Datasets
Human thymus scRNA-seq data from GSE144870, alongside separate breast and cortex evaluations.
Task
Human thymus cell-type classification
Human thymus annotation evaluates transfer from a mouse-trained gene representation after homolog mapping.
Sources
Mouse-Geneformer: A deep learning model for mouse single-cell transcriptome and its cross-species utility · Results: cross-species human cell classification; cached text line 41Overview
Metrics
Cell-type classification accuracy.
Allowed inputs
Gene-expression profiles represented by Geneformer models.
Sources
Mouse-Geneformer: A deep learning model for mouse single-cell transcriptome and its cross-species utility · Results: cross-species human cell classification; cached text line 41Evaluation procedure diagram
How it worksComputational evaluation flow
Conceptual summary of the cited evaluation; exact task configuration and source version remain part of the protocol.
Sources
Mouse-Geneformer: A deep learning model for mouse single-cell transcriptome and its cross-species utility · Results: cross-species human cell classification; cached text line 41; Materials and methods: Human cell type classification using mouse-Geneformer; Table 4limited source coverage · Automated source review, 2026-09-16. All specifications and missing details
Results
Results are available, but no reviewed comparison panel is linked in this release.
All evaluations
2 evaluations · 2 results. Different protocols are not a single leaderboard.
Filter evaluations
Applied filters: All linked evaluations
| Tested configuration | Protocol and dataset | Finding | Evidence and details |
|---|---|---|---|
| Configuration: Mouse-Geneformer | Task: Human thymus cell-type classification Dataset: Human thymus scRNA-seq | 48.6 F1 % · unknown Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceMouse-Geneformer: Human thymus cell-type classification Ortholog-based gene conversion; zero-shot mouse model on human cells. Aggregation: Not reported Mouse-Geneformer: A deep learning model for mouse single-cell transcriptome and its cross-species utility · Table 4, h/ Thymus row, Mouse-Geneformer Zero-shot F1 column |
| Configuration: Human-Geneformer | Task: Human thymus cell-type classification Dataset: Human thymus scRNA-seq | 74.5 F1 % · unknown Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourceHuman-Geneformer: Human thymus cell-type classification Native human model; zero-shot setting. Aggregation: Not reported Mouse-Geneformer: A deep learning model for mouse single-cell transcriptome and its cross-species utility · Table 4, h/ Thymus row, Human-Geneformer Zero-shot F1 column |
Source checking is not independent reproduction. Release 2026-09-29-06401fd5b220.
Methods and evaluation design
Procedure, tasks and evaluated configurations
How it works
Evaluation methodology
Human thymus scRNA-seq data from GSE144870, alongside separate breast and cortex evaluations. Human thymus cells come from GSE144870. After mapping human genes to mouse homologues, the fine-tuning experiment randomly uses 80% of cells for training and 20% for testing; the zero-shot column is a separate evaluation setting. Cell-type classification accuracy. Mouse-Geneformer and human Geneformer. The source states these datasets are outside Genecorpus-30M; this review does not treat its feature-distance check as proof of complete leakage absence.
Sources
Mouse-Geneformer: A deep learning model for mouse single-cell transcriptome and its cross-species utility · Results: cross-species human cell classification; cached text line 41; Materials and methods: Human cell type classification using mouse-Geneformer; Table 4Recorded evaluations
Each evaluation records what was tested and under which conditions.
Run instructions
No runnable recipe has been reviewed for this task. Dataset access, model requirements, licences and compute requirements must be checked against its sources before execution.
A task describes a biological question. Choose a linked protocol to obtain concrete split and scoring instructions.
Strengths, limitations and unresolved questions
Strengths and limitations
Strengths and considerations
No source-reviewed explanatory claims are recorded here yet.
Limitations and conditions
- The fine-tuning experiment randomly partitions cells; it does not establish donor-held-out transfer. Mapping human genes to mouse homologues changes the available feature set.
Sources
Mouse-Geneformer: A deep learning model for mouse single-cell transcriptome and its cross-species utility · Materials and methods: Human cell type classification using mouse-Geneformer; Table 4; Materials and methods: Human cell type classification using mouse-Geneformer; Table 4 caption
Profile review details
Targeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change.
