Configuration: Borzoi (128-bp) (Alavi 2026) Protocol: Spliceogenic versus benign classification on an independent 65-gene set with OPA1-derived thresholds (Alavi Table IV) Dataset: Multi-gene spliceogenic test set (76 spliceogenic, 107 benign, 65 genes) 80.9% Accuracypercent · higher
Uncertainty: Not reported by the source
Coverage: Not reported scored / Not reported eligible
Independent external evaluation · Source checked Evidence concern: excluded from comparisons The AlphaGenome rows of Tables III, IV and the extended OPA1 positive calls come from scripts that pass a 0-based position to AlphaGenome's 1-based genome.Variant, so each variant was applied one base from its true position. The author labelled the report a bug on 2026-10-20 and said rerunning with the 1-based position substantially improved accuracy. The AlphaGenome results are disputed until the rerun is published; the other models' rows are not affected.Probing Genomic Foundation Models with Splice-Variant Perturbations (Alavi, bioRxiv 2026) · Table III and Table IV, rows 'ALPHAGENOME (SPLICE SCORER)', 'ALPHAGENOME (JUNCTION SCORER)' and 'ALPHAGENOME (EITHER MODULE)'; scripts 2c8_alphagenome_splicescorer.py lines 98 and 120 and 2c8_alphagenome_junctionscorer.py lines 89 and 110 at commit 3c0c6cc; https://github.com/marcel-2c8/Probing-genomic-foundation-models-2026/issues/2
Methods, coverage and source Borzoi (128-bp) on Multi-gene spliceogenic test set (76 spliceogenic, 107 benign, 65 genes)
rna-splicing-20261011-alavi2026-protocol-multigene
Aggregation: Not reported
Probing Genomic Foundation Models with Splice-Variant Perturbations (Alavi, bioRxiv 2026) · Table IV, row 'BORZOI (128-BP)', column 'Accuracy' (PDF page 9 of 11) Configuration: Borzoi (128-bp) (Alavi 2026) Protocol: Spliceogenic versus benign classification on an independent 65-gene set with OPA1-derived thresholds (Alavi Table IV) Dataset: Multi-gene spliceogenic test set (76 spliceogenic, 107 benign, 65 genes) 87.5% Precisionpercent · higher
Uncertainty: Not reported by the source
Coverage: Not reported scored / Not reported eligible
Independent external evaluation · Source checked Evidence concern: excluded from comparisons The AlphaGenome rows of Tables III, IV and the extended OPA1 positive calls come from scripts that pass a 0-based position to AlphaGenome's 1-based genome.Variant, so each variant was applied one base from its true position. The author labelled the report a bug on 2026-10-20 and said rerunning with the 1-based position substantially improved accuracy. The AlphaGenome results are disputed until the rerun is published; the other models' rows are not affected.Probing Genomic Foundation Models with Splice-Variant Perturbations (Alavi, bioRxiv 2026) · Table III and Table IV, rows 'ALPHAGENOME (SPLICE SCORER)', 'ALPHAGENOME (JUNCTION SCORER)' and 'ALPHAGENOME (EITHER MODULE)'; scripts 2c8_alphagenome_splicescorer.py lines 98 and 120 and 2c8_alphagenome_junctionscorer.py lines 89 and 110 at commit 3c0c6cc; https://github.com/marcel-2c8/Probing-genomic-foundation-models-2026/issues/2
Methods, coverage and source Borzoi (128-bp) on Multi-gene spliceogenic test set (76 spliceogenic, 107 benign, 65 genes)
rna-splicing-20261011-alavi2026-protocol-multigene
Aggregation: Not reported
Probing Genomic Foundation Models with Splice-Variant Perturbations (Alavi, bioRxiv 2026) · Table IV, row 'BORZOI (128-BP)', column 'PPV' (PDF page 9 of 11) Configuration: Borzoi (128-bp) (Alavi 2026) Protocol: Spliceogenic versus benign classification on an independent 65-gene set with OPA1-derived thresholds (Alavi Table IV) Dataset: Multi-gene spliceogenic test set (76 spliceogenic, 107 benign, 65 genes) 49 (64.5%) Recallpercent · higher
Uncertainty: Not reported by the source
Coverage: Not reported scored / Not reported eligible
Independent external evaluation · Source checked Evidence concern: excluded from comparisons The AlphaGenome rows of Tables III, IV and the extended OPA1 positive calls come from scripts that pass a 0-based position to AlphaGenome's 1-based genome.Variant, so each variant was applied one base from its true position. The author labelled the report a bug on 2026-10-20 and said rerunning with the 1-based position substantially improved accuracy. The AlphaGenome results are disputed until the rerun is published; the other models' rows are not affected.Probing Genomic Foundation Models with Splice-Variant Perturbations (Alavi, bioRxiv 2026) · Table III and Table IV, rows 'ALPHAGENOME (SPLICE SCORER)', 'ALPHAGENOME (JUNCTION SCORER)' and 'ALPHAGENOME (EITHER MODULE)'; scripts 2c8_alphagenome_splicescorer.py lines 98 and 120 and 2c8_alphagenome_junctionscorer.py lines 89 and 110 at commit 3c0c6cc; https://github.com/marcel-2c8/Probing-genomic-foundation-models-2026/issues/2
Methods, coverage and source Borzoi (128-bp) on Multi-gene spliceogenic test set (76 spliceogenic, 107 benign, 65 genes)
rna-splicing-20261011-alavi2026-protocol-multigene
Aggregation: Not reported
Probing Genomic Foundation Models with Splice-Variant Perturbations (Alavi, bioRxiv 2026) · Table IV, row 'BORZOI (128-BP)', column 'Sensitivity' (PDF page 9 of 11) Configuration: Borzoi (128-bp) (Alavi 2026) Protocol: Spliceogenic versus benign classification on an independent 65-gene set with OPA1-derived thresholds (Alavi Table IV) Dataset: Multi-gene spliceogenic test set (76 spliceogenic, 107 benign, 65 genes) 100 (93.5%) Specificitypercent · higher
Uncertainty: Not reported by the source
Coverage: Not reported scored / Not reported eligible
