Configuration

scGPT blood (Kedzierska et al. 2025)

scGPT blood: scGPT blood cell representation; Zero-shot; pretrained weights, no fine-tuning; scGPT cell embedding.

14 evaluations · 97 results 4 open disagreements between studies involve its model

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.

Evaluations and results

14 evaluations · 97 results. Different protocols are not a single leaderboard.

Sorted by Adjusted rand index (Louvain clusters at best-NMI resolution versus cell-type labels; whole dataset; full embedding dimensions) (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 configuration	Protocol and dataset	Adjusted rand index (Louvain clusters at best-NMI resolution versus cell-type labels; whole dataset; full embedding dimensions)	Adjusted rand index (Louvain clusters at best-NMI resolution versus cell-type labels; whole dataset; UMAP projection of the embedding)	Avg bio (AvgBIO (mean of cell-type ASW, NMI and ARI; NMI and ARI on Louvain clusters at the best-NMI resolution); whole dataset; full embedding dimensions)	Avg bio (AvgBIO (mean of cell-type ASW, NMI and ARI; NMI and ARI on Louvain clusters at the best-NMI resolution); whole dataset; UMAP projection of the embedding)	Normalized mutual information (Louvain clusters at best-NMI resolution versus cell-type labels; whole dataset; full embedding dimensions)	Normalized mutual information (Louvain clusters at best-NMI resolution versus cell-type labels; whole dataset; UMAP projection of the embedding)	Scib asw label (cell-type ASW; whole dataset; full embedding dimensions)	Scib asw label (cell-type ASW; whole dataset; UMAP projection of the embedding)	Average batch score (average batch score (mean of batch integration score and PCR batch score); whole dataset; full embedding dimensions)	Average batch score (average batch score (mean of batch integration score and PCR batch score); whole dataset; UMAP projection of the embedding)	Rank (rank among the eight representations by mean biological-conservation and batch-mixing scores on this dataset (1 = best); full embedding dimensions)	Rank (rank among the eight representations by mean biological-conservation and batch-mixing scores on this dataset (1 = best); UMAP projection of the embedding)	Scib asw batch (batch integration score (batch ASW per cell type); whole dataset; full embedding dimensions)	Scib asw batch (batch integration score (batch ASW per cell type); whole dataset; UMAP projection of the embedding)	Scib pcr batch (principal component regression on batch; whole dataset; full embedding dimensions)	Scib pcr batch (principal component regression on batch; whole dataset; UMAP projection of the embedding)	Rank (overall average ranking across datasets, based on mean biological-conservation and batch-mixing scores (1 = best); full embedding dimensions)	Rank (overall average ranking across datasets, based on mean biological-conservation and batch-mixing scores (1 = best); UMAP projection of the embedding)	Rank (rank of the median ARI score across datasets among the eight representations (1 = best); full embedding dimensions)	Rank (rank of the median ASW score across datasets among the eight representations (1 = best); full embedding dimensions)	Rank (rank of the median Average batch score across datasets among the eight representations (1 = best); full embedding dimensions)	Rank (rank of the median Average BIO score across datasets among the eight representations (1 = best); full embedding dimensions)	Rank (rank of the median Batch integration score across datasets among the eight representations (1 = best); full embedding dimensions)	Rank (rank of the median NMI score across datasets among the eight representations (1 = best); full embedding dimensions)	Rank (rank of the median PCR score across datasets among the eight representations (1 = best); full embedding dimensions)
scGPT blood (Kedzierska et al. 2025)Evaluation	Kedzierska et al. 2025 cell embedding scoring, full embedding dimensions, PBMC (12k) (Kedzierska et al. 2025)	0.87 (best in column)	Not reported	0.76 (best in column)	Not reported	0.83 (best in column)	Not reported	0.6 (best in column)	Not reported	0.48	Not reported	4	Not reported	0.97 (best in column)	Not reported	0	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
