Configuration

SpliceAI (Riepe et al. 2021)

Configuration of SpliceAI: version v1.3.1; Classification cutoff per data set.

Overview

An explanatory profile has not yet been reviewed for this record.

Consult the linked sources for architecture or protocol details. Missing evidence is not evidence of a missing capability.

Evaluations and results

3 evaluations · 33 results. Different protocols are not a single leaderboard.

Sorted by Accuracy (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	Accuracy	Count (variants without a score)	False negatives	False positives	MCC	Negative predictive value	Precision	Recall	Specificity	True negatives	True positives
SpliceAI (Riepe et al. 2021)Evaluation	ABCA4 deep-intronic variants: classification against mini- or midigene splicing results (Riepe et al. Table 4), ABCA4 deep-intronic variants (Riepe et al. benchmark set)	94% (best in column)	0 (best in column)	2 (best in column)	3	0.84 (best in column)	97% (best in column)	86%	90% (best in column)	95% (best in column)	57 (best in column)	19
SpliceAI (Riepe et al. 2021)Evaluation	ABCA4 noncanonical splice-site variants: classification against mini- or midigene splicing results (Riepe et al. Table 3), ABCA4 noncanonical splice-site variants (Riepe et al. benchmark set)	79%	0 (best in column)	14	1 (best in column)	0.42	30%	98% (best in column)	78%	86%	6	50 (best in column)
SpliceAI (Riepe et al. 2021)Evaluation	MYBPC3 noncanonical splice-site variants: classification against mini- or midigene splicing results (Riepe et al. Table 5), MYBPC3 noncanonical splice-site variants (Riepe et al. benchmark set)	67%	0 (best in column)	12	8	0.35	61%	73%	65%	70%	19	22

