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