Protocol

ABCA4 deep-intronic variants: classification against mini- or midigene splicing results (Riepe et al. Table 4)

Binary classification of assay-measured splice alteration by splice prediction tools.

Overview

Binary classification of assay-measured splice alteration by splice prediction tools.

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

9 recorded evaluations, 99 metric rows. A comparison chart has not yet been validated for these results. The table retains the individual findings and their sources.

View coverage and remaining gaps across all benchmarks

Results

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

All evaluations

9 evaluations · 99 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: Alamut Consensus 3/4 (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)	70% 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 Alamut Consensus 3/4 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 'Alamut Consensus 3/4', column 'Accuracy (%)'
Configuration: Alamut Consensus 3/4 (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)	10 false-negative-count count · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Alamut Consensus 3/4 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 'Alamut Consensus 3/4', column 'FN'
Configuration: Alamut Consensus 3/4 (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)	14 false-positive-count count · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Alamut Consensus 3/4 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 'Alamut Consensus 3/4', column 'FP'
Configuration: Alamut Consensus 3/4 (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)	0.28 matthews-correlation-coefficient unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Alamut Consensus 3/4 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 'Alamut Consensus 3/4', column 'MCC'
Configuration: Alamut Consensus 3/4 (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 count · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Alamut Consensus 3/4 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 'Alamut Consensus 3/4', column 'Missing values'
Configuration: Alamut Consensus 3/4 (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)	82% 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 Alamut Consensus 3/4 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 'Alamut Consensus 3/4', column 'NPV (%)'
Configuration: Alamut Consensus 3/4 (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)	44% 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 Alamut Consensus 3/4 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 'Alamut Consensus 3/4', column 'PPV (%)'
Configuration: Alamut Consensus 3/4 (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)	52% 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 Alamut Consensus 3/4 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 'Alamut Consensus 3/4', column 'Sensitivity (%)'
Configuration: Alamut Consensus 3/4 (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)	77% 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 Alamut Consensus 3/4 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 'Alamut Consensus 3/4', column 'Specificity (%)'
Configuration: Alamut Consensus 3/4 (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)	46 true-negative-count count · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Alamut Consensus 3/4 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 'Alamut Consensus 3/4', column 'TN'
Configuration: Alamut Consensus 3/4 (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)	11 true-positive-count count · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Alamut Consensus 3/4 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 'Alamut Consensus 3/4', column 'TP'
Configuration: CADD (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)	59% 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 CADD 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 'CADD', column 'Accuracy (%)'
Configuration: CADD (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)	9 false-negative-count count · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source CADD 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 'CADD', column 'FN'
Configuration: CADD (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)	24 false-positive-count count · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source CADD 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 'CADD', column 'FP'
Configuration: CADD (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)	0.15 matthews-correlation-coefficient unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source CADD 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 'CADD', column 'MCC'
Configuration: CADD (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 count · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source CADD 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 'CADD', column 'Missing values'
Configuration: CADD (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)	80% 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 CADD 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 'CADD', column 'NPV (%)'
Configuration: CADD (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)	33% 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 CADD 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 'CADD', column 'PPV (%)'
Configuration: CADD (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% 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 CADD 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 'CADD', column 'Sensitivity (%)'
Configuration: CADD (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)	60% 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 CADD 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 'CADD', column 'Specificity (%)'
Configuration: CADD (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)	36 true-negative-count count · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source CADD 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 'CADD', column 'TN'
Configuration: CADD (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)	12 true-positive-count count · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source CADD 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 'CADD', column 'TP'
Configuration: DSSP (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)	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 DSSP 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 'DSSP', column 'Accuracy (%)'
Configuration: DSSP (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)	8 false-negative-count count · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source DSSP 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 'DSSP', column 'FN'
Configuration: DSSP (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 false-positive-count count · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source DSSP 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 'DSSP', column 'FP'

Source checking is not independent reproduction. Release 2026-10-10-6e93f504adfc.

