Package: SpaGER 1.0.0

SpaGER: Spatial Gene Expression Prediction using scRNA-seq

Integrates spatial transcriptomics data with single-cell RNA sequencing (scRNA-seq) data to predict expression of unmeasured genes in spatial data. Uses Principal Vectors (PVs) for domain adaptation followed by k-nearest neighbor weighted imputation. This R implementation provides identical results to the original Python SpaGE package with efficient C++ acceleration.

Authors:Zaoqu Liu [aut, cre], Tamim Abdelaal [ctb], Soufiane Mourragui [ctb]

SpaGER_1.0.0.tar.gz
SpaGER_1.0.0.zip(r-4.7)SpaGER_1.0.0.zip(r-4.6)SpaGER_1.0.0.zip(r-4.5)
SpaGER_1.0.0.tgz(r-4.6-x86_64)SpaGER_1.0.0.tgz(r-4.6-arm64)SpaGER_1.0.0.tgz(r-4.5-x86_64)SpaGER_1.0.0.tgz(r-4.5-arm64)
SpaGER_1.0.0.tar.gz(r-4.7-arm64)SpaGER_1.0.0.tar.gz(r-4.7-x86_64)SpaGER_1.0.0.tar.gz(r-4.6-arm64)SpaGER_1.0.0.tar.gz(r-4.6-x86_64)
SpaGER_1.0.0.tgz(r-4.6-emscripten)
manual.pdf |manual.html
DESCRIPTION
card.svg |card.png
SpaGER/json (API)

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

Bug tracker:https://github.com/zaoqu-liu/spager/issues

Uses libs:
  • openblas– Optimized BLAS
  • c++– GNU Standard C++ Library v3

On CRAN:

Conda:

openblascpp

3.51 score 1 stars 16 scripts 21 exports 14 dependencies

Last updated from:fa7fc0afbd (on main). Checks:11 WARNING, 2 OK. Indexed: yes.

TargetResultTimeFilesSyslog
linux-devel-arm64WARNING190
linux-devel-x86_64WARNING199
source / vignettesOK284
linux-release-arm64WARNING198
linux-release-x86_64WARNING211
macos-release-arm64WARNING110
macos-release-x86_64WARNING330
macos-oldrel-arm64WARNING119
macos-oldrel-x86_64WARNING330
windows-develWARNING198
windows-releaseWARNING197
windows-oldrelWARNING155
wasm-releaseOK171

Exports:check_seurat_versioncompare_expressioncompute_principal_vectorscosine_knnfilter_genesknn_imputelog_normalizelog_normalize_mediannormalize_rowsprepare_seuratprocess_dim_reductionPVComputationreset_parallelset_parallelSpaGESpaGE_batchSpaGE_cvSpaGE.Seuratvalidate_inputversion_infozscore

Dependencies:codetoolsdigestFNNfuturefuture.applyglobalsirlbalatticelistenvMASSMatrixparallellyRcppRcppArmadillo

SpaGER: Algorithm and Mathematical Foundation
Overview | The Challenge | Algorithm Steps | Step 1: Data Standardization | Step 2: Dimensionality Reduction | Step 3: Matrix Orthogonalization | Step 4: Principal Vectors Computation | Step 5: Projection | Step 6: Weighted k-NN Imputation | Comparison with Python Implementation | Summary | References | Session Information

Last update: 2026-01-24
Started: 2026-01-24

SpaGER: Quick Start Guide
Introduction | Why SpaGER? | Installation | Basic Usage | Load Package | Generate Simulated Data | Run SpaGE Prediction | Predict Specific Genes | Cross-Validation | Visualize CV Results | Accessing Metadata | Session Information

Last update: 2026-01-24
Started: 2026-01-24

SpaGER: Seurat Integration Guide
Overview | Prerequisites | Basic Workflow with Seurat | Load Your Data | Prepare Data (Optional) | Run SpaGE | Access Predictions | Seurat v4 vs v5 | Explicit Version Control | Predict Specific Genes | Return Data Frame Instead | Working with Different Assays | Visualization After Prediction | Batch Processing Multiple Gene Sets | Tips for Best Results | 1. Matching Cell Types | 2. Gene Filtering | 3. Normalize Consistently | Complete Example Workflow | Troubleshooting | Common Issues | Session Information

Last update: 2026-01-24
Started: 2026-01-24

SpaGER: Visualization and Analysis
Introduction | Simulated Dataset | Run SpaGE Prediction | Visualizing Principal Vector Selection | Spatial Expression Patterns | Cross-Validation Results | Measured vs Predicted Scatter Plots | Expression Distribution Comparison | Correlation Heatmap | Summary Statistics | Exporting Results | Session Information

Last update: 2026-01-24
Started: 2026-01-24