Name Mode Size
.github 040000
R 040000
data 040000
inst 040000
man 040000
pkgdown 040000
tests 040000
vignettes 040000
.Rbuildignore 100644 0 kb
.gitignore 100644 1 kb
DESCRIPTION 100644 2 kb
Dockerfile 100644 1 kb
LICENSE 100644 34 kb
NAMESPACE 100644 1 kb 100644 4 kb 100644 4 kb
codecov.yml 100644 0 kb
# MISTy - **M**ultiview **I**ntercellular **S**pa**T**ial modeling framework <img src="" align="right" height = "139"> <!-- badges: start --> [![BioC status](]( [![BioC devel status](]( [![Codecov test coverage](]( [![Docker Cloud Automated build](]( [![install with bioconda](]( <!-- badges: end --> ## Overview The advancement of technologies for measurement of highly multiplexed spatial data require the development of scalable methods that can leverage the availability of the spatial context. Multiview Intercellular SpaTial modeling framework (MISTy) is an explainable machine learning framework for knowledge extraction and analysis of single-cell, highly multiplexed, spatially resolved data. <img src="" align="center" width="800"> MISTy facilitates an in-depth understanding of marker interactions by profiling the intra- and intercellular relationships. MISTy is a flexible framework able to process a custom number of views. Each of these views can describe a different spatial context, i.e., define a relationship among the observed expressions of the markers, such as intracellular regulation or paracrine regulation. However, the views can also capture cell-type specific relationships, capture relations between functional footprints or focus on relations between different anatomical regions. Each MISTy view is considered as a potential source of variability in the measured marker expressions. Each MISTy view is then analyzed for its contribution to the total expression of each marker and is explained in terms of the interactions with other measurements that led to the observed contribution. Our approach is modular, easily parallelizable and thus scalable to samples with millions of cells and thousands of measured markers. **mistyR** is a R package implementing MISTy. ## System Requirements **mistyR** requires a standard configuration and enough RAM to store the analyzed dataset and to support in-memory operations. The package requires R version 4.0 or higher. This package is developed on macOS Big Sur. The package should be compatible with Windows, Linux and maxOS operating systems. ## Installation Install from Bioconductor: ```r # install.packages("BiocManager") BiocManager::install("mistyR") ``` You can install the latest stable and development versions from GitHub with `remotes`: - stable ```r # install.packages("remotes") remotes::install_github("saezlab/mistyR") ``` - development ```R remotes::install_github("saezlab/mistyR@devel") ``` ## Docker For the released and the latest stable and development versions we also provide [Docker images]( based on the [Rocker project]( - [rocker/r-base]( image. To create and start a container from the latest docker image and run R in interactive mode: ```bash docker run -it tanevski/mistyr:latest ``` ## Usage Start by reading `vignette("mistyR")` to learn how to run **mistyR**. To learn how to use the package with commonly used objects for spatial omics data see the [articles]( Example pipelines and synthetic data for **mistyR** are also available from [this repository]( To run **mistyR** on the provided synthetic data run the script *synthetic_pipeline.R*. ## Citation If you use **mistyR** for your research please cite the [following publication]( > Jovan Tanevski, Ricardo Omar Ramirez Flores, Attila Gabor, Denis Schapiro, Julio Saez-Rodriguez. Explainable multiview framework for dissecting spatial relationships from highly multiplexed data. Genome Biology 23, 97 (2022).