Model type
Transformer representation pipeline; this record is the paper-specific evaluated configuration.
Configuration
Mouse-Geneformer
Mouse-Geneformer adapts the Geneformer transformer design to mouse single-cell transcriptomes.
Sources
Mouse-Geneformer: A deep learning model for mouse single-cell transcriptome and its cross-species utility · Results/In silico perturbation experiments/In silico perturbation experiment in COP1 KO microglia. (paragraph 2); Results/Cross-species application of mouse-Geneformer through orthologous gene name conversion/Human cell type classification using mouse-Geneformer. (paragraph 1)How it worksEvaluated procedure (conceptual)
Conceptual input–method–output guide. Check the procedure text and linked evaluation for fitted components, additional inputs and exact settings.
Sources
Mouse-Geneformer: A deep learning model for mouse single-cell transcriptome and its cross-species utility · Materials and methods/Construction of the mouse-Geneformer/Pretraining of the mouse-Geneformer. (paragraph 1); Materials and methods/Construction of the mouse-Geneformer/Architecture. (paragraph 1)At a glance
Biological inputs
Rank-encoded mouse single-cell transcriptomes
Sources
Mouse-Geneformer: A deep learning model for mouse single-cell transcriptome and its cross-species utility · Results/In silico perturbation experiments/In silico perturbation experiment in COP1 KO microglia. (paragraph 2); Results/Cross-species application of mouse-Geneformer through orthologous gene name conversion/Human cell type classification using mouse-Geneformer. (paragraph 1)Outputs
Gene/cell representations and adapted cell-type or perturbation analyses
Sources
Mouse-Geneformer: A deep learning model for mouse single-cell transcriptome and its cross-species utility · Introduction (paragraph 4); Results/Cross-species application of mouse-Geneformer through orthologous gene name conversion/Human cell type classification using mouse-Geneformer. (paragraph 1)limited source coverage · Automated source review, 2026-09-16. All specifications and missing details
Evaluations and results
Release 2026-09-17-d277315f7d76 · 1 evaluation · 1 metric row. Different protocols are not a single leaderboard.
| Metric and finding | Coverage and uncertainty | Evidence |
|---|---|---|
| Mouse-Geneformer: Human thymus cell-type classification Configuration: Mouse-GeneformerTask: Human thymus cell-type classificationDataset: Human thymus scRNA-seq Ortholog-based gene conversion; zero-shot mouse model on human cells. Author-reported evaluation · Evaluation metadata: needs review | ||
| 48.57 F1 Unit: % · Direction: unknown | Uncertainty: not reported in legacy extract Scored: Not reported · Eligible: Not reported | source checkedMouse-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 Source checking is not independent reproduction. |
How it works
How the evaluated method works
Rank Value Encoding orders genes by expression-derived values for a transformer encoder. The mouse model follows the human Geneformer design with minor modifications and mouse-specific pretraining.
Sources
Mouse-Geneformer: A deep learning model for mouse single-cell transcriptome and its cross-species utility · Materials and methods/Construction of the mouse-Geneformer/Pretraining of the mouse-Geneformer. (paragraph 1); Materials and methods/Construction of the mouse-Geneformer/Architecture. (paragraph 1)What was evaluated
The linked evaluation record identifies Mouse-Geneformer: Human thymus cell-type classification. Its dataset, split, adaptation and evidence origin remain attached to the reported results.
Sources
Mouse-Geneformer: A deep learning model for mouse single-cell transcriptome and its cross-species utility · The named evaluation’s methods and comparison table; exact preserved evaluation IDs: evaluation-lit-b3-003Strengths and limitations
Strengths and considerations
- Tests species-specific pretraining instead of assuming a human representation transfers unchanged to mouse.
Sources
Mouse-Geneformer: A deep learning model for mouse single-cell transcriptome and its cross-species utility · Results/Cross-species application of mouse-Geneformer through orthologous gene name conversion (paragraph 2); Discussion (paragraph 1)
Limitations and conditions
- In-silico perturbation scores are model predictions; validation of selected genes does not validate every predicted regulatory relationship.
Sources
Mouse-Geneformer: A deep learning model for mouse single-cell transcriptome and its cross-species utility · Results/Cross-species application of mouse-Geneformer through orthologous gene name conversion/In silico perturbation of human data using mouse-Geneformer 2: COVID-19 human blood. (paragraph 1); Results/Cross-species application of mouse-Geneformer through orthologous gene name conversion (paragraph 2)
Profile review details
Primary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction.
