Model

SpliceAI

SpliceAI annotates sequence variants with predicted splice acceptor and donor changes.

Sources (2)

illumina/SpliceAI: README.md; spliceai: Primary paper PDF · Jaganathan et al., Cell 2019, STAR Methods: SpliceAI architecture and Model training and testing (pp. e2–e3); README.md: usage and License

6 evaluations · 14 results · 1 evaluated configuration using this model

How it worksSpliceAI workflow

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

Sources (2)

Overview

Model type

Dilated convolutional splicing predictor

Inputs

VCF variants, reference FASTA and matching gene annotation, or custom one-hot-encoded sequence.

Outputs

Acceptor/donor gain/loss scores and positions in VCF INFO annotations.

Access

Official project documentation and implementation: https://github.com/illumina/SpliceAI

Sources (2)

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

Evaluations and results

6 evaluations · 14 results. 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
Configuration: SpliceAI (paper Table 3)	Protocol: Human splice-site classification: RNA-derived (AlphaGenome paper) Dataset subset: Human splice-site classification: RNA-derived: evaluated data subset	0.755 auPRC dimensionless · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source SpliceAI (paper Table 3): Human splice-site classification: RNA-derived Compare probabilities with the selected binary splice-site labels at genomic positions. Aggregation: Compute auPRC separately for four strand/site classes and average the four values. AlphaGenome Nature 2026 supplementary comparison tables · 'Suppl Table 3 Track performance'!J2
Configuration: SpliceAI (paper Table 3)	Protocol: Human splice-site usage (AlphaGenome paper) Dataset subset: Human splice-site usage: evaluated data subset	0.769 pearsonr correlation · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source SpliceAI (paper Table 3): Human splice-site usage Correlate predicted and measured usage over held-out splice-site positions for each tissue track. Aggregation: Per-tissue Pearson correlation; the table provides an aggregate scalar but this task paragraph does not explicitly define its cross-tissue weighting. AlphaGenome Nature 2026 supplementary comparison tables · 'Suppl Table 3 Track performance'!J7
Configuration: SpliceAI (paper Table 3)	Protocol: Human splice-site classification: annotation-derived (AlphaGenome paper) Dataset subset: Human splice-site classification: annotation-derived: evaluated data subset	0.815 auPRC dimensionless · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source SpliceAI (paper Table 3): Human splice-site classification: annotation-derived Compare probabilities with the selected binary splice-site labels at genomic positions. Aggregation: Compute auPRC separately for four strand/site classes and average the four values. AlphaGenome Nature 2026 supplementary comparison tables · 'Suppl Table 3 Track performance'!J4
Configuration: SpliceAI 1.3.1 · mask 0 (S0)	Protocol: MFASS: matched GENCODE 44 canonical annotation Dataset subset: MFASS v2 test: matched canonical annotation coverage	0.804 AUROC dimensionless · higher Uncertainty: Not reported Coverage: 8297/8324	Rewire evaluation · Source checked Methods, coverage and source SpliceAI 1.3.1 · mask 0 (S0) 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.S0.metrics.auroc
Configuration: SpliceAI 1.3.1 · mask 0 (S0)	Protocol: MFASS: matched GENCODE 44 canonical annotation Dataset subset: MFASS v2 test: matched canonical annotation coverage	0.295 Average precision dimensionless · higher Uncertainty: Not reported Coverage: 8297/8324	Rewire evaluation · Source checked Methods, coverage and source SpliceAI 1.3.1 · mask 0 (S0) 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.S0.metrics.average_precision_sklearn
Configuration: SpliceAI 1.3.1 · mask 0 (S0)	Protocol: MFASS: matched GENCODE 44 canonical annotation Dataset subset: MFASS v2 test: matched canonical annotation coverage	0.63 Precision at 100 dimensionless · higher Uncertainty: Not reported Coverage: 8297/8324	Rewire evaluation · Source checked Methods, coverage and source SpliceAI 1.3.1 · mask 0 (S0) 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.S0.metrics.precision_at_capacity
