rewirebio.iobenchmarks
Configuration

HyCell (HyCell report)

Produces a frozen cell embedding with HyCell as the HyCell report runs it.

38 evaluations · 38 results

Overview

An explanatory profile has not yet been reviewed for this record.

Consult the linked sources for architecture or protocol details. Missing evidence is not evidence of a missing capability.

Model Capabilities & Hardware Requirements

Deployment facts recorded for HyCell (HyCell report). Fields the record does not carry are marked not recorded.

ParametersNot recorded
Minimum VRAMNot recorded
Inference LatencyNot recorded
Context WindowNot recorded
AccessNot recorded
LicenseNot recorded

Evaluated Checkpoint: hycell-16m, package 0.1.0

Evaluations and results

38 evaluations · 38 results. Different protocols are not a single leaderboard.

Sorted by Scib bio conservation score (Mean of seven scIB biological-conservation metrics (isolated-label score, NMI and ARI of k-means and of Leiden clusters against the cell types, cell-type silhouette and cLISI), per atlas or averaged over the seven atlases) (higher is better). The best value in each column is highlighted. Decimals are rounded for display; each value links to the printed value and its source.

Tested configurationProtocol and datasetScib bio conservation score (Mean of seven scIB biological-conservation metrics (isolated-label score, NMI and ARI of k-means and of Leiden clusters against the cell types, cell-type silhouette and cLISI), per atlas or averaged over the seven atlases)Weighted composite score (S = 0.3 Bio + 0.2 Batch + 0.25 LR + 0.25 kNN, the authors' weighting, which gives the scIB total (0.6 Bio + 0.4 Batch) and annotation transfer equal weight; per atlas or averaged over the seven atlases)Macro F1 (Macro-F1 of a 15-nearest-neighbour classifier trained on the other batches, over the cell types of the held-out batch, averaged over held-out batches; per atlas or averaged over the seven atlases)Macro F1 (Macro-F1 of a logistic-regression classifier trained on the other batches, over the cell types of the held-out batch, averaged over held-out batches; per atlas or averaged over the seven atlases)Scib batch correction score (Mean of five scIB batch-correction metrics (batch silhouette, iLISI, kBET, graph connectivity and principal-component regression), per atlas or averaged over the seven atlases)Adjusted rand index (ARI between a two-group k-means split of the embeddings of the atlas's 2,778 CD4 T cells (1,343 naive or central-memory, 1,435 effector or effector-memory) and the naive-effector annotation, over all cells)Adjusted rand index (ARI between a two-group split of gamma-delta T cells and tissue-resident CD8 T cells and their annotation)Adjusted rand index (The same two-group split made within each donor, where chemistry no longer varies; mean ARI over the 12 donors)Normalized mutual information (NMI between the two-group k-means split of the CD4 T cells and their sequencing chemistry; lower means the split ignores chemistry, which is what the analysis seeks)Spearman (Mean over donors of the Spearman correlation between one donor's program for classical to nonclassical monocytes and the program of all other donors, from the HyCell decoder or from pseudobulk counts)Spearman (Mean over donors of the Spearman correlation between one donor's program for naive B to plasma cells and the program of all other donors, from the HyCell decoder or from pseudobulk counts)Spearman (Mean over donors of the Spearman correlation between one donor's program for naive to effector CD4 T cells and the program of all other donors, from the HyCell decoder or from pseudobulk counts)Spearman (Spearman correlation between diffusion pseudotime and differentiation stage (naive B, germinal-centre B, plasmablast, plasma cell) over the 3,751 cells of these states, rooted at the medoid of the 50 cells with the highest naive-B marker score (TCL1A, IGHD, FCER2))Spearman (Spearman correlation between the decoder's fold change and the counted pseudobulk fold change from naive B to plasma cells over the 12,879 genes detected in at least 1% of either state)Spearman (The same Spearman correlation between pseudotime and stage computed per donor and averaged over the 12 donors)
HyCell (HyCell report)EvaluationscIB biological conservation (HyCell report), PBMC from two 10x Genomics runs (HyCell report)0.78 (best in column)Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
HyCell (HyCell report)EvaluationscIB biological conservation (HyCell report), MultiVINE brain vasculature, healthy donors (HyCell report)0.757Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
HyCell (HyCell report)EvaluationscIB biological conservation (HyCell report), scIB human pancreas atlas, integer-count part (HyCell report)0.725Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
HyCell (HyCell report)EvaluationscIB biological conservation (HyCell report), Seven held-out atlases of the HyCell report0.7Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
HyCell (HyCell report)EvaluationscIB biological conservation (HyCell report), scIB human immune atlas, integer-count part (HyCell report)0.681Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
HyCell (HyCell report)EvaluationscIB biological conservation (HyCell report), scIB human lung atlas, integer-count part (HyCell report)0.677Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
HyCell (HyCell report)EvaluationscIB biological conservation (HyCell report), Asian Immune Diversity Atlas, sample (HyCell report)0.644Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
HyCell (HyCell report)EvaluationscIB biological conservation (HyCell report), Cross-tissue immune atlas, stratified sample (HyCell report)0.633Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
HyCell (HyCell report)EvaluationAnnotation transfer with 15-nearest neighbours (HyCell report), scIB human immune atlas, integer-count part (HyCell report)Not reportedNot reported0.873Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
HyCell (HyCell report)EvaluationAnnotation transfer with 15-nearest neighbours (HyCell report), scIB human lung atlas, integer-count part (HyCell report)Not reportedNot reported0.758Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
HyCell (HyCell report)EvaluationAnnotation transfer with 15-nearest neighbours (HyCell report), scIB human pancreas atlas, integer-count part (HyCell report)Not reportedNot reported0.838Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
