Pipeline

scLLMDA

scLLMDA annotates scATAC-seq cells using peak-sequence embeddings and graph-based domain adaptation.

Sources

Cell type annotation for scATAC-seq via DNA large language model and graph domain adaptation · Discussion (paragraph 1); Introduction (paragraph 4)

1 evaluation · 1 result

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

Cell type annotation for scATAC-seq via DNA large language model and graph domain adaptation · Materials and methods/Cell type annotation via graph domain adaptation/Capture the local consistency relationship of each graph. (paragraph 4); Materials and methods/Loss function (paragraph 1)

Overview

Model type

Graph-based predictive method; this record is the paper-specific evaluated configuration.

Sources

Biological inputs

scATAC-seq accessibility values, peak DNA sequences and labelled reference cells

Sources

Cell type annotation for scATAC-seq via DNA large language model and graph domain adaptation · Materials and methods/Feature extraction from genomic sequences (paragraph 5); Materials and methods/Feature extraction from genomic sequences (paragraph 4)

Outputs

Cell-type annotations in a target scATAC-seq dataset

Sources

Cell type annotation for scATAC-seq via DNA large language model and graph domain adaptation · Materials and methods/Problem definition (paragraph 1); Results/Effectiveness of GDA module (paragraph 3)

Access

Official study implementation and usage documentation: https://github.com/sheng-guan-2001/scLLMDA/blob/5e24025710bb068312d50a5749ef6bb838ef5a32/README.md. This pinned documentation revision is not automatically the evaluated weight revision.

Sources

sheng-guan-2001/scLLMDA README.md · README.md; installation, model download and usage instructions

limited source coverage · Automated source review, 2026-09-16. All specifications and missing details

Evaluations and results

1 evaluation · 1 result. Different protocols are not a single leaderboard.

Filter evaluations

Tested model or methodProtocolDatasetEvaluation setupMetricEvidence origin

Applied filters: All linked evaluations

Exact evaluated configurations and original reported results
Tested configuration	Protocol and dataset	Finding	Evidence and details
Pipeline: scLLMDA	Task: Cross-platform scATAC cell-type annotation Dataset: MosA1 reference → WholeBrainA query	0.652 F1 unitless · unknown Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source scLLMDA: Cross-platform scATAC cell-type annotation Cross-platform reference-query cell-type annotation. Aggregation: Not reported Cell type annotation for scATAC-seq via DNA large language model and graph domain adaptation · Table 2, scLLMDA row, Ref: MosA1 / Q: WholeBrainA F1 column

Source checking is not independent reproduction. Release 2026-09-29-06401fd5b220.

Use this model

How it works, versions and access

How it works

How the evaluated method works

A pretrained DNA model encodes peak sequences; accessibility values form cell representations. Source and target similarity graphs enter a graph neural network that aligns domains while retaining local neighbourhoods.

Sources

What was evaluated

The linked evaluation record identifies scLLMDA: Cross-platform scATAC cell-type annotation. Its dataset, split, adaptation and evidence origin remain attached to the reported results.

Sources

Cell type annotation for scATAC-seq via DNA large language model and graph domain adaptation · The named evaluation’s methods and comparison table; exact preserved evaluation IDs: evaluation-lit-b3-005

Strengths, limitations and unresolved questions

Strengths and limitations

Strengths and considerations

Uses both sequence features and cell-neighbourhood context for transfer within the ATAC modality.
Sources
Cell type annotation for scATAC-seq via DNA large language model and graph domain adaptation · Materials and methods/Cell type annotation via graph domain adaptation/Feature fusion via attention. (paragraph 6); Materials and methods/Cell type annotation via graph domain adaptation/Feature fusion via attention. (paragraph 1)

Limitations and conditions

Access to target-cell structure is part of the adaptation protocol; it is not equivalent to a purely inductive sequence-only test.
Sources
Cell type annotation for scATAC-seq via DNA large language model and graph domain adaptation · Materials and methods/Parameter settings (paragraph 1); Materials and methods/Cell type annotation via graph domain adaptation/Feature fusion via attention. (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-a0db32ae53e5ed

Specifications

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.