scGPT blood (Kedzierska et al. 2025)Evaluation	Kedzierska et al. 2025 cell embedding scoring, full embedding dimensions, Immune (330k) (Kedzierska et al. 2025)	0.4	Not reported	0.53	Not reported	0.66	Not reported	0.52	Not reported	0.59 (best in column)	Not reported	3	Not reported	0.89	Not reported	0.28	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
scGPT blood (Kedzierska et al. 2025)Evaluation	Kedzierska et al. 2025 cell embedding scoring, full embedding dimensions, PBMC (95k) (Kedzierska et al. 2025)	0.37	Not reported	0.52	Not reported	0.65	Not reported	0.56	Not reported	Not reported	Not reported	5	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
scGPT blood (Kedzierska et al. 2025)Evaluation	Kedzierska et al. 2025 cell embedding scoring, full embedding dimensions, Tabula Sapiens (483k) (Kedzierska et al. 2025)	0.31	Not reported	0.45	Not reported	0.56	Not reported	0.47	Not reported	0.55	Not reported	2 (best in column)	Not reported	0.92	Not reported	0.17	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
scGPT blood (Kedzierska et al. 2025)Evaluation	Kedzierska et al. 2025 cell embedding scoring, full embedding dimensions, Pancreas (16k) (Kedzierska et al. 2025)	0.17	Not reported	0.34	Not reported	0.35	Not reported	0.49	Not reported	0.4	Not reported	6	Not reported	0.79	Not reported	0	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
scGPT blood (Kedzierska et al. 2025)Evaluation	Kedzierska et al. 2025 cell embedding scoring, full embedding dimensions, Pancreas (8k) (Kedzierska et al. 2025)	0.09	Not reported	0.28	Not reported	0.28	Not reported	0.49	Not reported	0.55	Not reported	Not reported	Not reported	0.82	Not reported	0.29 (best in column)	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
scGPT blood (Kedzierska et al. 2025)Evaluation	Kedzierska et al. 2025 cell embedding scoring, full embedding dimensions, Evaluated datasets, aggregated (Kedzierska et al. 2025)	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	4	Not reported	5	4	5	4	3	4	5
scGPT blood (Kedzierska et al. 2025)Evaluation	Kedzierska et al. 2025 cell embedding scoring after UMAP projection, Evaluated datasets, aggregated (Kedzierska et al. 2025)	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	4	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
scGPT blood (Kedzierska et al. 2025)Evaluation	Kedzierska et al. 2025 cell embedding scoring after UMAP projection, Immune (330k) (Kedzierska et al. 2025)	Not reported	0.35	Not reported	0.48	Not reported	0.6	Not reported	0.5	Not reported	0.59	Not reported	4	Not reported	0.56	Not reported	0.61	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
scGPT blood (Kedzierska et al. 2025)Evaluation	Kedzierska et al. 2025 cell embedding scoring after UMAP projection, Pancreas (16k) (Kedzierska et al. 2025)	Not reported	0.15	Not reported	0.31	Not reported	0.34	Not reported	0.45	Not reported	0.24	Not reported	5	Not reported	0.48	Not reported	0	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
scGPT blood (Kedzierska et al. 2025)Evaluation	Kedzierska et al. 2025 cell embedding scoring after UMAP projection, Pancreas (8k) (Kedzierska et al. 2025)	Not reported	0.1	Not reported	0.26	Not reported	0.28	Not reported	0.4	Not reported	0.18	Not reported	Not reported	Not reported	0.37	Not reported	0	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
scGPT blood (Kedzierska et al. 2025)Evaluation	Kedzierska et al. 2025 cell embedding scoring after UMAP projection, PBMC (12k) (Kedzierska et al. 2025)	Not reported	0.57 (best in column)	Not reported	0.68 (best in column)	Not reported	0.75 (best in column)	Not reported	0.73 (best in column)	Not reported	0.84 (best in column)	Not reported	3 (best in column)	Not reported	0.9 (best in column)	Not reported	0.77 (best in column)	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
scGPT blood (Kedzierska et al. 2025)Evaluation	Kedzierska et al. 2025 cell embedding scoring after UMAP projection, PBMC (95k) (Kedzierska et al. 2025)	Not reported	0.39	Not reported	0.51	Not reported	0.54	Not reported	0.6	Not reported	Not reported	Not reported	3 (best in column)	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
scGPT blood (Kedzierska et al. 2025)Evaluation	Kedzierska et al. 2025 cell embedding scoring after UMAP projection, Tabula Sapiens (483k) (Kedzierska et al. 2025)	Not reported	0.31	Not reported	0.41	Not reported	0.54	Not reported	0.37	Not reported	0.43	Not reported	4	Not reported	0.68	Not reported	0.18	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported

