Task

enhancer prediction

Enhancer classification evaluates a stacked predictor using functional genomic signal features.

Sources

Hi-Enhancer: a two-stage framework for prediction and localization of enhancers based on Blending-KAN and Stacking-Auto models · Methods §§2.1.1–2.1.2; cached text lines 13–14, 20–22; task metric definitions and corresponding results table

1 evaluation · 1 result

Overview

Datasets

HCT116 and A549 annotations assembled from ENCODE accessibility, activity and chromatin-mark data, with class-imbalanced negatives.

Metrics

Accuracy, AUROC and AUPRC; fold-wise standard deviations are reported separately from runtime.

Allowed inputs

Genomic regions with functional/epigenetic signals used by the classifier; this is not a sequence-only evaluation.

Sources

Evaluation procedure diagram

How it worksComputational evaluation flow

Conceptual summary of the cited evaluation; exact task configuration and source version remain part of the protocol.

Sources

Source reviewed · Automated source review, 2026-09-16. All specifications and missing details

Results

Results are available, but no reviewed comparison panel is linked in this release.

All evaluations

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: Stacking-Auto	Task: enhancer prediction Dataset: enhancer independent comparison	80.5% accuracy percent · unknown Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Stacking-Auto: enhancer prediction Two-stage Hi-Enhancer system; paper Table 2 method comparison Aggregation: Not reported Hi-Enhancer: a two-stage framework for prediction and localization of enhancers based on Blending-KAN and Stacking-Auto models · Table 2, Ours (Stacking-Auto) row, Accuracy column

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

Methods and evaluation design

Procedure, tasks and evaluated configurations

How it works

Evaluation methodology

HCT116 and A549 annotations assembled from ENCODE accessibility, activity and chromatin-mark data, with class-imbalanced negatives. The first layer uses a training/validation partition; subsequent stacking uses held-out base-model predictions and cross-validation. Accuracy, AUROC and AUPRC; fold-wise standard deviations are reported separately from runtime. AutoGluon base classifiers and a KAN meta-classifier are components of the evaluation. For the separate sequence-based boundary stage, Supplementary Text S6 reports CD-HIT filtering of iEnhancer-2L sequences but gives an unusual “>20% similarity” threshold without a reproducible command. The signal-based region detector instead uses the blending splits in Text S4. Neither passage establishes chromosome separation across that detector’s evaluation folds.

Sources (2)

Hi-Enhancer: a two-stage framework for prediction and localization of enhancers based on Blending-KAN and Stacking-Auto models; hi-enhancer-2025__btaf441_supplementary_data.docx · Methods §§2.1.1–2.1.2; cached text lines 13–14, 20–22; task metric definitions and corresponding results table; Supplementary Text S4 Dataset division and comparison with DECODE; Text S6 Benchmark datasets and performance evaluation metrics

Recorded evaluations

Each evaluation records what was tested and under which conditions.

Stacking-Auto: enhancer prediction

Run instructions

No runnable recipe has been reviewed for this task. Dataset access, model requirements, licences and compute requirements must be checked against its sources before execution.

A task describes a biological question. Choose a linked protocol to obtain concrete split and scoring instructions.

Strengths, limitations and unresolved questions

Strengths and limitations

Strengths supported by sources

No source-reviewed explanatory claims are recorded here yet.

Limitations and conditions

The epigenetic-signal region detector and the sequence-based boundary stage use different data and splits. The supplement’s unusual CD-HIT threshold requires an implementation-level clarification before claiming homology-disjoint evaluation.
Sources (2)
Hi-Enhancer: a two-stage framework for prediction and localization of enhancers based on Blending-KAN and Stacking-Auto models; hi-enhancer-2025__btaf441_supplementary_data.docx · Supplementary Text S4 Dataset division and comparison with DECODE; Text S6 Benchmark datasets and performance evaluation metrics

Profile review details

Targeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change.

