Micro-droplet data classification method
A micro-droplet and data technology, applied in the field of micro-droplets, can solve problems such as the decrease in the repeatability of classification results, the misjudgment of multiple classifications as one classification, and the vulnerability to the influence of scattered points.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0031] Embodiment 1: A classification process of micro-droplet data
[0032] In this embodiment, a kind of micro-droplet data is used to illustrate the complete implementation process of the micro-droplet data classification method.
[0033] Step 1: Input droplet data and droplet classification morphology parameters
[0034] The input droplet data ( figure 1 a) A total of 50,000 members are included, and the dimension of each member is 2, corresponding to the fluorescence values of the two channels. The classification morphological parameters of the micro-droplets are a checkerboard distribution of 2 rows and 2 columns, in which the number parameter is 4, and the reference point A in the lower left corner is used as a reference, and the relative position parameters are the reference point B directly above the reference point A, and the reference point A is directly above the reference point A. The datum point D on the right and the datum point C located on the right side o...
Embodiment 2
[0053] Embodiment 2: A classification process of clearly classified micro-droplet data
[0054] This example illustrates the applicability of the method to well-classified droplet data (the most common droplet data).
[0055] A clearly classified droplet data ( Figure 6 a), after step 2, the micro-droplet data is divided into grids ( Figure 6 b), step 3 divides the grid map into 4 regions ( Figure 6 c), step 4 determines that the optimal classification morphological parameter is a checkerboard distribution of 2 rows and 2 columns ( Figure 6 d), equal to the number of regions after step 3 is completed, so the micro-droplet data is directly classified according to the region ( Figure 6 e).
Embodiment 3
[0056] Example 3: A Classification Process of Droplet Data with Density Fluctuation
[0057] This embodiment focuses on the role of the merged region in processing micro-droplet data with density fluctuations.
[0058] A microdroplet data with density fluctuations ( Figure 7 a), after step 2, the micro-droplet data is divided into grids ( Figure 7 b), step 3 divides the grid map into 6 regions ( Figure 7 c), step 4 determines that the optimal classification morphological parameter is a checkerboard distribution of 2 rows and 2 columns ( Figure 7 d) Since the number of regions (6) after step 3 is completed is greater than the quantity parameter (4) of the optimal classification morphological parameters described in step 4, it is necessary to perform region merging. merged and become 4 regions after merging ( Figure 7 e), and then classify the droplet data according to the region ( Figure 7 f).
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More