Methods for Image-Based Cell Profiling

Typical morphological profiling datasets have millions of cells and hundreds of features per cell. When working with this data, you must clean the data, normalize the features to make them comparable across experiments, transform the features, select features based on their quality, and aggregate the single-cell data, if needed. 'cytominer' makes these steps fast and easy. Methods used in practice in the field are discussed in Caicedo (2017) . An overview of the field is presented in Caicedo (2016) .

cytominer

Typical morphological profiling datasets have millions of cells and hundreds of features per cell. When working with this data, you must

• clean the data

• normalize the features so that they are comparable across experiments

• transform the features so that their distributions are well-behaved ( i.e., bring them in line with assumptions we want to make about their disributions)

• select features based on their quality

• aggregate the single-cell data, if needed

The cytominer package makes these steps fast and easy.

Installation

You can install cytominer from CRAN:

install.packages("cytominer")

Or, install the development version from GitHub:

# install.packages("devtools")
devtools::install_github("cytomining/cytominer", dependencies = TRUE, build_vignettes = TRUE)

Occasionally, the Suggests dependencies may not get installed, depending on your system, so you'd need to install those explicitly.

Example

See vignette("cytominer-pipeline") for basic example of using cytominer to analyze a morphological profiling dataset.