Stable record: reported-task-22024610c4d658

Specifications

Inputs, training, access and other details

Explanatory profile: source reviewed · Automated source review, 2026-09-16. Review applies to the cited claims; unresolved fields are listed below. Numerical results retain their own review status.

Data, procedure and scoring
Property	Description and evidence
Datasets	HCT116 and A549 annotations assembled from ENCODE accessibility, activity and chromatin-mark data, with class-imbalanced negatives. Sources Hi-Enhancer: a two-stage framework for prediction and localization of enhancers based on Blending-KAN and Stacking-Auto models · Methods §§2.1.1–2.1.2; cached text lines 13–14, 20–22; task metric definitions and corresponding results table
Splits	The first layer uses a training/validation partition; subsequent stacking uses held-out base-model predictions and cross-validation. Sources Hi-Enhancer: a two-stage framework for prediction and localization of enhancers based on Blending-KAN and Stacking-Auto models · Methods §§2.1.1–2.1.2; cached text lines 13–14, 20–22; task metric definitions and corresponding results table
Metrics	Accuracy, AUROC and AUPRC; fold-wise standard deviations are reported separately from runtime. Sources Hi-Enhancer: a two-stage framework for prediction and localization of enhancers based on Blending-KAN and Stacking-Auto models · Methods §§2.1.1–2.1.2; cached text lines 13–14, 20–22; task metric definitions and corresponding results table
Baselines	AutoGluon base classifiers and a KAN meta-classifier are components of the evaluation. Sources Hi-Enhancer: a two-stage framework for prediction and localization of enhancers based on Blending-KAN and Stacking-Auto models · Methods §§2.1.1–2.1.2; cached text lines 13–14, 20–22; task metric definitions and corresponding results table
Leakage controls	For the separate sequence-based boundary stage, Supplementary Text S6 reports CD-HIT filtering of iEnhancer-2L sequences but gives an unusual “>20% similarity” threshold without a reproducible command. The signal-based region detector instead uses the blending splits in Text S4. Neither passage establishes chromosome separation across that detector’s evaluation folds. Sources (2) Hi-Enhancer: a two-stage framework for prediction and localization of enhancers based on Blending-KAN and Stacking-Auto models; hi-enhancer-2025__btaf441_supplementary_data.docx · Supplementary Text S4 Dataset division and comparison with DECODE; Text S6 Benchmark datasets and performance evaluation metrics
Uncertainty	Standard deviations across five cross-validation folds are reported for the classification metrics. Sources Hi-Enhancer: a two-stage framework for prediction and localization of enhancers based on Blending-KAN and Stacking-Auto models · Methods §§2.1.1–2.1.2; cached text lines 13–14, 20–22; task metric definitions and corresponding results table
Entity type	Paper-specific computational evaluation protocol. Sources Hi-Enhancer: a two-stage framework for prediction and localization of enhancers based on Blending-KAN and Stacking-Auto models · Methods §§2.1.1–2.1.2; cached text lines 13–14, 20–22; task metric definitions and corresponding results table
Organisms	Human HCT116 and A549 cells. Sources Hi-Enhancer: a two-stage framework for prediction and localization of enhancers based on Blending-KAN and Stacking-Auto models · Methods §§2.1.1–2.1.2; cached text lines 13–14, 20–22; task metric definitions and corresponding results table
Assays	ENCODE accessibility, activity and chromatin-mark annotations. Sources Hi-Enhancer: a two-stage framework for prediction and localization of enhancers based on Blending-KAN and Stacking-Auto models · Methods §§2.1.1–2.1.2; cached text lines 13–14, 20–22; task metric definitions and corresponding results table
Allowed inputs	Genomic regions with functional/epigenetic signals used by the classifier; this is not a sequence-only evaluation. Sources Hi-Enhancer: a two-stage framework for prediction and localization of enhancers based on Blending-KAN and Stacking-Auto models · Methods §§2.1.1–2.1.2; cached text lines 13–14, 20–22; task metric definitions and corresponding results table
Adaptation	Supervised stacked prediction; second-stage learning uses held-out base-model predictions. Sources Hi-Enhancer: a two-stage framework for prediction and localization of enhancers based on Blending-KAN and Stacking-Auto models · Methods §§2.1.1–2.1.2; cached text lines 13–14, 20–22; task metric definitions and corresponding results table

Evidence

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

Papers and result coverage

Last literature check: 2026-09-17. Primary-paper discovery and source inspection. Source-checked results are not independently reproduced experiments.

