Model

Pangolin

Pangolin predicts splice-site strength and changes caused by genetic variants.

Sources (2)

tkzeng/Pangolin: README.md; pangolin: Journal full-text XML · Paper: Deep neural network architecture and Generating training and test sets; README.md: Usage

8 evaluations · 16 results 2 configurations with further results

How it worksPangolin workflow

Conceptual summary of the documented data flow; optional inputs and configured downstream stages must be reported for a reproducible evaluation.

Sources (2)

tkzeng/Pangolin: README.md; pangolin: Journal full-text XML · Paper: Deep neural network architecture and Generating training and test sets; README.md: Usage

Overview

Model type

Dilated convolutional splicing predictor

Inputs

VCF or CSV variants, reference FASTA and matching gene annotations; custom sequence inference is also available.

Outputs

Predicted increases/decreases in splice-site strength and their positions.

Access

Official project documentation and implementation: https://github.com/tkzeng/Pangolin

Sources (2)

tkzeng/Pangolin: README.md; pangolin: Journal full-text XML · Paper: Deep neural network architecture and Generating training and test sets; README.md: Usage

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

Evaluations and results

8 evaluations · 16 results. Different protocols are not a single leaderboard.

Sorted by AUROC (higher is better). The best value in each column is highlighted. Decimals are rounded for display; each value links to the printed value and its source.

Tested configuration	Protocol and dataset	AUROC	Average precision	Precision at 100	AUPRC (max absolute track aggregation)	Recall at 100	AUPRC	AUPRC (all tissues pooled)	AUPRC (tissue-weighted mean)
Pangolin 1.0.2 + per-gene masking patch · mask False (P0)Evaluation	MFASS: matched GENCODE 44 canonical annotation, MFASS v2 test: matched canonical annotation coverage	0.876 (best in column)	0.389	0.65	Not reported	0.207	Not reported	Not reported	Not reported
Pangolin · mask=FalseEvaluation	MFASS v2, MFASS v2 eligible assay cohort	0.876	0.389	0.65	Not reported	Not reported	Not reported	Not reported	Not reported
Pangolin 1.0.2 + per-gene masking patch · mask True (P1)Evaluation	MFASS: matched GENCODE 44 canonical annotation, MFASS v2 test: matched canonical annotation coverage	0.873	0.411 (best in column)	0.66 (best in column)	Not reported	0.21 (best in column)	Not reported	Not reported	Not reported
Pangolin (paper Table 4)Evaluation	Deep intronic and synonymous variants splicing-based classification (AlphaGenome paper), Deep intronic and synonymous variants splicing-based classification: evaluated data subset	Not reported	Not reported	Not reported	0.641 (best in column)	Not reported	Not reported	Not reported	Not reported
Pangolin (paper Table 4)Evaluation	Splicing-QTL causality (AlphaGenome paper), Splicing-QTL causality: evaluated data subset	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	0.732
Pangolin (paper Table 4)Evaluation	Author MFASS splice-disruption prediction (AlphaGenome paper), Author MFASS splice-disruption prediction: evaluated data subset	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	0.542	Not reported
Pangolin (paper Table 4)Evaluation	Zero-shot GTEx splicing-outlier prediction (AlphaGenome paper), Zero-shot GTEx splicing-outlier prediction: evaluated data subset	Not reported	Not reported	Not reported	Not reported	Not reported	0.14	Not reported	Not reported
Pangolin (paper Table 4)Evaluation	Splice-site-region variants splicing-based classification (AlphaGenome paper), Splice-site-region variants splicing-based classification: evaluated data subset	Not reported	Not reported	Not reported	0.554	Not reported	Not reported	Not reported	Not reported