Inputs, outputs and configuration
Property	Description and evidence
Model type	Graph-based predictive method; this record is the paper-specific evaluated configuration. Sources Cell type annotation for scATAC-seq via DNA large language model and graph domain adaptation · Materials and methods/Cell type annotation via graph domain adaptation/Capture the local consistency relationship of each graph. (paragraph 4); Materials and methods/Loss function (paragraph 1)
Architecture / procedure	A pretrained DNA model encodes peak sequences; accessibility values form cell representations. Source and target similarity graphs enter a graph neural network that aligns domains while retaining local neighbourhoods. Sources Cell type annotation for scATAC-seq via DNA large language model and graph domain adaptation · Materials and methods/Cell type annotation via graph domain adaptation/Capture the local consistency relationship of each graph. (paragraph 4); Materials and methods/Loss function (paragraph 1)
Biological inputs	scATAC-seq accessibility values, peak DNA sequences and labelled reference cells Sources Cell type annotation for scATAC-seq via DNA large language model and graph domain adaptation · Materials and methods/Feature extraction from genomic sequences (paragraph 5); Materials and methods/Feature extraction from genomic sequences (paragraph 4)
Outputs	Cell-type annotations in a target scATAC-seq dataset Sources Cell type annotation for scATAC-seq via DNA large language model and graph domain adaptation · Materials and methods/Problem definition (paragraph 1); Results/Effectiveness of GDA module (paragraph 3)
Parameters	An aggregate parameter total for this exact evaluated configuration is not established by the inspected sources. · Not reported in inspected sources Sources (2) Cell type annotation for scATAC-seq via DNA large language model and graph domain adaptation; sheng-guan-2001/scLLMDA README.md · Materials and methods/Benchmark datasets; Materials and methods/Benchmark methods; Materials and methods/Problem definition; Materials and methods/Feature extraction from genomic sequences; Materials and methods/Cell type annotation via graph domain adaptation/Graph construction.; Materials and methods/Cell type annotation via graph domain adaptation/Capture the local consistency relationship of each graph.; Materials and methods/Cell type annotation via graph domain adaptation/Capture the global consistency relationship of each graph.; Materials and methods/Cell type annotation via graph domain adaptation/Feature fusion via attention.; inspected for aggregate parameter count (component sizes are not added without an exact configuration); README.md at pinned repository revision
Known versions / configuration	scLLMDA is the comparison-table label; that label does not specify an immutable weight revision. · Not reported in inspected sources Sources Cell type annotation for scATAC-seq via DNA large language model and graph domain adaptation · Model identification in the comparison table and corresponding Methods; immutable checkpoint revision is not supplied by the table label.
Training data / fitting	Cross-dataset cell annotation uses mouse snATAC-seq/ATAC-seq datasets GSE126724 and GSE111586 plus10xMouseBrain; assemblies differ (GRCm38/mm10 versus mm9) and remain dataset-specific. Sources Cell type annotation for scATAC-seq via DNA large language model and graph domain adaptation · Materials and methods/Benchmark datasets (paragraph 1); Results/Cross-platform cell type annotation (paragraph 1)
Context limits	A maximum input/context length for this exact evaluated configuration is not established by the inspected sources. · Not reported in inspected sources Sources (2) Cell type annotation for scATAC-seq via DNA large language model and graph domain adaptation; sheng-guan-2001/scLLMDA README.md · Materials and methods/Benchmark datasets; Materials and methods/Benchmark methods; Materials and methods/Problem definition; Materials and methods/Feature extraction from genomic sequences; Materials and methods/Cell type annotation via graph domain adaptation/Graph construction.; Materials and methods/Cell type annotation via graph domain adaptation/Capture the local consistency relationship of each graph.; Materials and methods/Cell type annotation via graph domain adaptation/Capture the global consistency relationship of each graph.; Materials and methods/Cell type annotation via graph domain adaptation/Feature fusion via attention.; 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/sheng-guan-2001/scLLMDA/blob/5e24025710bb068312d50a5749ef6bb838ef5a32/README.md. This pinned documentation revision is not automatically the evaluated weight revision. Sources sheng-guan-2001/scLLMDA 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 sources Sources sheng-guan-2001/scLLMDA 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 sources Sources sheng-guan-2001/scLLMDA README.md · README.md; checkpoint/access documentation and licence scope

Evidence

Source checking verifies the cited claim or transcription. It does not establish independent reproduction.