Independent external evaluation · Source checked Evidence concern: excluded from comparisons The AlphaGenome rows of Tables III, IV and the extended OPA1 positive calls come from scripts that pass a 0-based position to AlphaGenome's 1-based genome.Variant, so each variant was applied one base from its true position. The author labelled the report a bug on 2026-10-20 and said rerunning with the 1-based position substantially improved accuracy. The AlphaGenome results are disputed until the rerun is published; the other models' rows are not affected.Probing Genomic Foundation Models with Splice-Variant Perturbations (Alavi, bioRxiv 2026) · Table III and Table IV, rows 'ALPHAGENOME (SPLICE SCORER)', 'ALPHAGENOME (JUNCTION SCORER)' and 'ALPHAGENOME (EITHER MODULE)'; scripts 2c8_alphagenome_splicescorer.py lines 98 and 120 and 2c8_alphagenome_junctionscorer.py lines 89 and 110 at commit 3c0c6cc; https://github.com/marcel-2c8/Probing-genomic-foundation-models-2026/issues/2
Methods, coverage and source Borzoi (128-bp) on Multi-gene spliceogenic test set (76 spliceogenic, 107 benign, 65 genes)
rna-splicing-20261011-alavi2026-protocol-multigene
Aggregation: Not reported
Probing Genomic Foundation Models with Splice-Variant Perturbations (Alavi, bioRxiv 2026) · Table IV, row 'BORZOI (128-BP)', column 'Specificity' (PDF page 9 of 11) Configuration: Borzoi (128-bp) (Alavi 2026) Protocol: Spliceogenic versus benign classification on an independent 65-gene set with OPA1-derived thresholds (Alavi Table IV) Dataset: Multi-gene spliceogenic test set (76 spliceogenic, 107 benign, 65 genes) 7 (6.5%) False positive rate (type I error: false positives as a share of the benign set)percent · lower
Uncertainty: Not reported by the source
Coverage: Not reported scored / Not reported eligible
Independent external evaluation · Source checked Evidence concern: excluded from comparisons The AlphaGenome rows of Tables III, IV and the extended OPA1 positive calls come from scripts that pass a 0-based position to AlphaGenome's 1-based genome.Variant, so each variant was applied one base from its true position. The author labelled the report a bug on 2026-10-20 and said rerunning with the 1-based position substantially improved accuracy. The AlphaGenome results are disputed until the rerun is published; the other models' rows are not affected.Probing Genomic Foundation Models with Splice-Variant Perturbations (Alavi, bioRxiv 2026) · Table III and Table IV, rows 'ALPHAGENOME (SPLICE SCORER)', 'ALPHAGENOME (JUNCTION SCORER)' and 'ALPHAGENOME (EITHER MODULE)'; scripts 2c8_alphagenome_splicescorer.py lines 98 and 120 and 2c8_alphagenome_junctionscorer.py lines 89 and 110 at commit 3c0c6cc; https://github.com/marcel-2c8/Probing-genomic-foundation-models-2026/issues/2
Methods, coverage and source Borzoi (128-bp) on Multi-gene spliceogenic test set (76 spliceogenic, 107 benign, 65 genes)
rna-splicing-20261011-alavi2026-protocol-multigene
Aggregation: Not reported
Probing Genomic Foundation Models with Splice-Variant Perturbations (Alavi, bioRxiv 2026) · Table IV, row 'BORZOI (128-BP)', column 'Type I error' (PDF page 9 of 11) Configuration: Borzoi (128-bp) (Alavi 2026) Protocol: Spliceogenic versus benign classification on an independent 65-gene set with OPA1-derived thresholds (Alavi Table IV) Dataset: Multi-gene spliceogenic test set (76 spliceogenic, 107 benign, 65 genes) 27 (35.5%) Proportion (type II error: false negatives as a share of the splicing set (false-negative rate))percent · lower
Uncertainty: Not reported by the source
Coverage: Not reported scored / Not reported eligible
Independent external evaluation · Source checked Evidence concern: excluded from comparisons The AlphaGenome rows of Tables III, IV and the extended OPA1 positive calls come from scripts that pass a 0-based position to AlphaGenome's 1-based genome.Variant, so each variant was applied one base from its true position. The author labelled the report a bug on 2026-10-20 and said rerunning with the 1-based position substantially improved accuracy. The AlphaGenome results are disputed until the rerun is published; the other models' rows are not affected.Probing Genomic Foundation Models with Splice-Variant Perturbations (Alavi, bioRxiv 2026) · Table III and Table IV, rows 'ALPHAGENOME (SPLICE SCORER)', 'ALPHAGENOME (JUNCTION SCORER)' and 'ALPHAGENOME (EITHER MODULE)'; scripts 2c8_alphagenome_splicescorer.py lines 98 and 120 and 2c8_alphagenome_junctionscorer.py lines 89 and 110 at commit 3c0c6cc; https://github.com/marcel-2c8/Probing-genomic-foundation-models-2026/issues/2
Methods, coverage and source Borzoi (128-bp) on Multi-gene spliceogenic test set (76 spliceogenic, 107 benign, 65 genes)
rna-splicing-20261011-alavi2026-protocol-multigene
Aggregation: Not reported
Probing Genomic Foundation Models with Splice-Variant Perturbations (Alavi, bioRxiv 2026) · Table IV, row 'BORZOI (128-BP)', column 'Type II error' (PDF page 9 of 11) Configuration: Borzoi (32-bp) (Alavi 2026) Protocol: Spliceogenic versus benign classification on an independent 65-gene set with OPA1-derived thresholds (Alavi Table IV) Dataset: Multi-gene spliceogenic test set (76 spliceogenic, 107 benign, 65 genes) 86.9% Accuracypercent · higher
Uncertainty: Not reported by the source
Coverage: Not reported scored / Not reported eligible