HyCell (HyCell report)EvaluationAnnotation transfer with 15-nearest neighbours (HyCell report), PBMC from two 10x Genomics runs (HyCell report)Not reportedNot reported0.936 (best in column)Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
HyCell (HyCell report)EvaluationAnnotation transfer with 15-nearest neighbours (HyCell report), Seven held-out atlases of the HyCell reportNot reportedNot reported0.833Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
HyCell (HyCell report)EvaluationAnnotation transfer with logistic regression (HyCell report), scIB human immune atlas, integer-count part (HyCell report)Not reportedNot reportedNot reported0.857Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
HyCell (HyCell report)EvaluationAnnotation transfer with logistic regression (HyCell report), scIB human lung atlas, integer-count part (HyCell report)Not reportedNot reportedNot reported0.768Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
HyCell (HyCell report)EvaluationAnnotation transfer with logistic regression (HyCell report), scIB human pancreas atlas, integer-count part (HyCell report)Not reportedNot reportedNot reported0.832Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
HyCell (HyCell report)EvaluationAnnotation transfer with logistic regression (HyCell report), PBMC from two 10x Genomics runs (HyCell report)Not reportedNot reportedNot reported0.961 (best in column)Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
HyCell (HyCell report)EvaluationAnnotation transfer with logistic regression (HyCell report), Seven held-out atlases of the HyCell reportNot reportedNot reportedNot reported0.847Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
HyCell (HyCell report)EvaluationscIB batch correction (HyCell report), Cross-tissue immune atlas, stratified sample (HyCell report)Not reportedNot reportedNot reportedNot reported0.54 (best in column)Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
HyCell (HyCell report)EvaluationscIB batch correction (HyCell report), Seven held-out atlases of the HyCell reportNot reportedNot reportedNot reportedNot reported0.527Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
HyCell (HyCell report)EvaluationNaive against effector CD4 T-cell split, ARI (HyCell report), Cross-tissue immune atlas, stratified sample (HyCell report)Not reportedNot reportedNot reportedNot reportedNot reported0.64Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
HyCell (HyCell report)EvaluationNaive against effector CD4 T-cell split within donors, ARI (HyCell report), Cross-tissue immune atlas, stratified sample (HyCell report)Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported0.66Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
HyCell (HyCell report)EvaluationCD4 T-cell split against sequencing chemistry, NMI (HyCell report), Cross-tissue immune atlas, stratified sample (HyCell report)Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported0.012Not reportedNot reportedNot reportedNot reportedNot reportedNot reported
HyCell (HyCell report)EvaluationComposite score S (HyCell report), Asian Immune Diversity Atlas, sample (HyCell report)Not reported0.665Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
HyCell (HyCell report)EvaluationComposite score S (HyCell report), MultiVINE brain vasculature, healthy donors (HyCell report)Not reported0.775Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
HyCell (HyCell report)EvaluationComposite score S (HyCell report), Cross-tissue immune atlas, stratified sample (HyCell report)Not reported0.697Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
HyCell (HyCell report)EvaluationComposite score S (HyCell report), scIB human immune atlas, integer-count part (HyCell report)Not reported0.735Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
HyCell (HyCell report)EvaluationComposite score S (HyCell report), scIB human lung atlas, integer-count part (HyCell report)Not reported0.686Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
HyCell (HyCell report)EvaluationComposite score S (HyCell report), scIB human pancreas atlas, integer-count part (HyCell report)Not reported0.717Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
HyCell (HyCell report)EvaluationComposite score S (HyCell report), PBMC from two 10x Genomics runs (HyCell report)Not reported0.871 (best in column)Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
HyCell (HyCell report)EvaluationComposite score S (HyCell report), Seven held-out atlases of the HyCell reportNot reported0.735Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
HyCell (HyCell report)EvaluationDecoded against counted fold change, plasma against naive B (HyCell report), Cross-tissue immune atlas, stratified sample (HyCell report)Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported0.81Not reported
HyCell (HyCell report)EvaluationGene-program consistency across donors, naive to effector CD4 T cells (HyCell report), Cross-tissue immune atlas, stratified sample (HyCell report)Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported0.957Not reportedNot reportedNot reported
HyCell (HyCell report)EvaluationGene-program consistency across donors, classical to nonclassical monocytes (HyCell report), Cross-tissue immune atlas, stratified sample (HyCell report)Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported0.94Not reportedNot reportedNot reportedNot reportedNot reported
HyCell (HyCell report)EvaluationGene-program consistency across donors, naive B to plasma cells (HyCell report), Cross-tissue immune atlas, stratified sample (HyCell report)Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported0.965Not reportedNot reportedNot reportedNot reported
HyCell (HyCell report)Evaluationgamma-delta T against tissue-resident CD8 T split, ARI (HyCell report), Cross-tissue immune atlas, stratified sample (HyCell report)Not reportedNot reportedNot reportedNot reportedNot reportedNot reported0.37Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported
HyCell (HyCell report)EvaluationB-cell to plasma-cell pseudotime ordering, donor mean (HyCell report), Cross-tissue immune atlas, stratified sample (HyCell report)Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported0.894
HyCell (HyCell report)EvaluationB-cell to plasma-cell pseudotime ordering, all cells (HyCell report), Cross-tissue immune atlas, stratified sample (HyCell report)Not reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reportedNot reported0.937Not reportedNot reported
All 38 result rows with coverage, uncertainty and sources
Filter evaluations