Stable record: reported-model-e2f2f0d4830bb0Specifications
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 |
|---|---|
| Model type | Transformer representation pipeline; this record is the paper-specific evaluated configuration.SourcesMouse-Geneformer: A deep learning model for mouse single-cell transcriptome and its cross-species utility · Materials and methods/Construction of the mouse-Geneformer/Pretraining of the mouse-Geneformer. (paragraph 1); Materials and methods/Construction of the mouse-Geneformer/Architecture. (paragraph 1) |
| Architecture / procedure | Rank Value Encoding orders genes by expression-derived values for a transformer encoder. The mouse model follows the human Geneformer design with minor modifications and mouse-specific pretraining.SourcesMouse-Geneformer: A deep learning model for mouse single-cell transcriptome and its cross-species utility · Materials and methods/Construction of the mouse-Geneformer/Pretraining of the mouse-Geneformer. (paragraph 1); Materials and methods/Construction of the mouse-Geneformer/Architecture. (paragraph 1) |
| Biological inputs | Rank-encoded mouse single-cell transcriptomesSourcesMouse-Geneformer: A deep learning model for mouse single-cell transcriptome and its cross-species utility · Results/In silico perturbation experiments/In silico perturbation experiment in COP1 KO microglia. (paragraph 2); Results/Cross-species application of mouse-Geneformer through orthologous gene name conversion/Human cell type classification using mouse-Geneformer. (paragraph 1) |
| Outputs | Gene/cell representations and adapted cell-type or perturbation analysesSourcesMouse-Geneformer: A deep learning model for mouse single-cell transcriptome and its cross-species utility · Introduction (paragraph 4); Results/Cross-species application of mouse-Geneformer through orthologous gene name conversion/Human cell type classification using mouse-Geneformer. (paragraph 1) |
| Parameters | Six transformer blocks, four heads and 256-dimensional embeddings are specified; a total parameter count is not reported in Table 1. · Not reported in inspected sourcesSourcesMouse-Geneformer: A deep learning model for mouse single-cell transcriptome and its cross-species utility · Table1 Summary of Experimental conditions |
| Known versions / configuration | Mouse-Geneformer is the comparison-table label; that label does not specify an immutable weight revision. · Not reported in inspected sourcesSourcesMouse-Geneformer: A deep learning model for mouse single-cell transcriptome and its cross-species utility · Model identification in the comparison table and corresponding Methods; immutable checkpoint revision is not supplied by the table label. |
| Training data / fitting | Approximately 21 million mouse single-cell RNA-seq profiles; the human comparator was pretrained separately on human cells.SourcesMouse-Geneformer: A deep learning model for mouse single-cell transcriptome and its cross-species utility · Results/Development of mouse-Geneformer (paragraph 1); Results/Cell type classification: pretraining is effective (paragraph 1) |
| Context limits | 2,048 gene tokens (Table 1); six transformer blocks, four attention heads and 256-dimensional embeddings.SourcesMouse-Geneformer: A deep learning model for mouse single-cell transcriptome and its cross-species utility · Table1; Input max dimensions row |
| Access | Official study implementation and usage documentation: https://github.com/machine-perception-robotics-group/Mouse-Geneformer/blob/ed17d455193ed4c4d93230a8f5f2de349cf20c81/README.md. This pinned documentation revision is not automatically the evaluated weight revision.Sourcesmachine-perception-robotics-group/Mouse-Geneformer README.md · README.md; installation, model download and usage instructions |
| Code licence | No explicit code licence was established from the paper’s availability statement and inspected repository-root documentation. · Not reported in inspected sourcesSourcesmachine-perception-robotics-group/Mouse-Geneformer README.md · README.md and repository-root licence-file search |
| Weights licence | The inspected model-access documentation does not explicitly identify terms for this exact evaluated checkpoint or fitted head; repository code terms are shown separately. · Not reported in inspected sourcesSourcesmachine-perception-robotics-group/Mouse-Geneformer README.md · README.md; checkpoint/access documentation and licence scope |
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.