All 97 result rows with coverage, uncertainty and sources

Filter evaluations

Tested model or methodProtocolDatasetEvaluation setupMetricEvidence origin

Applied filters: All linked evaluations

Exact evaluated configurations and original reported results
Tested configuration	Protocol and dataset	Finding	Evidence and details
Configuration: scGPT blood (Kedzierska et al. 2025)	Protocol: Kedzierska et al. 2025 cell embedding scoring, full embedding dimensions Dataset subset: Evaluated datasets, aggregated (Kedzierska et al. 2025)	4 Rank (overall average ranking across datasets, based on mean biological-conservation and batch-mixing scores (1 = best); full embedding dimensions) unitless · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source scGPT blood cell embedding on evaluated datasets (Kedzierska et al. 2025) gfm-guides-20261014-kedzierska2025-protocol-cell-embedding Aggregation: Not reported Kedzierska et al. 2025, Additional file 1 (Supplementary Tables S1-S7, xlsx) · Additional file 1, sheet 'TableS4' cell B6, row 'scGPT blood', column 'Average ranking'
Configuration: scGPT blood (Kedzierska et al. 2025)	Protocol: Kedzierska et al. 2025 cell embedding scoring, full embedding dimensions Dataset subset: Evaluated datasets, aggregated (Kedzierska et al. 2025)	5 Rank (rank of the median ARI score across datasets among the eight representations (1 = best); full embedding dimensions) unitless · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source scGPT blood cell embedding on evaluated datasets (Kedzierska et al. 2025) gfm-guides-20261014-kedzierska2025-protocol-cell-embedding Aggregation: Not reported Kedzierska et al. 2025, Additional file 1 (Supplementary Tables S1-S7, xlsx) · Additional file 1, sheet 'TableS3' cell D6, row 'scGPT blood', column 'ARI'
Configuration: scGPT blood (Kedzierska et al. 2025)	Protocol: Kedzierska et al. 2025 cell embedding scoring, full embedding dimensions Dataset subset: Evaluated datasets, aggregated (Kedzierska et al. 2025)	4 Rank (rank of the median ASW score across datasets among the eight representations (1 = best); full embedding dimensions) unitless · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source scGPT blood cell embedding on evaluated datasets (Kedzierska et al. 2025) gfm-guides-20261014-kedzierska2025-protocol-cell-embedding Aggregation: Not reported Kedzierska et al. 2025, Additional file 1 (Supplementary Tables S1-S7, xlsx) · Additional file 1, sheet 'TableS3' cell C6, row 'scGPT blood', column 'ASW'
Configuration: scGPT blood (Kedzierska et al. 2025)	Protocol: Kedzierska et al. 2025 cell embedding scoring, full embedding dimensions Dataset subset: Evaluated datasets, aggregated (Kedzierska et al. 2025)	5 Rank (rank of the median Average batch score across datasets among the eight representations (1 = best); full embedding dimensions) unitless · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source scGPT blood cell embedding on evaluated datasets (Kedzierska et al. 2025) gfm-guides-20261014-kedzierska2025-protocol-cell-embedding Aggregation: Not reported Kedzierska et al. 2025, Additional file 1 (Supplementary Tables S1-S7, xlsx) · Additional file 1, sheet 'TableS3' cell F6, row 'scGPT blood', column 'Average batch'
Configuration: scGPT blood (Kedzierska et al. 2025)	Protocol: Kedzierska et al. 2025 cell embedding scoring, full embedding dimensions Dataset subset: Evaluated datasets, aggregated (Kedzierska et al. 2025)	4 Rank (rank of the median Average BIO score across datasets among the eight representations (1 = best); full embedding dimensions) unitless · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source scGPT blood cell embedding on evaluated datasets (Kedzierska et al. 2025) gfm-guides-20261014-kedzierska2025-protocol-cell-embedding Aggregation: Not reported Kedzierska et al. 2025, Additional file 1 (Supplementary Tables S1-S7, xlsx) · Additional file 1, sheet 'TableS3' cell B6, row 'scGPT blood', column 'Average BIO'