Independent external evaluation · Source checked Evidence concern: excluded from comparisons The AlphaGenome rows of Tables III, IV and the extended OPA1 positive calls come from scripts that pass a 0-based position to AlphaGenome's 1-based genome.Variant, so each variant was applied one base from its true position. The author labelled the report a bug on 2026-10-20 and said rerunning with the 1-based position substantially improved accuracy. The AlphaGenome results are disputed until the rerun is published; the other models' rows are not affected.Probing Genomic Foundation Models with Splice-Variant Perturbations (Alavi, bioRxiv 2026) · Table III and Table IV, rows 'ALPHAGENOME (SPLICE SCORER)', 'ALPHAGENOME (JUNCTION SCORER)' and 'ALPHAGENOME (EITHER MODULE)'; scripts 2c8_alphagenome_splicescorer.py lines 98 and 120 and 2c8_alphagenome_junctionscorer.py lines 89 and 110 at commit 3c0c6cc; https://github.com/marcel-2c8/Probing-genomic-foundation-models-2026/issues/2
Methods, coverage and source Borzoi (32-bp) on Multi-gene spliceogenic test set (76 spliceogenic, 107 benign, 65 genes)
rna-splicing-20261011-alavi2026-protocol-multigene
Aggregation: Not reported
Probing Genomic Foundation Models with Splice-Variant Perturbations (Alavi, bioRxiv 2026) · Table IV, row 'BORZOI (32-BP)', column 'Accuracy' (PDF page 9 of 11) Configuration: Borzoi (32-bp) (Alavi 2026) Protocol: Spliceogenic versus benign classification on an independent 65-gene set with OPA1-derived thresholds (Alavi Table IV) Dataset: Multi-gene spliceogenic test set (76 spliceogenic, 107 benign, 65 genes) 93.3% Precisionpercent · higher
Uncertainty: Not reported by the source
Coverage: Not reported scored / Not reported eligible
Independent external evaluation · Source checked Evidence concern: excluded from comparisons The AlphaGenome rows of Tables III, IV and the extended OPA1 positive calls come from scripts that pass a 0-based position to AlphaGenome's 1-based genome.Variant, so each variant was applied one base from its true position. The author labelled the report a bug on 2026-10-20 and said rerunning with the 1-based position substantially improved accuracy. The AlphaGenome results are disputed until the rerun is published; the other models' rows are not affected.Probing Genomic Foundation Models with Splice-Variant Perturbations (Alavi, bioRxiv 2026) · Table III and Table IV, rows 'ALPHAGENOME (SPLICE SCORER)', 'ALPHAGENOME (JUNCTION SCORER)' and 'ALPHAGENOME (EITHER MODULE)'; scripts 2c8_alphagenome_splicescorer.py lines 98 and 120 and 2c8_alphagenome_junctionscorer.py lines 89 and 110 at commit 3c0c6cc; https://github.com/marcel-2c8/Probing-genomic-foundation-models-2026/issues/2
Methods, coverage and source Borzoi (32-bp) on Multi-gene spliceogenic test set (76 spliceogenic, 107 benign, 65 genes)
rna-splicing-20261011-alavi2026-protocol-multigene
Aggregation: Not reported
Probing Genomic Foundation Models with Splice-Variant Perturbations (Alavi, bioRxiv 2026) · Table IV, row 'BORZOI (32-BP)', column 'PPV' (PDF page 9 of 11) Configuration: Borzoi (32-bp) (Alavi 2026) Protocol: Spliceogenic versus benign classification on an independent 65-gene set with OPA1-derived thresholds (Alavi Table IV) Dataset: Multi-gene spliceogenic test set (76 spliceogenic, 107 benign, 65 genes) 56 (73.7%) Recallpercent · higher
Uncertainty: Not reported by the source
Coverage: Not reported scored / Not reported eligible
Independent external evaluation · Source checked Evidence concern: excluded from comparisons The AlphaGenome rows of Tables III, IV and the extended OPA1 positive calls come from scripts that pass a 0-based position to AlphaGenome's 1-based genome.Variant, so each variant was applied one base from its true position. The author labelled the report a bug on 2026-10-20 and said rerunning with the 1-based position substantially improved accuracy. The AlphaGenome results are disputed until the rerun is published; the other models' rows are not affected.Probing Genomic Foundation Models with Splice-Variant Perturbations (Alavi, bioRxiv 2026) · Table III and Table IV, rows 'ALPHAGENOME (SPLICE SCORER)', 'ALPHAGENOME (JUNCTION SCORER)' and 'ALPHAGENOME (EITHER MODULE)'; scripts 2c8_alphagenome_splicescorer.py lines 98 and 120 and 2c8_alphagenome_junctionscorer.py lines 89 and 110 at commit 3c0c6cc; https://github.com/marcel-2c8/Probing-genomic-foundation-models-2026/issues/2
Methods, coverage and source Borzoi (32-bp) on Multi-gene spliceogenic test set (76 spliceogenic, 107 benign, 65 genes)
rna-splicing-20261011-alavi2026-protocol-multigene
Aggregation: Not reported
Probing Genomic Foundation Models with Splice-Variant Perturbations (Alavi, bioRxiv 2026) · Table IV, row 'BORZOI (32-BP)', column 'Sensitivity' (PDF page 9 of 11) Configuration: Borzoi (32-bp) (Alavi 2026) Protocol: Spliceogenic versus benign classification on an independent 65-gene set with OPA1-derived thresholds (Alavi Table IV) Dataset: Multi-gene spliceogenic test set (76 spliceogenic, 107 benign, 65 genes) 103 (96.3%) Specificitypercent · higher
Uncertainty: Not reported by the source
Coverage: Not reported scored / Not reported eligible
Independent external evaluation · Source checked Evidence concern: excluded from comparisons The AlphaGenome rows of Tables III, IV and the extended OPA1 positive calls come from scripts that pass a 0-based position to AlphaGenome's 1-based genome.Variant, so each variant was applied one base from its true position. The author labelled the report a bug on 2026-10-20 and said rerunning with the 1-based position substantially improved accuracy. The AlphaGenome results are disputed until the rerun is published; the other models' rows are not affected.Probing Genomic Foundation Models with Splice-Variant Perturbations (Alavi, bioRxiv 2026) · Table III and Table IV, rows 'ALPHAGENOME (SPLICE SCORER)', 'ALPHAGENOME (JUNCTION SCORER)' and 'ALPHAGENOME (EITHER MODULE)'; scripts 2c8_alphagenome_splicescorer.py lines 98 and 120 and 2c8_alphagenome_junctionscorer.py lines 89 and 110 at commit 3c0c6cc; https://github.com/marcel-2c8/Probing-genomic-foundation-models-2026/issues/2