Applied filters: All linked evaluations

Exact evaluated configurations and original reported results
Tested configurationProtocol and datasetFindingEvidence and details
Configuration: HyCell (HyCell report)Protocol: Annotation transfer with 15-nearest neighbours (HyCell report)
Dataset: scIB human immune atlas, integer-count part (HyCell report)
0.873 Macro F1 (Macro-F1 of a 15-nearest-neighbour classifier trained on the other batches, over the cell types of the held-out batch, averaged over held-out batches; per atlas or averaged over the seven atlases)
fraction · higher

Uncertainty: Not reported by the source: No uncertainty is printed anywhere in the report.

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

HyCell on annotation-transfer-knn, immune (HyCell report)

hycell-20261106-protocol-annotation-transfer-knn

Aggregation: Not reported

HyCell: a Compact Embedding Model for Single-Cell Transcriptomes (Hyra Team, 2026-11-01) · Table 5, row 'Immune', column 'Frozen + kNN' (page 8 of 9)
Configuration: HyCell (HyCell report)Protocol: Annotation transfer with 15-nearest neighbours (HyCell report)
Dataset: scIB human lung atlas, integer-count part (HyCell report)
0.758 Macro F1 (Macro-F1 of a 15-nearest-neighbour classifier trained on the other batches, over the cell types of the held-out batch, averaged over held-out batches; per atlas or averaged over the seven atlases)
fraction · higher

Uncertainty: Not reported by the source: No uncertainty is printed anywhere in the report.