Configuration: scGPT blood (Kedzierska et al. 2025)	Protocol: Kedzierska et al. 2025 cell embedding scoring, full embedding dimensions Dataset subset: Evaluated datasets, aggregated (Kedzierska et al. 2025)	3 Rank (rank of the median Batch integration score across datasets among the eight representations (1 = best); full embedding dimensions) unitless · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source scGPT blood cell embedding on evaluated datasets (Kedzierska et al. 2025) gfm-guides-20261014-kedzierska2025-protocol-cell-embedding Aggregation: Not reported Kedzierska et al. 2025, Additional file 1 (Supplementary Tables S1-S7, xlsx) · Additional file 1, sheet 'TableS3' cell G6, row 'scGPT blood', column 'Batch integration'
Configuration: scGPT blood (Kedzierska et al. 2025)	Protocol: Kedzierska et al. 2025 cell embedding scoring, full embedding dimensions Dataset subset: Evaluated datasets, aggregated (Kedzierska et al. 2025)	4 Rank (rank of the median NMI score across datasets among the eight representations (1 = best); full embedding dimensions) unitless · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source scGPT blood cell embedding on evaluated datasets (Kedzierska et al. 2025) gfm-guides-20261014-kedzierska2025-protocol-cell-embedding Aggregation: Not reported Kedzierska et al. 2025, Additional file 1 (Supplementary Tables S1-S7, xlsx) · Additional file 1, sheet 'TableS3' cell E6, row 'scGPT blood', column 'NMI'
Configuration: scGPT blood (Kedzierska et al. 2025)	Protocol: Kedzierska et al. 2025 cell embedding scoring, full embedding dimensions Dataset subset: Evaluated datasets, aggregated (Kedzierska et al. 2025)	5 Rank (rank of the median PCR score across datasets among the eight representations (1 = best); full embedding dimensions) unitless · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source scGPT blood cell embedding on evaluated datasets (Kedzierska et al. 2025) gfm-guides-20261014-kedzierska2025-protocol-cell-embedding Aggregation: Not reported Kedzierska et al. 2025, Additional file 1 (Supplementary Tables S1-S7, xlsx) · Additional file 1, sheet 'TableS3' cell H6, row 'scGPT blood', column 'PCR'
Configuration: scGPT blood (Kedzierska et al. 2025)	Protocol: Kedzierska et al. 2025 cell embedding scoring, full embedding dimensions Dataset subset: Immune (330k) (Kedzierska et al. 2025)	0.4 Adjusted rand index (Louvain clusters at best-NMI resolution versus cell-type labels; whole dataset; full embedding dimensions) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source scGPT blood cell embedding on Immune (330k) (Kedzierska et al. 2025) gfm-guides-20261014-kedzierska2025-protocol-cell-embedding Aggregation: Not reported Kedzierska et al. 2025, Additional file 1 (Supplementary Tables S1-S7, xlsx) · Additional file 1, sheet 'TableS6' cell M19, metric block 'ARI', row 'Immune (330k)', column 'scGPT blood' (single-value column)
Configuration: scGPT blood (Kedzierska et al. 2025)	Protocol: Kedzierska et al. 2025 cell embedding scoring, full embedding dimensions Dataset subset: Immune (330k) (Kedzierska et al. 2025)	0.52 Scib asw label (cell-type ASW; whole dataset; full embedding dimensions) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source scGPT blood cell embedding on Immune (330k) (Kedzierska et al. 2025) gfm-guides-20261014-kedzierska2025-protocol-cell-embedding Aggregation: Not reported Kedzierska et al. 2025, Additional file 1 (Supplementary Tables S1-S7, xlsx) · Additional file 1, sheet 'TableS6' cell M7, metric block 'ASW', row 'Immune (330k)', column 'scGPT blood' (single-value column)
Configuration: scGPT blood (Kedzierska et al. 2025)	Protocol: Kedzierska et al. 2025 cell embedding scoring, full embedding dimensions Dataset subset: Immune (330k) (Kedzierska et al. 2025)	0.59 Average batch score (average batch score (mean of batch integration score and PCR batch score); whole dataset; full embedding dimensions) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source scGPT blood cell embedding on Immune (330k) (Kedzierska et al. 2025) gfm-guides-20261014-kedzierska2025-protocol-cell-embedding Aggregation: Not reported Kedzierska et al. 2025, Additional file 1 (Supplementary Tables S1-S7, xlsx) · Additional file 1, sheet 'TableS6' cell M40, metric block 'Average batch', row 'Immune (330k)', column 'scGPT blood' (single-value column)
