Functional Data Analysis for Multiplexed Cell Images

Compare variables of interest between (potentially large numbers of) spatial interactions and meta-variables. Spatial variables are summarized using K, or other, functions, and projected for use in a modified random forest model. The model allows comparison of functional and non-functional variables to each other and to noise, giving statistical significance to the results. Included are preparation, modeling, and interpreting tools along with example datasets, as described in VanderDoes et al., (2023) .

funkycells

The term ${\tt funkycells}$ comes from functional data analysis of K functions+ for multiplexed images of cells. This package organizes ways to analyze cell relationships based on their (empirical) K functions, or other such functions. The approach achieves effective analysis for many different data constructions and accounts for issues such as overfitting. We encourage all feedback and improvements, which can be submitted through this github repo or the package website.

Please see the package website for an introduction to ${\tt funkycells}$, given in the vignette vignette("funkycells"). Additional vignettes are also present showing applications and simulated performance. The website also contains the change log, documenting changes for each version of the package.

Installation

The stable version of ${\tt funkycells}$ can be found on CRAN. Install using:

install.packages("funkycells")

You can also install the development version of ${\tt funkycells}$ from GitHub with:

devtools::install_github("jrvanderdoes/funkycells")

We are actively developing the package. So while new functionality consistently pops up in the development version, we regularly update the CRAN version with the stable additions.