Image-Based IACS Secretome Sorting for Real-Time Cell Selection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing cell sorting methods for analyzing and purifying cells based on their secreted products are cumbersome and inefficient, requiring expertise and expensive equipment, limiting the development of advanced biologic drugs like antibody therapies.
Innovation Solution
A secretion analysis and sorting system using image-based cell sorting with carriers that capture secretions, employing an image classification workflow and supervised classification system for real-time sorting decisions, enabling efficient screening and purification of cells secreting desired products.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If multi-well plates are used for cell secretion analysis, then cells can be clonally isolated and secreted products can be contained, but the process requires expertise and expensive dedicated equipment
Solution Approach 1:
The patent uses image-based detection to create a visual copy/representation of the secretion events, replacing the need for complex dedicated equipment. The imaging system captures fluorescence signals from carriers, creating a digital record that can be analyzed without specialized secretion analysis equipment
Solution Approach 2:
The patent replaces the mechanical/physical handling of multi-well plates with automated image acquisition and analysis. The flow cytometer or imaging system automatically detects and sorts carriers based on fluorescence signals, eliminating the need for manual plate handling and specialized secretion analysis equipment
2Measurement precision
If traditional plate-based approaches are used for cell sorting, then cells can be analyzed based on secreted products, but the process is cumbersome and time-consuming
Solution Approach 1:
The patent performs preliminary classification of carriers into event types (empty, single cell, multiple cells) using image classification before the actual sorting decision. This pre-processing step allows the system to quickly identify which carriers contain cells of interest, accelerating the overall sorting process while maintaining detection accuracy
Solution Approach 2:
The patent implements a dynamic classification system that adapts to different cell types and secretion patterns. The image classification workflow can identify various event types and the system can be retrained for different applications, allowing flexible and rapid adaptation to different sorting requirements without sacrificing precision
3Extent of automation
If image classification workflow is implemented to identify event types, then real-time sort decisions can be made, but the system requires training and classification setup
Solution Approach 1:
The patent performs preliminary training of the classification system using a training set of images before actual sorting. The system learns to distinguish between different event types (empty carriers, single cells, multiple cells) in advance, which enables automated real-time decisions during sorting without requiring complex manual classification setup during operation
Solution Approach 2:
The image classification system automatically identifies and classifies event types without requiring manual intervention during the sorting process. The trained classifier independently makes real-time sort decisions based on image analysis, reducing the need for operator expertise and simplifying the operational complexity
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Enables rapid and accurate sorting of cells secreting specific biomolecules, allowing for large-scale sample preparation in minutes rather than hours, and reducing the need for complex plate-based approaches.
Implementation Method 1
Each cluster of the plurality of clusters is based on intensity and/or location of a fluorescence secretion signal
Data Source
AI summary
A secretion analysis and sorting system where cell(s) are deposited into a carrier that will capture any secretions from the cell, and is small enough to be sorted using flow cytometry based cell sorting, is described herein. The use of an image classification workflow that identifies the event types present in a sample of carriers allows the user to select which event types they would like to purify, and then train a supervised classification system that will be used to make real time sort decisions to purify the carriers which contain cells that secrete the desired product. A flow cytometer is then able to be used to screen the individual carriers to see if each one has the desired secreted product.