Methods, coverage and source Borzoi (32-bp) on Multi-gene spliceogenic test set (76 spliceogenic, 107 benign, 65 genes)
rna-splicing-20261011-alavi2026-protocol-multigene
Aggregation: Not reported
Probing Genomic Foundation Models with Splice-Variant Perturbations (Alavi, bioRxiv 2026) · Table IV, row 'BORZOI (32-BP)', column 'Specificity' (PDF page 9 of 11) Configuration: Borzoi (32-bp) (Alavi 2026) Protocol: Spliceogenic versus benign classification on an independent 65-gene set with OPA1-derived thresholds (Alavi Table IV) Dataset: Multi-gene spliceogenic test set (76 spliceogenic, 107 benign, 65 genes) 4 (3.7%) False positive rate (type I error: false positives as a share of the benign set)percent · lower
Uncertainty: Not reported by the source
Coverage: Not reported scored / Not reported eligible
Independent external evaluation · Source checked Evidence concern: excluded from comparisons The AlphaGenome rows of Tables III, IV and the extended OPA1 positive calls come from scripts that pass a 0-based position to AlphaGenome's 1-based genome.Variant, so each variant was applied one base from its true position. The author labelled the report a bug on 2026-10-20 and said rerunning with the 1-based position substantially improved accuracy. The AlphaGenome results are disputed until the rerun is published; the other models' rows are not affected.Probing Genomic Foundation Models with Splice-Variant Perturbations (Alavi, bioRxiv 2026) · Table III and Table IV, rows 'ALPHAGENOME (SPLICE SCORER)', 'ALPHAGENOME (JUNCTION SCORER)' and 'ALPHAGENOME (EITHER MODULE)'; scripts 2c8_alphagenome_splicescorer.py lines 98 and 120 and 2c8_alphagenome_junctionscorer.py lines 89 and 110 at commit 3c0c6cc; https://github.com/marcel-2c8/Probing-genomic-foundation-models-2026/issues/2
Methods, coverage and source Borzoi (32-bp) on Multi-gene spliceogenic test set (76 spliceogenic, 107 benign, 65 genes)
rna-splicing-20261011-alavi2026-protocol-multigene
Aggregation: Not reported
Probing Genomic Foundation Models with Splice-Variant Perturbations (Alavi, bioRxiv 2026) · Table IV, row 'BORZOI (32-BP)', column 'Type I error' (PDF page 9 of 11) Configuration: Borzoi (32-bp) (Alavi 2026) Protocol: Spliceogenic versus benign classification on an independent 65-gene set with OPA1-derived thresholds (Alavi Table IV) Dataset: Multi-gene spliceogenic test set (76 spliceogenic, 107 benign, 65 genes) 20 (26.3%) Proportion (type II error: false negatives as a share of the splicing set (false-negative rate))percent · lower
Uncertainty: Not reported by the source
Coverage: Not reported scored / Not reported eligible
Independent external evaluation · Source checked Evidence concern: excluded from comparisons The AlphaGenome rows of Tables III, IV and the extended OPA1 positive calls come from scripts that pass a 0-based position to AlphaGenome's 1-based genome.Variant, so each variant was applied one base from its true position. The author labelled the report a bug on 2026-10-20 and said rerunning with the 1-based position substantially improved accuracy. The AlphaGenome results are disputed until the rerun is published; the other models' rows are not affected.Probing Genomic Foundation Models with Splice-Variant Perturbations (Alavi, bioRxiv 2026) · Table III and Table IV, rows 'ALPHAGENOME (SPLICE SCORER)', 'ALPHAGENOME (JUNCTION SCORER)' and 'ALPHAGENOME (EITHER MODULE)'; scripts 2c8_alphagenome_splicescorer.py lines 98 and 120 and 2c8_alphagenome_junctionscorer.py lines 89 and 110 at commit 3c0c6cc; https://github.com/marcel-2c8/Probing-genomic-foundation-models-2026/issues/2
Methods, coverage and source Borzoi (32-bp) on Multi-gene spliceogenic test set (76 spliceogenic, 107 benign, 65 genes)
rna-splicing-20261011-alavi2026-protocol-multigene
Aggregation: Not reported
Probing Genomic Foundation Models with Splice-Variant Perturbations (Alavi, bioRxiv 2026) · Table IV, row 'BORZOI (32-BP)', column 'Type II error' (PDF page 9 of 11) Configuration: Evo2 40B (human identifier) (Alavi 2026) Protocol: Spliceogenic versus benign classification on an independent 65-gene set with OPA1-derived thresholds (Alavi Table IV) Dataset: Multi-gene spliceogenic test set (76 spliceogenic, 107 benign, 65 genes) 88% Accuracypercent · higher
Uncertainty: Not reported by the source
Coverage: Not reported scored / Not reported eligible
Independent external evaluation · Source checked Evidence concern: excluded from comparisons The AlphaGenome rows of Tables III, IV and the extended OPA1 positive calls come from scripts that pass a 0-based position to AlphaGenome's 1-based genome.Variant, so each variant was applied one base from its true position. The author labelled the report a bug on 2026-10-20 and said rerunning with the 1-based position substantially improved accuracy. The AlphaGenome results are disputed until the rerun is published; the other models' rows are not affected.Probing Genomic Foundation Models with Splice-Variant Perturbations (Alavi, bioRxiv 2026) · Table III and Table IV, rows 'ALPHAGENOME (SPLICE SCORER)', 'ALPHAGENOME (JUNCTION SCORER)' and 'ALPHAGENOME (EITHER MODULE)'; scripts 2c8_alphagenome_splicescorer.py lines 98 and 120 and 2c8_alphagenome_junctionscorer.py lines 89 and 110 at commit 3c0c6cc; https://github.com/marcel-2c8/Probing-genomic-foundation-models-2026/issues/2