Paper or primary resource	Version	Reference
Hi-Enhancer: a two-stage framework for prediction and localization of enhancers based on Blending-KAN and Stacking-Auto models	version of record	Read source DOI: 10.1093/bioinformatics/btaf441

Historical gaps recorded on 2026-09-17

The catalogue now holds 1 result rows for this benchmark. A note below about pending extraction describes the state on 2026-09-17 and may since have been answered by a later batch. The result rows and their sources are the current record.

Text S6 defines the independent test set; supplementary data is necessary for a complete dataset manifest.
Table 2 does not report replicate uncertainty; other-method provenance must retain paper citations rather than imply all were rerun.

Search and extraction details

primary comparison table screened

Searches

"Hi-enhancer" 2025
"PMC12758598"

Evidence locations

Table 2
Results: Stacking-Auto comparison
Methods: Stacking-Auto
Supplement Text S6 (required context)

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

Claims, original sources and review scope · Release 2026-09-29-06401fd5b220
Property and statement	Original source and location	Review and provenance
Diagram caption Conceptual summary of the cited evaluation; exact task configuration and source version remain part of the protocol. Individual claims	Hi-Enhancer: a two-stage framework for prediction and localization of enhancers based on Blending-KAN and Stacking-Auto models Original source ↗ Methods §§2.1.1–2.1.2; cached text lines 13–14, 20–22; task metric definitions and corresponding results table Version: version of record Retrieved: 2026-09-16T10:41:06Z	source checked automated source review · 2026-09-16 Audit details Targeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: `attributes.profile.diagram.caption` Source artifact SHA-256: `c86488c9f60329b7a3c4370598e7a0a9e4c8c45d1758b87007bfc8242376b009` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Diagram steps Input: Genomic regions with functional/epigenetic signals used by the classifier; this is not a sequence-only evaluation. Evaluation: The first layer uses a training/validation partition; subsequent stacking uses held-out base-model predictions and cross-validation. Readout: Accuracy, AUROC and AUPRC; fold-wise standard deviations are reported separately from runtime. Individual claims	Hi-Enhancer: a two-stage framework for prediction and localization of enhancers based on Blending-KAN and Stacking-Auto models Original source ↗ Methods §§2.1.1–2.1.2; cached text lines 13–14, 20–22; task metric definitions and corresponding results table Version: version of record Retrieved: 2026-09-16T10:41:06Z	source checked automated source review · 2026-09-16 Audit details Targeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: `attributes.profile.diagram.steps` Source artifact SHA-256: `c86488c9f60329b7a3c4370598e7a0a9e4c8c45d1758b87007bfc8242376b009` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Diagram title Computational evaluation flow Individual claims	Hi-Enhancer: a two-stage framework for prediction and localization of enhancers based on Blending-KAN and Stacking-Auto models Original source ↗ Methods §§2.1.1–2.1.2; cached text lines 13–14, 20–22; task metric definitions and corresponding results table Version: version of record Retrieved: 2026-09-16T10:41:06Z	source checked automated source review · 2026-09-16 Audit details Targeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: `attributes.profile.diagram.title` Source artifact SHA-256: `c86488c9f60329b7a3c4370598e7a0a9e4c8c45d1758b87007bfc8242376b009` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Datasets HCT116 and A549 annotations assembled from ENCODE accessibility, activity and chromatin-mark data, with class-imbalanced negatives. Individual claims	Hi-Enhancer: a two-stage framework for prediction and localization of enhancers based on Blending-KAN and Stacking-Auto models Original source ↗ Methods §§2.1.1–2.1.2; cached text lines 13–14, 20–22; task metric definitions and corresponding results table Version: version of record Retrieved: 2026-09-16T10:41:06Z	source checked automated source review · 2026-09-16 Audit details Targeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: `attributes.profile.facts.0.value` Source artifact SHA-256: `c86488c9f60329b7a3c4370598e7a0a9e4c8c45d1758b87007bfc8242376b009` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Splits The first layer uses a training/validation partition; subsequent stacking uses held-out base-model predictions and cross-validation. Individual claims	Hi-Enhancer: a two-stage framework for prediction and localization of enhancers based on Blending-KAN and Stacking-Auto models Original source ↗ Methods §§2.1.1–2.1.2; cached text lines 13–14, 20–22; task metric definitions and corresponding results