Model type
Study-specific predictive method; this record is the paper-specific evaluated configuration.
Configuration
scGen
This scGen configuration is evaluated for predicted expression responses and recovery of differentially expressed genes.
Sources
AUPRC: a metric for evaluating the performance of in-silico perturbation methods in identifying differentially expressed genes · Results/DEG prediction on cell-level responses under single stimulus across multiple cell types (paragraph 3); Results/DEG prediction on cell-level responses under single stimulus across multiple cell types/High \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{upgreek} \usepackage{mathrsfs} \setlength{\oddsidemargin}{-69pt} \begin{document} $R^{2}$\end{document} does not imply ability to identify differentially expressed genes (paragraph 6)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
AUPRC: a metric for evaluating the performance of in-silico perturbation methods in identifying differentially expressed genes · Results/DEG prediction on cell-level responses under single stimulus across multiple cell types/Comparative analysis of two-factor and scGen models for DEG prediction (paragraph 13); Materials and methods/Assessing model performance via differential expression classification (paragraph 12)At a glance
Biological inputs
Single-cell expression profiles and perturbation conditions
Sources
AUPRC: a metric for evaluating the performance of in-silico perturbation methods in identifying differentially expressed genes · Results/DEG prediction on population-level responses under multiple perturbations across multiple cell types (paragraph 2); Results/DEG prediction on population-level responses under multiple perturbations across multiple cell types (paragraph 3)Outputs
Predicted perturbed expression profiles
Sources
AUPRC: a metric for evaluating the performance of in-silico perturbation methods in identifying differentially expressed genes · Materials and methods/Limitations of traditional performance metrics in perturbation response prediction (paragraph 4); Results/DEG prediction on cell-level responses under single stimulus across multiple cell types/Comparative analysis of two-factor and scGen models for DEG prediction (paragraph 3)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 |
|---|---|---|
| scGen: differentially expressed gene identification Configuration: scGenTask: differentially expressed gene identificationDataset: stimulated immune PBMC In-silico perturbation assessment with precision sampled at fixed 50% recall Independent external evaluation · Evaluation metadata: needs review | ||
| 0.91 precision at 50% recall Unit: fraction · Direction: unknown | Uncertainty: not reported in legacy extract Scored: Not reported · Eligible: Not reported | source checkedAUPRC: a metric for evaluating the performance of in-silico perturbation methods in identifying differentially expressed genes · Table 3, CD14+Mono section, scGen row, Precision at 50% Recall column Source checking is not independent reproduction. |
How it works
How the evaluated method works
A learned single-cell perturbation predictor is assessed with differential-expression precision/recall in addition to overall expression-fit metrics.
Sources
AUPRC: a metric for evaluating the performance of in-silico perturbation methods in identifying differentially expressed genes · Results/DEG prediction on cell-level responses under single stimulus across multiple cell types/Comparative analysis of two-factor and scGen models for DEG prediction (paragraph 13); Materials and methods/Assessing model performance via differential expression classification (paragraph 12)What was evaluated
The linked evaluation record identifies scGen: differentially expressed gene identification. Its dataset, split, adaptation and evidence origin remain attached to the reported results.
Sources
AUPRC: a metric for evaluating the performance of in-silico perturbation methods in identifying differentially expressed genes · The named evaluation’s methods and comparison table; exact preserved evaluation IDs: evaluation-lit-b4-016Strengths and limitations
Strengths and considerations
- The evaluation tests biologically relevant differential-expression recovery rather than relying only on global R².
Sources
AUPRC: a metric for evaluating the performance of in-silico perturbation methods in identifying differentially expressed genes · Results/DEG prediction on cell-level responses under single stimulus across multiple cell types/High \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{upgreek} \usepackage{mathrsfs} \setlength{\oddsidemargin}{-69pt} \begin{document} $R^{2}$\end{document} does not imply ability to identify differentially expressed genes (paragraph 8); Materials and methods/Limitations of traditional performance metrics in perturbation response prediction (paragraph 6)
Limitations and conditions
- High overall expression agreement can coexist with poor recovery of differentially expressed genes; both evaluation targets must remain visible.