Configuration: SpliceAI 1.3.1 · mask 0 (S0)	Protocol: MFASS: matched GENCODE 44 canonical annotation Dataset subset: MFASS v2 test: matched canonical annotation coverage	0.201 Recall at 100 dimensionless · higher Uncertainty: Not reported Coverage: 8297/8324	Rewire evaluation · Source checked Methods, coverage and source SpliceAI 1.3.1 · mask 0 (S0) 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.S0.metrics.recall_at_capacity
Configuration: SpliceAI 1.3.1 · mask 1 (S1)	Protocol: MFASS: matched GENCODE 44 canonical annotation Dataset subset: MFASS v2 test: matched canonical annotation coverage	0.815 AUROC dimensionless · higher Uncertainty: Not reported Coverage: 8297/8324	Rewire evaluation · Source checked Methods, coverage and source SpliceAI 1.3.1 · mask 1 (S1) 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.S1.metrics.auroc
Configuration: SpliceAI 1.3.1 · mask 1 (S1)	Protocol: MFASS: matched GENCODE 44 canonical annotation Dataset subset: MFASS v2 test: matched canonical annotation coverage	0.313 Average precision dimensionless · higher Uncertainty: Not reported Coverage: 8297/8324	Rewire evaluation · Source checked Methods, coverage and source SpliceAI 1.3.1 · mask 1 (S1) 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.S1.metrics.average_precision_sklearn
Configuration: SpliceAI 1.3.1 · mask 1 (S1)	Protocol: MFASS: matched GENCODE 44 canonical annotation Dataset subset: MFASS v2 test: matched canonical annotation coverage	0.65 Precision at 100 dimensionless · higher Uncertainty: Not reported Coverage: 8297/8324	Rewire evaluation · Source checked Methods, coverage and source SpliceAI 1.3.1 · mask 1 (S1) 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.S1.metrics.precision_at_capacity
Configuration: SpliceAI 1.3.1 · mask 1 (S1)	Protocol: MFASS: matched GENCODE 44 canonical annotation Dataset subset: MFASS v2 test: matched canonical annotation coverage	0.207 Recall at 100 dimensionless · higher Uncertainty: Not reported Coverage: 8297/8324	Rewire evaluation · Source checked Methods, coverage and source SpliceAI 1.3.1 · mask 1 (S1) 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.S1.metrics.recall_at_capacity
Configuration: SpliceAI 1.3.1	Protocol: MFASS v2 Dataset: MFASS v2 eligible assay cohort	0.806 auroc fraction · higher Uncertainty: Not reported Coverage: 8194/8324	Rewire evaluation · Independently reproduced Methods, coverage and source SpliceAI 1.3.1 on MFASS v2 Unchanged specialist run in genomic context with bundled annotation; zero-shot on MFASS assay labels. Point metrics use the scored subset. Aggregation: Not reported MFASS v2 pinned rewire artifacts · benchmarks/mfass/results/spliceai-1.3.1.json :: auroc
Configuration: SpliceAI 1.3.1	Protocol: MFASS v2 Dataset: MFASS v2 eligible assay cohort	0.299 average_precision fraction · higher Uncertainty: Not reported Coverage: 8194/8324	Rewire evaluation · Independently reproduced Methods, coverage and source SpliceAI 1.3.1 on MFASS v2 Unchanged specialist run in genomic context with bundled annotation; zero-shot on MFASS assay labels. Point metrics use the scored subset. Aggregation: Not reported MFASS v2 pinned rewire artifacts · benchmarks/mfass/results/spliceai-1.3.1.json :: average_precision
Configuration: SpliceAI 1.3.1	Protocol: MFASS v2 Dataset: MFASS v2 eligible assay cohort	0.64 precision_at_100 fraction · higher Uncertainty: Not reported Coverage: 8194/8324	Rewire evaluation · Independently reproduced Methods, coverage and source SpliceAI 1.3.1 on MFASS v2 Unchanged specialist run in genomic context with bundled annotation; zero-shot on MFASS assay labels. Point metrics use the scored subset. Aggregation: Not reported MFASS v2 pinned rewire artifacts · benchmarks/mfass/results/spliceai-1.3.1.json :: precision_at_100

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

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.

