| Configuration: CI-SpliceAI (Fortier et al. 2026) | Protocol: Splice-altering variant classification, Barbosa et al. ClinVar intronic SNV benchmark (53,600 variants) (Fortier et al. Table 5)
Dataset: Barbosa et al. ClinVar intronic SNV benchmark (53,600 variants) | 0.977 Balanced accuracy (maximum delta score > 0.5 (Legacy Ensemble N > 1)) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourceCI-SpliceAI on the Barbosa et al. ClinVar intronic SNV benchmark (53,600 variants) rna-splicing-20261011-fortier2026-protocol-barbosa-clinvar Aggregation: Not reported Analyzing the performance of deep learning splice prediction algorithms (Fortier, Rudy and Scherer, PLOS One 2026) · Table 5, row 'CI-SpliceAI', column 'Balanced Accuracy' |
|---|
| Configuration: CI-SpliceAI (Fortier et al. 2026) | Protocol: Splice-altering variant classification, Barbosa et al. ClinVar intronic SNV benchmark (53,600 variants) (Fortier et al. Table 5)
Dataset: Barbosa et al. ClinVar intronic SNV benchmark (53,600 variants) | 0.974 F1 (maximum delta score > 0.5 (Legacy Ensemble N > 1)) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourceCI-SpliceAI on the Barbosa et al. ClinVar intronic SNV benchmark (53,600 variants) rna-splicing-20261011-fortier2026-protocol-barbosa-clinvar Aggregation: Not reported Analyzing the performance of deep learning splice prediction algorithms (Fortier, Rudy and Scherer, PLOS One 2026) · Table 5, row 'CI-SpliceAI', column 'F1' |
|---|
| Configuration: CI-SpliceAI (Fortier et al. 2026) | Protocol: Splice-altering variant classification, Barbosa et al. ClinVar intronic SNV benchmark (53,600 variants) (Fortier et al. Table 5)
Dataset: Barbosa et al. ClinVar intronic SNV benchmark (53,600 variants) | 0.958 Recall (maximum delta score > 0.5 (Legacy Ensemble N > 1)) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourceCI-SpliceAI on the Barbosa et al. ClinVar intronic SNV benchmark (53,600 variants) rna-splicing-20261011-fortier2026-protocol-barbosa-clinvar Aggregation: Not reported Analyzing the performance of deep learning splice prediction algorithms (Fortier, Rudy and Scherer, PLOS One 2026) · Table 5, row 'CI-SpliceAI', column 'Sensitivity' |
|---|
| Configuration: CI-SpliceAI (Fortier et al. 2026) | Protocol: Splice-altering variant classification, Barbosa et al. ClinVar intronic SNV benchmark (53,600 variants) (Fortier et al. Table 5)
Dataset: Barbosa et al. ClinVar intronic SNV benchmark (53,600 variants) | 0.997 Specificity (maximum delta score > 0.5 (Legacy Ensemble N > 1)) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourceCI-SpliceAI on the Barbosa et al. ClinVar intronic SNV benchmark (53,600 variants) rna-splicing-20261011-fortier2026-protocol-barbosa-clinvar Aggregation: Not reported Analyzing the performance of deep learning splice prediction algorithms (Fortier, Rudy and Scherer, PLOS One 2026) · Table 5, row 'CI-SpliceAI', column 'Specificity' |
|---|
| Configuration: CI-SpliceAI (Fortier et al. 2026) | Protocol: Splice-altering variant classification, Barbosa et al. deep intronic pathogenic variants with matched common controls (484 variants) (Fortier et al. Table 4)
Dataset: Barbosa et al. deep intronic pathogenic variants with matched common controls (484 variants) | 0.89 Balanced accuracy (threshold optimised per algorithm for balanced accuracy on this dataset) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourceCI-SpliceAI on the Barbosa et al. deep intronic pathogenic variants with matched common controls (484 variants) rna-splicing-20261011-fortier2026-protocol-barbosa-deep-intronic Aggregation: Not reported Analyzing the performance of deep learning splice prediction algorithms (Fortier, Rudy and Scherer, PLOS One 2026) · Table 4, row 'CI-SpliceAI', column 'Balanced Accuracy' |
|---|
| Configuration: CI-SpliceAI (Fortier et al. 2026) | Protocol: Splice-altering variant classification, Barbosa et al. deep intronic pathogenic variants with matched common controls (484 variants) (Fortier et al. Table 4)
Dataset: Barbosa et al. deep intronic pathogenic variants with matched common controls (484 variants) | 0.886 F1 (threshold optimised per algorithm for balanced accuracy on this dataset) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourceCI-SpliceAI on the Barbosa et al. deep intronic pathogenic variants with matched common controls (484 variants) rna-splicing-20261011-fortier2026-protocol-barbosa-deep-intronic Aggregation: Not reported Analyzing the performance of deep learning splice prediction algorithms (Fortier, Rudy and Scherer, PLOS One 2026) · Table 4, row 'CI-SpliceAI', column 'F1' |
