Evaluation Metrics
Review 24 benchmark metrics used to compare 23 single-cell analysis models across 66 datasets.
Full LAIOR Dashboard
For interactive charts, detailed comparisons, and full filtering capabilities, visit the LAIOR Dashboard. Note: this portal documents the evaluation metrics used; full benchmark results are available on the LAIOR Dashboard.
Open Full DashboardEvaluation Metrics
Clustering
- NMI
- ARI
- ASW
- Calinski-Harabasz
- Davies-Bouldin
Dim. Reduction
- Q_local
- Q_global
- Trustworthiness
- Continuity
Latent Space
- Manifold Dim.
- Intrinsic Dim.
- Spectral Decay
Runtime
- Training Time
- Memory Usage
- Inference Speed
Model Categories
Predictive Models
2 modelsModels focused on prediction tasks
Generative Models
10 modelsVAE-based generative approaches
scATAC-Specific
2 modelsChromatin accessibility focused
Trajectory
1 modelsTrajectory inference models
Geometric
4 modelsHyperbolic and geometric approaches
Disentanglement
4 modelsDisentangled representation learning
Benchmark Repositories
LAIOR
Benchmark dataset repository with 24 evaluation metrics across 66 datasets (48 scRNA-seq, 18 scATAC-seq) and 23 models.
View LAIOR DashboardiAODE
Benchmark dataset repository with 617 datasets from 113 studies (434 scATAC-seq, 183 scRNA-seq).
View iAODE BrowserRelated Destinations
Move from metric documentation into the public benchmark and dataset destinations that supply the surrounding context.
LAIOR Benchmarks
Related SiteCompare models, rankings, and benchmark results in LAIOR.
Open LAIOR BenchmarksscCCVGBen
Related SiteReview scCCVGBen model comparisons, metric coverage, and benchmark figures.
Open scCCVGBenGAHIB Companion Site
Related SiteRead how GAHIB works and compare it with other benchmark methods.
Open GAHIB Companion SiteiAODE Pages
Related SiteOpen the matching iAODE dataset and explorer pages for these metrics.
Open iAODE Pages