SpliceAI 1.3.1 Configuration · 3 results

Use this model

How it works, versions and access

Versions and evaluated configurations

SpliceAI (paper Table 3) · family
SpliceAI · variant of
SpliceAI · alias of
SpliceAI 1.3.1 · mask 0 (S0) · variant of
SpliceAI 1.3.1 · mask 1 (S1) · variant of

How it works

SpliceAI reads one-hot-encoded DNA through dilated convolutional residual blocks. Skip connections combine features at different depths, and a softmax layer assigns acceptor, donor or neither probabilities to the central positions. The 10kb version requires 5kb of sequence on each side of a scored position; variant scoring compares the reference and alternate predictions.

Sources (2)

Versions and reproducibility

The paper studies 80nt, 400nt, 2kb and 10kb receptive spans. Variant scoring averages five independently trained models; these are not five different assay results. SpliceAI-10k uses 5,000 flanking bases on each side. An input of length l + 10,000 produces predictions for l central positions; receptive span is distinct from maximum input length.

Sources (2)

Strengths, limitations and unresolved questions

Strengths and limitations

Strengths and considerations

Provides direct sequence inference and an annotation workflow with explicit genome and distance settings.
Sources (2)
illumina/SpliceAI: README.md; spliceai: Primary paper PDF · Jaganathan et al., Cell 2019, STAR Methods: SpliceAI architecture and Model training and testing (pp. e2–e3); README.md: usage and License

Limitations and conditions

The command-line pipeline skips unsupported variants and variants outside its gene annotations. Code, model weights and downloadable precomputed scores have distinct licensing provisions.
Sources (2)
illumina/SpliceAI: README.md; spliceai: Primary paper PDF · Jaganathan et al., Cell 2019, STAR Methods: SpliceAI architecture and Model training and testing (pp. e2–e3); README.md: usage and License

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-spliceai

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) illumina/SpliceAI: README.md; spliceai: Primary paper PDF · Jaganathan et al., Cell 2019, STAR Methods: SpliceAI architecture and Model training and testing (pp. e2–e3); README.md: usage and License
Architecture	Residual one-dimensional convolutional network with dilated kernels and skip connections; a softmax head predicts acceptor, donor and neither at each central position. Sources (2) illumina/SpliceAI: README.md; spliceai: Primary paper PDF · Jaganathan et al., Cell 2019, STAR Methods: SpliceAI architecture and Model training and testing (pp. e2–e3); README.md: usage and License
Inputs	VCF variants, reference FASTA and matching gene annotation, or custom one-hot-encoded sequence. Sources (2) illumina/SpliceAI: README.md; spliceai: Primary paper PDF · Jaganathan et al., Cell 2019, STAR Methods: SpliceAI architecture and Model training and testing (pp. e2–e3); README.md: usage and License
Outputs	Acceptor/donor gain/loss scores and positions in VCF INFO annotations. Sources (2) illumina/SpliceAI: README.md; spliceai: Primary paper PDF · Jaganathan et al., Cell 2019, STAR Methods: SpliceAI architecture and Model training and testing (pp. e2–e3); README.md: usage and License
Parameters	The original STAR Methods specifies residual blocks, dilation and receptive spans, but does not state a complete parameter count for each released five-model scoring ensemble. · Not reported in inspected sources Sources (2) illumina/SpliceAI: README.md; spliceai: Primary paper PDF · Jaganathan et al., Cell 2019, STAR Methods: SpliceAI architecture and Model training and testing (pp. e2–e3); README.md: usage and License
Known versions	The paper studies 80nt, 400nt, 2kb and 10kb receptive spans. Variant scoring averages five independently trained models; these are not five different assay results. Sources (2) illumina/SpliceAI: README.md; spliceai: Primary paper PDF · Jaganathan et al., Cell 2019, STAR Methods: SpliceAI architecture and Model training and testing (pp. e2–e3); README.md: usage and License
Training data	Human GRCh37 sequence and GENCODE V24lift37 principal protein-coding transcripts, split by chromosome with non-paralogous held-out test genes. The paper distinguishes GENCODE-only training from GTEx-junction-augmented models used for variant analyses. Sources (2) illumina/SpliceAI: README.md; spliceai: Primary paper PDF · Jaganathan et al., Cell 2019, STAR Methods: SpliceAI architecture and Model training and testing (pp. e2–e3); README.md: usage and License
Training cutoff	GENCODE V24lift37 on GRCh37 defines the documented transcript annotations. GTEx-augmented training is separately described; the paper does not give one common latest-data date for both variants. Sources (2) illumina/SpliceAI: README.md; spliceai: Primary paper PDF · Jaganathan et al., Cell 2019, STAR Methods: SpliceAI architecture and Model training and testing (pp. e2–e3); README.md: usage and License
Context limits	SpliceAI-10k uses 5,000 flanking bases on each side. An input of length l + 10,000 produces predictions for l central positions; receptive span is distinct from maximum input length. Sources (2) illumina/SpliceAI: README.md; spliceai: Primary paper PDF · Jaganathan et al., Cell 2019, STAR Methods: SpliceAI architecture and Model training and testing (pp. e2–e3); README.md: usage and License
Weights licence	CC-BY-NC-4.0 for trained models; commercial use requires a separate licence. Code is PolyForm Strict 1.0.0. Sources (2) illumina/SpliceAI: README.md; spliceai: Primary paper PDF · Jaganathan et al., Cell 2019, STAR Methods: SpliceAI architecture and Model training and testing (pp. e2–e3); README.md: usage and License
Access	Official project documentation and implementation: https://github.com/illumina/SpliceAI Sources (2) illumina/SpliceAI: README.md; spliceai: Primary paper PDF · Jaganathan et al., Cell 2019, STAR Methods: SpliceAI architecture and Model training and testing (pp. e2–e3); README.md: usage and License
Code licence	PolyForm Strict 1.0.0 for code; trained weights have separate terms. Sources illumina/SpliceAI: 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.

