Model type
Single-cell foundation model; this record is the paper-specific evaluated configuration.
Configuration
scGPT
This single-cell model is evaluated in a study of parameter-efficient adaptation for cell-type identification.
Sources
Parameter-Efficient Fine-Tuning Enhances Adaptation of Single Cell Large Language Model for Cell Type Identification · Introduction (paragraph 5); Results/Comparison of proposed PEFT strategies and other finetuning approaches (paragraph 2)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
Parameter-Efficient Fine-Tuning Enhances Adaptation of Single Cell Large Language Model for Cell Type Identification · Introduction (paragraph 4); Proposed PEFT strategies for scLLMs/Finetuning and evaluation settings (paragraph 1)At a glance
Biological inputs
Single-cell gene-expression profiles
Sources
Parameter-Efficient Fine-Tuning Enhances Adaptation of Single Cell Large Language Model for Cell Type Identification · An overview of current scLLMs (paragraph 1); Data and code availability (paragraph 1)Outputs
Cell-type predictions
Sources
Parameter-Efficient Fine-Tuning Enhances Adaptation of Single Cell Large Language Model for Cell Type Identification · Proposed PEFT strategies for scLLMs/Finetuning and evaluation settings (paragraph 2); Results/Comparison of native scLLMs on cell type identification (paragraph 4)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 |
|---|---|---|
| scGPT: Cell-type identification Native scLLM cell-type identification as reported in Table 2. Independent external evaluation · Evaluation metadata: needs review | ||
| 0.734 F1-Score Unit: unitless · Direction: unknown | Uncertainty: not reported in legacy extract Scored: Not reported · Eligible: Not reported | source checkedParameter-Efficient Fine-Tuning Enhances Adaptation of Single Cell Large Language Model for Cell Type Identification · Table 2, M.S. / scGPT row, F1-Score column Source checking is not independent reproduction. |
How it works
How the evaluated method works
The study compares ordinary fine-tuning with methods that retain original model parameters while learning additional tensors.
Sources
Parameter-Efficient Fine-Tuning Enhances Adaptation of Single Cell Large Language Model for Cell Type Identification · Introduction (paragraph 4); Proposed PEFT strategies for scLLMs/Finetuning and evaluation settings (paragraph 1)Underlying method and version boundaries
The official scGPT implementation supplies pretrained checkpoints and separate workflows for embedding extraction, cell annotation, integration and perturbation modelling. The checkpoint and adaptation procedure must be identified separately for each result.
Sources
bowang-lab/scGPT README.md · README.md; introduction, model description, pretrained-model and usage sections at pinned revisionWhat was evaluated
The linked evaluation record identifies scGPT: Cell-type identification. Its dataset, split, adaptation and evidence origin remain attached to the reported results.
Sources
Parameter-Efficient Fine-Tuning Enhances Adaptation of Single Cell Large Language Model for Cell Type Identification · The named evaluation’s methods and comparison table; exact preserved evaluation IDs: evaluation-lit-025Strengths and limitations
Strengths and considerations
- Examines the trade-off between adaptation performance and the number of trainable parameters.
Sources
Parameter-Efficient Fine-Tuning Enhances Adaptation of Single Cell Large Language Model for Cell Type Identification · Results/Comparison of proposed PEFT strategies and other finetuning approaches (paragraph 3); Results/Comparison of proposed PEFT strategies and other finetuning approaches (paragraph 2)
Limitations and conditions
- The base-model label alone does not identify which adaptation tensors were trained; exact PEFT and full-fine-tuning rows must remain separate.
Sources
Parameter-Efficient Fine-Tuning Enhances Adaptation of Single Cell Large Language Model for Cell Type Identification · Results/Comparison of proposed PEFT strategies and other finetuning approaches (paragraph 2); Introduction (paragraph 5)
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-3bdb3093e8d531Specifications
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 | Single-cell foundation model; this record is the paper-specific evaluated configuration.Sourcesbowang-lab/scGPT README.md · README.md model description |
| Architecture / procedure | The study compares ordinary fine-tuning with methods that retain original model parameters while learning additional tensors.SourcesParameter-Efficient Fine-Tuning Enhances Adaptation of Single Cell Large Language Model for Cell Type Identification · Introduction (paragraph 4); Proposed PEFT strategies for scLLMs/Finetuning and evaluation settings (paragraph 1) |
| Biological inputs | Single-cell gene-expression profilesSourcesParameter-Efficient Fine-Tuning Enhances Adaptation of Single Cell Large Language Model for Cell Type Identification · An overview of current scLLMs (paragraph 1); Data and code availability (paragraph 1) |
| Outputs | Cell-type predictionsSourcesParameter-Efficient Fine-Tuning Enhances Adaptation of Single Cell Large Language Model for Cell Type Identification · Proposed PEFT strategies for scLLMs/Finetuning and evaluation settings (paragraph 2); Results/Comparison of native scLLMs on cell type identification (paragraph 4) |
| Parameters | Table 3 reports 51M trainable parameters for full fine-tuning. Prompt/classifier variants train different subsets; this count is not assigned to every adaptation.SourcesParameter-Efficient Fine-Tuning Enhances Adaptation of Single Cell Large Language Model for Cell Type Identification · Table3; Trainable Parameters column |
| Known versions / configuration | scGPT is the comparison-table label; that label does not specify an immutable weight revision. · Not reported in inspected sourcesSourcesParameter-Efficient Fine-Tuning Enhances Adaptation of Single Cell Large Language Model for Cell Type Identification · Model identification in the comparison table and corresponding Methods; immutable checkpoint revision is not supplied by the table label. |
| Training data / fitting | The evaluation separately compares native scGPT, full fine-tuning, classifier-only fitting and four prompting methods across the named cell-annotation datasets.SourcesParameter-Efficient Fine-Tuning Enhances Adaptation of Single Cell Large Language Model for Cell Type Identification · Proposed PEFT strategies for scLLMs / Data preparation; Table3 |
| Context limits | A maximum input/context length for this exact evaluated configuration is not established by the inspected sources. · Not reported in inspected sourcesSources (2)Parameter-Efficient Fine-Tuning Enhances Adaptation of Single Cell Large Language Model for Cell Type Identification; bowang-lab/scGPT README.md · An overview of current scLLMs/Pretrainer:; inspected for explicit maximum input length (dataset lengths and family-wide limits are not substituted); README.md at pinned repository revision |
| Access | Official upstream implementation and usage documentation: https://github.com/bowang-lab/scGPT/blob/cebd6fae655b9c585a4807daa3ac31bb764f06b4/README.md. This pinned documentation revision is not automatically the evaluated weight revision.Sourcesbowang-lab/scGPT README.md · README.md; installation, model download and usage instructions |
| Code licence | MIT (upstream repository code at the cited revision; this does not establish every dependency or historical checkpoint licence).Sourcesbowang-lab/scGPT LICENSE · LICENSE; complete licence text |
| 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 sourcesSourcesbowang-lab/scGPT 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.