Methods, coverage and source Evo2 40B (human identifier) on Multi-gene spliceogenic test set (76 spliceogenic, 107 benign, 65 genes)
rna-splicing-20261011-alavi2026-protocol-multigene
Aggregation: Not reported
Probing Genomic Foundation Models with Splice-Variant Perturbations (Alavi, bioRxiv 2026) · Table IV, row 'EVO2 40B (HU. IDENT.)', column 'Accuracy' (PDF page 9 of 11) Configuration: Evo2 40B (human identifier) (Alavi 2026) Protocol: Spliceogenic versus benign classification on an independent 65-gene set with OPA1-derived thresholds (Alavi Table IV) Dataset: Multi-gene spliceogenic test set (76 spliceogenic, 107 benign, 65 genes) 100% Precisionpercent · higher
Uncertainty: Not reported by the source
Coverage: Not reported scored / Not reported eligible
Independent external evaluation · Source checked Evidence concern: excluded from comparisons The AlphaGenome rows of Tables III, IV and the extended OPA1 positive calls come from scripts that pass a 0-based position to AlphaGenome's 1-based genome.Variant, so each variant was applied one base from its true position. The author labelled the report a bug on 2026-10-20 and said rerunning with the 1-based position substantially improved accuracy. The AlphaGenome results are disputed until the rerun is published; the other models' rows are not affected.Probing Genomic Foundation Models with Splice-Variant Perturbations (Alavi, bioRxiv 2026) · Table III and Table IV, rows 'ALPHAGENOME (SPLICE SCORER)', 'ALPHAGENOME (JUNCTION SCORER)' and 'ALPHAGENOME (EITHER MODULE)'; scripts 2c8_alphagenome_splicescorer.py lines 98 and 120 and 2c8_alphagenome_junctionscorer.py lines 89 and 110 at commit 3c0c6cc; https://github.com/marcel-2c8/Probing-genomic-foundation-models-2026/issues/2
Methods, coverage and source Evo2 40B (human identifier) on Multi-gene spliceogenic test set (76 spliceogenic, 107 benign, 65 genes)
rna-splicing-20261011-alavi2026-protocol-multigene
Aggregation: Not reported
Probing Genomic Foundation Models with Splice-Variant Perturbations (Alavi, bioRxiv 2026) · Table IV, row 'EVO2 40B (HU. IDENT.)', column 'PPV' (PDF page 9 of 11) Configuration: Evo2 40B (human identifier) (Alavi 2026) Protocol: Spliceogenic versus benign classification on an independent 65-gene set with OPA1-derived thresholds (Alavi Table IV) Dataset: Multi-gene spliceogenic test set (76 spliceogenic, 107 benign, 65 genes) 54 (71.1%) Recallpercent · higher
Uncertainty: Not reported by the source
Coverage: Not reported scored / Not reported eligible
Independent external evaluation · Source checked Evidence concern: excluded from comparisons The AlphaGenome rows of Tables III, IV and the extended OPA1 positive calls come from scripts that pass a 0-based position to AlphaGenome's 1-based genome.Variant, so each variant was applied one base from its true position. The author labelled the report a bug on 2026-10-20 and said rerunning with the 1-based position substantially improved accuracy. The AlphaGenome results are disputed until the rerun is published; the other models' rows are not affected.Probing Genomic Foundation Models with Splice-Variant Perturbations (Alavi, bioRxiv 2026) · Table III and Table IV, rows 'ALPHAGENOME (SPLICE SCORER)', 'ALPHAGENOME (JUNCTION SCORER)' and 'ALPHAGENOME (EITHER MODULE)'; scripts 2c8_alphagenome_splicescorer.py lines 98 and 120 and 2c8_alphagenome_junctionscorer.py lines 89 and 110 at commit 3c0c6cc; https://github.com/marcel-2c8/Probing-genomic-foundation-models-2026/issues/2
Methods, coverage and source Evo2 40B (human identifier) on Multi-gene spliceogenic test set (76 spliceogenic, 107 benign, 65 genes)
rna-splicing-20261011-alavi2026-protocol-multigene
Aggregation: Not reported
Probing Genomic Foundation Models with Splice-Variant Perturbations (Alavi, bioRxiv 2026) · Table IV, row 'EVO2 40B (HU. IDENT.)', column 'Sensitivity' (PDF page 9 of 11) Configuration: Evo2 40B (human identifier) (Alavi 2026) Protocol: Spliceogenic versus benign classification on an independent 65-gene set with OPA1-derived thresholds (Alavi Table IV) Dataset: Multi-gene spliceogenic test set (76 spliceogenic, 107 benign, 65 genes) 107 (100%) Specificitypercent · higher
Uncertainty: Not reported by the source
Coverage: Not reported scored / Not reported eligible
Independent external evaluation · Source checked Evidence concern: excluded from comparisons The AlphaGenome rows of Tables III, IV and the extended OPA1 positive calls come from scripts that pass a 0-based position to AlphaGenome's 1-based genome.Variant, so each variant was applied one base from its true position. The author labelled the report a bug on 2026-10-20 and said rerunning with the 1-based position substantially improved accuracy. The AlphaGenome results are disputed until the rerun is published; the other models' rows are not affected.Probing Genomic Foundation Models with Splice-Variant Perturbations (Alavi, bioRxiv 2026) · Table III and Table IV, rows 'ALPHAGENOME (SPLICE SCORER)', 'ALPHAGENOME (JUNCTION SCORER)' and 'ALPHAGENOME (EITHER MODULE)'; scripts 2c8_alphagenome_splicescorer.py lines 98 and 120 and 2c8_alphagenome_junctionscorer.py lines 89 and 110 at commit 3c0c6cc; https://github.com/marcel-2c8/Probing-genomic-foundation-models-2026/issues/2
