-Free Peak Integration
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing peak integration algorithms that use specific information about a compound of interest are dependent on experimental peak shapes, limiting their applicability and requiring additional experimental standards for each compound.
Innovation Solution
A machine learning model is trained using actual peak shapes of compounds in various separation systems to generate a mathematical peak model, allowing peak integration without experimental standards, using chemical structure notation forms like SMILES or InChi to create numerical vectors for peak shape parameters.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If experimental peak shapes are used for each compound, then peak integration accuracy is improved, but device complexity and time consumption increase due to requiring additional experimental standards
Solution Approach 1:
The patent creates a mathematical copy of the peak shape model from training data that can be replicated and applied to any compound without requiring physical experimental standards for each compound. The model captures the essential characteristics of peak shapes and generates predictive representations that serve as virtual copies, eliminating the need for extensive experimental measurement for each new compound.
Solution Approach 2:
The patent transforms the approach from using fixed experimental peak shapes to using dynamically generated mathematical models with adjustable parameters. The model takes compound-specific features (such as chemical structure properties) and adjusts the peak shape parameters accordingly, allowing accurate peak integration without requiring experimental standards for each compound.
2Reliability
If experimental standards are required for each compound, then reliability of peak integration is improved, but productivity decreases due to additional experimental work
Solution Approach 1:
The patent performs preliminary action by training the mathematical peak shape model in advance using a comprehensive dataset of experimental peak shapes from various compounds and conditions. This pre-trained model can then be applied to new compounds without requiring additional experimental standards, thereby maintaining reliability while improving productivity during actual analysis.
Solution Approach 2:
The patent creates a universal peak shape model that can be applied across multiple compounds and chromatographic conditions. The model is designed to handle different compound types and separation systems, providing reliable peak integration for diverse analytes without requiring compound-specific experimental standards, thus improving both reliability and productivity.
3Measurement precision
If compound-specific peak shape information is used, then measurement precision is improved, but loss of time increases due to experimental measurement requirements
Solution Approach 1:
The patent creates virtual copies of peak shape information through mathematical modeling, eliminating the need for time-consuming experimental measurements for each compound. The model generates predictive peak shape representations instantaneously based on compound features, maintaining measurement precision while eliminating the time loss associated with experimental standard preparation and measurement.
Solution Approach 2:
The patent replaces the mechanical/experimental system of measuring peak shapes with actual standards with a computational system that generates mathematical models. This substitution eliminates the need for physical experimental measurements, thereby maintaining precision while eliminating the time loss associated with experimental procedures.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A compound is separated or introduced from a sample at a plurality of different times. The compound is ionized, producing an ion beam. The compound is selected and mass analyzed or the compound is selected, fragmented, and fragments of the compound are analyzed from the ion beam at the plurality of different times, producing a plurality of mass spectra. An XIC is calculated for the compound using the plurality of mass spectra. A chemical structure of the compound received in notation form is converted to a numerical vector using a processing algorithm operable to convert the notation form to the numerical vector. A plurality of peak shape parameters is calculated for the compound using the numerical vector and a machine trained model. A peak of the XIC is identified as a peak of the compound using the plurality of peak shape parameters and optionally a peak integration algorithm.