Methods and evaluation design

Procedure, tasks and evaluated configurations

Recorded evaluations

Each evaluation records what was tested and under which conditions.

Baseline coverage

Reference methods help show what a model adds beyond simple controls. We track a null control and a conventional method for each protocol.

0 of 2 active baseline roles have published Rewire measurements in this release. Measurements on a selected protocol do not establish coverage of an entire suite.

No execution recipe linked to this protocol. Recipe availability does not establish a completed evaluation.

External evaluations: 9

Literature evidence is not a Rewire measurement. Executed but unpublished runs and private review status are not included.

Null control

Proposed control: requires review

Training-set class prior where supervised fitting is permitted

Protocol-specific applicability, permitted inputs, access, split, evaluator and execution requirements need review before implementation or execution.

This is a suggested selection rule, not a validated method or a measured score.

Conventional reference

Proposed control: requires review

Regularised classifier on simple permitted features, or protocol's conventional reference

Protocol-specific applicability, permitted inputs, access, split, evaluator and execution requirements need review before implementation or execution.

This is a suggested selection rule, not a validated method or a measured score.

Protocol coverage CSV (gzip) · Model evaluation matrix (gzip) · Source table (gzip) · Release and checksums (gzip)

Coverage is derived from release 2026-10-10-6e93f504adfc. Source citations describe the original records; they do not validate an unreviewed baseline proposal. No results have been generated by this audit.

Run instructions

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

Strengths, limitations and unresolved questions

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 2026-10-10-6e93f504adfc
Property and statement	Original source and location	Review and provenance

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

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

Sources and history

Release 2026-10-10-6e93f504adfc · Record review: source checked

1 source records 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-protocol-riepe2021-abca4-di

areas: dna-genomes
contexts: research
protocol: Score each variant with each tool (missing Alamut scores set to zero); classify at a per-data-set cutoff and report the confusion matrix, accuracy, PPV, sensitivity, specificity, NPV and MCC (formulas in Table S2 of the article).
version: Table 4
source locator: Table 4; Methods 'Classification metrics and receiver operator curve'
limitations: Variants were selected for testing with Alamut tools (ABCA4) or MaxEntScan (MYBPC3), which can favour those tools and their relatives.; Cutoffs appear to be tuned on the same data set (Table 2 ROC-optimal thresholds); Tables 3-5 do not state the cutoff, so values may be optimistic.; Small single-gene sets with strong class imbalance (ABCA4 NCSS 90% positive, ABCA4 DI 26% positive).; Variants are from patients but splicing was measured in mini- or midigene assays in HEK293T, not in patient tissue.; The authors note the selection bias but report the opposite of what it would predict: Alamut 3/4 performs best on MYBPC3 and MaxEntScan only relatively well on ABCA4 (Discussion).; Spidex's unscored variants (5 in ABCA4 NCSS, 3 in MYBPC3) are counted in its confusion matrix without a stated class; MMSplice and Spidex are absent from the deep-intronic table because they scored fewer than half of those variants.
missing metadata: metric implementation: reason: unreported; note: Cutoff applied in Tables 3-5 is not stated; analysis scripts are at github.com/cmbi/Benchmarking_splice_prediction_tools (not read)

Related records

uses data: ABCA4 deep-intronic variants (Riepe et al. benchmark set)
subject: allowed_information: splicing-follow-up-20261009-protocol-riepe2021-abca4-di
assessment: Alamut Consensus 3/4 on ABCA4 deep-intronic variants
assessment: CADD on ABCA4 deep-intronic variants
assessment: DSSP on ABCA4 deep-intronic variants
assessment: GeneSplicer on ABCA4 deep-intronic variants
assessment: MaxEntScan on ABCA4 deep-intronic variants
assessment: NNSPLICE on ABCA4 deep-intronic variants
assessment: SpliceAI on ABCA4 deep-intronic variants
assessment: SpliceRover on ABCA4 deep-intronic variants
assessment: SpliceSiteFinder-like on ABCA4 deep-intronic variants
assessed by: Prioritise variants for splicing experiments

Suggest a correction