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

HyCell on annotation-transfer-knn, lung (HyCell report)

hycell-20261106-protocol-annotation-transfer-knn

Aggregation: Not reported

HyCell: a Compact Embedding Model for Single-Cell Transcriptomes (Hyra Team, 2026-11-01) · Table 5, row 'Lung', column 'Frozen + kNN' (page 8 of 9)
Configuration: HyCell (HyCell report)Protocol: Annotation transfer with 15-nearest neighbours (HyCell report)
Dataset: scIB human pancreas atlas, integer-count part (HyCell report)
0.838 Macro F1 (Macro-F1 of a 15-nearest-neighbour classifier trained on the other batches, over the cell types of the held-out batch, averaged over held-out batches; per atlas or averaged over the seven atlases)
fraction · higher

Uncertainty: Not reported by the source: No uncertainty is printed anywhere in the report.

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

HyCell on annotation-transfer-knn, pancreas (HyCell report)

hycell-20261106-protocol-annotation-transfer-knn

Aggregation: Not reported

HyCell: a Compact Embedding Model for Single-Cell Transcriptomes (Hyra Team, 2026-11-01) · Table 5, row 'Pancreas', column 'Frozen + kNN' (page 8 of 9)
Configuration: HyCell (HyCell report)Protocol: Annotation transfer with 15-nearest neighbours (HyCell report)
Dataset: PBMC from two 10x Genomics runs (HyCell report)
0.936 Macro F1 (Macro-F1 of a 15-nearest-neighbour classifier trained on the other batches, over the cell types of the held-out batch, averaged over held-out batches; per atlas or averaged over the seven atlases)
fraction · higher

Uncertainty: Not reported by the source: No uncertainty is printed anywhere in the report.

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

HyCell on annotation-transfer-knn, pbmc (HyCell report)

hycell-20261106-protocol-annotation-transfer-knn

Aggregation: Not reported

HyCell: a Compact Embedding Model for Single-Cell Transcriptomes (Hyra Team, 2026-11-01) · Table 5, row 'PBMC', column 'Frozen + kNN' (page 8 of 9)
Configuration: HyCell (HyCell report)Protocol: Annotation transfer with 15-nearest neighbours (HyCell report)
Dataset: Seven held-out atlases of the HyCell report
0.833 Macro F1 (Macro-F1 of a 15-nearest-neighbour classifier trained on the other batches, over the cell types of the held-out batch, averaged over held-out batches; per atlas or averaged over the seven atlases)
fraction · higher

Uncertainty: Not reported by the source: No uncertainty is printed anywhere in the report.

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

HyCell on annotation-transfer-knn, seven-held-out-atlases (HyCell report)

hycell-20261106-protocol-annotation-transfer-knn

Aggregation: Not reported

HyCell: a Compact Embedding Model for Single-Cell Transcriptomes (Hyra Team, 2026-11-01) · Table 3, row 'HyCell', column 'kNN' (page 5 of 9)
Configuration: HyCell (HyCell report)Protocol: Annotation transfer with logistic regression (HyCell report)
Dataset: scIB human immune atlas, integer-count part (HyCell report)
0.857 Macro F1 (Macro-F1 of a logistic-regression classifier trained on the other batches, over the cell types of the held-out batch, averaged over held-out batches; per atlas or averaged over the seven atlases)
fraction · higher

Uncertainty: Not reported by the source: No uncertainty is printed anywhere in the report.

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

HyCell on annotation-transfer-lr, immune (HyCell report)

hycell-20261106-protocol-annotation-transfer-lr

Aggregation: Not reported

HyCell: a Compact Embedding Model for Single-Cell Transcriptomes (Hyra Team, 2026-11-01) · Table 5, row 'Immune', column 'Frozen + LR' (page 8 of 9)
Configuration: HyCell (HyCell report)Protocol: Annotation transfer with logistic regression (HyCell report)
Dataset: scIB human lung atlas, integer-count part (HyCell report)
0.768 Macro F1 (Macro-F1 of a logistic-regression classifier trained on the other batches, over the cell types of the held-out batch, averaged over held-out batches; per atlas or averaged over the seven atlases)
fraction · higher

Uncertainty: Not reported by the source: No uncertainty is printed anywhere in the report.