All 16 result rows with coverage, uncertainty and sources

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
Configuration: Pangolin (paper Table 4)	Protocol: Deep intronic and synonymous variants splicing-based classification (AlphaGenome paper) Dataset subset: Deep intronic and synonymous variants splicing-based classification: evaluated data subset	0.641 AUPRC (max absolute track aggregation) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Pangolin (paper Table 4): Deep intronic and synonymous variants splicing-based classification Score each variant from its predicted splicing changes and compare with the selected ClinVar pathogenicity labels. Aggregation: auPRC in the category, retaining its own class prevalence and sampling scheme. AlphaGenome Nature 2026 supplementary comparison tables · 'Suppl Table 4 Variant performan'!L3
Configuration: Pangolin (paper Table 4)	Protocol: Splicing-QTL causality (AlphaGenome paper) Dataset subset: Splicing-QTL causality: evaluated data subset	0.732 AUPRC (tissue-weighted mean) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Pangolin (paper Table 4): Splicing-QTL causality Compare predicted splicing effects for causal sQTLs and matched negatives; keep the wide and proximal splice-distance analyses distinct. Aggregation: auPRC per tissue, averaged with variant-count weights. AlphaGenome Nature 2026 supplementary comparison tables · 'Suppl Table 4 Variant performan'!L5
Configuration: Pangolin (paper Table 4)	Protocol: Author MFASS splice-disruption prediction (AlphaGenome paper) Dataset subset: Author MFASS splice-disruption prediction: evaluated data subset	0.542 AUPRC (all tissues pooled) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Pangolin (paper Table 4): Author MFASS splice-disruption prediction Use the MFASS-specific donor/acceptor and junction scoring procedure, sum splicing components, then average across tissues. Compare with the source’s exon-inclusion disruption label. Aggregation: auPRC for the splice-disrupting label defined by the MFASS exon-inclusion threshold. AlphaGenome Nature 2026 supplementary comparison tables · 'Suppl Table 4 Variant performan'!L8
Configuration: Pangolin (paper Table 4)	Protocol: Zero-shot GTEx splicing-outlier prediction (AlphaGenome paper) Dataset subset: Zero-shot GTEx splicing-outlier prediction: evaluated data subset	0.14 AUPRC unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Pangolin (paper Table 4): Zero-shot GTEx splicing-outlier prediction Evaluate the sequence-derived scores directly on the held-out variants. Aggregation: Pooled auPRC across GTEx tissues after assigning positive variants their observed tissues and negatives tissues sampled to match the positive tissue distribution. AlphaGenome Nature 2026 supplementary comparison tables · 'Suppl Table 4 Variant performan'!L6
Configuration: Pangolin (paper Table 4)	Protocol: Splice-site-region variants splicing-based classification (AlphaGenome paper) Dataset subset: Splice-site-region variants splicing-based classification: evaluated data subset	0.554 AUPRC (max absolute track aggregation) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Pangolin (paper Table 4): Splice-site-region variants splicing-based classification Score each variant from its predicted splicing changes and compare with the selected ClinVar pathogenicity labels. Aggregation: auPRC in the category, retaining its own class prevalence and sampling scheme. AlphaGenome Nature 2026 supplementary comparison tables · 'Suppl Table 4 Variant performan'!L4
Configuration: Pangolin 1.0.2 + per-gene masking patch · mask False (P0)	Protocol: MFASS: matched GENCODE 44 canonical annotation Dataset subset: MFASS v2 test: matched canonical annotation coverage	0.876 AUROC unitless · higher Uncertainty: Not reported by the source: Point estimate; paired contrast intervals are reported separately in the source and must not be used as intervals for this individual condition. Coverage: 8297/8324 scored	Rewire evaluation · Source checked Methods, coverage and source Pangolin 1.0.2 + per-gene masking patch · mask False (P0) on MFASS matched annotation MFASS matched GENCODE 44 canonical annotation Aggregation: Not reported MFASS matched canonical annotation v1: report.json; MFASS matched canonical annotation v1: manifest-v1.json; MFASS matched canonical annotation v1: verification.json; MFASS matched canonical annotation v1: provenance.json; MFASS matched canonical annotation v1: exclusion-verification.json · report.json: conditions.P0.metrics.auroc
