How to install Cellpose on OnDemand

Cellpose is a general model for cell and nuclear segmentation. The following is a simple, step-by-step guide to installing Cellpose on OnDemand.

More detailed information on installing Cellpose can be found here if needed.

Step 1: Open xterm

When your GPU OnDemand Desktop session starts, right click and select xterm to open a terminal:

Step 2: Load Anaconda

You need to set up a conda environment, which will contain your Cellpose installation. To do this, you first need to load Anaconda. Type the following in your terminal window and press Enter:

ml Anaconda3

Step 3: Create Cellpose environment

You then need to create the environment that will contain the Cellpose installation, using the following command:

conda create --name cellpose-env python=3.8

In this example, the environment has been named cellpose-env, but you can call it whatever you want. The terminal will produce output similar to the following, where user_name will be replaced with whatever your user name is:

Retrieving notices: ...working... done
Collecting package metadata (current_repodata.json): done
Solving environment: done
 
## Package Plan ##
 
environment location: /camp/home/user_name/.conda/envs/cellpose-env

Proceed ([y]/n)?

Press y and Enter to proceed.

Step 4: Activate environment

Activate your new Cellpose environment with the following command:

conda activate cellpose-env

Step 5: Install Cellpose

At this point, it is important to note that you have merely created what is essentially an empty environment called cellpose-env. To actually install Cellpose within this environment, run the following series of commands:

pip install cellpose
pip uninstall torch
conda install pytorch==1.12.0 cudatoolkit=11.3 -c pytorch

The terminal will produce a large amount of output as the necessary packages are installed. Press y and Enter to proceed.

Step 6: Verify installation

To test whether the installation was successful, run the following:

cellpose --help

If the installation was successful, this should produce a list of all the parameters that can be used when running Cellpose.

Step 7: Deactivate environment

You can now deactivate your Cellpose environment by running the following:

conda deactivate

Step 8 (Optional): Run Cellpose from FIJI

It is possible to run Cellpose directly from FIJI. Instructions for installing the necessary FIJI Plugin can be found here.

Step 9: Cite!

If you use Cellpose in your work, be sure to cite the relevant paper:

• Version 3 (Latest): Carsen Stringer and Marius Pachitariu. Cellpose3: one-click image restoration for improved cellular segmentation. bioRxiv 2024.02.10.579780
• Version 2: Marius Pachitariu and Carsen Stringer. Cellpose 2.0: how to train your own model. Nature methods, 19(12):1634–1641, 2022.
• Version 1: Carsen Stringer, Tim Wang, Michalis Michaelos, and Marius Pachitariu. Cellpose: a generalist algorithm for cellular segmentation. Nature methods, 18(1):100–106, 2021.