Configuration: scGPT blood (Kedzierska et al. 2025)	Protocol: Kedzierska et al. 2025 cell embedding scoring, full embedding dimensions Dataset subset: Immune (330k) (Kedzierska et al. 2025)	0.53 Avg bio (AvgBIO (mean of cell-type ASW, NMI and ARI; NMI and ARI on Louvain clusters at the best-NMI resolution); whole dataset; full embedding dimensions) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source scGPT blood cell embedding on Immune (330k) (Kedzierska et al. 2025) gfm-guides-20261014-kedzierska2025-protocol-cell-embedding Aggregation: Not reported Kedzierska et al. 2025, Additional file 1 (Supplementary Tables S1-S7, xlsx) · Additional file 1, sheet 'TableS6' cell M25, metric block 'AvgBIO', row 'Immune (330k)', column 'scGPT blood' (single-value column)
Configuration: scGPT blood (Kedzierska et al. 2025)	Protocol: Kedzierska et al. 2025 cell embedding scoring, full embedding dimensions Dataset subset: Immune (330k) (Kedzierska et al. 2025)	0.89 Scib asw batch (batch integration score (batch ASW per cell type); whole dataset; full embedding dimensions) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source scGPT blood cell embedding on Immune (330k) (Kedzierska et al. 2025) gfm-guides-20261014-kedzierska2025-protocol-cell-embedding Aggregation: Not reported Kedzierska et al. 2025, Additional file 1 (Supplementary Tables S1-S7, xlsx) · Additional file 1, sheet 'TableS6' cell M30, metric block 'Batch integration', row 'Immune (330k)', column 'scGPT blood' (single-value column)
Configuration: scGPT blood (Kedzierska et al. 2025)	Protocol: Kedzierska et al. 2025 cell embedding scoring, full embedding dimensions Dataset subset: Immune (330k) (Kedzierska et al. 2025)	0.66 Normalized mutual information (Louvain clusters at best-NMI resolution versus cell-type labels; whole dataset; full embedding dimensions) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source scGPT blood cell embedding on Immune (330k) (Kedzierska et al. 2025) gfm-guides-20261014-kedzierska2025-protocol-cell-embedding Aggregation: Not reported Kedzierska et al. 2025, Additional file 1 (Supplementary Tables S1-S7, xlsx) · Additional file 1, sheet 'TableS6' cell M13, metric block 'NMI', row 'Immune (330k)', column 'scGPT blood' (single-value column)
Configuration: scGPT blood (Kedzierska et al. 2025)	Protocol: Kedzierska et al. 2025 cell embedding scoring, full embedding dimensions Dataset subset: Immune (330k) (Kedzierska et al. 2025)	0.28 Scib pcr batch (principal component regression on batch; whole dataset; full embedding dimensions) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source scGPT blood cell embedding on Immune (330k) (Kedzierska et al. 2025) gfm-guides-20261014-kedzierska2025-protocol-cell-embedding Aggregation: Not reported Kedzierska et al. 2025, Additional file 1 (Supplementary Tables S1-S7, xlsx) · Additional file 1, sheet 'TableS6' cell M35, metric block 'PCR', row 'Immune (330k)', column 'scGPT blood' (single-value column)
Configuration: scGPT blood (Kedzierska et al. 2025)	Protocol: Kedzierska et al. 2025 cell embedding scoring, full embedding dimensions Dataset subset: Immune (330k) (Kedzierska et al. 2025)	3 Rank (rank among the eight representations by mean biological-conservation and batch-mixing scores on this dataset (1 = best); full embedding dimensions) unitless · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source scGPT blood cell embedding on Immune (330k) (Kedzierska et al. 2025) gfm-guides-20261014-kedzierska2025-protocol-cell-embedding Aggregation: Not reported Kedzierska et al. 2025, Additional file 1 (Supplementary Tables S1-S7, xlsx) · Additional file 1, sheet 'TableS4' cell F6, row 'scGPT blood', column 'Immune (330k)'