Configuration: Pangolin 1.0.2 + per-gene masking patch · mask False (P0)	Protocol: MFASS: matched GENCODE 44 canonical annotation Dataset subset: MFASS v2 test: matched canonical annotation coverage	0.389 Average precision unitless · higher Uncertainty: Not reported by the source: Point estimate; paired contrast intervals are reported separately in the source and must not be used as intervals for this individual condition. Coverage: 8297/8324 scored	Rewire evaluation · Source checked Methods, coverage and source Pangolin 1.0.2 + per-gene masking patch · mask False (P0) on MFASS matched annotation MFASS matched GENCODE 44 canonical annotation Aggregation: Not reported MFASS matched canonical annotation v1: report.json; MFASS matched canonical annotation v1: manifest-v1.json; MFASS matched canonical annotation v1: verification.json; MFASS matched canonical annotation v1: provenance.json; MFASS matched canonical annotation v1: exclusion-verification.json · report.json: conditions.P0.metrics.average_precision_sklearn
Configuration: Pangolin 1.0.2 + per-gene masking patch · mask False (P0)	Protocol: MFASS: matched GENCODE 44 canonical annotation Dataset subset: MFASS v2 test: matched canonical annotation coverage	0.65 Precision at 100 unitless · higher Uncertainty: Not reported by the source: Point estimate; paired contrast intervals are reported separately in the source and must not be used as intervals for this individual condition. Coverage: 8297/8324 scored	Rewire evaluation · Source checked Methods, coverage and source Pangolin 1.0.2 + per-gene masking patch · mask False (P0) on MFASS matched annotation MFASS matched GENCODE 44 canonical annotation Aggregation: Not reported MFASS matched canonical annotation v1: report.json; MFASS matched canonical annotation v1: manifest-v1.json; MFASS matched canonical annotation v1: verification.json; MFASS matched canonical annotation v1: provenance.json; MFASS matched canonical annotation v1: exclusion-verification.json · report.json: conditions.P0.metrics.precision_at_capacity
Configuration: Pangolin 1.0.2 + per-gene masking patch · mask False (P0)	Protocol: MFASS: matched GENCODE 44 canonical annotation Dataset subset: MFASS v2 test: matched canonical annotation coverage	0.207 Recall at 100 unitless · higher Uncertainty: Not reported by the source: Point estimate; paired contrast intervals are reported separately in the source and must not be used as intervals for this individual condition. Coverage: 8297/8324 scored	Rewire evaluation · Source checked Methods, coverage and source Pangolin 1.0.2 + per-gene masking patch · mask False (P0) on MFASS matched annotation MFASS matched GENCODE 44 canonical annotation Aggregation: Not reported MFASS matched canonical annotation v1: report.json; MFASS matched canonical annotation v1: manifest-v1.json; MFASS matched canonical annotation v1: verification.json; MFASS matched canonical annotation v1: provenance.json; MFASS matched canonical annotation v1: exclusion-verification.json · report.json: conditions.P0.metrics.recall_at_capacity
Configuration: Pangolin 1.0.2 + per-gene masking patch · mask True (P1)	Protocol: MFASS: matched GENCODE 44 canonical annotation Dataset subset: MFASS v2 test: matched canonical annotation coverage	0.873 AUROC unitless · higher Uncertainty: Not reported by the source: Point estimate; paired contrast intervals are reported separately in the source and must not be used as intervals for this individual condition. Coverage: 8297/8324 scored	Rewire evaluation · Source checked Methods, coverage and source Pangolin 1.0.2 + per-gene masking patch · mask True (P1) on MFASS matched annotation MFASS matched GENCODE 44 canonical annotation Aggregation: Not reported MFASS matched canonical annotation v1: report.json; MFASS matched canonical annotation v1: manifest-v1.json; MFASS matched canonical annotation v1: verification.json; MFASS matched canonical annotation v1: provenance.json; MFASS matched canonical annotation v1: exclusion-verification.json · report.json: conditions.P1.metrics.auroc