table Version: version of record Retrieved: 2026-09-16T10:41:06Z	source checked automated source review · 2026-09-16 Audit details Targeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: `attributes.profile.facts.1.value` Source artifact SHA-256: `c86488c9f60329b7a3c4370598e7a0a9e4c8c45d1758b87007bfc8242376b009` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Adaptation Supervised stacked prediction; second-stage learning uses held-out base-model predictions. Individual claims	Hi-Enhancer: a two-stage framework for prediction and localization of enhancers based on Blending-KAN and Stacking-Auto models Original source ↗ Methods §§2.1.1–2.1.2; cached text lines 13–14, 20–22; task metric definitions and corresponding results table Version: version of record Retrieved: 2026-09-16T10:41:06Z	source checked automated source review · 2026-09-16 Audit details Targeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: `attributes.profile.facts.10.value` Source artifact SHA-256: `c86488c9f60329b7a3c4370598e7a0a9e4c8c45d1758b87007bfc8242376b009` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Metrics Accuracy, AUROC and AUPRC; fold-wise standard deviations are reported separately from runtime. Individual claims	Hi-Enhancer: a two-stage framework for prediction and localization of enhancers based on Blending-KAN and Stacking-Auto models Original source ↗ Methods §§2.1.1–2.1.2; cached text lines 13–14, 20–22; task metric definitions and corresponding results table Version: version of record Retrieved: 2026-09-16T10:41:06Z	source checked automated source review · 2026-09-16 Audit details Targeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: `attributes.profile.facts.2.value` Source artifact SHA-256: `c86488c9f60329b7a3c4370598e7a0a9e4c8c45d1758b87007bfc8242376b009` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Baselines AutoGluon base classifiers and a KAN meta-classifier are components of the evaluation. Individual claims	Hi-Enhancer: a two-stage framework for prediction and localization of enhancers based on Blending-KAN and Stacking-Auto models Original source ↗ Methods §§2.1.1–2.1.2; cached text lines 13–14, 20–22; task metric definitions and corresponding results table Version: version of record Retrieved: 2026-09-16T10:41:06Z	source checked automated source review · 2026-09-16 Audit details Targeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: `attributes.profile.facts.3.value` Source artifact SHA-256: `c86488c9f60329b7a3c4370598e7a0a9e4c8c45d1758b87007bfc8242376b009` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Leakage controls For the separate sequence-based boundary stage, Supplementary Text S6 reports CD-HIT filtering of iEnhancer-2L sequences but gives an unusual “>20% similarity” threshold without a reproducible command. The signal-based region detector instead uses the blending splits in Text S4. Neither passage establishes chromosome separation across that detector’s evaluation folds. Individual claims	hi-enhancer-2025__btaf441_supplementary_data.docx Original source ↗ Supplementary Text S4 Dataset division and comparison with DECODE; Text S6 Benchmark datasets and performance evaluation metrics Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Retrieved 2026-09-16; sha256:26de5de88996a9da7723ba4036eb4cf234a77fae3bbab833edffbc7d99ec56a5 Retrieved: 2026-09-16T21:05:56.618187+00:00	source checked automated source review · 2026-09-16 Audit details Targeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: `attributes.profile.facts.4.value` Source artifact SHA-256: `26de5de88996a9da7723ba4036eb4cf234a77fae3bbab833edffbc7d99ec56a5` Hash scope: Hash scope not separately documented; inspect source record Archive member: btaf441_supplementary_data.docx Inspected artifact
Leakage controls For the separate sequence-based boundary stage, Supplementary Text S6 reports CD-HIT filtering of iEnhancer-2L sequences but gives an unusual “>20% similarity” threshold without a reproducible command. The signal-based region detector instead uses the blending splits in Text S4. Neither passage establishes chromosome separation across that detector’s evaluation folds. Individual claims	Hi-Enhancer: a two-stage framework for prediction and localization of enhancers based on Blending-KAN and Stacking-Auto models Original source ↗ Supplementary Text S4 Dataset division and comparison with DECODE; Text S6 Benchmark datasets and performance evaluation metrics Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: version of record Retrieved: 2026-09-16T10:41:06Z	source checked automated source review · 2026-09-16 Audit details Targeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: `attributes.profile.facts.4.value` Source artifact SHA-256: `c86488c9f60329b7a3c4370598e7a0a9e4c8c45d1758b87007bfc8242376b009` 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

