Skip to main content

CELL SPOTTER (CSPOT): A scalable framework for automated processing of highly multiplexed tissue images

Project description

Downloads docs build-unix-mac-win

🐊 Getting Started with CSPOT

Kindly note that CSPOT is not a plug-and-play solution. It's a framework that requires significant upfront investment of time from potential users for training and validating deep learning models, which can then be utilized in a plug-and-play manner for processing large volumes of similar multiplexed imaging data.

System Requirements:

Hardware :
CSPOT comprises two modules: training and prediction. Training can be efficiently executed on a standard laptop without the need for a GPU. However, for predictions, leveraging a GPU significantly enhances processing speed (particularly for large images).

Software :
This package is supported for Windows (10, 11), macOS (Sonoma, Ventura) and Linux (Ubuntu 16.04).

Dependencies : The pyproject.toml file contains a comprehensive list of dependencies.

Installation Guide:

There are two ways to set it up based on how you would like to run the program

  • Using an interactive environment like Jupyter Notebooks
  • Using Command Line Interface

Before we set up CSPOT, we highly recommend using a environment manager like Conda. Using an environment manager like Conda allows you to create and manage isolated environments with specific package versions and dependencies.

Download and Install the right conda based on the opertating system that you are using

Create a new conda environment

# use the terminal (mac/linux) and anaconda promt (windows) to run the following command
conda create --name cspot -y python=3.9
conda activate cspot

Install cspot within the conda environment.

pip install cspot

The installation time for cspot generally falls under 5 minutes, based on internet speed and connectivity.

Interactive Mode

Using IDE or Jupyter notebooks

pip install notebook

# open the notebook and import CSPOT
import cspot as cs
# Go to the tutorial section to follow along

Command Line Interface

wget https://github.com/nirmalLab/cspot/archive/main.zip
unzip main.zip 
cd cspot-main/cspot 
# Go to the tutorial section to follow along

Docker Container

docker pull nirmallab/cspot:cspot
# Go to the tutorial section to follow along

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

cspot-1.0.12.tar.gz (94.3 kB view details)

Uploaded Source

Built Distribution

cspot-1.0.12-py3-none-any.whl (95.1 kB view details)

Uploaded Python 3

File details

Details for the file cspot-1.0.12.tar.gz.

File metadata

  • Download URL: cspot-1.0.12.tar.gz
  • Upload date:
  • Size: 94.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.7.0 CPython/3.11.3 Windows/10

File hashes

Hashes for cspot-1.0.12.tar.gz
Algorithm Hash digest
SHA256 7da2205097e1d30074968ade20cbbff127bf5a84f778efa602c7a7a53e850b50
MD5 14234dce703e9dcf8d1647d446aa01d9
BLAKE2b-256 789be3afc7cab90929d42aefede84d71a56a9e8f101c35abfe7d11cb7121d053

See more details on using hashes here.

File details

Details for the file cspot-1.0.12-py3-none-any.whl.

File metadata

  • Download URL: cspot-1.0.12-py3-none-any.whl
  • Upload date:
  • Size: 95.1 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.7.0 CPython/3.11.3 Windows/10

File hashes

Hashes for cspot-1.0.12-py3-none-any.whl
Algorithm Hash digest
SHA256 5257141d4da9784df48a91b4b23706427f48fce8a9293311fab18d36ebde2868
MD5 3348b0adca602bdeff41f8d7be353f54
BLAKE2b-256 f38f95b22de18b2ec66dee20ab9c5ea001f8a35e2fdb70d2f6e8bebbe0f0da8e

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page