OpenProblems - Benchmarks

Batch integration embed

Removing batch effects while preserving biological variation (embedding output)

Batch integration feature

Removing batch effects while preserving biological variation (feature output)

Batch integration graph

Removing batch effects while preserving biological variation (graph output)

Cell-Cell Communication Inference (Ligand-Target)

Detect interactions between ligands and target cell types

Cell-Cell Communication Inference (Source-Target)

Detect interactions between source and target cell types

Denoising

Removing noise in sparse single-cell RNA-sequencing count data

Dimensionality reduction for visualisation

Reduction of high-dimensional datasets to 2D for visualization & interpretation

Label Projection

Automated cell type annotation from rich, labeled reference data

Matching modalities

Alignment of cellular profiles from two different modalities

Regulatory effect prediction

Prediction of gene expression from chromatin accessibility

Spatial Decomposition

Calling cell-type compositions for spot-based spatial transcriptomics data

Additional information

Task quality control