|---|
| Configuration: CI-SpliceAI (Fortier et al. 2026) | Protocol: Splice-altering variant classification, Barbosa et al. deep intronic pathogenic variants with matched common controls (484 variants) (Fortier et al. Table 4)
Dataset: Barbosa et al. deep intronic pathogenic variants with matched common controls (484 variants) | 0.851 Recall (threshold optimised per algorithm for balanced accuracy on this dataset) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourceCI-SpliceAI on the Barbosa et al. deep intronic pathogenic variants with matched common controls (484 variants) rna-splicing-20261011-fortier2026-protocol-barbosa-deep-intronic Aggregation: Not reported Analyzing the performance of deep learning splice prediction algorithms (Fortier, Rudy and Scherer, PLOS One 2026) · Table 4, row 'CI-SpliceAI', column 'Sensitivity' |
|---|
| Configuration: CI-SpliceAI (Fortier et al. 2026) | Protocol: Splice-altering variant classification, Barbosa et al. deep intronic pathogenic variants with matched common controls (484 variants) (Fortier et al. Table 4)
Dataset: Barbosa et al. deep intronic pathogenic variants with matched common controls (484 variants) | 0.93 Specificity (threshold optimised per algorithm for balanced accuracy on this dataset) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourceCI-SpliceAI on the Barbosa et al. deep intronic pathogenic variants with matched common controls (484 variants) rna-splicing-20261011-fortier2026-protocol-barbosa-deep-intronic Aggregation: Not reported Analyzing the performance of deep learning splice prediction algorithms (Fortier, Rudy and Scherer, PLOS One 2026) · Table 4, row 'CI-SpliceAI', column 'Specificity' |
|---|
| Configuration: CI-SpliceAI (Fortier et al. 2026) | Protocol: Splice-altering variant classification, CI-SpliceAI benchmark variant set (1,316 variants) (Fortier et al. Table 1)
Dataset: CI-SpliceAI benchmark variant set (1,316 variants) | 0.907 Balanced accuracy (maximum delta score > 0.5 (Legacy Ensemble N > 1)) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourceCI-SpliceAI on the CI-SpliceAI benchmark variant set (1,316 variants) rna-splicing-20261011-fortier2026-protocol-ci-spliceai-benchmark Aggregation: Not reported Analyzing the performance of deep learning splice prediction algorithms (Fortier, Rudy and Scherer, PLOS One 2026) · Table 1, row 'CI-SpliceAI', column 'Balanced Accuracy' |
|---|
| Configuration: CI-SpliceAI (Fortier et al. 2026) | Protocol: Splice-altering variant classification, CI-SpliceAI benchmark variant set (1,316 variants) (Fortier et al. Table 1)
Dataset: CI-SpliceAI benchmark variant set (1,316 variants) | 0.899 F1 (maximum delta score > 0.5 (Legacy Ensemble N > 1)) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourceCI-SpliceAI on the CI-SpliceAI benchmark variant set (1,316 variants) rna-splicing-20261011-fortier2026-protocol-ci-spliceai-benchmark Aggregation: Not reported Analyzing the performance of deep learning splice prediction algorithms (Fortier, Rudy and Scherer, PLOS One 2026) · Table 1, row 'CI-SpliceAI', column 'F1' |
|---|
| Configuration: CI-SpliceAI (Fortier et al. 2026) | Protocol: Splice-altering variant classification, CI-SpliceAI benchmark variant set (1,316 variants) (Fortier et al. Table 1)
Dataset: CI-SpliceAI benchmark variant set (1,316 variants) | 0.837 Recall (maximum delta score > 0.5 (Legacy Ensemble N > 1)) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourceCI-SpliceAI on the CI-SpliceAI benchmark variant set (1,316 variants) rna-splicing-20261011-fortier2026-protocol-ci-spliceai-benchmark Aggregation: Not reported Analyzing the performance of deep learning splice prediction algorithms (Fortier, Rudy and Scherer, PLOS One 2026) · Table 1, row 'CI-SpliceAI', column 'Sensitivity' |
|---|
| Configuration: CI-SpliceAI (Fortier et al. 2026) | Protocol: Splice-altering variant classification, CI-SpliceAI benchmark variant set (1,316 variants) (Fortier et al. Table 1)
Dataset: CI-SpliceAI benchmark variant set (1,316 variants) | 0.976 Specificity (maximum delta score > 0.5 (Legacy Ensemble N > 1)) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourceCI-SpliceAI on the CI-SpliceAI benchmark variant set (1,316 variants) rna-splicing-20261011-fortier2026-protocol-ci-spliceai-benchmark Aggregation: Not reported Analyzing the performance of deep learning splice prediction algorithms (Fortier, Rudy and Scherer, PLOS One 2026) · Table 1, row 'CI-SpliceAI', column 'Specificity' |
