Package: SpatialDDLS 1.0.3

Diego Mañanes

SpatialDDLS: Deconvolution of Spatial Transcriptomics Data Based on Neural Networks

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.

Authors:Diego Mañanes [aut, cre], Carlos Torroja [aut], Fatima Sanchez-Cabo [aut]

SpatialDDLS_1.0.3.tar.gz
SpatialDDLS_1.0.3.zip(r-4.5)SpatialDDLS_1.0.3.zip(r-4.4)SpatialDDLS_1.0.3.zip(r-4.3)
SpatialDDLS_1.0.3.tgz(r-4.4-any)SpatialDDLS_1.0.3.tgz(r-4.3-any)
SpatialDDLS_1.0.3.tar.gz(r-4.5-noble)SpatialDDLS_1.0.3.tar.gz(r-4.4-noble)
SpatialDDLS_1.0.3.tgz(r-4.4-emscripten)SpatialDDLS_1.0.3.tgz(r-4.3-emscripten)
SpatialDDLS.pdf |SpatialDDLS.html✨
SpatialDDLS/json (API)
NEWS

# Install 'SpatialDDLS' in R:
install.packages('SpatialDDLS', repos = c('https://diegommcc.r-universe.dev', 'https://cloud.r-project.org'))

Peer review:

Bug tracker:https://github.com/diegommcc/spatialddls/issues

On CRAN:

deconvolutiondeep-learningneural-networkspatial-transcriptomics

5.13 score 3 stars 1 scripts 478 downloads 81 exports 168 dependencies

Last updated 18 days agofrom:5fe0df3e6e. Checks:OK: 6 WARNING: 1. Indexed: yes.

TargetResultDate
Doc / VignettesOKNov 18 2024
R-4.5-winOKNov 18 2024
R-4.5-linuxWARNINGNov 18 2024
R-4.4-winOKNov 18 2024
R-4.4-macOKNov 18 2024
R-4.3-winOKNov 18 2024
R-4.3-macOKNov 18 2024

Exports:barErrorPlotbarPlotCellTypesblandAltmanLehPlotcalculateEvalMetricscell.namescell.names<-cell.typescell.types<-corrExpPredPlotcreateSpatialDDLSobjectdeconv.spotsdeconv.spots<-DeconvDLModeldeconvSpatialDDLSdistErrorPlotestimateZinbwaveParamsfeaturesfeatures<-genMixedCellPropgetProbMatrixinstallTFpythoninterGradientsDLloadSTProfilesloadTrainedModelFromH5methodmethod<-mixed.profilesmixed.profiles<-modelmodel<-plotDistancesplotHeatmapGradsAggplotsplots<-plotSpatialClusteringplotSpatialGeneExprplotSpatialPropplotSpatialPropAllplotTrainingHistorypreparingToSaveprob.cell.typesprob.cell.types<-prob.matrixprob.matrix<-projectproject<-PropCellTypessaveRDSsaveTrainedModelAsH5setset.listset.list<-set<-showProbPlotsimMixedProfilessimSCProfilessingle.cell.realsingle.cell.real<-single.cell.simulsingle.cell.simul<-spatial.experimentsspatial.experiments<-SpatialDDLSspatialPropClusteringtest.deconv.metricstest.deconv.metrics<-test.metricstest.metrics<-test.predtest.pred<-topGradientsCellTypetrainDeconvModeltrained.modeltrained.model<-training.historytraining.history<-zinb.paramszinb.params<-ZinbParametersModelzinbwave.modelzinbwave.model<-