Sources
AUPRC: a metric for evaluating the performance of in-silico perturbation methods in identifying differentially expressed genes · Abstract (paragraph 1); Results/DEG prediction on cell-level responses under single stimulus across multiple cell types (paragraph 3)
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-fcf2cd29a81aaeSpecifications
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 | Study-specific predictive method; this record is the paper-specific evaluated configuration.SourcesAUPRC: a metric for evaluating the performance of in-silico perturbation methods in identifying differentially expressed genes · Results/DEG prediction on cell-level responses under single stimulus across multiple cell types/Comparative analysis of two-factor and scGen models for DEG prediction (paragraph 13); Materials and methods/Assessing model performance via differential expression classification (paragraph 12) |
| Architecture / procedure | A learned single-cell perturbation predictor is assessed with differential-expression precision/recall in addition to overall expression-fit metrics.SourcesAUPRC: a metric for evaluating the performance of in-silico perturbation methods in identifying differentially expressed genes · Results/DEG prediction on cell-level responses under single stimulus across multiple cell types/Comparative analysis of two-factor and scGen models for DEG prediction (paragraph 13); Materials and methods/Assessing model performance via differential expression classification (paragraph 12) |
| Biological inputs | Single-cell expression profiles and perturbation conditionsSourcesAUPRC: a metric for evaluating the performance of in-silico perturbation methods in identifying differentially expressed genes · Results/DEG prediction on population-level responses under multiple perturbations across multiple cell types (paragraph 2); Results/DEG prediction on population-level responses under multiple perturbations across multiple cell types (paragraph 3) |
| Outputs | Predicted perturbed expression profilesSourcesAUPRC: a metric for evaluating the performance of in-silico perturbation methods in identifying differentially expressed genes · Materials and methods/Limitations of traditional performance metrics in perturbation response prediction (paragraph 4); Results/DEG prediction on cell-level responses under single stimulus across multiple cell types/Comparative analysis of two-factor and scGen models for DEG prediction (paragraph 3) |
| Parameters | An aggregate parameter total for this exact evaluated configuration is not established by the inspected sources. · Not reported in inspected sourcesSources (2)AUPRC: a metric for evaluating the performance of in-silico perturbation methods in identifying differentially expressed genes; hxzhu491/Cell-Perturbation-evaluation-Metric README.md · Materials and methods/Mathematical formulation of cellular perturbation experiments; Materials and methods/Limitations of traditional performance metrics in perturbation response prediction; Materials and methods/Assessing model performance via differential expression classification; inspected for aggregate parameter count (component sizes are not added without an exact configuration); README.md at pinned repository revision |
| Known versions / configuration | scGen is the comparison-table label; that label does not specify an immutable weight revision. · Not reported in inspected sourcesSourcesAUPRC: a metric for evaluating the performance of in-silico perturbation methods in identifying differentially expressed genes · Model identification in the comparison table and corresponding Methods; immutable checkpoint revision is not supplied by the table label. |
| Training data / fitting | The study uses a processed PBMC dataset of 18,868 cells, seven cell types and 6,998 highly variable genes. Seven training iterations each withhold the stimulated cells of one cell type, evaluating an out-of-sample perturbation response.SourcesAUPRC: a metric for evaluating the performance of in-silico perturbation methods in identifying differentially expressed genes · Results / DEG prediction on cell-level responses under single stimulus across multiple cell types |
| Context limits | The evaluated input has 6,998 highly variable genes per cell; this is a feature set, not a sequence-token limit.SourcesAUPRC: a metric for evaluating the performance of in-silico perturbation methods in identifying differentially expressed genes · Results / DEG prediction on cell-level responses under single stimulus across multiple cell types |
| Access | Official study implementation and usage documentation: https://github.com/hxzhu491/Cell-Perturbation-evaluation-Metric/blob/3b5f8a2ed001c074936287ece478747376c8f5bf/README.md. This pinned documentation revision is not automatically the evaluated weight revision.Sourceshxzhu491/Cell-Perturbation-evaluation-Metric 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 sourcesSourceshxzhu491/Cell-Perturbation-evaluation-Metric 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 sourcesSourceshxzhu491/Cell-Perturbation-evaluation-Metric 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.