|---|
| Configuration: CI-SpliceAI (Fortier et al. 2026) | Protocol: Splice-altering variant classification, Extended ClinVar benchmark (58,064 variants) (Fortier et al. Table 6)
Dataset: Extended ClinVar benchmark (58,064 variants) | 0.895 Balanced accuracy (maximum delta score classification after legacy-tool pre-filtering (threshold not restated for this dataset)) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourceCI-SpliceAI on the Extended ClinVar benchmark (58,064 variants) rna-splicing-20261011-fortier2026-protocol-extended-clinvar Aggregation: Not reported Analyzing the performance of deep learning splice prediction algorithms (Fortier, Rudy and Scherer, PLOS One 2026) · Table 6, row 'CI-SpliceAI', column 'Balanced Accuracy' |
|---|
| Configuration: CI-SpliceAI (Fortier et al. 2026) | Protocol: Splice-altering variant classification, Extended ClinVar benchmark (58,064 variants) (Fortier et al. Table 6)
Dataset: Extended ClinVar benchmark (58,064 variants) | 0.876 F1 (maximum delta score classification after legacy-tool pre-filtering (threshold not restated for this dataset)) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourceCI-SpliceAI on the Extended ClinVar benchmark (58,064 variants) rna-splicing-20261011-fortier2026-protocol-extended-clinvar Aggregation: Not reported Analyzing the performance of deep learning splice prediction algorithms (Fortier, Rudy and Scherer, PLOS One 2026) · Table 6, row 'CI-SpliceAI', column 'F1' |
|---|
| Configuration: CI-SpliceAI (Fortier et al. 2026) | Protocol: Splice-altering variant classification, Extended ClinVar benchmark (58,064 variants) (Fortier et al. Table 6)
Dataset: Extended ClinVar benchmark (58,064 variants) | 0.8 Recall (maximum delta score classification after legacy-tool pre-filtering (threshold not restated for this dataset)) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourceCI-SpliceAI on the Extended ClinVar benchmark (58,064 variants) rna-splicing-20261011-fortier2026-protocol-extended-clinvar Aggregation: Not reported Analyzing the performance of deep learning splice prediction algorithms (Fortier, Rudy and Scherer, PLOS One 2026) · Table 6, row 'CI-SpliceAI', column 'Sensitivity' |
|---|
| Configuration: CI-SpliceAI (Fortier et al. 2026) | Protocol: Splice-altering variant classification, Extended ClinVar benchmark (58,064 variants) (Fortier et al. Table 6)
Dataset: Extended ClinVar benchmark (58,064 variants) | 0.991 Specificity (maximum delta score classification after legacy-tool pre-filtering (threshold not restated for this dataset)) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourceCI-SpliceAI on the Extended ClinVar benchmark (58,064 variants) rna-splicing-20261011-fortier2026-protocol-extended-clinvar Aggregation: Not reported Analyzing the performance of deep learning splice prediction algorithms (Fortier, Rudy and Scherer, PLOS One 2026) · Table 6, row 'CI-SpliceAI', column 'Specificity' |
|---|
| Configuration: CI-SpliceAI (Fortier et al. 2026) | Protocol: Splice-altering variant classification, Riepe et al. functional splice assay variants (213 variants, ABCA4 and MYBPC3) (Fortier et al. Table 2)
Dataset: Riepe et al. functional splice assay variants (213 variants, ABCA4 and MYBPC3) | 0.794 Balanced accuracy (delta score for each variant's effect type; threshold optimised per gene and algorithm for maximum accuracy (upper bound)) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourceCI-SpliceAI on the Riepe et al. functional splice assay variants (213 variants, ABCA4 and MYBPC3) rna-splicing-20261011-fortier2026-protocol-riepe Aggregation: Not reported Analyzing the performance of deep learning splice prediction algorithms (Fortier, Rudy and Scherer, PLOS One 2026) · Table 2, row 'CI-SpliceAI', column 'Balanced Accuracy' |
|---|
| Configuration: CI-SpliceAI (Fortier et al. 2026) | Protocol: Splice-altering variant classification, Riepe et al. functional splice assay variants (213 variants, ABCA4 and MYBPC3) (Fortier et al. Table 2)
Dataset: Riepe et al. functional splice assay variants (213 variants, ABCA4 and MYBPC3) | 0.785 F1 (delta score for each variant's effect type; threshold optimised per gene and algorithm for maximum accuracy (upper bound)) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourceCI-SpliceAI on the Riepe et al. functional splice assay variants (213 variants, ABCA4 and MYBPC3) rna-splicing-20261011-fortier2026-protocol-riepe Aggregation: Not reported Analyzing the performance of deep learning splice prediction algorithms (Fortier, Rudy and Scherer, PLOS One 2026) · Table 2, row 'CI-SpliceAI', column 'F1' |