Configuration: Pangolin 1.0.2 + per-gene masking patch · mask True (P1)	Protocol: MFASS: matched GENCODE 44 canonical annotation Dataset subset: MFASS v2 test: matched canonical annotation coverage	0.411 Average precision unitless · higher Uncertainty: Not reported by the source: Point estimate; paired contrast intervals are reported separately in the source and must not be used as intervals for this individual condition. Coverage: 8297/8324 scored	Rewire evaluation · Source checked Methods, coverage and source Pangolin 1.0.2 + per-gene masking patch · mask True (P1) on MFASS matched annotation MFASS matched GENCODE 44 canonical annotation Aggregation: Not reported MFASS matched canonical annotation v1: report.json; MFASS matched canonical annotation v1: manifest-v1.json; MFASS matched canonical annotation v1: verification.json; MFASS matched canonical annotation v1: provenance.json; MFASS matched canonical annotation v1: exclusion-verification.json · report.json: conditions.P1.metrics.average_precision_sklearn
Configuration: Pangolin 1.0.2 + per-gene masking patch · mask True (P1)	Protocol: MFASS: matched GENCODE 44 canonical annotation Dataset subset: MFASS v2 test: matched canonical annotation coverage	0.66 Precision at 100 unitless · higher Uncertainty: Not reported by the source: Point estimate; paired contrast intervals are reported separately in the source and must not be used as intervals for this individual condition. Coverage: 8297/8324 scored	Rewire evaluation · Source checked Methods, coverage and source Pangolin 1.0.2 + per-gene masking patch · mask True (P1) on MFASS matched annotation MFASS matched GENCODE 44 canonical annotation Aggregation: Not reported MFASS matched canonical annotation v1: report.json; MFASS matched canonical annotation v1: manifest-v1.json; MFASS matched canonical annotation v1: verification.json; MFASS matched canonical annotation v1: provenance.json; MFASS matched canonical annotation v1: exclusion-verification.json · report.json: conditions.P1.metrics.precision_at_capacity
Configuration: Pangolin 1.0.2 + per-gene masking patch · mask True (P1)	Protocol: MFASS: matched GENCODE 44 canonical annotation Dataset subset: MFASS v2 test: matched canonical annotation coverage	0.21 Recall at 100 unitless · higher Uncertainty: Not reported by the source: Point estimate; paired contrast intervals are reported separately in the source and must not be used as intervals for this individual condition. Coverage: 8297/8324 scored	Rewire evaluation · Source checked Methods, coverage and source Pangolin 1.0.2 + per-gene masking patch · mask True (P1) on MFASS matched annotation MFASS matched GENCODE 44 canonical annotation Aggregation: Not reported MFASS matched canonical annotation v1: report.json; MFASS matched canonical annotation v1: manifest-v1.json; MFASS matched canonical annotation v1: verification.json; MFASS matched canonical annotation v1: provenance.json; MFASS matched canonical annotation v1: exclusion-verification.json · report.json: conditions.P1.metrics.recall_at_capacity
Configuration: Pangolin · mask=False	Protocol: MFASS v2 Dataset: MFASS v2 eligible assay cohort	0.876 AUROC unitless · higher Uncertainty: Not reported by the source: Point estimate; see paired-comparison artifacts. Coverage: 8301/8324 scored	Rewire evaluation · Independently reproduced Methods, coverage and source Pangolin · mask=False on MFASS v2 Unchanged specialist run in genomic context with GENCODE v44; zero-shot on MFASS assay labels. Point metrics use the scored subset. Aggregation: Not reported MFASS v2 pinned rewire artifacts · benchmarks/mfass/results/pangolin-maskFalse.json :: auroc
Configuration: Pangolin · mask=False	Protocol: MFASS v2 Dataset: MFASS v2 eligible assay cohort	0.389 Average precision fraction · higher Uncertainty: Not reported by the source: Point estimate; see paired-comparison artifacts. Coverage: 8301/8324 scored	Rewire evaluation · Independently reproduced Methods, coverage and source Pangolin · mask=False on MFASS v2 Unchanged specialist run in genomic context with GENCODE v44; zero-shot on MFASS assay labels. Point metrics use the scored subset. Aggregation: Not reported MFASS v2 pinned rewire artifacts · benchmarks/mfass/results/pangolin-maskFalse.json :: average_precision
Configuration: Pangolin · mask=False	Protocol: MFASS v2 Dataset: MFASS v2 eligible assay cohort	0.65 Precision at 100 fraction · higher Uncertainty: Not reported by the source: Point estimate; see paired-comparison artifacts. Coverage: 8301/8324 scored	Rewire evaluation · Independently reproduced Methods, coverage and source Pangolin · mask=False on MFASS v2 Unchanged specialist run in genomic context with GENCODE v44; zero-shot on MFASS assay labels. Point metrics use the scored subset. Aggregation: Not reported MFASS v2 pinned rewire artifacts · benchmarks/mfass/results/pangolin-maskFalse.json :: precision_at_100

