Amplicon Design Workflow Optimizing Single-Cell Sequencing Uniformity
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
High throughput single-cell sequencing faces challenges with non-uniform amplification, leading to inadequate coverage of targets of interest, necessitating improved sequencing panel designs for better performance.
Innovation Solution
An amplicon design workflow using machine learning techniques to identify key attributes for optimizing amplicon design, involving feature selection and validation to enhance panel uniformity and detection sensitivity, specifically for RNA fusion amplicons like BCR-ABL.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If traditional amplicon design methods are used for sequencing panels, then the panel can be constructed and deployed, but the amplification is non-uniform resulting in inadequate coverage of targets of interest
Solution Approach 1:
The patent applies preliminary action by using machine learning models to predict amplicon performance and identify key attributes before the actual sequencing panel is constructed. The workflow performs feature selection and amplicon design in silico using trained models to predict which amplicons will perform well, thereby preventing non-uniform amplification issues before they occur in the actual sequencing experiment.
2Manufacturing precision
If machine learning feature selection is applied to identify key amplicon attributes, then improved panel uniformity is achieved, but the design workflow complexity increases
Solution Approach 1:
The patent applies copying by creating virtual representations of amplicons and their attributes in the machine learning model. Instead of physically testing numerous amplicon designs, the system uses computational copies (in silico models) to predict performance, thereby reducing the need for iterative physical experimentation and simplifying the overall workflow despite the sophisticated analysis performed.
3Reliability
If automated workflows are used for designing sequencing panels with machine learning, then improved performance is achieved, but the computational resources and time required increase
Solution Approach 1:
The patent applies preliminary action by performing comprehensive feature selection and amplicon optimization through machine learning before the actual sequencing experiment. The model trains on existing data and makes predictions about which amplicon designs will perform best, thereby reducing the need for time-consuming iterative validation and accelerating the overall panel development process.
Data Source
AI summary
Disclosed herein is an amplicon design workflow for improving the design of amplicons such that panels including newly designed amplicons can achieve improved performance (e.g., improved panel uniformity). The amplicon design workflow involves performing a feature selection process to identify key amplicon attributes that likely lead to improved amplicon performance. Therefore, improved amplicons can be designed based on these key attributes. A sequencing panel, such as a DNA sequencing panel or RNA sequencing panel can be constructed using these improved amplicons and further validated. Thus, such panels including improved amplicons can be deployed for analyzing single cells e.g., through a single cell workflow analysis, for characterizing the cells for nucleic acid events, such as the presence or absence of RNA fusion transcripts.