21 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 | Parameter-Efficient Fine-Tuning Enhances Adaptation of Single Cell Large Language Model for Cell Type Identification Introduction (paragraph 4); Proposed PEFT strategies for scLLMs/Finetuning and evaluation settings (paragraph 1) Version: preprint archived 2024-01-30 | 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 ["Single-cell gene-expression profiles","scGPT","Cell-type predictions"] Individual claims | Parameter-Efficient Fine-Tuning Enhances Adaptation of Single Cell Large Language Model for Cell Type Identification Introduction (paragraph 4); Proposed PEFT strategies for scLLMs/Finetuning and evaluation settings (paragraph 1) Version: preprint archived 2024-01-30 | 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 | Parameter-Efficient Fine-Tuning Enhances Adaptation of Single Cell Large Language Model for Cell Type Identification Introduction (paragraph 4); Proposed PEFT strategies for scLLMs/Finetuning and evaluation settings (paragraph 1) Version: preprint archived 2024-01-30 | 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 Single-cell foundation model; this record is the paper-specific evaluated configuration. Individual claims | bowang-lab/scGPT README.md README.md model description Version: cebd6fae655b9c585a4807daa3ac31bb764f06b4 | 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 The study compares ordinary fine-tuning with methods that retain original model parameters while learning additional tensors. Individual claims | Parameter-Efficient Fine-Tuning Enhances Adaptation of Single Cell Large Language Model for Cell Type Identification Introduction (paragraph 4); Proposed PEFT strategies for scLLMs/Finetuning and evaluation settings (paragraph 1) Version: preprint archived 2024-01-30 | 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 | bowang-lab/scGPT README.md README.md; checkpoint/access documentation and licence scope Version: cebd6fae655b9c585a4807daa3ac31bb764f06b4 | 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 Single-cell gene-expression profiles Individual claims | Parameter-Efficient Fine-Tuning Enhances Adaptation of Single Cell Large Language Model for Cell Type Identification An overview of current scLLMs (paragraph 1); Data and code availability (paragraph 1) Version: preprint archived 2024-01-30 | 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 Cell-type predictions Individual claims | Parameter-Efficient Fine-Tuning Enhances Adaptation of Single Cell Large Language Model for Cell Type Identification Proposed PEFT strategies for scLLMs/Finetuning and evaluation settings (paragraph 2); Results/Comparison of native scLLMs on cell type identification (paragraph 4) Version: preprint archived 2024-01-30 | 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 Table 3 reports 51M trainable parameters for full fine-tuning. Prompt/classifier variants train different subsets; this count is not assigned to every adaptation. Individual claims | Parameter-Efficient Fine-Tuning Enhances Adaptation of Single Cell Large Language Model for Cell Type Identification Table3; Trainable Parameters column Version: preprint archived 2024-01-30 | 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 |
| Known versions / configuration scGPT is the comparison-table label; that label does not specify an immutable weight revision. Individual claims | Parameter-Efficient Fine-Tuning Enhances Adaptation of Single Cell Large Language Model for Cell Type Identification Model identification in the comparison table and corresponding Methods; immutable checkpoint revision is not supplied by the table label. Version: preprint archived 2024-01-30 | 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
3 source records and release history
- Parameter-Efficient Fine-Tuning Enhances Adaptation of Single Cell Large Language Model for Cell Type Identification · Original source · preprint archived 2024-01-30
- bowang-lab/scGPT README.md · Original source · cebd6fae655b9c585a4807daa3ac31bb764f06b4
- bowang-lab/scGPT LICENSE · Original source · cebd6fae655b9c585a4807daa3ac31bb764f06b4
Technical metadata and extraction receipts
Stable ID: reported-model-3bdb3093e8d531
- areas
- cells-tissues
- entity level
- method
- version
- Not reported
- reported name
- scGPT
- 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: single-cell-peft-2024; evidence-reported-base-scgpt-readme-md; source locator: Introduction (paragraph 4); Proposed PEFT strategies for scLLMs/Finetuning and evaluation settings (paragraph 1) | README.md model description | Introduction (paragraph 5); Results/Comparison of proposed PEFT strategies and other finetuning approaches (paragraph 2); 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.