Source checking is not independent reproduction. Release 2026-11-02-a7f03c9e55a5.

Further results on linked records

2 linked records have results that are not included above, because no reviewed claim yet ties the link to this model. Each record keeps its own settings and evaluations, and its scores are on its own page.

Pangolin (Evo 2 paper variant effect evaluations) Configuration · configuration of this model · 26 evaluations · 52 results
Pangolin (evaluation mode not printed (Table 4 has no Eval. column), GUANinE v1.1) Configuration · configuration of this model · 1 evaluation · 1 result

Related configurations, pipelines and services

These configurations, services and pipelines use this model within their own configurations. Their results, where available, are not assigned to the underlying model.

Pangolin · mask=False Configuration · 3 results

Use this model

How it works, versions and access

Versions and evaluated configurations

Pangolin (paper Table 4) · configuration of
Pangolin · family
Pangolin · alias of
Pangolin 1.0.2 + per-gene masking patch · mask False (P0) · configuration of
Pangolin 1.0.2 + per-gene masking patch · mask True (P1) · configuration of

How it works

Dilated convolutional network with 16 residual blocks and skip connections; separate probability and usage outputs for heart, liver, brain and testis. The documented inputs are VCF or CSV variants, reference FASTA and matching gene annotations; custom sequence inference is also available. The output consists of predicted increases/decreases in splice-site strength and their positions.

Sources (2)

tkzeng/Pangolin: README.md; pangolin: Journal full-text XML · Paper: Deep neural network architecture and Generating training and test sets; README.md: Usage

Versions and reproducibility

Pangolin implementation; gene-annotation database and selected weights must be recorded with a run. 5,000 bases upstream and downstream each output position; minimum 10,001-base input for one prediction, with 15,000-base training blocks producing 5,000 central outputs.

Sources (2)

tkzeng/Pangolin: README.md; pangolin: Journal full-text XML · Paper: Deep neural network architecture and Generating training and test sets; README.md: Usage

Strengths, limitations and unresolved questions

Strengths and limitations

Strengths and considerations

Supports custom sequences and annotation-aware variant scoring with configurable search distance.
Sources (2)
tkzeng/Pangolin: README.md; pangolin: Journal full-text XML · Paper: Deep neural network architecture and Generating training and test sets; README.md: Usage

Limitations and conditions

Only substitutions and simple insertions/deletions are supported. The documented tool skips variants outside annotated genes, near chromosome ends, inconsistent with the reference or beyond supported deletion lengths.
Sources (2)
tkzeng/Pangolin: README.md; pangolin: Journal full-text XML · Paper: Deep neural network architecture and Generating training and test sets; README.md: Usage

Profile review details

Inspected pinned official documentation, relevant implementation files and named primary-paper sections. Claims are limited to those artifacts. Remaining field extraction and identity conflicts are explicit; no new performance claims, model runs or human review are implied.

