18391487. CONTEXT-DEPENDENT BASE CALLING simplified abstract (ILLUMINA, INC.)
Contents
CONTEXT-DEPENDENT BASE CALLING
Organization Name
Inventor(s)
Gery Vessere of San Francisco CA (US)
David Olmstead Bracher of San Diego CA (US)
Aathavan Karunakaran of Berkeley CA (US)
CONTEXT-DEPENDENT BASE CALLING - A simplified explanation of the abstract
This abstract first appeared for US patent application 18391487 titled 'CONTEXT-DEPENDENT BASE CALLING
The technology disclosed in this patent application is focused on context-dependent base calling, involving the use of k-mer-specific centroids to improve accuracy in sequencing.
- Memory stores k-mer-specific centroids for k-mers.
- Centroids are learned by training a base calling pipeline to represent base calls in k-mer-specific time series.
- Predicted centroids are generated by transforming the time series and merging them on a sequencing cycle basis.
- Training loss is determined by comparing predicted intensity values with known intensity values of base calls.
- Updated centroids are stored and used at runtime to base call bases in a sequence based on k-mer context.
Potential Applications: - Improving accuracy in DNA sequencing. - Enhancing the efficiency of base calling processes in genomics research.
Problems Solved: - Addressing inaccuracies in base calling. - Providing a context-dependent approach to improve sequencing results.
Benefits: - Increased accuracy in DNA sequencing. - Enhanced efficiency in genomics research. - Improved reliability of base calling processes.
Commercial Applications: Title: Context-Dependent Base Calling Technology in Genomics This technology could be utilized in research laboratories, biotechnology companies, and medical institutions for DNA sequencing and genomic analysis.
Questions about Context-Dependent Base Calling Technology: 1. How does this technology improve the accuracy of base calling in DNA sequencing? 2. What are the potential implications of using k-mer-specific centroids in genomics research?
Frequently Updated Research: Stay updated on advancements in DNA sequencing technologies and genomics research to understand the latest trends and developments in context-dependent base calling.
Original Abstract Submitted
The technology disclosed is directed to context-dependent base calling. The technology disclosed describes a system including memory storing k-mer-specific centroids for k-mers. The k-mer-specific centroids are learned by training a base calling pipeline to represent base calls of an already base called sequence in k-mer-specific time series, transform the k-mer-specific time series into predicted k-mer-specific centroids, merge the predicted k-mer-specific centroids on a sequencing cycle-by-sequencing cycle basis to generate predicted per-sequencing cycle intensity values, determine a training loss (e.g., a transformation loss) based on comparing the predicted per-sequencing cycle intensity values against known intensity values of the base calls, update the predicted k-mer-specific centroids based on the determined training loss, and store the updated centroids as the k-mer-specific centroids. The system also includes runtime logic that uses the k-mer-specific centroids to base call bases in a yet-to-be base called sequence in dependence upon k-mer context.
