Model type
Graph-based predictive method; this record is the paper-specific evaluated configuration.
Pipeline
scRegNet (scBERT backbone)
scRegNet predicts gene-regulatory links using single-cell foundation-model features and graph learning.
Sources
Prediction of Gene Regulatory Connections with Joint Single-Cell Foundation Models and Graph-Based Learning · Conclusions and Discussions (paragraph 1); Results/Performance on benchmark datasets (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
Prediction of Gene Regulatory Connections with Joint Single-Cell Foundation Models and Graph-Based Learning · Method/Graph-based learning with GNNs (paragraph 1); Method/Gene representations from foundation models (paragraph 1)At a glance
Biological inputs
Single-cell expression data, pretrained gene embeddings and known regulatory links
Sources
Prediction of Gene Regulatory Connections with Joint Single-Cell Foundation Models and Graph-Based Learning · Method/Gene representations from foundation models/Geneformer (paragraph 2); Method/Graph-based learning with GNNs (paragraph 1)Outputs
Predicted gene-regulatory connections
Sources
Prediction of Gene Regulatory Connections with Joint Single-Cell Foundation Models and Graph-Based Learning · Method/Model training (paragraph 1); Method/Link prediction layer (paragraph 2)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 |
|---|---|---|
| scRegNet (scBERT backbone): Gene-regulatory link prediction Pipeline: scRegNet (scBERT backbone)Task: Gene-regulatory link predictionDataset: hESC cell-type-specific GRN TFs plus 500 variable genes; mean from 50 independent evaluations. Author-reported evaluation · Evaluation metadata: needs review | ||
| 0.88 AUROC Unit: unitless · Direction: unknown | Uncertainty: ± 0.00 as printed Scored: Not reported · Eligible: Not reported | source checkedPrediction of Gene Regulatory Connections with Joint Single-Cell Foundation Models and Graph-Based Learning · Table 2, scRegNet (w/ scBERT) row, hESC AUROC entry Source checking is not independent reproduction. |
How it works
How the evaluated method works
A specified pretrained backbone supplies context-aware gene representations; a graph-based supervised predictor learns regulatory connections from known links. Geneformer and scBERT are separate backbone configurations.
Sources
Prediction of Gene Regulatory Connections with Joint Single-Cell Foundation Models and Graph-Based Learning · Method/Graph-based learning with GNNs (paragraph 1); Method/Gene representations from foundation models (paragraph 1)What was evaluated
The linked evaluation record identifies scRegNet (scBERT backbone): Gene-regulatory link prediction. Its dataset, split, adaptation and evidence origin remain attached to the reported results.
Sources
Prediction of Gene Regulatory Connections with Joint Single-Cell Foundation Models and Graph-Based Learning · The named evaluation’s methods and comparison table; exact preserved evaluation IDs: evaluation-lit-032Strengths and limitations
Strengths and considerations
- Tests whether pretrained gene representations help when experimentally supported regulatory links are limited.
Sources
Prediction of Gene Regulatory Connections with Joint Single-Cell Foundation Models and Graph-Based Learning · Method/Graph-based learning with GNNs (paragraph 1); Introduction (paragraph 3)
Limitations and conditions
- Supervised link prediction on known binding data does not establish causality or intervention effects for all inferred edges.
