AdaptiGate is a template-based, machine learning autogating algorithm. It aims to find the best fit for gates across different files using a template.
The data used to train the machine learning (ML) autogating algorithm was generated through Project Discovery. Project Discovery involves a multi-player game, Eve Online, where players analyzed millions of cell plots over the last 6 years. This training data forms the foundation of the AdaptiGate algorithm.
Project Discovery bivariate training plots used to train the ML model are available here under the Creative Commons Attribution 4.0 International License.
You can read more about this in the article below:
Montante, S., Yokosawa, D., Li L. et al. Citizen science gamers enable automated flow cytometry gating through machine learning. bioRxiv [Preprint]. 2025 Oct 08. https://doi.org/10.1101/2025.10.07.679685
1. Add a Gating Task
Click Add new child task and select Gating from the task selector.
Note that your Workflow might look slightly different if you are using Compact View.
2. Build the Gating Tree
Build the gating tree for your data. To learn more about using the gating task to build the gating tree, please see our article on Performing Manual Gating in OMIQ.
Please note that currently, the following filters (gates) cannot be used with AdaptiGate: Ellipse, Skewed Quadrant, Range, Split, Linked gates, and gates drawn on Dual Scatter parameters (e.g. FSC-A vs SSC-A, FSC-A vs FSC-H).
Here, we have created a simple gating tree to identify the T cell (CD3) subsets CD4 and CD8.
3. Set-up AdaptiGate
When gates are drawn, these are applied globally to all files within the dataset. The image above shows an example where in 1 file (Sample 1 Drug A, plot on the right) has some gates that do not fully capture the correct population (red arrows). We will use Sample 1 Vehicle (plot on the left) as the template file for AdaptiGate.
Click on AdaptiGate. This will open a dialogue box to set-up AdaptiGate.
1. Select the Filters you would like to use for AdaptiGate.
2. Select the Template file you want to use. Choose a file that is the most representative file of how the plots look like in your dataset.
Viewing multiple plots in the gating task might help you decide which is the best candidate to be the template file. To learn more on how to view multiple plots in the gating task, please see our article on Viewing Multiple Gating Plots in a Single Gating Task.
3. Select the Files you would want to run on AdaptiGate.
4. Click on AdaptiGate.
In the image above we see the progress bar after AdaptiGate has been launched.
Once launched, AdaptiGate will run within this Gating task. Please do not navigate away until it completes. You can open another browser window to continue using OMIQ.
The image above shows a completed AdaptiGate run. The gates for CD4 and CD8 in Sample 1 Drug A (right plot) now show that they are capturing the population more accurately (arrows). Note that the gates chosen for AdaptiGate are now in a per file mode.
You can still manually adjust the gates, if required, after AdaptiGate has completed.