Protocol

Kedzierska et al. 2025 cell embedding scoring, full embedding dimensions

Cell embeddings (or the 2,000-HVG expression matrix) of each dataset scored for cell-type separation (ASW, NMI, ARI, AvgBIO) and batch mixing (batch integration ASW, PCR, average batch score) in the full embedding dimensions.

56 evaluations · 416 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.

56 recorded evaluations, 416 metric rows. A comparison chart has not yet been validated for these results. The table retains the individual findings and their sources.

View coverage and remaining gaps across all benchmarks

Results

Results are available, but no reviewed comparison panel is linked in this release.

All evaluations

56 evaluations · 416 results. Different protocols are not a single leaderboard.

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: Geneformer (Kedzierska et al. 2025)	Protocol: Kedzierska et al. 2025 cell embedding scoring, full embedding dimensions Dataset subset: Evaluated datasets, aggregated (Kedzierska et al. 2025)	8 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 Geneformer 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 B10, row 'Geneformer', column 'Average ranking'
Configuration: Geneformer (Kedzierska et al. 2025)	Protocol: Kedzierska et al. 2025 cell embedding scoring, full embedding dimensions Dataset subset: Evaluated datasets, aggregated (Kedzierska et al. 2025)	7 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 Geneformer 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 D9, row 'Geneformer', column 'ARI'
Configuration: Geneformer (Kedzierska et al. 2025)	Protocol: Kedzierska et al. 2025 cell embedding scoring, full embedding dimensions Dataset subset: Evaluated datasets, aggregated (Kedzierska et al. 2025)	8 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 Geneformer 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 C9, row 'Geneformer', column 'ASW'
Configuration: Geneformer (Kedzierska et al. 2025)	Protocol: Kedzierska et al. 2025 cell embedding scoring, full embedding dimensions Dataset subset: Evaluated datasets, aggregated (Kedzierska et al. 2025)	8 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 Geneformer 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 F9, row 'Geneformer', column 'Average batch'
Configuration: Geneformer (Kedzierska et al. 2025)	Protocol: Kedzierska et al. 2025 cell embedding scoring, full embedding dimensions Dataset subset: Evaluated datasets, aggregated (Kedzierska et al. 2025)	7 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 Geneformer 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 B9, row 'Geneformer', column 'Average BIO'
Configuration: Geneformer (Kedzierska et al. 2025)	Protocol: Kedzierska et al. 2025 cell embedding scoring, full embedding dimensions Dataset subset: Evaluated datasets, aggregated (Kedzierska et al. 2025)	7 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 Geneformer 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 G9, row 'Geneformer', column 'Batch integration'
Configuration: Geneformer (Kedzierska et al. 2025)	Protocol: Kedzierska et al. 2025 cell embedding scoring, full embedding dimensions Dataset subset: Evaluated datasets, aggregated (Kedzierska et al. 2025)	8 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 Geneformer 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 E9, row 'Geneformer', column 'NMI'
Configuration: Geneformer (Kedzierska et al. 2025)	Protocol: Kedzierska et al. 2025 cell embedding scoring, full embedding dimensions Dataset subset: Evaluated datasets, aggregated (Kedzierska et al. 2025)	8 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 Geneformer 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 H9, row 'Geneformer', column 'PCR'
Configuration: Harmony (Kedzierska et al. 2025)	Protocol: Kedzierska et al. 2025 cell embedding scoring, full embedding dimensions Dataset subset: Evaluated datasets, aggregated (Kedzierska et al. 2025)	2 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 Harmony 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 B4, row 'Harmony', column 'Average ranking'
Configuration: Harmony (Kedzierska et al. 2025)	Protocol: Kedzierska et al. 2025 cell embedding scoring, full embedding dimensions Dataset subset: Evaluated datasets, aggregated (Kedzierska et al. 2025)	2 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 Harmony 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 D4, row 'Harmony', column 'ARI'