39 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 documented data flow; optional inputs and configured downstream stages must be reported for a reproducible evaluation. Individual claims	illumina/SpliceAI: README.md Original source ↗ Jaganathan et al., Cell 2019, STAR Methods: SpliceAI architecture and Model training and testing (pp. e2–e3); README.md: usage and License Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 03f42437aaf56dc5dfd822c4ccee5aec1a705079 Retrieved: 2026-09-16T19:46:19.364217+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: `8e5203afe343100832391e6155c7112f15cfe60bf0c21681d64e3420f854ef4d` 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	spliceai: Primary paper PDF Original source ↗ Jaganathan et al., Cell 2019, STAR Methods: SpliceAI architecture and Model training and testing (pp. e2–e3); README.md: usage and License Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Cell 2019 published article PDF, university-hosted copy Retrieved: 2026-09-16T20:04:38.697838+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: `e0d62bfd97c26907e184a6a262eb277e3ad0737322373df282c9832b56697dda` Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact Inspected artifact
Diagram steps Variant plus sequence context Reference and alternate predictions Splice-site differences Gain/loss annotations Individual claims	illumina/SpliceAI: README.md Original source ↗ Jaganathan et al., Cell 2019, STAR Methods: SpliceAI architecture and Model training and testing (pp. e2–e3); README.md: usage and License Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 03f42437aaf56dc5dfd822c4ccee5aec1a705079 Retrieved: 2026-09-16T19:46:19.364217+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: `8e5203afe343100832391e6155c7112f15cfe60bf0c21681d64e3420f854ef4d` Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact Inspected artifact
Diagram steps Variant plus sequence context Reference and alternate predictions Splice-site differences Gain/loss annotations Individual claims	spliceai: Primary paper PDF Original source ↗ Jaganathan et al., Cell 2019, STAR Methods: SpliceAI architecture and Model training and testing (pp. e2–e3); README.md: usage and License Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Cell 2019 published article PDF, university-hosted copy Retrieved: 2026-09-16T20:04:38.697838+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: `e0d62bfd97c26907e184a6a262eb277e3ad0737322373df282c9832b56697dda` Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact Inspected artifact
Diagram title SpliceAI workflow Individual claims	illumina/SpliceAI: README.md Original source ↗ Jaganathan et al., Cell 2019, STAR Methods: SpliceAI architecture and Model training and testing (pp. e2–e3); README.md: usage and License Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 03f42437aaf56dc5dfd822c4ccee5aec1a705079 Retrieved: 2026-09-16T19:46:19.364217+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: `8e5203afe343100832391e6155c7112f15cfe60bf0c21681d64e3420f854ef4d` Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact Inspected artifact
Diagram title SpliceAI workflow Individual claims	spliceai: Primary paper PDF Original source ↗ Jaganathan et al., Cell 2019, STAR Methods: SpliceAI architecture and Model training and testing (pp. e2–e3); README.md: usage and License Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Cell 2019 published article PDF, university-hosted copy Retrieved: 2026-09-16T20:04:38.697838+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: `e0d62bfd97c26907e184a6a262eb277e3ad0737322373df282c9832b56697dda` Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact Inspected artifact
Model type Dilated convolutional splicing predictor Individual claims	illumina/SpliceAI: README.md Original source ↗ Jaganathan et al., Cell 2019, STAR Methods: SpliceAI architecture and Model training and testing (pp. e2–e3); README.md: usage and License Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 03f42437aaf56dc5dfd822c4ccee5aec1a705079 Retrieved: 2026-09-16T19:46:19.364217+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: `8e5203afe343100832391e6155c7112f15cfe60bf0c21681d64e3420f854ef4d` Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact Inspected artifact
Model type Dilated convolutional splicing predictor Individual claims	spliceai: Primary paper PDF Original source ↗ Jaganathan et al., Cell 2019, STAR Methods: SpliceAI architecture and Model training and testing (pp. e2–e3); README.md: usage and License Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Cell 2019 published article PDF, university-hosted copy Retrieved: 2026-09-16T20:04:38.697838+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: `e0d62bfd97c26907e184a6a262eb277e3ad0737322373df282c9832b56697dda` Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact Inspected artifact
Architecture Residual one-dimensional convolutional network with dilated kernels and skip connections; a softmax head predicts acceptor, donor and neither at each central position. Individual claims	illumina/SpliceAI: README.md Original source ↗ Jaganathan et al., Cell 2019, STAR Methods: SpliceAI architecture and Model training and testing (pp. e2–e3); README.md: usage and License Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 03f42437aaf56dc5dfd822c4ccee5aec1a705079 Retrieved: 2026-09-16T19:46:19.364217+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: `8e5203afe343100832391e6155c7112f15cfe60bf0c21681d64e3420f854ef4d` Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact Inspected artifact
Architecture Residual one-dimensional convolutional network with dilated kernels and skip connections; a softmax head predicts acceptor, donor and neither at each central position. Individual claims	spliceai: Primary paper PDF Original source ↗ Jaganathan et al., Cell 2019, STAR Methods: SpliceAI architecture and Model training and testing (pp. e2–e3); README.md: usage and License Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Cell 2019 published article PDF, university-hosted copy Retrieved: 2026-09-16T20:04:38.697838+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: `e0d62bfd97c26907e184a6a262eb277e3ad0737322373df282c9832b56697dda` Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact 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: discovered