Stable record: reported-task-031186b57c62deSpecifications
Inputs, training, access and other details
Explanatory profile: limited source coverage · Automated source review, 2026-09-16. Review applies to the cited claims; unresolved fields are listed below. Numerical results retain their own review status.
| Property | Description and evidence |
|---|---|
| Datasets | Human thymus scRNA-seq data from GSE144870, alongside separate breast and cortex evaluations.SourcesMouse-Geneformer: A deep learning model for mouse single-cell transcriptome and its cross-species utility · Results: cross-species human cell classification; cached text line 41 |
| Splits | Human thymus cells come from GSE144870. After mapping human genes to mouse homologues, the fine-tuning experiment randomly uses 80% of cells for training and 20% for testing; the zero-shot column is a separate evaluation setting.SourcesMouse-Geneformer: A deep learning model for mouse single-cell transcriptome and its cross-species utility · Materials and methods: Human cell type classification using mouse-Geneformer; Table 4 |
| Metrics | Cell-type classification accuracy.SourcesMouse-Geneformer: A deep learning model for mouse single-cell transcriptome and its cross-species utility · Results: cross-species human cell classification; cached text line 41 |
| Baselines | Mouse-Geneformer and human Geneformer.SourcesMouse-Geneformer: A deep learning model for mouse single-cell transcriptome and its cross-species utility · Results: cross-species human cell classification; cached text line 41 |
| Leakage controls | The source states these datasets are outside Genecorpus-30M; this review does not treat its feature-distance check as proof of complete leakage absence.SourcesMouse-Geneformer: A deep learning model for mouse single-cell transcriptome and its cross-species utility · Results: cross-species human cell classification; cached text line 41 |
| Uncertainty | Table 4 prints one accuracy and F1 value per model/setting. Its caption and the human classification method do not report confidence intervals, standard deviations or repeated-split uncertainty for the thymus result. · Not reported in inspected sourcesSourcesMouse-Geneformer: A deep learning model for mouse single-cell transcriptome and its cross-species utility · Materials and methods: Human cell type classification using mouse-Geneformer; Table 4 caption |
| Entity type | Paper-specific computational evaluation protocol.SourcesMouse-Geneformer: A deep learning model for mouse single-cell transcriptome and its cross-species utility · Results: cross-species human cell classification; cached text line 41 |
| Organisms | Human thymus for the linked test; mouse pretraining is a separate data source.SourcesMouse-Geneformer: A deep learning model for mouse single-cell transcriptome and its cross-species utility · Results: cross-species human cell classification; cached text line 41 |
| Assays | Human thymus scRNA-seq cell-type annotations.SourcesMouse-Geneformer: A deep learning model for mouse single-cell transcriptome and its cross-species utility · Results: cross-species human cell classification; cached text line 41 |
| Allowed inputs | Gene-expression profiles represented by Geneformer models.SourcesMouse-Geneformer: A deep learning model for mouse single-cell transcriptome and its cross-species utility · Results: cross-species human cell classification; cached text line 41 |
| Adaptation | Cross-species representation transfer compared with the human Geneformer baseline.SourcesMouse-Geneformer: A deep learning model for mouse single-cell transcriptome and its cross-species utility · Results: cross-species human cell classification; cached text line 41 |
Evidence
Source checking verifies the cited claim or transcription. It does not establish independent reproduction.
Papers and result coverage
Last literature check: 2026-09-17. Primary-paper discovery and source inspection. Source-checked results are not independently reproduced experiments.
| Paper or primary resource | Version | Reference |
|---|---|---|
| Mouse-Geneformer: A deep learning model for mouse single-cell transcriptome and its cross-species utility | version of record | Read source DOI: 10.1371/journal.pgen.1011420 |
Historical gaps recorded on 2026-09-17
The catalogue now holds 2 result rows for this benchmark. A note below about pending extraction describes the state on 2026-09-17 and may since have been answered by a later batch. The result rows and their sources are the current record.
- Only the thymus row belongs to the assigned benchmark; cortex and breast must be separate protocols.
- The authors' Euclidean nonidentity check is not proof that all leakage is absent; source wording must not become an independently established guarantee.
- No replicate uncertainty in Table 4.
Search and extraction details
primary comparison table screened
Searches
- "mouse" "Geneformer" "PMC11964219"
Evidence locations
- Table 4 and footnote
- Methods: Cell type classification
- Methods: Cross-species application
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.