All 33 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: SpliceAI (Riepe et al. 2021)	Protocol: ABCA4 deep-intronic variants: classification against mini- or midigene splicing results (Riepe et al. Table 4) Dataset: ABCA4 deep-intronic variants (Riepe et al. benchmark set)	94% Accuracy percent · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source SpliceAI on ABCA4 deep-intronic variants splicing-follow-up-20261009-protocol-riepe2021-abca4-di Aggregation: Not reported Benchmarking deep learning splice prediction tools using functional splice assays · Table 4 row 'SpliceAI', column 'Accuracy (%)'
Configuration: SpliceAI (Riepe et al. 2021)	Protocol: ABCA4 deep-intronic variants: classification against mini- or midigene splicing results (Riepe et al. Table 4) Dataset: ABCA4 deep-intronic variants (Riepe et al. benchmark set)	2 False negatives count · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source SpliceAI on ABCA4 deep-intronic variants splicing-follow-up-20261009-protocol-riepe2021-abca4-di Aggregation: Not reported Benchmarking deep learning splice prediction tools using functional splice assays · Table 4 row 'SpliceAI', column 'FN'
Configuration: SpliceAI (Riepe et al. 2021)	Protocol: ABCA4 deep-intronic variants: classification against mini- or midigene splicing results (Riepe et al. Table 4) Dataset: ABCA4 deep-intronic variants (Riepe et al. benchmark set)	3 False positives count · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source SpliceAI on ABCA4 deep-intronic variants splicing-follow-up-20261009-protocol-riepe2021-abca4-di Aggregation: Not reported Benchmarking deep learning splice prediction tools using functional splice assays · Table 4 row 'SpliceAI', column 'FP'
Configuration: SpliceAI (Riepe et al. 2021)	Protocol: ABCA4 deep-intronic variants: classification against mini- or midigene splicing results (Riepe et al. Table 4) Dataset: ABCA4 deep-intronic variants (Riepe et al. benchmark set)	0.84 MCC unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source SpliceAI on ABCA4 deep-intronic variants splicing-follow-up-20261009-protocol-riepe2021-abca4-di Aggregation: Not reported Benchmarking deep learning splice prediction tools using functional splice assays · Table 4 row 'SpliceAI', column 'MCC'
Configuration: SpliceAI (Riepe et al. 2021)	Protocol: ABCA4 deep-intronic variants: classification against mini- or midigene splicing results (Riepe et al. Table 4) Dataset: ABCA4 deep-intronic variants (Riepe et al. benchmark set)	0 Count (variants without a score) count · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source SpliceAI on ABCA4 deep-intronic variants splicing-follow-up-20261009-protocol-riepe2021-abca4-di Aggregation: Not reported Benchmarking deep learning splice prediction tools using functional splice assays · Table 4 row 'SpliceAI', column 'Missing values'
Configuration: SpliceAI (Riepe et al. 2021)	Protocol: ABCA4 deep-intronic variants: classification against mini- or midigene splicing results (Riepe et al. Table 4) Dataset: ABCA4 deep-intronic variants (Riepe et al. benchmark set)	97% Negative predictive value percent · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source SpliceAI on ABCA4 deep-intronic variants splicing-follow-up-20261009-protocol-riepe2021-abca4-di Aggregation: Not reported Benchmarking deep learning splice prediction tools using functional splice assays · Table 4 row 'SpliceAI', column 'NPV (%)'
Configuration: SpliceAI (Riepe et al. 2021)	Protocol: ABCA4 deep-intronic variants: classification against mini- or midigene splicing results (Riepe et al. Table 4) Dataset: ABCA4 deep-intronic variants (Riepe et al. benchmark set)	86% Precision percent · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source SpliceAI on ABCA4 deep-intronic variants splicing-follow-up-20261009-protocol-riepe2021-abca4-di Aggregation: Not reported Benchmarking deep learning splice prediction tools using functional splice assays · Table 4 row 'SpliceAI', column 'PPV (%)'
Configuration: SpliceAI (Riepe et al. 2021)	Protocol: ABCA4 deep-intronic variants: classification against mini- or midigene splicing results (Riepe et al. Table 4) Dataset: ABCA4 deep-intronic variants (Riepe et al. benchmark set)	90% Recall percent · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source SpliceAI on ABCA4 deep-intronic variants splicing-follow-up-20261009-protocol-riepe2021-abca4-di Aggregation: Not reported Benchmarking deep learning splice prediction tools using functional splice assays · Table 4 row 'SpliceAI', column 'Sensitivity (%)'
Configuration: SpliceAI (Riepe et al. 2021)	Protocol: ABCA4 deep-intronic variants: classification against mini- or midigene splicing results (Riepe et al. Table 4) Dataset: ABCA4 deep-intronic variants (Riepe et al. benchmark set)	95% Specificity percent · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source SpliceAI on ABCA4 deep-intronic variants splicing-follow-up-20261009-protocol-riepe2021-abca4-di Aggregation: Not reported Benchmarking deep learning splice prediction tools using functional splice assays · Table 4 row 'SpliceAI', column 'Specificity (%)'
Configuration: SpliceAI (Riepe et al. 2021)	Protocol: ABCA4 deep-intronic variants: classification against mini- or midigene splicing results (Riepe et al. Table 4) Dataset: ABCA4 deep-intronic variants (Riepe et al. benchmark set)	57 True negatives count · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source SpliceAI on ABCA4 deep-intronic variants splicing-follow-up-20261009-protocol-riepe2021-abca4-di Aggregation: Not reported Benchmarking deep learning splice prediction tools using functional splice assays · Table 4 row 'SpliceAI', column 'TN'
Configuration: SpliceAI (Riepe et al. 2021)	Protocol: ABCA4 deep-intronic variants: classification against mini- or midigene splicing results (Riepe et al. Table 4) Dataset: ABCA4 deep-intronic variants (Riepe et al. benchmark set)	19 True positives count · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source SpliceAI on ABCA4 deep-intronic variants splicing-follow-up-20261009-protocol-riepe2021-abca4-di Aggregation: Not reported Benchmarking deep learning splice prediction tools using functional splice assays · Table 4 row 'SpliceAI', column 'TP'
Configuration: SpliceAI (Riepe et al. 2021)	Protocol: ABCA4 noncanonical splice-site variants: classification against mini- or midigene splicing results (Riepe et al. Table 3) Dataset: ABCA4 noncanonical splice-site variants (Riepe et al. benchmark set)	79% Accuracy percent · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source SpliceAI on ABCA4 noncanonical splice-site variants splicing-follow-up-20261009-protocol-riepe2021-abca4-ncss Aggregation: Not reported Benchmarking deep learning splice prediction tools using functional splice assays · Table 3 row 'SpliceAI', column 'Accuracy (%)'
Configuration: SpliceAI (Riepe et al. 2021)	Protocol: ABCA4 noncanonical splice-site variants: classification against mini- or midigene splicing results (Riepe et al. Table 3) Dataset: ABCA4 noncanonical splice-site variants (Riepe et al. benchmark set)	14 False negatives count · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source SpliceAI on ABCA4 noncanonical splice-site variants splicing-follow-up-20261009-protocol-riepe2021-abca4-ncss Aggregation: Not reported Benchmarking deep learning splice prediction tools using functional splice assays · Table 3 row 'SpliceAI', column 'FN'