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

HyCell on annotation-transfer-lr, lung (HyCell report)

hycell-20261106-protocol-annotation-transfer-lr

Aggregation: Not reported

HyCell: a Compact Embedding Model for Single-Cell Transcriptomes (Hyra Team, 2026-11-01) · Table 5, row 'Lung', column 'Frozen + LR' (page 8 of 9)
Configuration: HyCell (HyCell report)Protocol: Annotation transfer with logistic regression (HyCell report)
Dataset: scIB human pancreas atlas, integer-count part (HyCell report)
0.832 Macro F1 (Macro-F1 of a logistic-regression classifier trained on the other batches, over the cell types of the held-out batch, averaged over held-out batches; per atlas or averaged over the seven atlases)
fraction · higher

Uncertainty: Not reported by the source: No uncertainty is printed anywhere in the report.

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

HyCell on annotation-transfer-lr, pancreas (HyCell report)

hycell-20261106-protocol-annotation-transfer-lr

Aggregation: Not reported

HyCell: a Compact Embedding Model for Single-Cell Transcriptomes (Hyra Team, 2026-11-01) · Table 5, row 'Pancreas', column 'Frozen + LR' (page 8 of 9)
Configuration: HyCell (HyCell report)Protocol: Annotation transfer with logistic regression (HyCell report)
Dataset: PBMC from two 10x Genomics runs (HyCell report)
0.961 Macro F1 (Macro-F1 of a logistic-regression classifier trained on the other batches, over the cell types of the held-out batch, averaged over held-out batches; per atlas or averaged over the seven atlases)
fraction · higher

Uncertainty: Not reported by the source: No uncertainty is printed anywhere in the report.

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

HyCell on annotation-transfer-lr, pbmc (HyCell report)

hycell-20261106-protocol-annotation-transfer-lr

Aggregation: Not reported

HyCell: a Compact Embedding Model for Single-Cell Transcriptomes (Hyra Team, 2026-11-01) · Table 5, row 'PBMC', column 'Frozen + LR' (page 8 of 9)
Configuration: HyCell (HyCell report)Protocol: Annotation transfer with logistic regression (HyCell report)
Dataset: Seven held-out atlases of the HyCell report
0.847 Macro F1 (Macro-F1 of a logistic-regression classifier trained on the other batches, over the cell types of the held-out batch, averaged over held-out batches; per atlas or averaged over the seven atlases)
fraction · higher

Uncertainty: Not reported by the source: No uncertainty is printed anywhere in the report.

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

HyCell on annotation-transfer-lr, seven-held-out-atlases (HyCell report)

hycell-20261106-protocol-annotation-transfer-lr

Aggregation: Not reported

HyCell: a Compact Embedding Model for Single-Cell Transcriptomes (Hyra Team, 2026-11-01) · Table 3, row 'HyCell', column 'LR' (page 5 of 9)
Configuration: HyCell (HyCell report)Protocol: scIB batch correction (HyCell report)
Dataset: Cross-tissue immune atlas, stratified sample (HyCell report)
0.54 Scib batch correction score (Mean of five scIB batch-correction metrics (batch silhouette, iLISI, kBET, graph connectivity and principal-component regression), per atlas or averaged over the seven atlases)
unitless · higher

Uncertainty: Not reported by the source: No uncertainty is printed anywhere in the report.

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

HyCell on batch-correction, cross-tissue-immune (HyCell report)

hycell-20261106-protocol-batch-correction

Aggregation: Not reported

HyCell: a Compact Embedding Model for Single-Cell Transcriptomes (Hyra Team, 2026-11-01) · Section 3.2 'Embedding structure', final sentence (page 6 of 9); HyCell batch correction
Configuration: HyCell (HyCell report)Protocol: scIB batch correction (HyCell report)
Dataset: Seven held-out atlases of the HyCell report
0.527 Scib batch correction score (Mean of five scIB batch-correction metrics (batch silhouette, iLISI, kBET, graph connectivity and principal-component regression), per atlas or averaged over the seven atlases)
unitless · higher

Uncertainty: Not reported by the source: No uncertainty is printed anywhere in the report.