Configuration: scGPT blood (Kedzierska et al. 2025)	Protocol: Kedzierska et al. 2025 cell embedding scoring, full embedding dimensions Dataset subset: Pancreas (16k) (Kedzierska et al. 2025)	0.17 Adjusted rand index (Louvain clusters at best-NMI resolution versus cell-type labels; whole dataset; full embedding dimensions) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source scGPT blood cell embedding on Pancreas (16k) (Kedzierska et al. 2025) gfm-guides-20261014-kedzierska2025-protocol-cell-embedding Aggregation: Not reported Kedzierska et al. 2025, Additional file 1 (Supplementary Tables S1-S7, xlsx) · Additional file 1, sheet 'TableS6' cell M15, metric block 'ARI', row 'Pancreas (16k)', column 'scGPT blood' (single-value column)
Configuration: scGPT blood (Kedzierska et al. 2025)	Protocol: Kedzierska et al. 2025 cell embedding scoring, full embedding dimensions Dataset subset: Pancreas (16k) (Kedzierska et al. 2025)	0.49 Scib asw label (cell-type ASW; whole dataset; full embedding dimensions) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source scGPT blood cell embedding on Pancreas (16k) (Kedzierska et al. 2025) gfm-guides-20261014-kedzierska2025-protocol-cell-embedding Aggregation: Not reported Kedzierska et al. 2025, Additional file 1 (Supplementary Tables S1-S7, xlsx) · Additional file 1, sheet 'TableS6' cell M3, metric block 'ASW', row 'Pancreas (16k)', column 'scGPT blood' (single-value column)
Configuration: scGPT blood (Kedzierska et al. 2025)	Protocol: Kedzierska et al. 2025 cell embedding scoring, full embedding dimensions Dataset subset: Pancreas (16k) (Kedzierska et al. 2025)	0.4 Average batch score (average batch score (mean of batch integration score and PCR batch score); whole dataset; full embedding dimensions) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source scGPT blood cell embedding on Pancreas (16k) (Kedzierska et al. 2025) gfm-guides-20261014-kedzierska2025-protocol-cell-embedding Aggregation: Not reported Kedzierska et al. 2025, Additional file 1 (Supplementary Tables S1-S7, xlsx) · Additional file 1, sheet 'TableS6' cell M37, metric block 'Average batch', row 'Pancreas (16k)', column 'scGPT blood' (single-value column)
Configuration: scGPT blood (Kedzierska et al. 2025)	Protocol: Kedzierska et al. 2025 cell embedding scoring, full embedding dimensions Dataset subset: Pancreas (16k) (Kedzierska et al. 2025)	0.34 Avg bio (AvgBIO (mean of cell-type ASW, NMI and ARI; NMI and ARI on Louvain clusters at the best-NMI resolution); whole dataset; full embedding dimensions) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source scGPT blood cell embedding on Pancreas (16k) (Kedzierska et al. 2025) gfm-guides-20261014-kedzierska2025-protocol-cell-embedding Aggregation: Not reported Kedzierska et al. 2025, Additional file 1 (Supplementary Tables S1-S7, xlsx) · Additional file 1, sheet 'TableS6' cell M21, metric block 'AvgBIO', row 'Pancreas (16k)', column 'scGPT blood' (single-value column)
Configuration: scGPT blood (Kedzierska et al. 2025)	Protocol: Kedzierska et al. 2025 cell embedding scoring, full embedding dimensions Dataset subset: Pancreas (16k) (Kedzierska et al. 2025)	0.79 Scib asw batch (batch integration score (batch ASW per cell type); whole dataset; full embedding dimensions) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source scGPT blood cell embedding on Pancreas (16k) (Kedzierska et al. 2025) gfm-guides-20261014-kedzierska2025-protocol-cell-embedding Aggregation: Not reported Kedzierska et al. 2025, Additional file 1 (Supplementary Tables S1-S7, xlsx) · Additional file 1, sheet 'TableS6' cell M27, metric block 'Batch integration', row 'Pancreas (16k)', column 'scGPT blood' (single-value column)