17 evidence rows matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| Diagram caption Conceptual summary of the cited evaluation; exact task configuration and source version remain part of the protocol. Individual claims | Mouse-Geneformer: A deep learning model for mouse single-cell transcriptome and its cross-species utility Results: cross-species human cell classification; cached text line 41; Materials and methods: Human cell type classification using mouse-Geneformer; Table 4 Version: version of record | source checked automated source review · 2026-09-16 Audit detailsTargeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
Diagram steps
| Mouse-Geneformer: A deep learning model for mouse single-cell transcriptome and its cross-species utility Results: cross-species human cell classification; cached text line 41; Materials and methods: Human cell type classification using mouse-Geneformer; Table 4 Version: version of record | source checked automated source review · 2026-09-16 Audit detailsTargeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Diagram title Computational evaluation flow Individual claims | Mouse-Geneformer: A deep learning model for mouse single-cell transcriptome and its cross-species utility Results: cross-species human cell classification; cached text line 41; Materials and methods: Human cell type classification using mouse-Geneformer; Table 4 Version: version of record | source checked automated source review · 2026-09-16 Audit detailsTargeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Datasets Human thymus scRNA-seq data from GSE144870, alongside separate breast and cortex evaluations. Individual claims | Mouse-Geneformer: A deep learning model for mouse single-cell transcriptome and its cross-species utility Results: cross-species human cell classification; cached text line 41 Version: version of record | source checked automated source review · 2026-09-16 Audit detailsTargeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Splits Human thymus cells come from GSE144870. After mapping human genes to mouse homologues, the fine-tuning experiment randomly uses 80% of cells for training and 20% for testing; the zero-shot column is a separate evaluation setting. Individual claims | Mouse-Geneformer: A deep learning model for mouse single-cell transcriptome and its cross-species utility Materials and methods: Human cell type classification using mouse-Geneformer; Table 4 Version: version of record | source checked automated source review · 2026-09-16 Audit detailsTargeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Adaptation Cross-species representation transfer compared with the human Geneformer baseline. Individual claims | Mouse-Geneformer: A deep learning model for mouse single-cell transcriptome and its cross-species utility Results: cross-species human cell classification; cached text line 41 Version: version of record | source checked automated source review · 2026-09-16 Audit detailsTargeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Metrics Cell-type classification accuracy. Individual claims | Mouse-Geneformer: A deep learning model for mouse single-cell transcriptome and its cross-species utility Results: cross-species human cell classification; cached text line 41 Version: version of record | source checked automated source review · 2026-09-16 Audit detailsTargeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Baselines Mouse-Geneformer and human Geneformer. Individual claims | Mouse-Geneformer: A deep learning model for mouse single-cell transcriptome and its cross-species utility Results: cross-species human cell classification; cached text line 41 Version: version of record | source checked automated source review · 2026-09-16 Audit detailsTargeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Leakage controls The source states these datasets are outside Genecorpus-30M; this review does not treat its feature-distance check as proof of complete leakage absence. Individual claims | Mouse-Geneformer: A deep learning model for mouse single-cell transcriptome and its cross-species utility Results: cross-species human cell classification; cached text line 41 Version: version of record | source checked automated source review · 2026-09-16 Audit detailsTargeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Uncertainty Table 4 prints one accuracy and F1 value per model/setting. Its caption and the human classification method do not report confidence intervals, standard deviations or repeated-split uncertainty for the thymus result. Individual claims | Mouse-Geneformer: A deep learning model for mouse single-cell transcriptome and its cross-species utility Materials and methods: Human cell type classification using mouse-Geneformer; Table 4 caption Version: version of record | unreported automated source review · 2026-09-16 Audit detailsTargeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
Sources and history
View linked audit checks and correction history
Release 2026-09-29-06401fd5b220 · Record review: needs review
2 source records and release history
- Mouse-Geneformer: A deep learning model for mouse single-cell transcriptome and its cross-species utility · Original source · version of record
- Mouse-Geneformer: A deep learning model for mouse single-cell transcriptome and its cross-species utility · Original source · version of record
Technical metadata and extraction receipts
Stable ID: reported-task-031186b57c62de
- areas
- cells-tissues
- tasks
- Human thymus cell-type classification
- entity level
- task
- version
- Not reported
- task
- Human thymus cell-type classification
- scope note
- Paper-specific evaluation task; protocol completeness requires further extraction.
- benchmark research
- review date: 2026-09-17; status: primary_comparison_table_screened; primary sources: expansion-p3-mouse-geneformer-2025; inspected locators: Table 4 and footnote; Methods: Cell type classification; Methods: Cross-species application; searched queries: "mouse" "Geneformer" "PMC11964219"; gaps: Only the thymus row belongs to the assigned benchmark; cortex and breast must be separate protocols.; The authors' Euclidean nonidentity check is not proof that all leakage is absent; source wording must not become an independently established guarantee.; No replicate uncertainty in Table 4.; claim scope: Primary-paper discovery and source inspection. Source-checked results are not independently reproduced experiments.
- historical missing metadata
- protocol version: not_reported_in_legacy_extract; split: not_reported_in_legacy_extract
- metadata review scope
- historical_missing_metadata preserves the original discovery state. Current descriptive evidence and missingness are recorded in profile.facts; numerical-result review is separate.
- legacy kinds
- benchmark
- entity classification
- review date: 2026-09-17; rationale: This source-scoped record identifies the biological prediction task and holds its paper context. Preserve the existing task identity; exact split, model adaptation and scoring remain in linked evaluations or separate protocol records.; source ids: mouse-geneformer-2025; source locator: Results: cross-species human cell classification; cached text line 41; ambiguities: A paper- or suite-specific task may constrain some inputs or metrics; that alone does not make it interchangeable with a complete versioned protocol. No protocol equivalence is inferred.; Some legacy profile Entity type facts use the generic phrase computational evaluation protocol. That boilerplate is not sufficient to establish a single fixed protocol identity or to merge this task with another protocol record.