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

Claims, original sources and review scope · Release 2026-09-29-06401fd5b220
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	Cell type annotation for scATAC-seq via DNA large language model and graph domain adaptation Original source ↗ Materials and methods/Cell type annotation via graph domain adaptation/Capture the local consistency relationship of each graph. (paragraph 4); Materials and methods/Loss function (paragraph 1) Version: version of record Retrieved: 2026-09-16T10:44:03.395850+00:00	source checked automated source review · 2026-09-16 Audit 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. Field: `attributes.profile.diagram.caption` Source artifact SHA-256: `f1cdc7d54c6b2d491e4a74a44a1188a3679c555262c988e95a1c0de4614fe3cb` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Diagram steps scATAC-seq accessibility values, peak DNA sequences and labelled reference cells scLLMDA Cell-type annotations in a target scATAC-seq dataset Individual claims	Cell type annotation for scATAC-seq via DNA large language model and graph domain adaptation Original source ↗ Materials and methods/Cell type annotation via graph domain adaptation/Capture the local consistency relationship of each graph. (paragraph 4); Materials and methods/Loss function (paragraph 1) Version: version of record Retrieved: 2026-09-16T10:44:03.395850+00:00	source checked automated source review · 2026-09-16 Audit 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. Field: `attributes.profile.diagram.steps` Source artifact SHA-256: `f1cdc7d54c6b2d491e4a74a44a1188a3679c555262c988e95a1c0de4614fe3cb` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Diagram title Evaluated procedure (conceptual) Individual claims	Cell type annotation for scATAC-seq via DNA large language model and graph domain adaptation Original source ↗ Materials and methods/Cell type annotation via graph domain adaptation/Capture the local consistency relationship of each graph. (paragraph 4); Materials and methods/Loss function (paragraph 1) Version: version of record Retrieved: 2026-09-16T10:44:03.395850+00:00	source checked automated source review · 2026-09-16 Audit 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. Field: `attributes.profile.diagram.title` Source artifact SHA-256: `f1cdc7d54c6b2d491e4a74a44a1188a3679c555262c988e95a1c0de4614fe3cb` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Model type Graph-based predictive method; this record is the paper-specific evaluated configuration. Individual claims	Cell type annotation for scATAC-seq via DNA large language model and graph domain adaptation Original source ↗ Materials and methods/Cell type annotation via graph domain adaptation/Capture the local consistency relationship of each graph. (paragraph 4); Materials and methods/Loss function (paragraph 1) Version: version of record Retrieved: 2026-09-16T10:44:03.395850+00:00	source checked automated source review · 2026-09-16 Audit 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. Field: `attributes.profile.facts.0.value` Source artifact SHA-256: `f1cdc7d54c6b2d491e4a74a44a1188a3679c555262c988e95a1c0de4614fe3cb` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Architecture / procedure A pretrained DNA model encodes peak sequences; accessibility values form cell representations. Source and target similarity graphs enter a graph neural network that aligns domains while retaining local neighbourhoods. Individual claims	Cell type annotation for scATAC-seq via DNA large language model and graph domain adaptation Original source ↗ Materials and methods/Cell type annotation via graph domain adaptation/Capture the local consistency relationship of each graph. (paragraph 4); Materials and methods/Loss function (paragraph 1) Version: version of record Retrieved: 2026-09-16T10:44:03.395850+00:00	source checked automated source review · 2026-09-16 Audit 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. Field: `attributes.profile.facts.1.value` Source artifact SHA-256: `f1cdc7d54c6b2d491e4a74a44a1188a3679c555262c988e95a1c0de4614fe3cb` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
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	sheng-guan-2001/scLLMDA README.md Original source ↗ README.md; checkpoint/access documentation and licence scope Version: 5e24025710bb068312d50a5749ef6bb838ef5a32 Retrieved: 2026-09-16T19:54:22.541360+00:00	unreported automated source review · 2026-09-16 Audit 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. Field: `attributes.profile.facts.10.value` Source artifact SHA-256: `b8327f7bbd867d6e5b7ab369873b59aeba64fe4ca79c879dd54c3b036b127d3b` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Biological inputs scATAC-seq accessibility values, peak DNA sequences and labelled reference cells Individual claims	Cell type annotation for scATAC-seq via DNA large language model and graph domain adaptation Original source ↗ Materials and methods/Feature extraction from genomic sequences (paragraph 5); Materials and methods/Feature extraction from genomic sequences (paragraph 4) Version: version of record Retrieved: 2026-09-16T10:44:03.395850+00:00	source checked automated source review · 2026-09-16 Audit 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. Field: `attributes.profile.facts.2.value` Source artifact SHA-256: `f1cdc7d54c6b2d491e4a74a44a1188a3679c555262c988e95a1c0de4614fe3cb` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Outputs Cell-type annotations in a target scATAC-seq dataset Individual claims	Cell type annotation for scATAC-seq via DNA large language model and graph domain adaptation Original source ↗ Materials and methods/Problem definition (paragraph 1); Results/Effectiveness of GDA module (paragraph 3) Version: version of record Retrieved: 2026-09-16T10:44:03.395850+00:00	source checked automated source review · 2026-09-16 Audit 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. Field: `attributes.profile.facts.3.value` Source artifact SHA-256: `f1cdc7d54c6b2d491e4a74a44a1188a3679c555262c988e95a1c0de4614fe3cb` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Parameters An aggregate parameter total for this exact evaluated configuration is not established by the inspected sources. Individual claims	sheng-guan-2001/scLLMDA README.md Original source ↗ Materials and methods/Benchmark datasets; Materials and methods/Benchmark methods; Materials and methods/Problem definition; Materials and methods/Feature extraction from genomic sequences; Materials and methods/Cell type annotation via graph domain adaptation/Graph construction.; Materials and methods/Cell type annotation via graph domain adaptation/Capture the local consistency relationship of each graph.; Materials and methods/Cell type annotation via graph domain adaptation/Capture the global consistency relationship of each graph.; Materials and methods/Cell type annotation via graph domain adaptation/Feature fusion via attention.; 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: 5e24025710bb068312d50a5749ef6bb838ef5a32 Retrieved: 2026-09-16T19:54:22.541360+00:00	unreported automated source review · 2026-09-16 Audit 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. Field: `attributes.profile.facts.4.value` Source artifact SHA-256: `b8327f7bbd867d6e5b7ab369873b59aeba64fe4ca79c879dd54c3b036b127d3b` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Parameters An aggregate parameter total for this exact evaluated configuration is not established by the inspected sources. Individual claims	Cell type annotation for scATAC-seq via DNA large language model and graph domain adaptation Original source ↗ Materials and methods/Benchmark datasets; Materials and methods/Benchmark methods; Materials and methods/Problem definition; Materials and methods/Feature extraction from genomic sequences; Materials and methods/Cell type annotation via graph domain adaptation/Graph construction.; Materials and methods/Cell type annotation via graph domain adaptation/Capture the local consistency relationship of each graph.; Materials and methods/Cell type annotation via graph domain adaptation/Capture the global consistency relationship of each graph.; Materials and methods/Cell type annotation via graph domain adaptation/Feature fusion via attention.; 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: version of record Retrieved: 2026-09-16T10:44:03.395850+00:00	unreported automated source review · 2026-09-16 Audit 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. Field: `attributes.profile.facts.4.value` Source artifact SHA-256: `f1cdc7d54c6b2d491e4a74a44a1188a3679c555262c988e95a1c0de4614fe3cb` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact

