https://github.com/diegommcc/spatialddls
Deconvolution of spatial transcriptomics data based on Deep Learning
https://github.com/diegommcc/spatialddls
deconvolution deep-learning neural-network spatial-transcriptomics
Last synced: 4 months ago
JSON representation
Deconvolution of spatial transcriptomics data based on Deep Learning
- Host: GitHub
- URL: https://github.com/diegommcc/spatialddls
- Owner: diegommcc
- Created: 2023-01-31T09:33:35.000Z (about 3 years ago)
- Default Branch: main
- Last Pushed: 2024-10-31T08:59:50.000Z (over 1 year ago)
- Last Synced: 2025-10-22T03:53:31.071Z (4 months ago)
- Topics: deconvolution, deep-learning, neural-network, spatial-transcriptomics
- Language: R
- Homepage: https://diegommcc.github.io/SpatialDDLS/
- Size: 131 MB
- Stars: 5
- Watchers: 1
- Forks: 2
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- Changelog: NEWS.md
Awesome Lists containing this project
README
# **SpatialDDLS** 
[](https://github.com/diegommcc/SpatialDDLS/actions)
An R package to deconvolute spatial transcriptomics data using single-cell RNA-seq and deep neural networks
The **SpatialDDLS** R package provides a neural network-based solution for cell type deconvolution of spatial transcriptomics data. The package takes advantage of single-cell RNA sequencing (scRNA-seq) data to simulate mixed transcriptional profiles with known cell composition and train fully-connected neural networks to predict cell type composition of spatial transcriptomics spots. The resulting trained models can be applied to new spatial transcriptomics data to predict cell type proportions, allowing for a more accurate cell type identification and characterization of spatially-resolved transcriptomic data. Overall, SpatialDDLS is a powerful tool for cell type deconvolution in spatial transcriptomics data, providing a reliable, fast and flexible solution for researchers in the field.
For more details about the algorithm and functionalities implemented in this package, see .
## Installation
**SpatialDDLS** is already available on CRAN:
```r
install.packages("SpatialDDLS")
```
The version under development is available on GitHub and can be installed as follows:
```r
if (!requireNamespace("devtools", quietly = TRUE))
install.packages("devtools")
devtools::install_github("diegommcc/SpatialDDLS")
```
The package depends on the [tensorflow](https://cran.r-project.org/package=tensorflow) and [keras](https://cran.r-project.org/package=keras) R packages, so a working Python interpreter with the Tensorflow Python library installed is needed. The `installTFpython` function provides an easy way to install a conda environment named `spatialddls-env` with all necessary dependencies covered. We recommend installing the TensorFlow Python library in this way, although a custom installation is possible.
```r
library("SpatialDDLS")
installTFpython(install.conda = TRUE)
```
## References
Mañanes, D., Rivero-García, I., Relaño, C., Jimenez-Carretero, D., Torres, M., Sancho, D., Torroja, C. and Sánchez-Cabo, F. (2024). SpatialDDLS: An R package to deconvolute spatial transcriptomics data using neural networks.
Bioinformatics
40 2
doi:10.1093/bioinformatics/btae072
Torroja, C. and Sánchez-Cabo, F. (2019). digitalDLSorter: A Deep Learning algorithm to quantify immune cell populations based on scRNA-Seq data.
Frontiers in Genetics
10 978
doi:10.3389/fgene.2019.00978