cfDNA Fragmentation Pattern Analysis for Biological Age Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for predicting biological age and disease risk are limited in accuracy and complexity, making it difficult to effectively assess age-related health issues and disease progression.
Innovation Solution
Utilizing machine learning models trained on fragmentomic patterns, specifically the relative frequencies and sizes of cell-free DNA (cfDNA) fragments, to predict biological age and detect the presence of pathologies by analyzing sequence end motifs and fragment sizes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional methods are used for predicting biological age and disease risk, then the process is simple, but the accuracy and predictive power are limited
Solution Approach 1:
The patent replaces traditional manual or simple computational methods with machine learning models that automatically analyze fragmentomic patterns. The ML models process cfDNA fragment sizes and sequence end motifs to predict biological age and disease risk, substituting complex computational algorithms for simple prediction methods while significantly improving accuracy.
Solution Approach 2:
The patent transforms the prediction approach by changing from analyzing traditional biomarkers to analyzing fragmentomic parameters including cfDNA fragment size distributions and sequence end motif frequencies. This parameter transformation enables the machine learning models to capture subtle biological variations that traditional methods miss, thereby improving predictive power.
2Reliability
If complex predictive models are developed, then the predictive power increases, but the computational complexity and resource requirements increase
Solution Approach 1:
The patent extracts specific informative features from the complex cfDNA data, focusing on fragment size distributions and sequence end motifs. By selecting and extracting only the most relevant features rather than processing all possible data, the model achieves high predictive reliability while managing computational complexity through feature dimensionality reduction.
Solution Approach 2:
The patent segments the analysis into distinct components: fragment size analysis, sequence end motif analysis, and machine learning prediction. This segmentation allows each component to be optimized independently and processed efficiently, reducing overall computational complexity while maintaining comprehensive disease prediction capability.
3Measurement precision
If traditional biomarker analysis is performed, then the methodology is well-established, but the ability to detect early disease and assess biological age is limited
Solution Approach 1:
The patent replaces traditional biomarker analysis with machine learning-based fragmentomic pattern recognition. The ML models automatically learn complex patterns from cfDNA data, providing superior biological age prediction accuracy and early disease detection capability compared to established biomarker methods, while the automated nature of ML reduces manual analysis complexity.
Data Source
AI summary
The present disclosure describes techniques for predicting biological age based on fragmentomic patterns in cell-free DNA (cfDNA). In some examples, the techniques may include determining relative frequencies of sequence end motifs of cfDNA fragments, relative frequencies of cfDNA fragments of different, or a combination thereof for a biological sample from a subject. The relative frequencies can be used for predicting a biological age of the subject. For example, a feature vector can be generated using the relative frequencies of end motifs or the relative frequencies of the cfDNA fragments of each size. The feature vector can be input into a machine learning model trained using training samples having known chronological ages and having measured reference vectors of the end motifs or the sizes. The machine learning model may then be used to predict a biological age of the subject.