Dependencies:abindannotateAnnotationDbiaskpassassortheadbackportsbase64encbeachmatBHBiobaseBiocFileCacheBiocGenericsBiocNeighborsBiocParallelBiocSingularBiostringsbitbit64blobblusterbootbroomcachemcarcarDatacliclustercodetoolscolorspaceconfigcorrplotcowplotcpp11crayoncurlDBIdbplyrDelayedArrayDerivdoBydplyrdqrngedgeRfansifarverfastmapfilelockFNNformatRFormulafutile.loggerfutile.optionsgenefiltergenericsGenomeInfoDbGenomeInfoDbDataGenomicRangesggplot2ggpubrggrepelggsciggsignifgluegridExtragrrgtablegtoolsherehttrigraphIRangesirlbaisobandjsonliteKEGGRESTkeraslabelinglambda.rlatticelifecyclelimmalme4locfitmagickmagrittrMASSMatrixMatrixGenericsMatrixModelsmatrixStatsmemoisemetapodmgcvmicrobenchmarkmimeminqamodelrmunsellnlmenloptrnnetnumDerivopensslpbapplypbkrtestpillarpkgconfigplogrplyrpngpolynomprocessxpspurrrquantregR6rappdirsRColorBrewerRcppRcppEigenRcppTOMLreshape2reticulaterjsonrlangrprojrootRSQLiterstatixrstudioapirsvdS4ArraysS4VectorsScaledMatrixscalesscranscuttleSingleCellExperimentsitmosnowsoftImputeSparseArraySparseMSpatialExperimentstatmodstringistringrSummarizedExperimentsurvivalsystensorflowtfautographtfrunstibbletidyrtidyselectUCSC.utilsutf8vctrsviridisLitewhiskerwithrXMLxtableXVectoryamlzeallotzinbwavezlibbioc

Get started! Deconvolution of mouse lymph node samples

Rendered fromrealModelExample.Rmdusingknitr::rmarkdownon Nov 18 2024.

