actk

Automated Cell Toolkit

A pipeline to process field-of-view (FOV) microscopy images and generate data and render-ready products for the cells in each field. Of note, the data produced by this pipeline is used for the Cell Feature Explorer.

Features

All steps and functionality in this package can be run as single steps or all together by using the command line.

In general, all commands for this package will follow the format: actk {step} {command}

• step is the name of the step, such as "StandardizeFOVArray" or "SingleCellFeatures"
• command is what you want that step to do, such as "run" or "push"

Each step will check that the dataset provided contains the required fields prior to processing. For details and definitions on each field, see our dataset fields documentation.

An example dataset can be seen here.

Pipeline

To run the entire pipeline from start to finish you can simply run:

actk all run --dataset {path to dataset}

Step specific parameters can additionally be passed by simply appending them. For example: the step SingleCellFeatures has a parameter for cell_ceiling_adjustment and this can be set on both the individual step run level and also for the entire pipeline with:

actk all run --dataset {path to dataset} --cell_ceiling_adjustment {integer}

To run in distributed mode across the SLURM cluster at AICS you can add the --distributed flag to the pipeline call.

To set distributed cluster and worker parameters you can additionally add the flags:

• --n_workers {int} (i.e. --n_workers 100)
• --worker_cpu {int} (i.e. --worker_cpu 2)
• --worker_mem {str} (i.e. --worker_mem 100GB)

Individual Steps

• actk standardizefovarray run --dataset {path to dataset}, Generate standardized, ordered, and normalized FOV images as OME-Tiffs.
• actk singlecellfeatures run --dataset {path to dataset}, Generate a features JSON file for each cell in the dataset.

Installation

Install Requires: The python package, numpy, must be installed prior to the installation of this package: pip install numpy

Stable Release: pip install actk
Development Head: pip install git+https://github.com/AllenCellModeling/actk.git

Documentation

For full package documentation please visit allencellmodeling.github.io/actk.

Development

See CONTRIBUTING.md for information related to developing the code.

For more details on how this pipeline is constructed please see cookiecutter-stepworkflow and datastep.

To add new steps to this pipeline, run make_new_step and follow the instructions in CONTRIBUTING.md

Developer Installation

The following two commands will install the package with dev dependencies in editable mode and download all resources required for testing.

pip install -e .[dev]
python scripts/download_test_data.py

AICS Developer Instructions

If you want to run this pipeline with the Pipeline Integrated Cell dataset (pipeline 4.*) run the following commands:

pip install -e .[all]
python scripts/download_aics_dataset.py

Options for this script are available and can be viewed with: python scripts/download_aics_dataset.py --help

Free software: Allen Institute Software License