Methods, coverage and source Evo2 40B (human identifier) on Multi-gene spliceogenic test set (76 spliceogenic, 107 benign, 65 genes)
rna-splicing-20261011-alavi2026-protocol-multigene
Aggregation: Not reported
Probing Genomic Foundation Models with Splice-Variant Perturbations (Alavi, bioRxiv 2026) · Table IV, row 'EVO2 40B (HU. IDENT.)', column 'Specificity' (PDF page 9 of 11) Configuration: Evo2 40B (human identifier) (Alavi 2026) Protocol: Spliceogenic versus benign classification on an independent 65-gene set with OPA1-derived thresholds (Alavi Table IV) Dataset: Multi-gene spliceogenic test set (76 spliceogenic, 107 benign, 65 genes) 0 (0.0 %) False positive rate (type I error: false positives as a share of the benign set)percent · lower
Uncertainty: Not reported by the source
Coverage: Not reported scored / Not reported eligible
Independent external evaluation · Source checked Evidence concern: excluded from comparisons The AlphaGenome rows of Tables III, IV and the extended OPA1 positive calls come from scripts that pass a 0-based position to AlphaGenome's 1-based genome.Variant, so each variant was applied one base from its true position. The author labelled the report a bug on 2026-10-20 and said rerunning with the 1-based position substantially improved accuracy. The AlphaGenome results are disputed until the rerun is published; the other models' rows are not affected.Probing Genomic Foundation Models with Splice-Variant Perturbations (Alavi, bioRxiv 2026) · Table III and Table IV, rows 'ALPHAGENOME (SPLICE SCORER)', 'ALPHAGENOME (JUNCTION SCORER)' and 'ALPHAGENOME (EITHER MODULE)'; scripts 2c8_alphagenome_splicescorer.py lines 98 and 120 and 2c8_alphagenome_junctionscorer.py lines 89 and 110 at commit 3c0c6cc; https://github.com/marcel-2c8/Probing-genomic-foundation-models-2026/issues/2
Methods, coverage and source Evo2 40B (human identifier) on Multi-gene spliceogenic test set (76 spliceogenic, 107 benign, 65 genes)
rna-splicing-20261011-alavi2026-protocol-multigene
Aggregation: Not reported
Probing Genomic Foundation Models with Splice-Variant Perturbations (Alavi, bioRxiv 2026) · Table IV, row 'EVO2 40B (HU. IDENT.)', column 'Type I error' (PDF page 9 of 11) Configuration: Evo2 40B (human identifier) (Alavi 2026) Protocol: Spliceogenic versus benign classification on an independent 65-gene set with OPA1-derived thresholds (Alavi Table IV) Dataset: Multi-gene spliceogenic test set (76 spliceogenic, 107 benign, 65 genes) 22 (28.9%) Proportion (type II error: false negatives as a share of the splicing set (false-negative rate))percent · lower
Uncertainty: Not reported by the source
Coverage: Not reported scored / Not reported eligible
Independent external evaluation · Source checked Evidence concern: excluded from comparisons The AlphaGenome rows of Tables III, IV and the extended OPA1 positive calls come from scripts that pass a 0-based position to AlphaGenome's 1-based genome.Variant, so each variant was applied one base from its true position. The author labelled the report a bug on 2026-10-20 and said rerunning with the 1-based position substantially improved accuracy. The AlphaGenome results are disputed until the rerun is published; the other models' rows are not affected.Probing Genomic Foundation Models with Splice-Variant Perturbations (Alavi, bioRxiv 2026) · Table III and Table IV, rows 'ALPHAGENOME (SPLICE SCORER)', 'ALPHAGENOME (JUNCTION SCORER)' and 'ALPHAGENOME (EITHER MODULE)'; scripts 2c8_alphagenome_splicescorer.py lines 98 and 120 and 2c8_alphagenome_junctionscorer.py lines 89 and 110 at commit 3c0c6cc; https://github.com/marcel-2c8/Probing-genomic-foundation-models-2026/issues/2
Methods, coverage and source Evo2 40B (human identifier) on Multi-gene spliceogenic test set (76 spliceogenic, 107 benign, 65 genes)
rna-splicing-20261011-alavi2026-protocol-multigene
Aggregation: Not reported
Probing Genomic Foundation Models with Splice-Variant Perturbations (Alavi, bioRxiv 2026) · Table IV, row 'EVO2 40B (HU. IDENT.)', column 'Type II error' (PDF page 9 of 11) Configuration: Evo2 40B (without human identifier) (Alavi 2026) Protocol: Spliceogenic versus benign classification on an independent 65-gene set with OPA1-derived thresholds (Alavi Table IV) Dataset: Multi-gene spliceogenic test set (76 spliceogenic, 107 benign, 65 genes) 85.2% Accuracypercent · higher
Uncertainty: Not reported by the source
Coverage: Not reported scored / Not reported eligible
Independent external evaluation · Source checked Evidence concern: excluded from comparisons The AlphaGenome rows of Tables III, IV and the extended OPA1 positive calls come from scripts that pass a 0-based position to AlphaGenome's 1-based genome.Variant, so each variant was applied one base from its true position. The author labelled the report a bug on 2026-10-20 and said rerunning with the 1-based position substantially improved accuracy. The AlphaGenome results are disputed until the rerun is published; the other models' rows are not affected.Probing Genomic Foundation Models with Splice-Variant Perturbations (Alavi, bioRxiv 2026) · Table III and Table IV, rows 'ALPHAGENOME (SPLICE SCORER)', 'ALPHAGENOME (JUNCTION SCORER)' and 'ALPHAGENOME (EITHER MODULE)'; scripts 2c8_alphagenome_splicescorer.py lines 98 and 120 and 2c8_alphagenome_junctionscorer.py lines 89 and 110 at commit 3c0c6cc; https://github.com/marcel-2c8/Probing-genomic-foundation-models-2026/issues/2
Methods, coverage and source Evo2 40B (without human identifier) on Multi-gene spliceogenic test set (76 spliceogenic, 107 benign, 65 genes)
