SpatialDDLS: Deconvolution of Spatial Transcriptomics Data Based on Neural Networks

Deconvolution of spatial transcriptomics data using deconvolution models based on deep neural networks and single-cell RNA-seq data. These models are able to make accurate estimates of the cell composition of spots in spatial transcriptomics datasets from the same context using the advances provided by deep learning and the meaningful information provided by single-cell RNA-Seq data. See Torroja and Sanchez-Cabo (2019) <doi:10.3389/fgene.2019.00978> and Mañanes et al. (2023) <doi:10.1101/2023.08.31.555677> to get an overview of the method and see some examples of its performance.

Version: 1.0.0
Depends: R (≥ 4.0.0)
Imports: rlang, grr, Matrix, methods, SpatialExperiment, SingleCellExperiment, SummarizedExperiment, zinbwave, stats, pbapply, S4Vectors, dplyr, reshape2, gtools, reticulate, keras, tensorflow, FNN, ggplot2, ggpubr, scran, scuttle
Suggests: knitr, rmarkdown, BiocParallel, rhdf5, DelayedArray, DelayedMatrixStats, HDF5Array, testthat, ComplexHeatmap, grid, bluster, lsa, irlba
Published: 2023-12-06
Author: Diego Mañanes ORCID iD [aut, cre], Carlos Torroja ORCID iD [aut], Fatima Sanchez-Cabo ORCID iD [aut]
Maintainer: Diego Mañanes <dmananesc at>
License: GPL-3
NeedsCompilation: no
SystemRequirements: Python (>= 2.7.0), TensorFlow (
Materials: README NEWS
CRAN checks: SpatialDDLS results


Reference manual: SpatialDDLS.pdf
Vignettes: Deconvolution of mouse lymph node samples


Package source: SpatialDDLS_1.0.0.tar.gz
Windows binaries: r-devel:, r-release:, r-oldrel:
macOS binaries: r-release (arm64): not available, r-oldrel (arm64): not available, r-release (x86_64): not available
Old sources: SpatialDDLS archive


Please use the canonical form to link to this page.