Stable record: discovery-model-pangolin

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	Dilated convolutional splicing predictor Sources (2) tkzeng/Pangolin: README.md; pangolin: Journal full-text XML · Paper: Deep neural network architecture and Generating training and test sets; README.md: Usage
Architecture	Dilated convolutional network with 16 residual blocks and skip connections; separate probability and usage outputs for heart, liver, brain and testis. Sources (2) tkzeng/Pangolin: README.md; pangolin: Journal full-text XML · Paper: Deep neural network architecture and Generating training and test sets; README.md: Usage
Inputs	VCF or CSV variants, reference FASTA and matching gene annotations; custom sequence inference is also available. Sources (2) tkzeng/Pangolin: README.md; pangolin: Journal full-text XML · Paper: Deep neural network architecture and Generating training and test sets; README.md: Usage
Outputs	Predicted increases/decreases in splice-site strength and their positions. Sources (2) tkzeng/Pangolin: README.md; pangolin: Journal full-text XML · Paper: Deep neural network architecture and Generating training and test sets; README.md: Usage
Parameters	The reviewed architecture section specifies the dilated residual network, but does not give a complete parameter total for the released ensemble. · Not reported in inspected sources Sources (2) tkzeng/Pangolin: README.md; pangolin: Journal full-text XML · Paper: Deep neural network architecture and Generating training and test sets; README.md: Usage
Known versions	Pangolin implementation; gene-annotation database and selected weights must be recorded with a run. Sources (2) tkzeng/Pangolin: README.md; pangolin: Journal full-text XML · Paper: Deep neural network architecture and Generating training and test sets; README.md: Usage
Training data	Human, rhesus macaque, mouse and rat sequence/splicing data. Human test chromosomes 1, 3, 5, 7 and 9 are held out, with homologous training genes filtered using Ensembl BioMart. Sources (2) tkzeng/Pangolin: README.md; pangolin: Journal full-text XML · Paper: Deep neural network architecture and Generating training and test sets; README.md: Usage
Training cutoff	Training annotations are GENCODE 34 (human), Ensembl 100 (rhesus), GENCODE M25 (mouse) and Ensembl 101 (rat). These component releases do not establish one latest RNA-seq collection date. Sources (2) tkzeng/Pangolin: README.md; pangolin: Journal full-text XML · Paper: Deep neural network architecture and Generating training and test sets; README.md: Usage
Context limits	5,000 bases upstream and downstream each output position; minimum 10,001-base input for one prediction, with 15,000-base training blocks producing 5,000 central outputs. Sources (2) tkzeng/Pangolin: README.md; pangolin: Journal full-text XML · Paper: Deep neural network architecture and Generating training and test sets; README.md: Usage
Weights licence	Separate checkpoint-distribution terms are not stated in the inspected release documentation and licence material. The source-code licence alone is not recorded as an explicit weight grant. · Not reported in inspected sources Sources (3) tkzeng/Pangolin: README.md; pangolin: Journal full-text XML; tkzeng/Pangolin: LICENSE · Paper: Deep neural network architecture and Generating training and test sets; README.md: Usage; LICENSE: licence text
Access	Official project documentation and implementation: https://github.com/tkzeng/Pangolin Sources (2) tkzeng/Pangolin: README.md; pangolin: Journal full-text XML · Paper: Deep neural network architecture and Generating training and test sets; README.md: Usage
Code licence	GPL-3.0; inspect the pinned licence and any file-specific terms. Sources tkzeng/Pangolin: LICENSE · LICENSE: licence text

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.