19 evidence rows matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| Diagram caption Conceptual input–method–output guide. Check the procedure text and linked evaluation for fitted components, additional inputs and exact settings. Individual claims | Mouse-Geneformer: A deep learning model for mouse single-cell transcriptome and its cross-species utility Materials and methods/Construction of the mouse-Geneformer/Pretraining of the mouse-Geneformer. (paragraph 1); Materials and methods/Construction of the mouse-Geneformer/Architecture. (paragraph 1) Version: version of record | source checked automated source review · 2026-09-16 Audit detailsPrimary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Diagram steps ["Rank-encoded mouse single-cell transcriptomes","Mouse-Geneformer","Gene/cell representations and adapted cell-type or perturbation analyses"] Individual claims | Mouse-Geneformer: A deep learning model for mouse single-cell transcriptome and its cross-species utility Materials and methods/Construction of the mouse-Geneformer/Pretraining of the mouse-Geneformer. (paragraph 1); Materials and methods/Construction of the mouse-Geneformer/Architecture. (paragraph 1) Version: version of record | source checked automated source review · 2026-09-16 Audit detailsPrimary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Diagram title Evaluated procedure (conceptual) Individual claims | Mouse-Geneformer: A deep learning model for mouse single-cell transcriptome and its cross-species utility Materials and methods/Construction of the mouse-Geneformer/Pretraining of the mouse-Geneformer. (paragraph 1); Materials and methods/Construction of the mouse-Geneformer/Architecture. (paragraph 1) Version: version of record | source checked automated source review · 2026-09-16 Audit detailsPrimary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Model type Transformer representation pipeline; this record is the paper-specific evaluated configuration. Individual claims | Mouse-Geneformer: A deep learning model for mouse single-cell transcriptome and its cross-species utility Materials and methods/Construction of the mouse-Geneformer/Pretraining of the mouse-Geneformer. (paragraph 1); Materials and methods/Construction of the mouse-Geneformer/Architecture. (paragraph 1) Version: version of record | source checked automated source review · 2026-09-16 Audit detailsPrimary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Architecture / procedure Rank Value Encoding orders genes by expression-derived values for a transformer encoder. The mouse model follows the human Geneformer design with minor modifications and mouse-specific pretraining. Individual claims | Mouse-Geneformer: A deep learning model for mouse single-cell transcriptome and its cross-species utility Materials and methods/Construction of the mouse-Geneformer/Pretraining of the mouse-Geneformer. (paragraph 1); Materials and methods/Construction of the mouse-Geneformer/Architecture. (paragraph 1) Version: version of record | source checked automated source review · 2026-09-16 Audit detailsPrimary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Weights licence The inspected model-access documentation does not explicitly identify terms for this exact evaluated checkpoint or fitted head; repository code terms are shown separately. Individual claims | machine-perception-robotics-group/Mouse-Geneformer README.md README.md; checkpoint/access documentation and licence scope Version: ed17d455193ed4c4d93230a8f5f2de349cf20c81 | unreported automated source review · 2026-09-16 Audit detailsPrimary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Biological inputs Rank-encoded mouse single-cell transcriptomes Individual claims | Mouse-Geneformer: A deep learning model for mouse single-cell transcriptome and its cross-species utility Results/In silico perturbation experiments/In silico perturbation experiment in COP1 KO microglia. (paragraph 2); Results/Cross-species application of mouse-Geneformer through orthologous gene name conversion/Human cell type classification using mouse-Geneformer. (paragraph 1) Version: version of record | source checked automated source review · 2026-09-16 Audit detailsPrimary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Outputs Gene/cell representations and adapted cell-type or perturbation analyses Individual claims | Mouse-Geneformer: A deep learning model for mouse single-cell transcriptome and its cross-species utility Introduction (paragraph 4); Results/Cross-species application of mouse-Geneformer through orthologous gene name conversion/Human cell type classification using mouse-Geneformer. (paragraph 1) Version: version of record | source checked automated source review · 2026-09-16 Audit detailsPrimary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Parameters Six transformer blocks, four heads and 256-dimensional embeddings are specified; a total parameter count is not reported in Table 1. Individual claims | Mouse-Geneformer: A deep learning model for mouse single-cell transcriptome and its cross-species utility Table1 Summary of Experimental conditions Version: version of record | unreported automated source review · 2026-09-16 Audit detailsPrimary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Known versions / configuration Mouse-Geneformer is the comparison-table label; that label does not specify an immutable weight revision. Individual claims | Mouse-Geneformer: A deep learning model for mouse single-cell transcriptome and its cross-species utility Model identification in the comparison table and corresponding Methods; immutable checkpoint revision is not supplied by the table label. Version: version of record | unreported automated source review · 2026-09-16 Audit detailsPrimary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
Sources and history
Release 2026-09-17-d277315f7d76 · 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
- machine-perception-robotics-group/Mouse-Geneformer README.md · Original source · ed17d455193ed4c4d93230a8f5f2de349cf20c81
Technical metadata and extraction receipts
Stable ID: reported-model-e2f2f0d4830bb0
- areas
- cells-tissues
- entity level
- method
- version
- Not reported
- reported name
- Mouse-Geneformer
- historical missing metadata
- version: not_reported_in_legacy_extract; checkpoint revision: not_reported_in_legacy_extract; training data: not_reported_in_legacy_extract; licence: 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
- model
- entity classification
- review date: 2026-09-17; rationale: This source-scoped entry preserves the method/configuration actually named in an evaluation. It is neither a global family identity nor proof of an immutable checkpoint; the linked evaluation retains adaptation, fitting and scoring details.; source ids: mouse-geneformer-2025; source locator: Materials and methods/Construction of the mouse-Geneformer/Pretraining of the mouse-Geneformer. (paragraph 1); Materials and methods/Construction of the mouse-Geneformer/Architecture. (paragraph 1) | Results/In silico perturbation experiments/In silico perturbation experiment in COP1 KO microglia. (paragraph 2); Results/Cross-species application of mouse-Geneformer through orthologous gene name conversion/Human cell type classification using mouse-Geneformer. (paragraph 1); ambiguities: Configuration means the source-labelled evaluated identity. It does not establish missing checkpoint hashes, default settings or equivalence to same-named records in other papers.