Configuration: SpliceAI (Riepe et al. 2021)	Protocol: ABCA4 noncanonical splice-site variants: classification against mini- or midigene splicing results (Riepe et al. Table 3) Dataset: ABCA4 noncanonical splice-site variants (Riepe et al. benchmark set)	1 False positives count · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source SpliceAI on ABCA4 noncanonical splice-site variants splicing-follow-up-20261009-protocol-riepe2021-abca4-ncss Aggregation: Not reported Benchmarking deep learning splice prediction tools using functional splice assays · Table 3 row 'SpliceAI', column 'FP'
Configuration: SpliceAI (Riepe et al. 2021)	Protocol: ABCA4 noncanonical splice-site variants: classification against mini- or midigene splicing results (Riepe et al. Table 3) Dataset: ABCA4 noncanonical splice-site variants (Riepe et al. benchmark set)	0.42 MCC unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source SpliceAI on ABCA4 noncanonical splice-site variants splicing-follow-up-20261009-protocol-riepe2021-abca4-ncss Aggregation: Not reported Benchmarking deep learning splice prediction tools using functional splice assays · Table 3 row 'SpliceAI', column 'MCC'
Configuration: SpliceAI (Riepe et al. 2021)	Protocol: ABCA4 noncanonical splice-site variants: classification against mini- or midigene splicing results (Riepe et al. Table 3) Dataset: ABCA4 noncanonical splice-site variants (Riepe et al. benchmark set)	0 Count (variants without a score) count · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source SpliceAI on ABCA4 noncanonical splice-site variants splicing-follow-up-20261009-protocol-riepe2021-abca4-ncss Aggregation: Not reported Benchmarking deep learning splice prediction tools using functional splice assays · Table 3 row 'SpliceAI', column 'Missing values'
Configuration: SpliceAI (Riepe et al. 2021)	Protocol: ABCA4 noncanonical splice-site variants: classification against mini- or midigene splicing results (Riepe et al. Table 3) Dataset: ABCA4 noncanonical splice-site variants (Riepe et al. benchmark set)	30% Negative predictive value percent · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source SpliceAI on ABCA4 noncanonical splice-site variants splicing-follow-up-20261009-protocol-riepe2021-abca4-ncss Aggregation: Not reported Benchmarking deep learning splice prediction tools using functional splice assays · Table 3 row 'SpliceAI', column 'NPV (%)'
Configuration: SpliceAI (Riepe et al. 2021)	Protocol: ABCA4 noncanonical splice-site variants: classification against mini- or midigene splicing results (Riepe et al. Table 3) Dataset: ABCA4 noncanonical splice-site variants (Riepe et al. benchmark set)	98% Precision percent · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source SpliceAI on ABCA4 noncanonical splice-site variants splicing-follow-up-20261009-protocol-riepe2021-abca4-ncss Aggregation: Not reported Benchmarking deep learning splice prediction tools using functional splice assays · Table 3 row 'SpliceAI', column 'PPV (%)'
Configuration: SpliceAI (Riepe et al. 2021)	Protocol: ABCA4 noncanonical splice-site variants: classification against mini- or midigene splicing results (Riepe et al. Table 3) Dataset: ABCA4 noncanonical splice-site variants (Riepe et al. benchmark set)	78% Recall percent · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source SpliceAI on ABCA4 noncanonical splice-site variants splicing-follow-up-20261009-protocol-riepe2021-abca4-ncss Aggregation: Not reported Benchmarking deep learning splice prediction tools using functional splice assays · Table 3 row 'SpliceAI', column 'Sensitivity (%)'
Configuration: SpliceAI (Riepe et al. 2021)	Protocol: ABCA4 noncanonical splice-site variants: classification against mini- or midigene splicing results (Riepe et al. Table 3) Dataset: ABCA4 noncanonical splice-site variants (Riepe et al. benchmark set)	86% Specificity percent · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source SpliceAI on ABCA4 noncanonical splice-site variants splicing-follow-up-20261009-protocol-riepe2021-abca4-ncss Aggregation: Not reported Benchmarking deep learning splice prediction tools using functional splice assays · Table 3 row 'SpliceAI', column 'Specificity (%)'
Configuration: SpliceAI (Riepe et al. 2021)	Protocol: ABCA4 noncanonical splice-site variants: classification against mini- or midigene splicing results (Riepe et al. Table 3) Dataset: ABCA4 noncanonical splice-site variants (Riepe et al. benchmark set)	6 True negatives count · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source SpliceAI on ABCA4 noncanonical splice-site variants splicing-follow-up-20261009-protocol-riepe2021-abca4-ncss Aggregation: Not reported Benchmarking deep learning splice prediction tools using functional splice assays · Table 3 row 'SpliceAI', column 'TN'
Configuration: SpliceAI (Riepe et al. 2021)	Protocol: ABCA4 noncanonical splice-site variants: classification against mini- or midigene splicing results (Riepe et al. Table 3) Dataset: ABCA4 noncanonical splice-site variants (Riepe et al. benchmark set)	50 True positives count · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source SpliceAI on ABCA4 noncanonical splice-site variants splicing-follow-up-20261009-protocol-riepe2021-abca4-ncss Aggregation: Not reported Benchmarking deep learning splice prediction tools using functional splice assays · Table 3 row 'SpliceAI', column 'TP'
Configuration: SpliceAI (Riepe et al. 2021)	Protocol: MYBPC3 noncanonical splice-site variants: classification against mini- or midigene splicing results (Riepe et al. Table 5) Dataset: MYBPC3 noncanonical splice-site variants (Riepe et al. benchmark set)	67% Accuracy percent · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source SpliceAI on MYBPC3 noncanonical splice-site variants splicing-follow-up-20261009-protocol-riepe2021-mybpc3-ncss Aggregation: Not reported Benchmarking deep learning splice prediction tools using functional splice assays · Table 5 row 'SpliceAI', column 'Accuracy (%)'
Configuration: SpliceAI (Riepe et al. 2021)	Protocol: MYBPC3 noncanonical splice-site variants: classification against mini- or midigene splicing results (Riepe et al. Table 5) Dataset: MYBPC3 noncanonical splice-site variants (Riepe et al. benchmark set)	12 False negatives count · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source SpliceAI on MYBPC3 noncanonical splice-site variants splicing-follow-up-20261009-protocol-riepe2021-mybpc3-ncss Aggregation: Not reported Benchmarking deep learning splice prediction tools using functional splice assays · Table 5 row 'SpliceAI', column 'FN'
Configuration: SpliceAI (Riepe et al. 2021)	Protocol: MYBPC3 noncanonical splice-site variants: classification against mini- or midigene splicing results (Riepe et al. Table 5) Dataset: MYBPC3 noncanonical splice-site variants (Riepe et al. benchmark set)	8 False positives count · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source SpliceAI on MYBPC3 noncanonical splice-site variants splicing-follow-up-20261009-protocol-riepe2021-mybpc3-ncss Aggregation: Not reported Benchmarking deep learning splice prediction tools using functional splice assays · Table 5 row 'SpliceAI', column 'FP'