rna-splicing-20261011-alavi2026-protocol-multigene
Aggregation: Not reported
Probing Genomic Foundation Models with Splice-Variant Perturbations (Alavi, bioRxiv 2026) · Table IV, row 'EVO2 40B (W/O HU. IDENT.)', column 'Accuracy' (PDF page 9 of 11) Configuration: Evo2 40B (without human identifier) (Alavi 2026) Protocol: Spliceogenic versus benign classification on an independent 65-gene set with OPA1-derived thresholds (Alavi Table IV) Dataset: Multi-gene spliceogenic test set (76 spliceogenic, 107 benign, 65 genes) 100% Precisionpercent · higher
Uncertainty: Not reported by the source
Coverage: Not reported scored / Not reported eligible
Independent external evaluation · Source checked Evidence concern: excluded from comparisons The AlphaGenome rows of Tables III, IV and the extended OPA1 positive calls come from scripts that pass a 0-based position to AlphaGenome's 1-based genome.Variant, so each variant was applied one base from its true position. The author labelled the report a bug on 2026-10-20 and said rerunning with the 1-based position substantially improved accuracy. The AlphaGenome results are disputed until the rerun is published; the other models' rows are not affected.Probing Genomic Foundation Models with Splice-Variant Perturbations (Alavi, bioRxiv 2026) · Table III and Table IV, rows 'ALPHAGENOME (SPLICE SCORER)', 'ALPHAGENOME (JUNCTION SCORER)' and 'ALPHAGENOME (EITHER MODULE)'; scripts 2c8_alphagenome_splicescorer.py lines 98 and 120 and 2c8_alphagenome_junctionscorer.py lines 89 and 110 at commit 3c0c6cc; https://github.com/marcel-2c8/Probing-genomic-foundation-models-2026/issues/2
Methods, coverage and source Evo2 40B (without human identifier) on Multi-gene spliceogenic test set (76 spliceogenic, 107 benign, 65 genes)
rna-splicing-20261011-alavi2026-protocol-multigene
Aggregation: Not reported
Probing Genomic Foundation Models with Splice-Variant Perturbations (Alavi, bioRxiv 2026) · Table IV, row 'EVO2 40B (W/O HU. IDENT.)', column 'PPV' (PDF page 9 of 11) Configuration: Evo2 40B (without human identifier) (Alavi 2026) Protocol: Spliceogenic versus benign classification on an independent 65-gene set with OPA1-derived thresholds (Alavi Table IV) Dataset: Multi-gene spliceogenic test set (76 spliceogenic, 107 benign, 65 genes) 49 (64.5%) Recallpercent · higher
Uncertainty: Not reported by the source
Coverage: Not reported scored / Not reported eligible
Independent external evaluation · Source checked Evidence concern: excluded from comparisons The AlphaGenome rows of Tables III, IV and the extended OPA1 positive calls come from scripts that pass a 0-based position to AlphaGenome's 1-based genome.Variant, so each variant was applied one base from its true position. The author labelled the report a bug on 2026-10-20 and said rerunning with the 1-based position substantially improved accuracy. The AlphaGenome results are disputed until the rerun is published; the other models' rows are not affected.Probing Genomic Foundation Models with Splice-Variant Perturbations (Alavi, bioRxiv 2026) · Table III and Table IV, rows 'ALPHAGENOME (SPLICE SCORER)', 'ALPHAGENOME (JUNCTION SCORER)' and 'ALPHAGENOME (EITHER MODULE)'; scripts 2c8_alphagenome_splicescorer.py lines 98 and 120 and 2c8_alphagenome_junctionscorer.py lines 89 and 110 at commit 3c0c6cc; https://github.com/marcel-2c8/Probing-genomic-foundation-models-2026/issues/2
Methods, coverage and source Evo2 40B (without human identifier) on Multi-gene spliceogenic test set (76 spliceogenic, 107 benign, 65 genes)
rna-splicing-20261011-alavi2026-protocol-multigene
Aggregation: Not reported
Probing Genomic Foundation Models with Splice-Variant Perturbations (Alavi, bioRxiv 2026) · Table IV, row 'EVO2 40B (W/O HU. IDENT.)', column 'Sensitivity' (PDF page 9 of 11) Configuration: Evo2 40B (without human identifier) (Alavi 2026) Protocol: Spliceogenic versus benign classification on an independent 65-gene set with OPA1-derived thresholds (Alavi Table IV) Dataset: Multi-gene spliceogenic test set (76 spliceogenic, 107 benign, 65 genes) 107 (100%) Specificitypercent · higher
Uncertainty: Not reported by the source
Coverage: Not reported scored / Not reported eligible
Independent external evaluation · Source checked Evidence concern: excluded from comparisons The AlphaGenome rows of Tables III, IV and the extended OPA1 positive calls come from scripts that pass a 0-based position to AlphaGenome's 1-based genome.Variant, so each variant was applied one base from its true position. The author labelled the report a bug on 2026-10-20 and said rerunning with the 1-based position substantially improved accuracy. The AlphaGenome results are disputed until the rerun is published; the other models' rows are not affected.Probing Genomic Foundation Models with Splice-Variant Perturbations (Alavi, bioRxiv 2026) · Table III and Table IV, rows 'ALPHAGENOME (SPLICE SCORER)', 'ALPHAGENOME (JUNCTION SCORER)' and 'ALPHAGENOME (EITHER MODULE)'; scripts 2c8_alphagenome_splicescorer.py lines 98 and 120 and 2c8_alphagenome_junctionscorer.py lines 89 and 110 at commit 3c0c6cc; https://github.com/marcel-2c8/Probing-genomic-foundation-models-2026/issues/2
Methods, coverage and source Evo2 40B (without human identifier) on Multi-gene spliceogenic test set (76 spliceogenic, 107 benign, 65 genes)
rna-splicing-20261011-alavi2026-protocol-multigene
Aggregation: Not reported