Configuration: scGPT blood (Kedzierska et al. 2025)	Protocol: Kedzierska et al. 2025 cell embedding scoring, full embedding dimensions Dataset subset: Pancreas (16k) (Kedzierska et al. 2025)	0.35 Normalized mutual information (Louvain clusters at best-NMI resolution versus cell-type labels; whole dataset; full embedding dimensions) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source scGPT blood cell embedding on Pancreas (16k) (Kedzierska et al. 2025) gfm-guides-20261014-kedzierska2025-protocol-cell-embedding Aggregation: Not reported Kedzierska et al. 2025, Additional file 1 (Supplementary Tables S1-S7, xlsx) · Additional file 1, sheet 'TableS6' cell M9, metric block 'NMI', row 'Pancreas (16k)', column 'scGPT blood' (single-value column)
Configuration: scGPT blood (Kedzierska et al. 2025)	Protocol: Kedzierska et al. 2025 cell embedding scoring, full embedding dimensions Dataset subset: Pancreas (16k) (Kedzierska et al. 2025)	0 Scib pcr batch (principal component regression on batch; whole dataset; full embedding dimensions) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source scGPT blood cell embedding on Pancreas (16k) (Kedzierska et al. 2025) gfm-guides-20261014-kedzierska2025-protocol-cell-embedding Aggregation: Not reported Kedzierska et al. 2025, Additional file 1 (Supplementary Tables S1-S7, xlsx) · Additional file 1, sheet 'TableS6' cell M32, metric block 'PCR', row 'Pancreas (16k)', column 'scGPT blood' (single-value column)
Configuration: scGPT blood (Kedzierska et al. 2025)	Protocol: Kedzierska et al. 2025 cell embedding scoring, full embedding dimensions Dataset subset: Pancreas (16k) (Kedzierska et al. 2025)	6 Rank (rank among the eight representations by mean biological-conservation and batch-mixing scores on this dataset (1 = best); full embedding dimensions) unitless · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source scGPT blood cell embedding on Pancreas (16k) (Kedzierska et al. 2025) gfm-guides-20261014-kedzierska2025-protocol-cell-embedding Aggregation: Not reported Kedzierska et al. 2025, Additional file 1 (Supplementary Tables S1-S7, xlsx) · Additional file 1, sheet 'TableS4' cell C6, row 'scGPT blood', column 'Pancreas (16k)'
Configuration: scGPT blood (Kedzierska et al. 2025)	Protocol: Kedzierska et al. 2025 cell embedding scoring, full embedding dimensions Dataset subset: Pancreas (8k) (Kedzierska et al. 2025)	0.09 Adjusted rand index (Louvain clusters at best-NMI resolution versus cell-type labels; whole dataset; full embedding dimensions) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source scGPT blood cell embedding on Pancreas (8k) (Kedzierska et al. 2025) gfm-guides-20261014-kedzierska2025-protocol-cell-embedding Aggregation: Not reported Kedzierska et al. 2025, Additional file 1 (Supplementary Tables S1-S7, xlsx) · Additional file 1, sheet 'TableS6' cell M16, metric block 'ARI', row 'Pancreas (8k)', column 'scGPT blood' (single-value column)

Source checking is not independent reproduction. Release 2026-10-23-5347695500ed.

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 2026-10-23-5347695500ed
Property and statement	Original source and location	Review and provenance

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

How to read the evidence

Sources and history

Release 2026-10-23-5347695500ed · Record review: source checked

1 source record and release history

Zero-shot evaluation reveals limitations of single-cell foundation models (Kedzierska et al. 2025, Genome Biology 26:101) · Original source · Version of record, Genome Biology 26:101, published 2025-04-18

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: gfm-guides-20261014-kedzierska2025-config-scgpt-blood

areas: single-cell
contexts: research
method types: foundation_model
reported name: scGPT blood
foundation model eligible: true
training setting: Zero-shot; pretrained weights, no fine-tuning
representation: scGPT cell embedding
version: scGPT code 0.1.6 (2023-09-14)
checkpoint: scGPT pretrained on 10.3 million blood and bone marrow cells
access reuse: Evaluation code: github.com/microsoft/zero-shot-scfoundation (MIT), archived on Zenodo; not pinned to a commit in the article
source locator: Pages 7-8 'Models and baselines'; page 11 'Code availability'
provenance note: scGPT blood cell representation as evaluated zero-shot by Kedzierska et al. 2025.

Related records

Suggest a correction