Models / single-cell / scimilarity / benchmarks

single-cell/scimilarity

Visibility: PUBLIC

Model card FilesBenchmarks

Group by

Single-cell batch integration (scIB) single-cell/single-cell-batch-integration

Drawn from: cellxgene-census

atlas-n500-v1

Metric	Value	95% CI	n	Rank	Best in catalogue	Source	Overlap	Board
Cell-type ASW (zero-shot) ↑ higher is better · zero-shot	0.624 best	[0.618, 0.631]	500	1 / 4	0.624	reproduced	overlap Train/test overlap declared by the evaluator: single-cell/cellxgene-census	Board
Batch ASW (zero-shot) ↑ higher is better · zero-shot	0.783	[0.770, 0.795]	500	4 / 4	0.875	reproduced	overlap Train/test overlap declared by the evaluator: single-cell/cellxgene-census	Board
Graph connectivity (zero-shot) ↑ higher is better · zero-shot	0.998	[0.994, 1.000]	500	2 / 4	1.000	reproduced	overlap Train/test overlap declared by the evaluator: single-cell/cellxgene-census	Board
scIB bio conservation, unscaled (zero-shot) ↑ higher is better · zero-shot	0.711 best	[0.702, 0.725]	500	1 / 4	0.711	reproduced	overlap Train/test overlap declared by the evaluator: single-cell/cellxgene-census	Board
scIB batch correction, unscaled (zero-shot) ↑ higher is better · zero-shot	0.644 best	[0.619, 0.665]	500	1 / 4	0.644	reproduced	overlap Train/test overlap declared by the evaluator: single-cell/cellxgene-census	Board
scIB total, unscaled (zero-shot) ↑ higher is better · zero-shot	0.684 best	[0.672, 0.696]	500	1 / 4	0.684	reproduced	overlap Train/test overlap declared by the evaluator: single-cell/cellxgene-census	Board
NMI, k-means (zero-shot) ↑ higher is better · zero-shot · secondary	0.764 best	[0.752, 0.787]	500	—	0.764	reproduced	overlap Train/test overlap declared by the evaluator: single-cell/cellxgene-census	Board
ARI, k-means (zero-shot) ↑ higher is better · zero-shot · secondary	0.534 best	[0.511, 0.569]	500	—	0.534	reproduced	overlap Train/test overlap declared by the evaluator: single-cell/cellxgene-census	Board
Isolated-label ASW (zero-shot) ↑ higher is better · zero-shot · secondary	0.681 best	[0.673, 0.689]	500	—	0.681	reproduced	overlap Train/test overlap declared by the evaluator: single-cell/cellxgene-census	Board
cLISI (zero-shot) ↑ higher is better · zero-shot · secondary	0.952 best	[0.943, 0.961]	500	—	0.952	reproduced	overlap Train/test overlap declared by the evaluator: single-cell/cellxgene-census	Board
iLISI (zero-shot) ↑ higher is better · zero-shot · secondary	0.245 best	[0.218, 0.267]	500	—	0.245	reproduced	overlap Train/test overlap declared by the evaluator: single-cell/cellxgene-census	Board
kBET acceptance (zero-shot) ↑ higher is better · zero-shot · secondary	0.621	[0.583, 0.661]	500	—	0.632	reproduced	overlap Train/test overlap declared by the evaluator: single-cell/cellxgene-census	Board
scIB batch correction, unscaled, without PCR (zero-shot) ↑ higher is better · zero-shot · secondary	0.662	[0.650, 0.674]	500	—	0.673	reproduced	overlap Train/test overlap declared by the evaluator: single-cell/cellxgene-census	Board
scIB total, unscaled, without PCR (zero-shot) ↑ higher is better · zero-shot · secondary	0.692 best	[0.684, 0.702]	500	—	0.692	reproduced	overlap Train/test overlap declared by the evaluator: single-cell/cellxgene-census	Board
PCR comparison (zero-shot) ↑ higher is better · zero-shot · secondary	0.573 best	[0.466, 0.650]	500	—	0.573	reproduced	overlap Train/test overlap declared by the evaluator: single-cell/cellxgene-census	Board