4 source records and release history

illumina/SpliceAI official source · Original source · 03f42437aaf56dc5dfd822c4ccee5aec1a705079
illumina/SpliceAI: README.md · Original source · 03f42437aaf56dc5dfd822c4ccee5aec1a705079
spliceai: Primary paper PDF · Original source · Cell 2019 published article PDF, university-hosted copy
illumina/SpliceAI: LICENSE · Original source · 03f42437aaf56dc5dfd822c4ccee5aec1a705079

Download this release

Technical metadata and extraction receipts

Stable ID: discovery-model-spliceai

areas: genomics
access: official_source_linked
benchmark applicability: candidate; not evidence of a reported evaluation
candidate benchmark ids: None recorded
entity level: family
reported name: SpliceAI
version: Not reported
historical missing metadata: checkpoint: unextracted; code licence: unextracted; parameters: unextracted; training cutoff: unextracted; training data: unextracted; version: unextracted; weights licence: unextracted
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.
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-9b820532ba8e3965f64e; evidence-official-ded281404bd1a0f3fdb7; source locator: Jaganathan et al., Cell 2019, STAR Methods: SpliceAI architecture and Model training and testing (pp. e2–e3); README.md: usage and License; ambiguities: None recorded

Related records

family: SpliceAI (paper Table 3)
variant of: SpliceAI
alias of: SpliceAI
model: Specialist splicing predictor
variant of: SpliceAI 1.3.1 · mask 0 (S0)
variant of: SpliceAI 1.3.1 · mask 1 (S1)
uses model: SpliceAI 1.3.1

Suggest a correction