Configuration: Harmony (Kedzierska et al. 2025)	Protocol: Kedzierska et al. 2025 cell embedding scoring, full embedding dimensions Dataset subset: Evaluated datasets, aggregated (Kedzierska et al. 2025)	1 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 Harmony 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 C4, row 'Harmony', column 'ASW'
Configuration: Harmony (Kedzierska et al. 2025)	Protocol: Kedzierska et al. 2025 cell embedding scoring, full embedding dimensions Dataset subset: Evaluated datasets, aggregated (Kedzierska et al. 2025)	2 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 Harmony 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 F4, row 'Harmony', column 'Average batch'
Configuration: Harmony (Kedzierska et al. 2025)	Protocol: Kedzierska et al. 2025 cell embedding scoring, full embedding dimensions Dataset subset: Evaluated datasets, aggregated (Kedzierska et al. 2025)	2 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 Harmony 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 B4, row 'Harmony', column 'Average BIO'
Configuration: Harmony (Kedzierska et al. 2025)	Protocol: Kedzierska et al. 2025 cell embedding scoring, full embedding dimensions Dataset subset: Evaluated datasets, aggregated (Kedzierska et al. 2025)	8 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 Harmony 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 G4, row 'Harmony', column 'Batch integration'
Configuration: Harmony (Kedzierska et al. 2025)	Protocol: Kedzierska et al. 2025 cell embedding scoring, full embedding dimensions Dataset subset: Evaluated datasets, aggregated (Kedzierska et al. 2025)	2 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 Harmony 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 E4, row 'Harmony', column 'NMI'
Configuration: Harmony (Kedzierska et al. 2025)	Protocol: Kedzierska et al. 2025 cell embedding scoring, full embedding dimensions Dataset subset: Evaluated datasets, aggregated (Kedzierska et al. 2025)	2 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 Harmony 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 H4, row 'Harmony', column 'PCR'
Configuration: 2,000 highly variable genes (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 (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 HVG 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 B5, row 'HVG', column 'Average ranking'
Configuration: 2,000 highly variable genes (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 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 HVG 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 D5, row 'HVG', column 'ARI'
Configuration: 2,000 highly variable genes (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 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 HVG 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 C5, row 'HVG', column 'ASW'
Configuration: 2,000 highly variable genes (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 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 HVG 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 F5, row 'HVG', column 'Average batch'
Configuration: 2,000 highly variable genes (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 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 HVG 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 B5, row 'HVG', column 'Average BIO'
Configuration: 2,000 highly variable genes (Kedzierska et al. 2025)	Protocol: Kedzierska et al. 2025 cell embedding scoring, full embedding dimensions Dataset subset: Evaluated datasets, aggregated (Kedzierska et al. 2025)	1 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 HVG 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 G5, row 'HVG', column 'Batch integration'
Configuration: 2,000 highly variable genes (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 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 HVG 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 E5, row 'HVG', column 'NMI'
Configuration: 2,000 highly variable genes (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 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 HVG 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 H5, row 'HVG', column 'PCR'
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'