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

Use this configuration

How it works, versions and access

Additional methodological details, versions and access terms have not yet been extracted into a structured profile for this configuration. Consult the linked sources and evaluation records below.

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.

0 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

No evidence rows match these filters. Choose another scope or clear the search.

How to read the evidence

Sources and history

Release 2026-11-02-a7f03c9e55a5 · Record review: source checked

1 source record and release history

Benchmarking deep learning splice prediction tools using functional splice assays · Original source · Human Mutation 42(7):799, published online 2021-05-20; PMC8360004 full-text XML

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: splicing-follow-up-20261009-config-riepe2021-spliceai-1-3-1

areas: dna-genomes
contexts: research
method types: supervised_machine_learning
reported name: SpliceAI (Riepe et al. 2021)
foundation model eligible: false
version: v1.3.1
parameters: Classification cutoff per data set; Table 2 prints the ROC-optimal thresholds, and Tables 3-5 do not restate which cutoff was applied
source locator: Methods 'In silico splice prediction tools'; Table 2
provenance note: SpliceAI (Riepe et al. 2021) as run in the cited comparison.

Related records

configuration of: SpliceAI
system: SpliceAI on ABCA4 deep-intronic variants
system: SpliceAI on ABCA4 noncanonical splice-site variants
system: SpliceAI on MYBPC3 noncanonical splice-site variants

Suggest a correction