Specialist Signal Profilers for Base Calling Accuracy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
High-throughput sequencing faces challenges in base calling accuracy due to variation in intensity profiles of clusters, caused by factors like spatial crosstalk, phase errors, and optical distortions, leading to increased error rates and reduced data throughput.
Innovation Solution
The implementation of specialist signal profilers, trained to maximize the signal-to-noise ratio for specific spatial and temporal configurations of clusters on a flow cell, using equalizer coefficients and adaptive algorithms to correct intensity variations and attenuate noise.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If high-throughput sequencing is implemented, then data throughput is increased, but base calling accuracy deteriorates due to intensity profile variations and spatial crosstalk
Solution Approach 1:
The patent segments the flow cell image into multiple spatial regions (tiles, lanes, rows, columns) and applies different signal profilers to each segment. This allows tailored correction for local intensity variations and spatial crosstalk patterns, improving base calling accuracy without sacrificing the high-throughput capability of processing entire flow cells.
Solution Approach 2:
The patent applies local quality correction by training specialized signal profilers for specific spatial configurations (e.g., edge clusters vs. central clusters, different tile regions). Each local region receives customized intensity correction based on its specific crosstalk characteristics, rather than applying a uniform correction across the entire flow cell.
2Measurement precision
If spatial crosstalk correction is applied, then signal-to-noise ratio is improved, but processing complexity increases
Solution Approach 1:
The patent performs preliminary action by training the signal profilers offline using training data from completed sequencing runs. The profilers are pre-computed and stored, so that during actual sequencing, only simple lookup and application operations are needed, avoiding complex real-time calculations and reducing processing complexity.
Solution Approach 2:
The patent creates a library of pre-trained signal profilers that can be copied and applied to different spatial configurations. Instead of computing corrections in real-time, the system copies appropriate pre-trained profilers to the relevant regions and applies them, significantly reducing computational complexity during sequencing.
3Measurement precision
If intensity correction is applied to all clusters, then overall accuracy is improved, but computational resources are consumed
Solution Approach 1:
The patent segments clusters into different spatial categories and applies intensity correction only where needed. By identifying regions with significant crosstalk or intensity variation, the system applies computational resources selectively rather than uniformly across all clusters, optimizing the balance between accuracy improvement and computational resource consumption.
Data Source
AI summary
We disclose a system. The system comprises a memory and a runtime logic. The memory stores a plurality of specialist signal profilers. Each specialist signal profiler in the plurality of specialist signal profilers is trained to maximize signal-to-noise ratio of sequenced signals in a particular signal profile detected for analytes in a particular analyte class and characterized in a particular training data set. The runtime logic, having access to the memory, is configured to execute a base calling operation by applying respective specialist signal profilers in the plurality of specialist signal profilers to sequenced signals in respective signal profiles detected for analytes in respective analyte classes during the base calling operation.