Probing Genomic Foundation Models with Splice-Variant Perturbations (Alavi, bioRxiv 2026) · Table IV, row 'EVO2 40B (W/O HU. IDENT.)', column 'Specificity' (PDF page 9 of 11) Configuration: Evo2 40B (without human identifier) (Alavi 2026) Protocol: Spliceogenic versus benign classification on an independent 65-gene set with OPA1-derived thresholds (Alavi Table IV) Dataset: Multi-gene spliceogenic test set (76 spliceogenic, 107 benign, 65 genes) 0 (0.0 %) False positive rate (type I error: false positives as a share of the benign set)percent · lower
Uncertainty: Not reported by the source
Coverage: Not reported scored / Not reported eligible
Independent external evaluation · Source checked Evidence concern: excluded from comparisons The AlphaGenome rows of Tables III, IV and the extended OPA1 positive calls come from scripts that pass a 0-based position to AlphaGenome's 1-based genome.Variant, so each variant was applied one base from its true position. The author labelled the report a bug on 2026-10-20 and said rerunning with the 1-based position substantially improved accuracy. The AlphaGenome results are disputed until the rerun is published; the other models' rows are not affected.Probing Genomic Foundation Models with Splice-Variant Perturbations (Alavi, bioRxiv 2026) · Table III and Table IV, rows 'ALPHAGENOME (SPLICE SCORER)', 'ALPHAGENOME (JUNCTION SCORER)' and 'ALPHAGENOME (EITHER MODULE)'; scripts 2c8_alphagenome_splicescorer.py lines 98 and 120 and 2c8_alphagenome_junctionscorer.py lines 89 and 110 at commit 3c0c6cc; https://github.com/marcel-2c8/Probing-genomic-foundation-models-2026/issues/2
Methods, coverage and source Evo2 40B (without human identifier) on Multi-gene spliceogenic test set (76 spliceogenic, 107 benign, 65 genes)
rna-splicing-20261011-alavi2026-protocol-multigene
Aggregation: Not reported
Probing Genomic Foundation Models with Splice-Variant Perturbations (Alavi, bioRxiv 2026) · Table IV, row 'EVO2 40B (W/O HU. IDENT.)', column 'Type I error' (PDF page 9 of 11) Configuration: Evo2 40B (without human identifier) (Alavi 2026) Protocol: Spliceogenic versus benign classification on an independent 65-gene set with OPA1-derived thresholds (Alavi Table IV) Dataset: Multi-gene spliceogenic test set (76 spliceogenic, 107 benign, 65 genes) 27 (35.5%) Proportion (type II error: false negatives as a share of the splicing set (false-negative rate))percent · lower
Uncertainty: Not reported by the source
Coverage: Not reported scored / Not reported eligible
Independent external evaluation · Source checked Evidence concern: excluded from comparisons The AlphaGenome rows of Tables III, IV and the extended OPA1 positive calls come from scripts that pass a 0-based position to AlphaGenome's 1-based genome.Variant, so each variant was applied one base from its true position. The author labelled the report a bug on 2026-10-20 and said rerunning with the 1-based position substantially improved accuracy. The AlphaGenome results are disputed until the rerun is published; the other models' rows are not affected.Probing Genomic Foundation Models with Splice-Variant Perturbations (Alavi, bioRxiv 2026) · Table III and Table IV, rows 'ALPHAGENOME (SPLICE SCORER)', 'ALPHAGENOME (JUNCTION SCORER)' and 'ALPHAGENOME (EITHER MODULE)'; scripts 2c8_alphagenome_splicescorer.py lines 98 and 120 and 2c8_alphagenome_junctionscorer.py lines 89 and 110 at commit 3c0c6cc; https://github.com/marcel-2c8/Probing-genomic-foundation-models-2026/issues/2
Methods, coverage and source Evo2 40B (without human identifier) on Multi-gene spliceogenic test set (76 spliceogenic, 107 benign, 65 genes)
rna-splicing-20261011-alavi2026-protocol-multigene
Aggregation: Not reported
Probing Genomic Foundation Models with Splice-Variant Perturbations (Alavi, bioRxiv 2026) · Table IV, row 'EVO2 40B (W/O HU. IDENT.)', column 'Type II error' (PDF page 9 of 11) Configuration: Genos 10B (Alavi 2026) Protocol: Spliceogenic versus benign classification on an independent 65-gene set with OPA1-derived thresholds (Alavi Table IV) Dataset: Multi-gene spliceogenic test set (76 spliceogenic, 107 benign, 65 genes) 61.7% Accuracypercent · higher
Uncertainty: Not reported by the source
Coverage: Not reported scored / Not reported eligible
Independent external evaluation · Source checked Evidence concern: excluded from comparisons The AlphaGenome rows of Tables III, IV and the extended OPA1 positive calls come from scripts that pass a 0-based position to AlphaGenome's 1-based genome.Variant, so each variant was applied one base from its true position. The author labelled the report a bug on 2026-10-20 and said rerunning with the 1-based position substantially improved accuracy. The AlphaGenome results are disputed until the rerun is published; the other models' rows are not affected.Probing Genomic Foundation Models with Splice-Variant Perturbations (Alavi, bioRxiv 2026) · Table III and Table IV, rows 'ALPHAGENOME (SPLICE SCORER)', 'ALPHAGENOME (JUNCTION SCORER)' and 'ALPHAGENOME (EITHER MODULE)'; scripts 2c8_alphagenome_splicescorer.py lines 98 and 120 and 2c8_alphagenome_junctionscorer.py lines 89 and 110 at commit 3c0c6cc; https://github.com/marcel-2c8/Probing-genomic-foundation-models-2026/issues/2
Methods, coverage and source Genos 10B on Multi-gene spliceogenic test set (76 spliceogenic, 107 benign, 65 genes)
rna-splicing-20261011-alavi2026-protocol-multigene
Aggregation: Not reported
Probing Genomic Foundation Models with Splice-Variant Perturbations (Alavi, bioRxiv 2026) · Table IV, row 'GENOS 10B', column 'Accuracy' (PDF page 9 of 11)