Retention Time Prediction Model for LC-MS Peptide Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In Liquid Chromatograph-Mass Spectrometry (LC-MS), accurately predicting the retention time of analytes is challenging due to variability in chromatography conditions and the presence of peptides with similar mass-to-charge ratios, making it difficult to distinguish target peptides from other peptides with similar m/z values, and the use of isotopically substituted standard heavy peptides is impractical due to high costs.
Innovation Solution
A method and apparatus that predict retention times by using a model based on the physiochemical information of analytes, involving the measurement and conversion of retention times of target and reference substances into indexed retention times, and employing artificial neural networks to correlate monomer sequences with indexed retention times, allowing for accurate prediction of retention times without the need for costly isotopic labeling.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If isotopically substituted standard heavy peptides are used to determine retention time, then retention time prediction accuracy is improved, but cost increases significantly
Solution Approach 1:
The patent creates a computational model that copies the retention time prediction function of expensive isotopically substituted peptides. Instead of physically using these costly standards, the invention develops an artificial neural network that learns from their behavior and reproduces their predictive capability using only the analyte's amino acid sequence and physicochemical properties, thereby eliminating the need for actual isotopic standards while maintaining prediction accuracy
Solution Approach 2:
The patent replaces expensive, rare isotopically substituted peptides with inexpensive computational models based on amino acid sequences. The 'cheap object' here is the computational prediction model that can be generated indefinitely from sequence data alone, unlike the costly physical isotopic standards that would be consumed or degraded
2Quantity of substance
If multiple peptides with similar mass-to-charge ratios are present, then sample complexity increases, but ability to distinguish target peptide decreases
Solution Approach 1:
The patent adds a new dimension for peptide identification by predicting retention time from amino acid sequences. Instead of relying solely on mass-to-charge ratio (one dimension), the system now uses both m/z and predicted retention time (two dimensions), creating a more robust identification space that can distinguish between peptides with similar masses but different retention characteristics
Solution Approach 2:
The patent introduces an artificial neural network as an intermediary that processes amino acid sequence information and outputs predicted retention times. This intermediary translates sequence data into chromatographic behavior predictions, enabling the system to differentiate target peptides from interferents by comparing predicted versus actual retention times
3Quantity of substance
If retention time prediction based on physicochemical information is used, then cost is reduced, but prediction accuracy may be insufficient compared to isotopic standards
Solution Approach 1:
The patent performs preliminary training of the artificial neural network using a database of peptides with known retention times and sequences. This preliminary action (training phase) allows the model to learn the relationship between physicochemical properties and retention behavior before actual prediction, ensuring high accuracy when the model is deployed without requiring costly isotopic standards during the prediction phase
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 enables high-accuracy prediction of retention times, improving the quantitative analysis of analytes by distinguishing their retention times on chromatograms, thereby enhancing the multiplexity of quantitative measurements in LC-MS without the need for expensive isotopic standards.
Implementation Method 1
Liquid Chromatograph-Mass Spectrometry (LC-MS) is a technology that separates target material into components by passing it through a column in a liquid state
Implementation Method 2
separates substances with different mass-to-charge ratios via mass spectrometry after ionizing each component
Data Source
AI summary
The present invention relates, with respect to liquid chromatograph-mass spectrometry (LC-MS), to a technique for predicting retention time of samples and thereby accurately separating signals of samples having mass that are close to each other to improve multiplexity of quantitative measurements.