the platform

Benchmarks

Formalized open problems in single-cell analysis, each with gold-standard datasets, quantitative metrics, and a continuously updated leaderboard.

showing 12 of 12

Batch Integration

Remove unwanted batch effects from scRNA-seq data while retaining biologically meaningful variation.

18 methods 6 datasets 13 metrics 4 releases

Cell-Cell Communication

Detect interactions between source and target cell types

7 methods 1 datasets 2 metrics 2 releases

Denoising

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

5 methods 3 datasets 2 metrics 1 release

Dimensionality Reduction for Visualisation

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

11 methods 4 datasets 10 metrics 1 release

Foundation Models

Modelling of single-cells to perform multiple tasks using

7 methods 4 datasets 2 metrics 1 release

Label Projection

Automated cell type annotation from rich, labeled reference data

14 methods 6 datasets 4 metrics 2 releases

Multimodal Data Integration

Alignment of cellular profiles from two different modalities

3 methods 3 datasets 2 metrics 1 release

Perturbation Prediction

Predicting how small molecules change gene expression in different cell types.

6 methods 1 datasets 5 metrics 1 release

Predict Modality

Predicting the profiles of one modality (e.g. protein abundance) from another (e.g. mRNA expression).

3 methods 6 datasets 8 metrics 1 release

Spatial Decomposition

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

9 methods 7 datasets 1 metrics 1 release

Spatial Simulators

Assessing the quality of spatial transcriptomics simulators

8 methods 10 datasets 39 metrics 1 release

Spatially Variable Genes

Spatially variable genes (SVGs) are genes whose expression levels vary significantly across different spatial regions within a tissue or across cells in a spatially structured context.

14 methods 50 datasets 1 metrics 1 release