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

Methods and evaluation design

Procedure, tasks and evaluated configurations

Recorded evaluations

Each evaluation records what was tested and under which conditions.

Explore all linked results

Baseline coverage

Reference methods help show what a model adds beyond simple controls. We track a null control and a conventional method for each protocol.

0 of 2 active baseline roles have published Rewire measurements in this release. Measurements on a selected protocol do not establish coverage of an entire suite.

No execution recipe linked to this protocol. Recipe availability does not establish a completed evaluation.

External evaluations: 56

Literature evidence is not a Rewire measurement. Executed but unpublished runs and private review status are not included.

Null control

Proposed control: requires review

Unintegrated representation using protocol preprocessing

Protocol-specific applicability, permitted inputs, access, split, evaluator and execution requirements need review before implementation or execution.

This is a suggested selection rule, not a validated method or a measured score.

Conventional reference

Proposed control: requires review

Protocol-specific conventional integration method

Protocol-specific applicability, permitted inputs, access, split, evaluator and execution requirements need review before implementation or execution.

This is a suggested selection rule, not a validated method or a measured score.

Protocol coverage CSV (gzip) · Model evaluation matrix (gzip) · Source table (gzip) · Release and checksums (gzip)

Coverage is derived from release 2026-10-23-5347695500ed. Source citations describe the original records; they do not validate an unreviewed baseline proposal. No results have been generated by this audit.

Run instructions

No runnable recipe has been reviewed for this protocol. Dataset access, model requirements, licences and compute requirements must be checked against its sources before execution.

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

2 source records 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
Kedzierska et al. 2025, Additional file 1 (Supplementary Tables S1-S7, xlsx) · Original source · Additional file 1 (13059_2025_3574_MOESM1_ESM.xlsx) of the version of record

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: gfm-guides-20261014-kedzierska2025-protocol-cell-embedding

areas: single-cell
contexts: research
protocol: Embed each whole dataset; compute scIB metrics against the dataset's cell-type and batch labels in the full embedding dimensions.
version: Genome Biology 26:101
metric implementation: scib 1.0.4. ASW of cell-type labels rescaled to [0, 1]; NMI and ARI on Louvain clusters at the resolution with the highest NMI out of 20; batch integration = 1 minus absolute batch silhouette per cell type, averaged; PCR = change in variance explained by batch between the original data and the embedding (Methods, pages 9-10).
unit: unitless
limitations: One run on each whole dataset; spread across 10 repeats of 10% subsamples is printed separately and not extracted.; scVI and Harmony are trained on each target dataset; scGPT and Geneformer are not trained on it.
source locator: Pages 9-10 'Biological preservation scores', 'Batch mixing scores'; Additional file 1 sheet TableS6