Sources
Prediction of Gene Regulatory Connections with Joint Single-Cell Foundation Models and Graph-Based Learning · Abstract (paragraph 1); Method/Graph-based learning with GNNs (paragraph 1)
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-89f5a8f309fa18Specifications
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 | Graph-based predictive method; this record is the paper-specific evaluated configuration.SourcesPrediction of Gene Regulatory Connections with Joint Single-Cell Foundation Models and Graph-Based Learning · Method/Graph-based learning with GNNs (paragraph 1); Method/Gene representations from foundation models (paragraph 1) |
| Architecture / procedure | A specified pretrained backbone supplies context-aware gene representations; a graph-based supervised predictor learns regulatory connections from known links. Geneformer and scBERT are separate backbone configurations.SourcesPrediction of Gene Regulatory Connections with Joint Single-Cell Foundation Models and Graph-Based Learning · Method/Graph-based learning with GNNs (paragraph 1); Method/Gene representations from foundation models (paragraph 1) |
| Biological inputs | Single-cell expression data, pretrained gene embeddings and known regulatory linksSourcesPrediction of Gene Regulatory Connections with Joint Single-Cell Foundation Models and Graph-Based Learning · Method/Gene representations from foundation models/Geneformer (paragraph 2); Method/Graph-based learning with GNNs (paragraph 1) |
| Outputs | Predicted gene-regulatory connectionsSourcesPrediction of Gene Regulatory Connections with Joint Single-Cell Foundation Models and Graph-Based Learning · Method/Model training (paragraph 1); Method/Link prediction layer (paragraph 2) |
| Parameters | An aggregate parameter total for this exact evaluated configuration is not established by the inspected sources. · Not reported in inspected sourcesSources (2)Prediction of Gene Regulatory Connections with Joint Single-Cell Foundation Models and Graph-Based Learning; sindhura-cs/scRegNet README.md · Method; Method/Gene representations from foundation models; Method/Gene representations from foundation models/scBERT; Method/Gene representations from foundation models/scFoundation; Method/Gene representations from foundation models/Geneformer; Method/Gene representations from foundation models/Mean pooling; Method/Graph-based learning with GNNs; Method/Unified gene representations; inspected for aggregate parameter count (component sizes are not added without an exact configuration); README.md at pinned repository revision |
| Known versions / configuration | scRegNet (scBERT backbone) is the comparison-table label; that label does not specify an immutable weight revision. · Not reported in inspected sourcesSourcesPrediction of Gene Regulatory Connections with Joint Single-Cell Foundation Models and Graph-Based Learning · Model identification in the comparison table and corresponding Methods; immutable checkpoint revision is not supplied by the table label. |
| Training data / fitting | Backbone pretraining is separate from supervised regulatory-link fitting; the study uses known TF–DNA binding information for the latter.SourcesPrediction of Gene Regulatory Connections with Joint Single-Cell Foundation Models and Graph-Based Learning · Experimental Setup/Datasets and data pre-processing (paragraph 2); Experimental Setup/Datasets and data pre-processing (paragraph 4) |
| 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)Prediction of Gene Regulatory Connections with Joint Single-Cell Foundation Models and Graph-Based Learning; sindhura-cs/scRegNet README.md · Method; Method/Gene representations from foundation models; Method/Gene representations from foundation models/scBERT; Method/Gene representations from foundation models/scFoundation; Method/Gene representations from foundation models/Geneformer; Method/Gene representations from foundation models/Mean pooling; Method/Graph-based learning with GNNs; Method/Unified gene representations; inspected for explicit maximum input length (dataset lengths and family-wide limits are not substituted); README.md at pinned repository revision |
| Access | Official study implementation and usage documentation: https://github.com/sindhura-cs/scRegNet/blob/30d0215efd99c40ceaceb37d161fc0a86a236e0b/README.md. This pinned documentation revision is not automatically the evaluated weight revision.Sourcessindhura-cs/scRegNet 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 sourcesSourcessindhura-cs/scRegNet 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 sourcesSourcessindhura-cs/scRegNet 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 | Prediction of Gene Regulatory Connections with Joint Single-Cell Foundation Models and Graph-Based Learning Method/Graph-based learning with GNNs (paragraph 1); Method/Gene representations from foundation models (paragraph 1) Version: PMC11838224.2 | 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 