---
title: "Scaling single-cell phenotyping with Cellpose and cloud GPU compute"
authors:
  - "Ryan Lane"
  - "James Kraemer"
doi: "10.57844/arcadia-tb5a-ft98"
license: "https://creativecommons.org/licenses/by/4.0/"
date: "2026-10-21"
version: 1
canonical_url: "https://thestacks.org/publications/resource-cloud-scaled-cell-phenotyping"
---

# Scaling single-cell phenotyping with Cellpose and cloud GPU compute

_We present a reusable, cloud-scalable pipeline that pairs Cellpose-SAM segmentation with on-demand GPU compute for single-cell phenotyping of high-content microscopy, demonstrated on a two-species yeast panel (_S. cerevisiae_ versus _S. pombe_)._

## Abstract

High-content microscopy can generate more images than a single workstation can process in a reasonable amount of time. Segmentation is the most computationally intensive step, but turning raw images into quantitative phenotypes also involves transferring large volumes of image data, provisioning GPUs, running sophisticated segmentation algorithms, and collecting standardized per-cell measurements. In this pub, we present a worked example that handles this entire workflow, pairing Cellpose-SAM [](https://doi.org/10.1101/2025.04.28.651001) with on-demand compute to scale segmentation across cloud GPUs. This shortens the path from imaging to biological interpretation and gives readers a pattern they can adapt to their own data rather than assemble from scratch. On a two-species yeast panel, we show:

1. Cellpose-SAM, combined with cloud GPU compute, can efficiently scale single-cell phenotyping across large microscopy datasets.
2. The phenotyping outputs derived from the segmentation resolve gross morphological differences between populations.

This pub is aimed at researchers developing high-throughput microscopy workflows or deciding how to scale segmentation and phenotyping. The analysis that follows runs on a dataset of two yeast species (_S. cerevisiae_ and _S. pombe_), which is useful for validating the pipeline rather than a source of new biological conclusions. The workflow isn't yeast-specific — the same steps of file I/O, segmentation, parallel execution, and per-cell measurement carry over to other images, though it's best suited to imaging individual cells, such as unicellular organisms or dissociated cell populations, where cells can be segmented cleanly. For background on the tools we build on, see the [Cellpose-SAM documentation](https://cellpose.readthedocs.io/en/latest/) and the [Modal documentation](https://modal.com/docs).

# View the notebook

::::::div{.info-box}
The **full pub** is available [here](https://arcadia-science.github.io/cloud-scaled-cell-phenotyping).

The **source code** to generate it is available in [this GitHub repo](https://github.com/Arcadia-Science/cloud-scaled-cell-phenotyping) (DOI: [10.5281/zenodo.23547346](https://doi.org/10.5281/zenodo.23547346)).
::::::

In the future, we hope to host [notebook pubs](https://dx.doi.org/10.57844/arcadia-ca21-23bb) directly on our publishing platform. Until that’s possible, we’ll create stubs like this with key metadata like the DOI, author roles, citation information, and an external link to the pub itself.