Related records

part of: Zero-shot cell embedding evaluation of single-cell foundation models (Kedzierska et al. 2025)
used in: Evaluated datasets, aggregated (Kedzierska et al. 2025)
used in: Immune (330k) (Kedzierska et al. 2025)
used in: Pancreas (16k) (Kedzierska et al. 2025)
used in: Pancreas (8k) (Kedzierska et al. 2025)
used in: PBMC (12k) (Kedzierska et al. 2025)
used in: PBMC (95k) (Kedzierska et al. 2025)
used in: Tabula Sapiens (483k) (Kedzierska et al. 2025)
assessment: Geneformer cell embedding on evaluated datasets (Kedzierska et al. 2025)
assessment: Harmony cell embedding on evaluated datasets (Kedzierska et al. 2025)
assessment: HVG cell embedding on evaluated datasets (Kedzierska et al. 2025)
assessment: scGPT blood cell embedding on evaluated datasets (Kedzierska et al. 2025)
assessment: scGPT human cell embedding on evaluated datasets (Kedzierska et al. 2025)
assessment: scGPT kidney cell embedding on evaluated datasets (Kedzierska et al. 2025)
assessment: scGPT random cell embedding on evaluated datasets (Kedzierska et al. 2025)
assessment: scVI cell embedding on evaluated datasets (Kedzierska et al. 2025)
assessment: Geneformer cell embedding on Immune (330k) (Kedzierska et al. 2025)
assessment: Harmony cell embedding on Immune (330k) (Kedzierska et al. 2025)
assessment: HVG cell embedding on Immune (330k) (Kedzierska et al. 2025)
assessment: scGPT blood cell embedding on Immune (330k) (Kedzierska et al. 2025)
assessment: scGPT human cell embedding on Immune (330k) (Kedzierska et al. 2025)
assessment: scGPT kidney cell embedding on Immune (330k) (Kedzierska et al. 2025)
assessment: scGPT random cell embedding on Immune (330k) (Kedzierska et al. 2025)
assessment: scVI cell embedding on Immune (330k) (Kedzierska et al. 2025)
assessment: Geneformer cell embedding on Pancreas (16k) (Kedzierska et al. 2025)
assessment: Harmony cell embedding on Pancreas (16k) (Kedzierska et al. 2025)
assessment: HVG cell embedding on Pancreas (16k) (Kedzierska et al. 2025)
assessment: scGPT blood cell embedding on Pancreas (16k) (Kedzierska et al. 2025)
assessment: scGPT human cell embedding on Pancreas (16k) (Kedzierska et al. 2025)
assessment: scGPT kidney cell embedding on Pancreas (16k) (Kedzierska et al. 2025)
assessment: scGPT random cell embedding on Pancreas (16k) (Kedzierska et al. 2025)
assessment: scVI cell embedding on Pancreas (16k) (Kedzierska et al. 2025)
assessment: Geneformer cell embedding on Pancreas (8k) (Kedzierska et al. 2025)
assessment: Harmony cell embedding on Pancreas (8k) (Kedzierska et al. 2025)
assessment: HVG cell embedding on Pancreas (8k) (Kedzierska et al. 2025)
assessment: scGPT blood cell embedding on Pancreas (8k) (Kedzierska et al. 2025)
assessment: scGPT human cell embedding on Pancreas (8k) (Kedzierska et al. 2025)
assessment: scGPT kidney cell embedding on Pancreas (8k) (Kedzierska et al. 2025)
assessment: scGPT random cell embedding on Pancreas (8k) (Kedzierska et al. 2025)
assessment: scVI cell embedding on Pancreas (8k) (Kedzierska et al. 2025)
assessment: Geneformer cell embedding on PBMC (12k) (Kedzierska et al. 2025)
assessment: Harmony cell embedding on PBMC (12k) (Kedzierska et al. 2025)
assessment: HVG cell embedding on PBMC (12k) (Kedzierska et al. 2025)
assessment: scGPT blood cell embedding on PBMC (12k) (Kedzierska et al. 2025)
assessment: scGPT human cell embedding on PBMC (12k) (Kedzierska et al. 2025)
assessment: scGPT kidney cell embedding on PBMC (12k) (Kedzierska et al. 2025)
assessment: scGPT random cell embedding on PBMC (12k) (Kedzierska et al. 2025)
assessment: scVI cell embedding on PBMC (12k) (Kedzierska et al. 2025)
assessment: Geneformer cell embedding on PBMC (95k) (Kedzierska et al. 2025)
assessment: Harmony cell embedding on PBMC (95k) (Kedzierska et al. 2025)
assessment: HVG cell embedding on PBMC (95k) (Kedzierska et al. 2025)
assessment: scGPT blood cell embedding on PBMC (95k) (Kedzierska et al. 2025)
assessment: scGPT human cell embedding on PBMC (95k) (Kedzierska et al. 2025)
assessment: scGPT kidney cell embedding on PBMC (95k) (Kedzierska et al. 2025)
assessment: scGPT random cell embedding on PBMC (95k) (Kedzierska et al. 2025)
assessment: scVI cell embedding on PBMC (95k) (Kedzierska et al. 2025)
assessment: Geneformer cell embedding on Tabula Sapiens (483k) (Kedzierska et al. 2025)
assessment: Harmony cell embedding on Tabula Sapiens (483k) (Kedzierska et al. 2025)
assessment: HVG cell embedding on Tabula Sapiens (483k) (Kedzierska et al. 2025)
assessment: scGPT blood cell embedding on Tabula Sapiens (483k) (Kedzierska et al. 2025)
assessment: scGPT human cell embedding on Tabula Sapiens (483k) (Kedzierska et al. 2025)
assessment: scGPT kidney cell embedding on Tabula Sapiens (483k) (Kedzierska et al. 2025)
assessment: scGPT random cell embedding on Tabula Sapiens (483k) (Kedzierska et al. 2025)
assessment: scVI cell embedding on Tabula Sapiens (483k) (Kedzierska et al. 2025)

Suggest a correction