40 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-11-02-a7f03c9e55a5
Property and statement	Original source and location	Review and provenance
Diagram caption Conceptual summary of the documented data flow; optional inputs and configured downstream stages must be reported for a reproducible evaluation. Individual claims	pangolin: Journal full-text XML Original source ↗ Paper: Deep neural network architecture and Generating training and test sets; README.md: Usage Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Retrieved page snapshot; no immutable publisher revision supplied Retrieved: 2026-09-16T19:53:03.008861+00:00	source checked automated source review · 2026-09-16 Audit details Inspected pinned official documentation, relevant implementation files and named primary-paper sections. Claims are limited to those artifacts. Remaining field extraction and identity conflicts are explicit; no new performance claims, model runs or human review are implied. Field: `attributes.profile.diagram.caption` Source artifact SHA-256: `c51d34f0bc17ffd34ee5c7caf4bbf627edd9f75f57497c8d6b133f405ec4c307` Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact Inspected artifact
Diagram caption Conceptual summary of the documented data flow; optional inputs and configured downstream stages must be reported for a reproducible evaluation. Individual claims	tkzeng/Pangolin: README.md Original source ↗ Paper: Deep neural network architecture and Generating training and test sets; README.md: Usage Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 5cf94b8db938c658391b4305cd7ce33297d44ff7 Retrieved: 2026-09-16T19:46:20.582143+00:00	source checked automated source review · 2026-09-16 Audit details Inspected pinned official documentation, relevant implementation files and named primary-paper sections. Claims are limited to those artifacts. Remaining field extraction and identity conflicts are explicit; no new performance claims, model runs or human review are implied. Field: `attributes.profile.diagram.caption` Source artifact SHA-256: `9117f9d255d6b6e810d224a600d381192bccccd3f0cd417fed9559d49ca8fffd` Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact Inspected artifact
Diagram steps Variant and reference genome Construct sequence inputs Splice-strength prediction Reference/alternate comparison Individual claims	pangolin: Journal full-text XML Original source ↗ Paper: Deep neural network architecture and Generating training and test sets; README.md: Usage Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Retrieved page snapshot; no immutable publisher revision supplied Retrieved: 2026-09-16T19:53:03.008861+00:00	source checked automated source review · 2026-09-16 Audit details Inspected pinned official documentation, relevant implementation files and named primary-paper sections. Claims are limited to those artifacts. Remaining field extraction and identity conflicts are explicit; no new performance claims, model runs or human review are implied. Field: `attributes.profile.diagram.steps` Source artifact SHA-256: `c51d34f0bc17ffd34ee5c7caf4bbf627edd9f75f57497c8d6b133f405ec4c307` Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact Inspected artifact
Diagram steps Variant and reference genome Construct sequence inputs Splice-strength prediction Reference/alternate comparison Individual claims	tkzeng/Pangolin: README.md Original source ↗ Paper: Deep neural network architecture and Generating training and test sets; README.md: Usage Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 5cf94b8db938c658391b4305cd7ce33297d44ff7 Retrieved: 2026-09-16T19:46:20.582143+00:00	source checked automated source review · 2026-09-16 Audit details Inspected pinned official documentation, relevant implementation files and named primary-paper sections. Claims are limited to those artifacts. Remaining field extraction and identity conflicts are explicit; no new performance claims, model runs or human review are implied. Field: `attributes.profile.diagram.steps` Source artifact SHA-256: `9117f9d255d6b6e810d224a600d381192bccccd3f0cd417fed9559d49ca8fffd` Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact Inspected artifact
Diagram title Pangolin workflow Individual claims	pangolin: Journal full-text XML Original source ↗ Paper: Deep neural network architecture and Generating training and test sets; README.md: Usage Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Retrieved page snapshot; no immutable publisher revision supplied Retrieved: 2026-09-16T19:53:03.008861+00:00	source checked automated source review · 2026-09-16 Audit details Inspected pinned official documentation, relevant implementation files and named primary-paper sections. Claims are limited to those artifacts. Remaining field extraction and identity conflicts are explicit; no new performance claims, model runs or human review are implied. Field: `attributes.profile.diagram.title` Source artifact SHA-256: `c51d34f0bc17ffd34ee5c7caf4bbf627edd9f75f57497c8d6b133f405ec4c307` Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact Inspected artifact
Diagram title Pangolin workflow Individual claims	tkzeng/Pangolin: README.md Original source ↗ Paper: Deep neural network architecture and Generating training and test sets; README.md: Usage Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 5cf94b8db938c658391b4305cd7ce33297d44ff7 Retrieved: 2026-09-16T19:46:20.582143+00:00	source checked automated source review · 2026-09-16 Audit details Inspected pinned official documentation, relevant implementation files and named primary-paper sections. Claims are limited to those artifacts. Remaining field extraction and identity conflicts are explicit; no new performance claims, model runs or human review are implied. Field: `attributes.profile.diagram.title` Source artifact SHA-256: `9117f9d255d6b6e810d224a600d381192bccccd3f0cd417fed9559d49ca8fffd` Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact Inspected artifact
Model type Dilated convolutional splicing predictor Individual claims	pangolin: Journal full-text XML Original source ↗ Paper: Deep neural network architecture and Generating training and test sets; README.md: Usage Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Retrieved page snapshot; no immutable publisher revision supplied Retrieved: 2026-09-16T19:53:03.008861+00:00	source checked automated source review · 2026-09-16 Audit details Inspected pinned official documentation, relevant implementation files and named primary-paper sections. Claims are limited to those artifacts. Remaining field extraction and identity conflicts are explicit; no new performance claims, model runs or human review are implied. Field: `attributes.profile.facts.0.value` Source artifact SHA-256: `c51d34f0bc17ffd34ee5c7caf4bbf627edd9f75f57497c8d6b133f405ec4c307` Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact Inspected artifact
Model type Dilated convolutional splicing predictor Individual claims	tkzeng/Pangolin: README.md Original source ↗ Paper: Deep neural network architecture and Generating training and test sets; README.md: Usage Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 5cf94b8db938c658391b4305cd7ce33297d44ff7 Retrieved: 2026-09-16T19:46:20.582143+00:00	source checked automated source review · 2026-09-16 Audit details Inspected pinned official documentation, relevant implementation files and named primary-paper sections. Claims are limited to those artifacts. Remaining field extraction and identity conflicts are explicit; no new performance claims, model runs or human review are implied. Field: `attributes.profile.facts.0.value` Source artifact SHA-256: `9117f9d255d6b6e810d224a600d381192bccccd3f0cd417fed9559d49ca8fffd` Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact Inspected artifact
Architecture Dilated convolutional network with 16 residual blocks and skip connections; separate probability and usage outputs for heart, liver, brain and testis. Individual claims	pangolin: Journal full-text XML Original source ↗ Paper: Deep neural network architecture and Generating training and test sets; README.md: Usage Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Retrieved page snapshot; no immutable publisher revision supplied Retrieved: 2026-09-16T19:53:03.008861+00:00	source checked automated source review · 2026-09-16 Audit details Inspected pinned official documentation, relevant implementation files and named primary-paper sections. Claims are limited to those artifacts. Remaining field extraction and identity conflicts are explicit; no new performance claims, model runs or human review are implied. Field: `attributes.profile.facts.1.value` Source artifact SHA-256: `c51d34f0bc17ffd34ee5c7caf4bbf627edd9f75f57497c8d6b133f405ec4c307` Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact Inspected artifact
Architecture Dilated convolutional network with 16 residual blocks and skip connections; separate probability and usage outputs for heart, liver, brain and testis. Individual claims	tkzeng/Pangolin: README.md Original source ↗ Paper: Deep neural network architecture and Generating training and test sets; README.md: Usage Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 5cf94b8db938c658391b4305cd7ce33297d44ff7 Retrieved: 2026-09-16T19:46:20.582143+00:00	source checked automated source review · 2026-09-16 Audit details Inspected pinned official documentation, relevant implementation files and named primary-paper sections. Claims are limited to those artifacts. Remaining field extraction and identity conflicts are explicit; no new performance claims, model runs or human review are implied. Field: `attributes.profile.facts.1.value` Source artifact SHA-256: `9117f9d255d6b6e810d224a600d381192bccccd3f0cd417fed9559d49ca8fffd` Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact Inspected artifact