20 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 | AUPRC: a metric for evaluating the performance of in-silico perturbation methods in identifying differentially expressed genes Results/DEG prediction on cell-level responses under single stimulus across multiple cell types/Comparative analysis of two-factor and scGen models for DEG prediction (paragraph 13); Materials and methods/Assessing model performance via differential expression classification (paragraph 12) Version: PMC archival version PMC12400816.1 | 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 expression profiles and perturbation conditions","scGen","Predicted perturbed expression profiles"] Individual claims | AUPRC: a metric for evaluating the performance of in-silico perturbation methods in identifying differentially expressed genes Results/DEG prediction on cell-level responses under single stimulus across multiple cell types/Comparative analysis of two-factor and scGen models for DEG prediction (paragraph 13); Materials and methods/Assessing model performance via differential expression classification (paragraph 12) Version: PMC archival version PMC12400816.1 | 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 | AUPRC: a metric for evaluating the performance of in-silico perturbation methods in identifying differentially expressed genes Results/DEG prediction on cell-level responses under single stimulus across multiple cell types/Comparative analysis of two-factor and scGen models for DEG prediction (paragraph 13); Materials and methods/Assessing model performance via differential expression classification (paragraph 12) Version: PMC archival version PMC12400816.1 | 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 Study-specific predictive method; this record is the paper-specific evaluated configuration. Individual claims | AUPRC: a metric for evaluating the performance of in-silico perturbation methods in identifying differentially expressed genes Results/DEG prediction on cell-level responses under single stimulus across multiple cell types/Comparative analysis of two-factor and scGen models for DEG prediction (paragraph 13); Materials and methods/Assessing model performance via differential expression classification (paragraph 12) Version: PMC archival version PMC12400816.1 | 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 A learned single-cell perturbation predictor is assessed with differential-expression precision/recall in addition to overall expression-fit metrics. Individual claims | AUPRC: a metric for evaluating the performance of in-silico perturbation methods in identifying differentially expressed genes Results/DEG prediction on cell-level responses under single stimulus across multiple cell types/Comparative analysis of two-factor and scGen models for DEG prediction (paragraph 13); Materials and methods/Assessing model performance via differential expression classification (paragraph 12) Version: PMC archival version PMC12400816.1 | 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 | hxzhu491/Cell-Perturbation-evaluation-Metric README.md README.md; checkpoint/access documentation and licence scope Version: 3b5f8a2ed001c074936287ece478747376c8f5bf | 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 expression profiles and perturbation conditions Individual claims | AUPRC: a metric for evaluating the performance of in-silico perturbation methods in identifying differentially expressed genes Results/DEG prediction on population-level responses under multiple perturbations across multiple cell types (paragraph 2); Results/DEG prediction on population-level responses under multiple perturbations across multiple cell types (paragraph 3) Version: PMC archival version PMC12400816.1 | 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 Predicted perturbed expression profiles Individual claims | AUPRC: a metric for evaluating the performance of in-silico perturbation methods in identifying differentially expressed genes Materials and methods/Limitations of traditional performance metrics in perturbation response prediction (paragraph 4); Results/DEG prediction on cell-level responses under single stimulus across multiple cell types/Comparative analysis of two-factor and scGen models for DEG prediction (paragraph 3) Version: PMC archival version PMC12400816.1 | 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 An aggregate parameter total for this exact evaluated configuration is not established by the inspected sources. Individual claims | hxzhu491/Cell-Perturbation-evaluation-Metric README.md Materials and methods/Mathematical formulation of cellular perturbation experiments; Materials and methods/Limitations of traditional performance metrics in perturbation response prediction; Materials and methods/Assessing model performance via differential expression classification; inspected for aggregate parameter count (component sizes are not added without an exact configuration); README.md at pinned repository revision Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 3b5f8a2ed001c074936287ece478747376c8f5bf | 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 |
| Parameters An aggregate parameter total for this exact evaluated configuration is not established by the inspected sources. Individual claims | AUPRC: a metric for evaluating the performance of in-silico perturbation methods in identifying differentially expressed genes Materials and methods/Mathematical formulation of cellular perturbation experiments; Materials and methods/Limitations of traditional performance metrics in perturbation response prediction; Materials and methods/Assessing model performance via differential expression classification; inspected for aggregate parameter count (component sizes are not added without an exact configuration); README.md at pinned repository revision Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: PMC archival version PMC12400816.1 | 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
- AUPRC: a metric for evaluating the performance of in-silico perturbation methods in identifying differentially expressed genes · Original source · PMC archival version PMC12400816.1
- hxzhu491/Cell-Perturbation-evaluation-Metric README.md · Original source · 3b5f8a2ed001c074936287ece478747376c8f5bf
Technical metadata and extraction receipts
Stable ID: reported-model-fcf2cd29a81aae
- areas
- cells-tissues
- entity level
- method
- version
- Not reported
- reported name
- scGen
- 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: insilico-perturbation-auprc-2025; source locator: Results/DEG prediction on cell-level responses under single stimulus across multiple cell types/Comparative analysis of two-factor and scGen models for DEG prediction (paragraph 13); Materials and methods/Assessing model performance via differential expression classification (paragraph 12) | Results/DEG prediction on cell-level responses under single stimulus across multiple cell types (paragraph 3); Results/DEG prediction on cell-level responses under single stimulus across multiple cell types/High \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{upgreek} \usepackage{mathrsfs} \setlength{\oddsidemargin}{-69pt} \begin{document} $R^{2}$\end{document} does not imply ability to identify differentially expressed genes (paragraph 6); 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.