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

HyCell on batch-correction, seven-held-out-atlases (HyCell report)

hycell-20261106-protocol-batch-correction

Aggregation: Not reported

HyCell: a Compact Embedding Model for Single-Cell Transcriptomes (Hyra Team, 2026-11-01) · Table 3, row 'HyCell', column 'Batch' (page 5 of 9)
Configuration: HyCell (HyCell report)Protocol: scIB biological conservation (HyCell report)
Dataset: Asian Immune Diversity Atlas, sample (HyCell report)
0.644 Scib bio conservation score (Mean of seven scIB biological-conservation metrics (isolated-label score, NMI and ARI of k-means and of Leiden clusters against the cell types, cell-type silhouette and cLISI), per atlas or averaged over the seven atlases)
unitless · higher

Uncertainty: Not reported by the source: No uncertainty is printed anywhere in the report.

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

HyCell on bio-conservation, aida (HyCell report)

hycell-20261106-protocol-bio-conservation

Aggregation: Not reported

HyCell: a Compact Embedding Model for Single-Cell Transcriptomes (Hyra Team, 2026-11-01) · Figure 1b, row 'AIDA', column 'HyCell', printed value (page 2 of 9)
Configuration: HyCell (HyCell report)Protocol: scIB biological conservation (HyCell report)
Dataset: MultiVINE brain vasculature, healthy donors (HyCell report)
0.757 Scib bio conservation score (Mean of seven scIB biological-conservation metrics (isolated-label score, NMI and ARI of k-means and of Leiden clusters against the cell types, cell-type silhouette and cLISI), per atlas or averaged over the seven atlases)
unitless · higher

Uncertainty: Not reported by the source: No uncertainty is printed anywhere in the report.

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

HyCell on bio-conservation, brain (HyCell report)

hycell-20261106-protocol-bio-conservation

Aggregation: Not reported

HyCell: a Compact Embedding Model for Single-Cell Transcriptomes (Hyra Team, 2026-11-01) · Figure 1b, row 'Brain', column 'HyCell', printed value (page 2 of 9)
Configuration: HyCell (HyCell report)Protocol: scIB biological conservation (HyCell report)
Dataset: Cross-tissue immune atlas, stratified sample (HyCell report)
0.633 Scib bio conservation score (Mean of seven scIB biological-conservation metrics (isolated-label score, NMI and ARI of k-means and of Leiden clusters against the cell types, cell-type silhouette and cLISI), per atlas or averaged over the seven atlases)
unitless · higher

Uncertainty: Not reported by the source: No uncertainty is printed anywhere in the report.

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

HyCell on bio-conservation, cross-tissue-immune (HyCell report)

hycell-20261106-protocol-bio-conservation

Aggregation: Not reported

HyCell: a Compact Embedding Model for Single-Cell Transcriptomes (Hyra Team, 2026-11-01) · Figure 1b, row 'Cross-tissue immune', column 'HyCell', printed value (page 2 of 9)
Configuration: HyCell (HyCell report)Protocol: scIB biological conservation (HyCell report)
Dataset: scIB human immune atlas, integer-count part (HyCell report)
0.681 Scib bio conservation score (Mean of seven scIB biological-conservation metrics (isolated-label score, NMI and ARI of k-means and of Leiden clusters against the cell types, cell-type silhouette and cLISI), per atlas or averaged over the seven atlases)
unitless · higher

Uncertainty: Not reported by the source: No uncertainty is printed anywhere in the report.

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

HyCell on bio-conservation, immune (HyCell report)

hycell-20261106-protocol-bio-conservation

Aggregation: Not reported

HyCell: a Compact Embedding Model for Single-Cell Transcriptomes (Hyra Team, 2026-11-01) · Figure 1b, row 'Immune', column 'HyCell', printed value (page 2 of 9)
Configuration: HyCell (HyCell report)Protocol: scIB biological conservation (HyCell report)
Dataset: scIB human lung atlas, integer-count part (HyCell report)
0.677 Scib bio conservation score (Mean of seven scIB biological-conservation metrics (isolated-label score, NMI and ARI of k-means and of Leiden clusters against the cell types, cell-type silhouette and cLISI), per atlas or averaged over the seven atlases)
unitless · higher

Uncertainty: Not reported by the source: No uncertainty is printed anywhere in the report.