Last update: 2024-03-11
Started: 2023-04-10

Readme and manuals

Help Manual

Help pageTopics
Generate bar error plotsbarErrorPlot
Bar plot of deconvoluted cell type proportionsbarPlotCellTypes
Generate Bland-Altman agreement plots between predicted and expected cell type proportions of test datablandAltmanLehPlot
Calculate evaluation metrics on test mixed transcriptional profilescalculateEvalMetrics
Get and set 'cell.names' slot in a 'PropCellTypes' objectcell.names cell.names,PropCellTypes-method cell.names<- cell.names<-,PropCellTypes-method
Get and set 'cell.types' slot in a 'DeconvDLModel' objectcell.types cell.types,DeconvDLModel-method cell.types<- cell.types<-,DeconvDLModel-method
Generate correlation plots between predicted and expected cell type proportions of test datacorrExpPredPlot
Create a 'SpatialDDLS' objectcreateSpatialDDLSobject
Get and set 'deconv.spots' slot in a 'SpatialExperiment' objectdeconv.spots deconv.spots,SpatialDDLS-method deconv.spots<- deconv.spots<-,SpatialDDLS-method
The DeconvDLModel ClassDeconvDLModel DeconvDLModel-class
Deconvolute spatial transcriptomics data using trained modeldeconvSpatialDDLS
Generate box or violin plots showing error distributiondistErrorPlot
Estimate parameters of the ZINB-WaVE model to simulate new single-cell RNA-Seq expression profilesestimateZinbwaveParams
Get and set 'features' slot in a 'DeconvDLModel' objectfeatures features,DeconvDLModel-method features<- features<-,DeconvDLModel-method
Generate training and test cell type composition matricesgenMixedCellProp
Getter function for the cell composition matrixgetProbMatrix
Install Python dependencies for SpatialDDLSinstallTFpython
Calculate gradients of predicted cell types/loss function with respect to input features for interpreting trained deconvolution modelsinterGradientsDL
Loads spatial transcriptomics data into a SpatialDDLS objectloadSTProfiles
Load from an HDF5 file a trained deep neural network model into a 'SpatialDDLS' objectloadTrainedModelFromH5
Get and set 'method' slot in a 'PropCellTypes' objectmethod method,PropCellTypes-method method<- method<-,PropCellTypes-method
Get and set 'mixed.profiles' slot in a 'SpatialExperiment' objectmixed.profiles mixed.profiles,SpatialDDLS-method mixed.profiles<- mixed.profiles<-,SpatialDDLS-method
Get and set 'model' slot in a 'DeconvDLModel' objectmodel model,DeconvDLModel-method model<- model<-,DeconvDLModel-method
Plot distances between intrinsic and extrinsic profilesplotDistances
Plot a heatmap of gradients of classes / loss function wtih respect to the inputplotHeatmapGradsAgg
Get and set 'plots' slot in a 'PropCellTypes' objectplots plots,PropCellTypes-method plots<- plots<-,PropCellTypes-method
Plot results of clustering based on predicted cell proportionsplotSpatialClustering
Plot normalized gene expression data (logCPM) in spatial coordinatesplotSpatialGeneExpr
Plot predicted proportions for a specific cell type using spatial coordinates of spotsplotSpatialProp
Plot predicted proportions for all cell types using spatial coordinates of spotsplotSpatialPropAll
Plot training history of a trained SpatialDDLS deep neural network modelplotTrainingHistory
Prepare 'SpatialDDLS' object to be saved as an RDA filepreparingToSave
Get and set 'prob.cell.types' slot in a 'SpatialExperiment' objectprob.cell.types prob.cell.types,SpatialDDLS-method prob.cell.types<- prob.cell.types<-,SpatialDDLS-method
Get and set 'prob.matrix' slot in a 'PropCellTypes' objectprob.matrix prob.matrix,PropCellTypes-method prob.matrix<- prob.matrix<-,PropCellTypes-method
Get and set 'project' slot in a 'SpatialExperiment' objectproject project,SpatialDDLS-method project<- project<-,SpatialDDLS-method
The PropCellTypes ClassPropCellTypes PropCellTypes-class
Save 'SpatialExperiment' objects as RDS filessaveRDS saveRDS,DeconvDLModel-method saveRDS,saveRDS-method saveRDS,SpatialDDLS-method
Save a trained 'SpatialDDLS' deep neural network model to disk as an HDF5 filesaveTrainedModelAsH5
Get and set 'set' slot in a 'PropCellTypes' objectset set,PropCellTypes-method set<- set<-,PropCellTypes-method
Get and set 'set.list' slot in a 'PropCellTypes' objectset.list set.list,PropCellTypes-method set.list<- set.list<-,PropCellTypes-method
Show distribution plots of the cell proportions generated by 'genMixedCellProp'showProbPlot
Simulate training and test mixed spot profilessimMixedProfiles
Simulate new single-cell RNA-Seq expression profiles using the ZINB-WaVE model parameterssimSCProfiles
Get and set 'single.cell.real' slot in a 'SpatialExperiment' objectsingle.cell.real single.cell.real,SpatialDDLS-method single.cell.real<- single.cell.real<-,SpatialDDLS-method
Get and set 'single.cell.simul' slot in a 'SpatialExperiment' objectsingle.cell.simul single.cell.simul,SpatialDDLS-method single.cell.simul<- single.cell.simul<-,SpatialDDLS-method
Get and set 'spatial.experiments' slot in a 'SpatialExperiment' objectspatial.experiments spatial.experiments,SpatialDDLS-method spatial.experiments<- spatial.experiments<-,SpatialDDLS-method
The SpatialDDLS ClassSpatialDDLS SpatialDDLS-class
SpatialDDLS: an R package to deconvolute spatial transcriptomics data using deep neural networksSpatialDDLS-Rpackage
Cluster spatial data based on predicted cell proportionsspatialPropClustering
Get and set 'test.deconv.metrics' slot in a 'DeconvDLModel' objecttest.deconv.metrics test.deconv.metrics,DeconvDLModel-method test.deconv.metrics<- test.deconv.metrics<-,DeconvDLModel-method
Get and set 'test.metrics' slot in a 'DeconvDLModel' objecttest.metrics test.metrics,DeconvDLModel-method test.metrics<- test.metrics<-,DeconvDLModel-method
Get and set 'test.pred' slot in a 'DeconvDLModel' objecttest.pred test.pred,DeconvDLModel-method test.pred<- test.pred<-,DeconvDLModel-method
Get top genes with largest/smallest gradients per cell typetopGradientsCellType
Train deconvolution model for spatial transcriptomics datatrainDeconvModel
Get and set 'trained.model' slot in a 'SpatialExperiment' objecttrained.model trained.model,SpatialDDLS-method trained.model<- trained.model<-,SpatialDDLS-method
Get and set 'training.history' slot in a 'DeconvDLModel' objecttraining.history training.history,DeconvDLModel-method training.history<- training.history<-,DeconvDLModel-method
Get and set 'zinb.params' slot in a 'SpatialExperiment' objectzinb.params zinb.params,SpatialDDLS-method zinb.params<- zinb.params<-,SpatialDDLS-method
The Class ZinbParametersModelZinbParametersModel ZinbParametersModel-class
Get and set 'zinbwave.model' slot in a 'ZinbParametersModel' objectzinbwave.model zinbwave.model,ZinbParametersModel-method zinbwave.model<- zinbwave.model<-,ZinbParametersModel-method