How to read the evidence

Sources and history

Release 2026-11-02-a7f03c9e55a5 · Record review: discovered

4 source records and release history

tkzeng/Pangolin official source · Original source · 5cf94b8db938c658391b4305cd7ce33297d44ff7
tkzeng/Pangolin: README.md · Original source · 5cf94b8db938c658391b4305cd7ce33297d44ff7
pangolin: Journal full-text XML · Original source · Retrieved page snapshot; no immutable publisher revision supplied
tkzeng/Pangolin: LICENSE · Original source · 5cf94b8db938c658391b4305cd7ce33297d44ff7

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: discovery-model-pangolin

areas: dna-genomes
access: official_source_linked
candidate benchmark ids: None recorded
entity level: family
reported name: Pangolin
entity classification: review date: 2026-09-17; rationale: The cited profile describes a named learned biological predictor or representation model/family. Preserve this identity separately from task-specific fitting, individual checkpoints, pipelines and hosted access.; source ids: evidence-official-eaf3efab8850672f44e4; evidence-official-de1ee43bdd6f04de9850; source locator: Paper: Deep neural network architecture and Generating training and test sets; README.md: Usage; ambiguities: None recorded
missing metadata: version: reason: unextracted

Related records

configuration of: Pangolin (paper Table 4)
family: Pangolin
alias of: Pangolin
configuration of: Pangolin (Evo 2 paper variant effect evaluations)
configuration of: Pangolin (evaluation mode not printed (Table 4 has no Eval. column), GUANinE v1.1)
configuration of: Pangolin 1.0.2 + per-gene masking patch · mask False (P0)
configuration of: Pangolin 1.0.2 + per-gene masking patch · mask True (P1)
uses model: Pangolin · mask=False

Suggest a correction