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

HyCell on bio-conservation, lung (HyCell report)

hycell-20261106-protocol-bio-conservation

Aggregation: Not reported

HyCell: a Compact Embedding Model for Single-Cell Transcriptomes (Hyra Team, 2026-11-01) · Figure 1b, row 'Lung', column 'HyCell', printed value (page 2 of 9)
Configuration: HyCell (HyCell report)Protocol: scIB biological conservation (HyCell report)
Dataset: scIB human pancreas atlas, integer-count part (HyCell report)
0.725 Scib bio conservation score (Mean of seven scIB biological-conservation metrics (isolated-label score, NMI and ARI of k-means and of Leiden clusters against the cell types, cell-type silhouette and cLISI), per atlas or averaged over the seven atlases)
unitless · higher

Uncertainty: Not reported by the source: No uncertainty is printed anywhere in the report.

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

HyCell on bio-conservation, pancreas (HyCell report)

hycell-20261106-protocol-bio-conservation

Aggregation: Not reported

HyCell: a Compact Embedding Model for Single-Cell Transcriptomes (Hyra Team, 2026-11-01) · Figure 1b, row 'Pancreas', column 'HyCell', printed value (page 2 of 9)
Configuration: HyCell (HyCell report)Protocol: scIB biological conservation (HyCell report)
Dataset: PBMC from two 10x Genomics runs (HyCell report)
0.78 Scib bio conservation score (Mean of seven scIB biological-conservation metrics (isolated-label score, NMI and ARI of k-means and of Leiden clusters against the cell types, cell-type silhouette and cLISI), per atlas or averaged over the seven atlases)
unitless · higher

Uncertainty: Not reported by the source: No uncertainty is printed anywhere in the report.

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

HyCell on bio-conservation, pbmc (HyCell report)

hycell-20261106-protocol-bio-conservation

Aggregation: Not reported

HyCell: a Compact Embedding Model for Single-Cell Transcriptomes (Hyra Team, 2026-11-01) · Figure 1b, row 'PBMC', column 'HyCell', printed value (page 2 of 9)
Configuration: HyCell (HyCell report)Protocol: scIB biological conservation (HyCell report)
Dataset: Seven held-out atlases of the HyCell report
0.7 Scib bio conservation score (Mean of seven scIB biological-conservation metrics (isolated-label score, NMI and ARI of k-means and of Leiden clusters against the cell types, cell-type silhouette and cLISI), per atlas or averaged over the seven atlases)
unitless · higher

Uncertainty: Not reported by the source: No uncertainty is printed anywhere in the report.

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

HyCell on bio-conservation, seven-held-out-atlases (HyCell report)

hycell-20261106-protocol-bio-conservation

Aggregation: Not reported

HyCell: a Compact Embedding Model for Single-Cell Transcriptomes (Hyra Team, 2026-11-01) · Table 3, row 'HyCell', column 'Bio' (page 5 of 9)
Configuration: HyCell (HyCell report)Protocol: Naive against effector CD4 T-cell split, ARI (HyCell report)
Dataset: Cross-tissue immune atlas, stratified sample (HyCell report)
0.64 Adjusted rand index (ARI between a two-group k-means split of the embeddings of the atlas's 2,778 CD4 T cells (1,343 naive or central-memory, 1,435 effector or effector-memory) and the naive-effector annotation, over all cells)
unitless · higher

Uncertainty: Not reported by the source: No uncertainty is printed anywhere in the report.

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

HyCell on cd4-split-ari, cross-tissue-immune (HyCell report)

hycell-20261106-protocol-cd4-split-ari

Aggregation: Not reported

HyCell: a Compact Embedding Model for Single-Cell Transcriptomes (Hyra Team, 2026-11-01) · Section 4.1 (page 6 of 9), sentence giving HyCell's split (ARI)
Configuration: HyCell (HyCell report)Protocol: Naive against effector CD4 T-cell split within donors, ARI (HyCell report)
Dataset: Cross-tissue immune atlas, stratified sample (HyCell report)
0.66 Adjusted rand index (The same two-group split made within each donor, where chemistry no longer varies; mean ARI over the 12 donors)
unitless · higher

Uncertainty: Not reported by the source: No uncertainty is printed anywhere in the report.