3 source records and release history

Hi-Enhancer: a two-stage framework for prediction and localization of enhancers based on Blending-KAN and Stacking-Auto models · Original source · version of record
Hi-Enhancer: a two-stage framework for prediction and localization of enhancers based on Blending-KAN and Stacking-Auto models · Original source · version of record
hi-enhancer-2025__btaf441_supplementary_data.docx · Original source · Retrieved 2026-09-16; sha256:26de5de88996a9da7723ba4036eb4cf234a77fae3bbab833edffbc7d99ec56a5

Download this release

Technical metadata and extraction receipts

Stable ID: reported-task-22024610c4d658

areas: dna-genomes
tasks: enhancer prediction
entity level: task
version: Not reported
task: enhancer prediction
scope note: Paper-specific evaluation task; protocol completeness requires further extraction.
benchmark research: review date: 2026-09-17; status: primary_comparison_table_screened; primary sources: expansion-p3-hi-enhancer-2025; inspected locators: Table 2; Results: Stacking-Auto comparison; Methods: Stacking-Auto; Supplement Text S6 (required context); searched queries: "Hi-enhancer" 2025; "PMC12758598"; gaps: Text S6 defines the independent test set; supplementary data is necessary for a complete dataset manifest.; Table 2 does not report replicate uncertainty; other-method provenance must retain paper citations rather than imply all were rerun.; claim scope: Primary-paper discovery and source inspection. Source-checked results are not independently reproduced experiments.
historical missing metadata: protocol version: not_reported_in_legacy_extract; split: 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: benchmark
entity classification: review date: 2026-09-17; rationale: This source-scoped record identifies the biological prediction task and holds its paper context. Preserve the existing task identity; exact split, model adaptation and scoring remain in linked evaluations or separate protocol records.; source ids: hi-enhancer-2025; source locator: Methods §§2.1.1–2.1.2; cached text lines 13–14, 20–22; task metric definitions and corresponding results table; ambiguities: A paper- or suite-specific task may constrain some inputs or metrics; that alone does not make it interchangeable with a complete versioned protocol. No protocol equivalence is inferred.; Some legacy profile Entity type facts use the generic phrase computational evaluation protocol. That boilerplate is not sufficient to establish a single fixed protocol identity or to merge this task with another protocol record.

Related records

dataset: enhancer independent comparison
benchmark: Stacking-Auto: enhancer prediction

Suggest a correction