|---|
| Configuration: CI-SpliceAI (Fortier et al. 2026) | Protocol: Splice-altering variant classification, Riepe et al. functional splice assay variants (213 variants, ABCA4 and MYBPC3) (Fortier et al. Table 2)
Dataset: Riepe et al. functional splice assay variants (213 variants, ABCA4 and MYBPC3) | 0.706 Recall (delta score for each variant's effect type; threshold optimised per gene and algorithm for maximum accuracy (upper bound)) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourceCI-SpliceAI on the Riepe et al. functional splice assay variants (213 variants, ABCA4 and MYBPC3) rna-splicing-20261011-fortier2026-protocol-riepe Aggregation: Not reported Analyzing the performance of deep learning splice prediction algorithms (Fortier, Rudy and Scherer, PLOS One 2026) · Table 2, row 'CI-SpliceAI', column 'Sensitivity' |
|---|
| Configuration: CI-SpliceAI (Fortier et al. 2026) | Protocol: Splice-altering variant classification, Riepe et al. functional splice assay variants (213 variants, ABCA4 and MYBPC3) (Fortier et al. Table 2)
Dataset: Riepe et al. functional splice assay variants (213 variants, ABCA4 and MYBPC3) | 0.883 Specificity (delta score for each variant's effect type; threshold optimised per gene and algorithm for maximum accuracy (upper bound)) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourceCI-SpliceAI on the Riepe et al. functional splice assay variants (213 variants, ABCA4 and MYBPC3) rna-splicing-20261011-fortier2026-protocol-riepe Aggregation: Not reported Analyzing the performance of deep learning splice prediction algorithms (Fortier, Rudy and Scherer, PLOS One 2026) · Table 2, row 'CI-SpliceAI', column 'Specificity' |
|---|
| Configuration: CI-SpliceAI (Fortier et al. 2026) | Protocol: Splice-altering variant classification, SPiP benchmark variant set (99,601 variants) (Fortier et al. Table 3)
Dataset: SPiP benchmark variant set (99,601 variants) | 0.798 Balanced accuracy (maximum delta score > 0.5 (Legacy Ensemble N > 1)) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourceCI-SpliceAI on the SPiP benchmark variant set (99,601 variants) rna-splicing-20261011-fortier2026-protocol-spip Aggregation: Not reported Analyzing the performance of deep learning splice prediction algorithms (Fortier, Rudy and Scherer, PLOS One 2026) · Table 3, row 'CI-SpliceAI', column 'Balanced Accuracy' |
|---|
| Configuration: CI-SpliceAI (Fortier et al. 2026) | Protocol: Splice-altering variant classification, SPiP benchmark variant set (99,601 variants) (Fortier et al. Table 3)
Dataset: SPiP benchmark variant set (99,601 variants) | 0.725 F1 (maximum delta score > 0.5 (Legacy Ensemble N > 1)) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourceCI-SpliceAI on the SPiP benchmark variant set (99,601 variants) rna-splicing-20261011-fortier2026-protocol-spip Aggregation: Not reported Analyzing the performance of deep learning splice prediction algorithms (Fortier, Rudy and Scherer, PLOS One 2026) · Table 3, row 'CI-SpliceAI', column 'F1' |
|---|
| Configuration: CI-SpliceAI (Fortier et al. 2026) | Protocol: Splice-altering variant classification, SPiP benchmark variant set (99,601 variants) (Fortier et al. Table 3)
Dataset: SPiP benchmark variant set (99,601 variants) | 0.596 Recall (maximum delta score > 0.5 (Legacy Ensemble N > 1)) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourceCI-SpliceAI on the SPiP benchmark variant set (99,601 variants) rna-splicing-20261011-fortier2026-protocol-spip Aggregation: Not reported Analyzing the performance of deep learning splice prediction algorithms (Fortier, Rudy and Scherer, PLOS One 2026) · Table 3, row 'CI-SpliceAI', column 'Sensitivity' |
|---|
| Configuration: CI-SpliceAI (Fortier et al. 2026) | Protocol: Splice-altering variant classification, SPiP benchmark variant set (99,601 variants) (Fortier et al. Table 3)
Dataset: SPiP benchmark variant set (99,601 variants) | 0.999 Specificity (maximum delta score > 0.5 (Legacy Ensemble N > 1)) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourceCI-SpliceAI on the SPiP benchmark variant set (99,601 variants) rna-splicing-20261011-fortier2026-protocol-spip Aggregation: Not reported Analyzing the performance of deep learning splice prediction algorithms (Fortier, Rudy and Scherer, PLOS One 2026) · Table 3, row 'CI-SpliceAI', column 'Specificity' |
|---|