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

HyCell on cd4-split-ari-within-donor, cross-tissue-immune (HyCell report)

hycell-20261106-protocol-cd4-split-ari-within-donor

Aggregation: Not reported

HyCell: a Compact Embedding Model for Single-Cell Transcriptomes (Hyra Team, 2026-11-01) · Section 4.1 (page 6 of 9), sentence 'Within single donors', value for HyCell
Configuration: HyCell (HyCell report)Protocol: CD4 T-cell split against sequencing chemistry, NMI (HyCell report)
Dataset: Cross-tissue immune atlas, stratified sample (HyCell report)
0.012 Normalized mutual information (NMI between the two-group k-means split of the CD4 T cells and their sequencing chemistry; lower means the split ignores chemistry, which is what the analysis seeks)
unitless · lower

Uncertainty: Not reported by the source: No uncertainty is printed anywhere in the report.

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

HyCell on cd4-split-nmi-chemistry, cross-tissue-immune (HyCell report)

hycell-20261106-protocol-cd4-split-nmi-chemistry

Aggregation: Not reported

HyCell: a Compact Embedding Model for Single-Cell Transcriptomes (Hyra Team, 2026-11-01) · Section 4.1 (page 6 of 9), 'NMI with chemistry'
Configuration: HyCell (HyCell report)Protocol: Composite score S (HyCell report)
Dataset: Asian Immune Diversity Atlas, sample (HyCell report)
0.665 Weighted composite score (S = 0.3 Bio + 0.2 Batch + 0.25 LR + 0.25 kNN, the authors' weighting, which gives the scIB total (0.6 Bio + 0.4 Batch) and annotation transfer equal weight; per atlas or averaged over the seven atlases)
unitless · higher

Uncertainty: Not reported by the source: No uncertainty is printed anywhere in the report.

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

HyCell on composite-score, aida (HyCell report)

hycell-20261106-protocol-composite-score

Aggregation: Not reported

HyCell: a Compact Embedding Model for Single-Cell Transcriptomes (Hyra Team, 2026-11-01) · Table 4, row 'HyCell', column 'AIDA' (page 5 of 9)
Configuration: HyCell (HyCell report)Protocol: Composite score S (HyCell report)
Dataset: MultiVINE brain vasculature, healthy donors (HyCell report)
0.775 Weighted composite score (S = 0.3 Bio + 0.2 Batch + 0.25 LR + 0.25 kNN, the authors' weighting, which gives the scIB total (0.6 Bio + 0.4 Batch) and annotation transfer equal weight; per atlas or averaged over the seven atlases)
unitless · higher

Uncertainty: Not reported by the source: No uncertainty is printed anywhere in the report.

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

HyCell on composite-score, brain (HyCell report)

hycell-20261106-protocol-composite-score

Aggregation: Not reported

HyCell: a Compact Embedding Model for Single-Cell Transcriptomes (Hyra Team, 2026-11-01) · Table 4, row 'HyCell', column 'Brain' (page 5 of 9)

Source checking is not independent reproduction. Release 2026-11-21-c8bea25e5abb.

Use this configuration

How it works, versions and access

Additional methodological details, versions and access terms have not yet been extracted into a structured profile for this configuration. Consult the linked sources and evaluation records below.

Evidence

Source checking verifies the cited claim or transcription. It does not establish independent reproduction.

Evidence table

Inspect claims, sources and review details

Trace each statement to its source and review. A context-only reference supports the record generally; it does not verify an individual field. Source checking does not reproduce an experiment.

One row per statement and cited source. Multiple citations are not independent evaluations. Shared locators are labelled explicitly.

0 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-11-21-c8bea25e5abb
Property and statementOriginal source and locationReview and provenance

No evidence rows match these filters. Choose another scope or clear the search.

Sources and history

Release 2026-11-21-c8bea25e5abb · Record review: source checked

1 source record and release historyDownload this release (gzip)
Technical metadata and record identifiers

Technical metadata for this record is tracked under stable ID hycell-20261106-config-hycell.

Source locator: Section 3.1 'Models'; Table 3

Related records

How to cite

HyCell (HyCell report). Rewire biological model benchmark database, release 2026-11-21-c8bea25e5abb. https://benchmarks.rewirebio.io/database/configuration/hycell-20261106-config-hycell/

Release 2026-11-21-c8bea25e5abb. Rankings and values change between releases, so keep the release id in the citation. Cite the original publication as well for any value you reuse: each result links its source.

The compilation and annotations made by Rewire in this release are offered under CC BY 4.0; values and text taken from cited sources stay under the terms of those sources and are not covered by this licence. Data licence

Suggest a correction