Zero-shot cell embedding evaluation of single-cell foundation models (Kedzierska et al. 2025)
Zero-shot cell embeddings from scGPT (four variants) and Geneformer compared with 2,000 highly variable genes, Harmony and scVI on five human scRNA-seq datasets, scored for cell-type separation and batch mixing with scIB metrics, plus a check of each model's pretraining reconstruction objective.
Results are recorded on the linked protocols, tasks or configurations listed below. Their settings and evaluations are kept separate.
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.
Results on linked records
This benchmark has no results of its own in this release. 3 linked records have results. They are not assigned to the underlying benchmark: each record keeps its own settings and evaluations, and its scores are on its own page.
- Kedzierska et al. 2025 cell embedding scoring, full embedding dimensions Protocol · part of this benchmark · 56 evaluations · 416 results
- Kedzierska et al. 2025 Geneformer pretraining-objective reconstruction Protocol · part of this benchmark · 1 evaluation · 2 results
- Kedzierska et al. 2025 cell embedding scoring after UMAP projection Protocol · part of this benchmark · 56 evaluations · 360 results
Methods and evaluation design
Procedure, tasks and evaluated configurations
Additional methodological details, tasks and evaluated configurations have not yet been extracted into a structured profile for this benchmark. Consult the linked sources and evaluation records below.
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 6 active baseline roles have published Rewire measurements in this release. Measurements on a selected protocol do not establish coverage of an entire suite.
Baseline status by linked protocol
- Kedzierska et al. 2025 cell embedding scoring, full embedding dimensions · 0/2 roles measured
- Kedzierska et al. 2025 Geneformer pretraining-objective reconstruction · 0/2 roles measured
- Kedzierska et al. 2025 cell embedding scoring after UMAP projection · 0/2 roles measured
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 benchmark. 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
| Property and statement | Original source and location | Review and provenance |
|---|
No evidence rows match these filters. Choose another scope or clear the search.
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
Technical metadata and extraction receipts
Stable ID: gfm-guides-20261014-kedzierska2025-benchmark-zero-shot-scfm
- areas
- single-cell
- contexts
- research
- entity level
- suite
- version
- Genome Biology 26:101 (2025)
- task
- Zero-shot cell embedding for cell-type clustering and batch integration
- scope note
- Five datasets (Pancreas, PBMC 12k, PBMC 95k, Immune, Tabula Sapiens) plus a Pancreas (8k) row; foundation models used without training, baselines fitted on each dataset.
- source locator
- Pages 3-5 'Results and discussion'; pages 7-10 'Methods'; Additional file 1