Biomarker Detection via Protein Depletion and ML Scoring
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for detecting biomarkers in complex biological samples, such as plasma or serum, face challenges in sensitivity and specificity, particularly for early cancer detection, due to the dominance of highly abundant proteins like albumin and noise fluctuations, which impede the accurate identification of low-level biomarkers.
Innovation Solution
A computer-implemented method involving multi-omic data analysis, where a trained model is applied to generate classification weights and scores from complex biological samples to identify biomarkers, even in low concentrations, by differentiating between specified biological states without prior protein depletion, using a Corona Knowledge Map to design particles that capture specific biomarkers.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If multiple biomarkers are used for detection, then the sensitivity improves, but the classification accuracy deteriorates due to noise from fluctuations in biomarker levels and highly abundant serum proteins
Solution Approach 1:
The patent extracts and removes highly abundant proteins (such as albumin) from the biological sample before biomarker detection. This extraction eliminates the noise these abundant proteins create, allowing for more accurate classification of low-level biomarkers without the interfering fluctuations caused by dominant serum proteins
Solution Approach 2:
The patent changes the concentration parameter of biomarkers in the sample by performing depletion of highly abundant proteins, thereby altering the relative concentrations and reducing the dynamic range. This allows low-abundance biomarkers to be detected more accurately without being overwhelmed by noise from abundant proteins
2Measurement precision
If highly abundant proteins are depleted, then the detection sensitivity for low-level biomarkers improves, but the device complexity increases due to additional processing steps
Solution Approach 1:
The patent introduces an intermediary depletion step that selectively removes highly abundant proteins before biomarker detection. This intermediary process acts as a mediator between the raw sample and the detection system, reducing noise and improving sensitivity while maintaining a manageable workflow through established depletion technologies
3Ease of operation
If a single biomarker is used for detection, then the method simplicity is maintained, but the detection sensitivity is insufficient to associate with specific disease states
Solution Approach 1:
The patent segments the detection process into distinct phases: first depleting highly abundant proteins, then detecting multiple low-level biomarkers. This segmentation allows the system to handle multiple biomarkers systematically, improving sensitivity while maintaining operational clarity through structured workflow separation
Data Source
AI summary
Provided herein relates to methods and systems of a complex biomolecule sampling using machine learning algorithms. The methods and systems provided herein can aid in selection of previously unknown biomarkers and provide a report comprising a score or probability relating to a specified biological state. The methods and systems provided herein can aid in the rational design of particles to capture biomarkers.