MALDI Mass Recalibration Using Neural Network Mass Defect Mapping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing mass spectrometry data, particularly MALDI MSI data, often suffer from low mass accuracy due to factors like sample type, instrument type, and preparation protocols, making it difficult to analyze and interpret the results accurately. Current recalibration methods may fail when calibrant peaks are undetectable or require high computational effort, and adding calibrants can affect ionization.
Innovation Solution
A machine-learned algorithm using multi-layered or convolutional neural networks is trained with mass-curated training spectra to recalibrate mass spectrometry data, applying mass defect analysis and compensating for mass-related scale modifications, improving mass accuracy by mapping ionic abundance values to a revised scale.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional recalibration methods using calibrant peaks are applied, then mass accuracy can be improved, but the method fails when calibrant peaks are undetectable or require high computational effort
Solution Approach 1:
The patent introduces an intermediary substance (calibrant) with known mass values that is added to the sample matrix. This calibrant serves as a mediator between the unknown analyte masses and the mass spectrometer measurement scale, enabling recalibration by comparing measured calibrant peak positions with their known theoretical masses. The calibrant peaks act as reference points that facilitate the transformation of raw mass measurements into accurate mass values without requiring direct measurement of analyte masses.
Solution Approach 2:
The patent changes the parameter being measured from direct analyte mass detection to calibrant peak position detection. By measuring the positions of known calibrant peaks and comparing them to their theoretical masses, the system derives calibration parameters (mass shifts, scaling factors) that are then applied to correct analyte mass measurements. This parameter transformation approach allows recalibration even when analyte peaks are difficult to detect, as long as calibrant peaks are visible.
2Measurement precision
If calibrants are added to the sample, then mass accuracy can be improved, but the ionization of analyte molecules is affected
Solution Approach 1:
The patent applies local quality by using different substances for different purposes within the same sample: the matrix serves the local function of facilitating ionization and desorption, while the calibrant serves the local function of providing mass reference points. By carefully selecting calibrants with masses distinct from analytes and optimizing their concentration, the system ensures that calibrant peaks provide accurate mass references without significantly interfering with analyte ionization or detection in their respective mass regions.
Solution Approach 2:
The patent uses partial action by adding calibrants at optimized concentrations that are sufficient to generate detectable calibration peaks but not so high as to cause excessive interference with analyte ionization. The calibrant concentration is tuned to provide just enough signal for accurate mass determination while minimizing competitive ionization effects. This partial addition strategy balances calibration quality with analyte detection sensitivity.
3Measurement precision
If existing recalibration methods are used, then some mass accuracy improvement can be achieved, but they are only applicable under certain preconditions or require high computational effort
Solution Approach 1:
The patent creates a universal recalibration method that can be applied across different sample types, ionization techniques, and mass spectrometer configurations. The approach uses fundamental principles of mass spectrometry (ion generation, mass analysis, detection) that are common to all MSI systems, making the recalibration methodology broadly applicable. The method works with various matrix materials, ionization conditions, and detector types, providing a multi-functional solution that adapts to different experimental conditions without requiring system-specific modifications.
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
The method achieves improved mass accuracy, reducing mass dispersion and absolute errors in mass spectrometry data, enhancing the reliability and applicability of mass spectrometry analysis, even in the presence of strong MALDI matrix signals.
Implementation Method 1
applying an algorithm on the mass spectrum which includes a mapping of ionic abundance values to a second mass-related scale... wherein the algorithm implements a result of training on a multitude of datasets using machine learning
Implementation Method 2
subjecting the mass spectrometry data to mass defect analysis, such as Kendrick mass defect analysis
Implementation Method 3
the training aims at providing for the mapping to substantially undo or substantially compensate for the one or more deliberate mass-related scale modifications
Data Source
AI summary
The disclosure relates to producing and using a machine-learned or trained algorithm, such as resulting from (supervised) training a multi-layered or convolutional neural network using mass-curated training spectra, for mass recalibration of mass spectrometry data, in particular applied to mass spectrometry data which are based on matrix-assisted laser desorption/ionization (MALDI) as ionization mechanism, further in particular applied to mass spectrometry imaging (MSI) data, and further in particular including subjecting the mass spectrometry data to mass defect analysis, such as Kendrick mass defect analysis. In so doing, the quality of mass spectrometry data can be improved in a timely manner.