Genetic Sequencing Classification Using Synthetic Reference Thresholds
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing genetic sequencing technologies suffer from errors in identifying the source of genetic material due to conserved sequences and symplesiomorphies, leading to false positives and false negatives, particularly in clinical settings where accurate identification is crucial.
Innovation Solution
A system and method using hardware processors to analyze genetic sequencing results, employing models and neural networks to identify diagnostically significant organisms by generating synthetic sequencing results, updating thresholds based on replicate-averaged signals, and applying pathogen-specific adaptive thresholds and uniqueness metrics to improve classification accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If genetic sequencing is performed to identify organisms in a sample, then detection capability is improved, but false positives and false negatives occur due to conserved sequences and symplesiomorphies
Solution Approach 1:
The system performs preliminary actions by generating synthetic sequencing data before analyzing clinical samples. This synthetic data, created from known reference genomes, establishes baseline thresholds for what constitutes a true positive detection. By preparing these reference thresholds in advance, the system can more accurately distinguish true organism presence from false positives caused by conserved sequences.
Solution Approach 2:
The patent introduces an intermediary layer between raw sequencing data and final identification results. This intermediary consists of the classification system that uses synthetic reference data and statistical models to evaluate whether detected sequences represent true organism presence or false positives. This intermediary processing step resolves the contradiction by filtering out erroneous identifications while preserving true detections.
2Reliability
If detection thresholds are set low to improve sensitivity, then false positives increase, but if set high to reduce false positives, then false negatives increase
Solution Approach 1:
The system performs self-service by automatically generating its own reference thresholds through synthetic data generation. Rather than relying on manual threshold setting or external calibration, the system creates its own baseline expectations for organism detection from reference genomes. This self-generated reference framework enables automatic, consistent threshold application that reduces both false positives and false negatives without requiring complex external calibration procedures.
3Measurement precision
If traditional sequencing analysis is used, then processing is simple, but errors in identifying source of genetic material occur
Solution Approach 1:
The patent replaces traditional mechanical/manual threshold-setting and sequence-analysis methods with computational automation. Instead of relying on expert manual evaluation of sequencing results, the system uses automated classification algorithms that compare detected sequences against synthetic reference data. This substitution of computational methods for manual analysis dramatically improves identification accuracy while managing complexity through algorithmic standardization.
Data Source
AI summary
In accordance with some embodiments, systems, methods, and media for classifying genetic sequencing results are provided. In some embodiments, a system includes a processor programmed to: receive a sample genetic sequencing result for a reference organism and for a host organism, generate a plurality of synthetic genetic sequencing results by combining a portion of the sample genetic sequencing result for the reference organism and the host organism, generate a matrix by cross-referencing a pair of synthetic genetic sequencing results, generate a model based on the synthetic genetic sequencing results, determine at least one threshold based on the matrix, update the model based on the threshold, receive a clinical sample genetic sequencing result, identify, utilizing the model, any values in the clinical sample genetic sequencing result that are likely to be diagnostically significant; generate a report; and cause the report to be presented to a user.