All evidence (CSV)All evidence (JSONL)How to read the evidence

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

Cell type annotation for scATAC-seq via DNA large language model and graph domain adaptation · Original source · version of record
sheng-guan-2001/scLLMDA README.md · Original source · 5e24025710bb068312d50a5749ef6bb838ef5a32

Download this release

Technical metadata and extraction receipts

Stable ID: reported-model-a0db32ae53e5ed

areas: cells-tissues
entity level: method
version: Not reported
reported name: scLLMDA
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: The source identifies three stages: DNABERT-2 sequence feature extraction, cell embedding learning, and graph construction with domain adaptation. Preserve the exact source-scoped composition and its results; no additional checkpoint or family equivalence is inferred.; source ids: scatac-llmda-2026; source locator: Materials and methods/Cell type annotation via graph domain adaptation/Capture the local consistency relationship of each graph. (paragraph 4); Materials and methods/Loss function (paragraph 1) | Discussion (paragraph 1); Introduction (paragraph 4) | Materials and methods: Feature extraction from genomic sequences; Cell type annotation via graph domain adaptation; Results: Computational efficiency and scalability; ambiguities: This is the paper-specific pipeline identity. Missing component versions or checkpoint hashes remain unknown; a shared upstream name does not establish equivalent pipelines.

Related records

model: scLLMDA: Cross-platform scATAC cell-type annotation

Suggest a correction