data, pretrained gene embeddings and known regulatory links","scRegNet (scBERT backbone)","Predicted gene-regulatory connections"] Individual claims | Prediction of Gene Regulatory Connections with Joint Single-Cell Foundation Models and Graph-Based Learning Method/Graph-based learning with GNNs (paragraph 1); Method/Gene representations from foundation models (paragraph 1) Version: PMC11838224.2 | 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 | Prediction of Gene Regulatory Connections with Joint Single-Cell Foundation Models and Graph-Based Learning Method/Graph-based learning with GNNs (paragraph 1); Method/Gene representations from foundation models (paragraph 1) Version: PMC11838224.2 | 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 Graph-based predictive method; this record is the paper-specific evaluated configuration. Individual claims | Prediction of Gene Regulatory Connections with Joint Single-Cell Foundation Models and Graph-Based Learning Method/Graph-based learning with GNNs (paragraph 1); Method/Gene representations from foundation models (paragraph 1) Version: PMC11838224.2 | 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 specified pretrained backbone supplies context-aware gene representations; a graph-based supervised predictor learns regulatory connections from known links. Geneformer and scBERT are separate backbone configurations. Individual claims | Prediction of Gene Regulatory Connections with Joint Single-Cell Foundation Models and Graph-Based Learning Method/Graph-based learning with GNNs (paragraph 1); Method/Gene representations from foundation models (paragraph 1) Version: PMC11838224.2 | 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 | sindhura-cs/scRegNet README.md README.md; checkpoint/access documentation and licence scope Version: 30d0215efd99c40ceaceb37d161fc0a86a236e0b | 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 data, pretrained gene embeddings and known regulatory links Individual claims | Prediction of Gene Regulatory Connections with Joint Single-Cell Foundation Models and Graph-Based Learning Method/Gene representations from foundation models/Geneformer (paragraph 2); Method/Graph-based learning with GNNs (paragraph 1) Version: PMC11838224.2 | 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 gene-regulatory connections Individual claims | Prediction of Gene Regulatory Connections with Joint Single-Cell Foundation Models and Graph-Based Learning Method/Model training (paragraph 1); Method/Link prediction layer (paragraph 2) Version: PMC11838224.2 | 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 | sindhura-cs/scRegNet README.md Method; Method/Gene representations from foundation models; Method/Gene representations from foundation models/scBERT; Method/Gene representations from foundation models/scFoundation; Method/Gene representations from foundation models/Geneformer; Method/Gene representations from foundation models/Mean pooling; Method/Graph-based learning with GNNs; Method/Unified gene representations; 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: 30d0215efd99c40ceaceb37d161fc0a86a236e0b | 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 | Prediction of Gene Regulatory Connections with Joint Single-Cell Foundation Models and Graph-Based Learning Method; Method/Gene representations from foundation models; Method/Gene representations from foundation models/scBERT; Method/Gene representations from foundation models/scFoundation; Method/Gene representations from foundation models/Geneformer; Method/Gene representations from foundation models/Mean pooling; Method/Graph-based learning with GNNs; Method/Unified gene representations; 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: PMC11838224.2 | 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
- Prediction of Gene Regulatory Connections with Joint Single-Cell Foundation Models and Graph-Based Learning · Original source · PMC11838224.2
- sindhura-cs/scRegNet README.md · Original source · 30d0215efd99c40ceaceb37d161fc0a86a236e0b
Technical metadata and extraction receipts
Stable ID: reported-model-89f5a8f309fa18
- areas
- cells-tissues
- entity level
- method
- version
- Not reported
- reported name
- scRegNet (scBERT backbone)
- 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 record identifies a composed analysis workflow with separately identifiable upstream models, representations or tools and a downstream prediction/scoring procedure. Results belong to that complete composition rather than to an upstream model alone.; source ids: scregnet-2025; source locator: Method/Graph-based learning with GNNs (paragraph 1); Method/Gene representations from foundation models (paragraph 1) | Conclusions and Discussions (paragraph 1); Results/Performance on benchmark datasets (paragraph 2); ambiguities: This is the paper-specific pipeline identity; unspecified component checkpoints or implementation versions are not inferred from its name.