Deconvolution of Spatial Transcriptomics Data Based on Neural Networks
Generate bar error plots
Bar plot of deconvoluted cell type proportions
Generate Bland-Altman agreement plots between predicted and expected c...
Calculate evaluation metrics on test mixed transcriptional profiles
Get and set cell.names slot in a PropCellTypes object
Get and set cell.types slot in a DeconvDLModel object
Generate correlation plots between predicted and expected cell type pr...
Create a SpatialDDLS object
Get and set deconv.spots slot in a SpatialExperiment object
The DeconvDLModel Class
Deconvolute spatial transcriptomics data using trained model
Generate box or violin plots showing error distribution
Estimate parameters of the ZINB-WaVE model to simulate new single-cell...
Get and set features slot in a DeconvDLModel object
Generate training and test cell type composition matrices
Getter function for the cell composition matrix
Install Python dependencies for SpatialDDLS
Calculate gradients of predicted cell types/loss function with respect...
Loads spatial transcriptomics data into a SpatialDDLS object
Load from an HDF5 file a trained deep neural network model into a `Spa...
Get and set method slot in a PropCellTypesobject
Get and set mixed.profiles slot in a SpatialExperiment object
Get and set model slot in a DeconvDLModelobject
Plot distances between intrinsic and extrinsic profiles
Plot a heatmap of gradients of classes / loss function wtih respect to...
Get and set plots slot in a PropCellTypesobject
Plot results of clustering based on predicted cell proportions
Plot normalized gene expression data (logCPM) in spatial coordinates
Plot predicted proportions for a specific cell type using spatial coor...
Plot predicted proportions for all cell types using spatial coordinate...
Plot training history of a trained SpatialDDLS deep neural network mod...
Prepare SpatialDDLS object to be saved as an RDA file
Get and set prob.cell.types slot in a SpatialExperiment object
Get and set prob.matrix slot in a PropCellTypes object
Get and set project slot in a SpatialExperiment object
The PropCellTypes Class
Save SpatialExperiment objects as RDS files
Save a trained SpatialDDLS deep neural network model to disk as an H...
Get and set set.list slot in a PropCellTypes object
Get and set set slot in a PropCellTypesobject
Show distribution plots of the cell proportions generated by `genMixed...
Simulate training and test mixed spot profiles
Simulate new single-cell RNA-Seq expression profiles using the ZINB-Wa...
Get and set single.cell.real slot in a SpatialExperiment object
Get and set single.cell.simul slot in a SpatialExperiment object
Get and set spatial.experiments slot in a SpatialExperiment object
The SpatialDDLS Class
SpatialDDLS: Deconvolution of Spatial Transcriptomics Data Based on Ne...
SpatialDDLS: an R package to deconvolute spatial transcriptomics data ...
Cluster spatial data based on predicted cell proportions
Get and set test.deconv.metrics slot in a DeconvDLModel object
Get and set test.metrics slot in a DeconvDLModel object
Get and set test.pred slot in a DeconvDLModel object
Get top genes with largest/smallest gradients per cell type
Train deconvolution model for spatial transcriptomics data
Get and set trained.model slot in a SpatialExperiment object
Get and set training.history slot in a DeconvDLModel object
Get and set zinb.params slot in a SpatialExperiment object
The Class ZinbParametersModel
Get and set zinbwave.model slot in a ZinbParametersModel object
Deconvolution of spatial transcriptomics data based on neural networks and single-cell RNA-seq data. SpatialDDLS implements a workflow to create neural network models able to make accurate estimates of cell composition of spots from spatial transcriptomics data using 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. (2024) <doi:10.1093/bioinformatics/btae072> to get an overview of the method and see some examples of its performance.
Useful links