Protocol

Zero-shot ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs classification (Evo 2 paper, Supplementary Data 1)

Zero-shot classification of pathogenic/likely pathogenic versus benign/likely benign variants in the ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs stratum, AUROC and AUPRC.

13 evaluations · 26 results

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.

13 recorded evaluations, 26 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

13 evaluations · 26 results. Different protocols are not a single leaderboard.

Protocol: Zero-shot ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs classification (Evo 2 paper, Supplementary Data 1) · Dataset: ClinVar October 2024 release, filtered (Brixi et al. 2026)

Sorted by AUPRC (zero-shot; ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs) (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	AUPRC (zero-shot; ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs)	AUROC (zero-shot; ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs)
CADD (Evo 2 paper variant effect evaluations)Evaluation	0.541 (best in column)	0.92 (best in column)
GPN-MSA (Evo 2 paper variant effect evaluations)Evaluation	0.36	0.915
Evo 2 7B (Evo 2 paper variant effect evaluations)Evaluation	0.353	0.881
PhyloP 100 (Evo 2 paper variant effect evaluations)Evaluation	0.341	0.876
Evo 2 40B (Evo 2 paper variant effect evaluations)Evaluation	0.311	0.92
Evo 2 40B base (Evo 2 paper variant effect evaluations)Evaluation	0.283	0.899
Evo 2 7B base (Evo 2 paper variant effect evaluations)Evaluation	0.277	0.889
PhyloP 447 (Evo 2 paper variant effect evaluations)Evaluation	0.269	0.883
PhyloP 470 (Evo 2 paper variant effect evaluations)Evaluation	0.262	0.886
PhyloP 241 (Evo 2 paper variant effect evaluations)Evaluation	0.214	0.897
Evo 1 (Evo 2 paper variant effect evaluations)Evaluation	0.016	0.548
NT (Evo 2 paper variant effect evaluations)Evaluation	0.005	0.52
RNA-FM (Evo 2 paper variant effect evaluations)Evaluation	0.004	0.536

All 26 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: CADD (Evo 2 paper variant effect evaluations)	Protocol: Zero-shot ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs classification (Evo 2 paper, Supplementary Data 1) Dataset: ClinVar October 2024 release, filtered (Brixi et al. 2026)	0.541 AUPRC (zero-shot; ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source CADD on ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs (Evo 2 paper) gfm-guides-20261014-evo2-brixi2026-protocol-clinvar-low-spliceai-pangolin-scores-snv Aggregation: Not reported Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026) · Supplementary Data 1 (sheet 'Sheet1') cell J664, row 664: Model 'CADD', Data 'ClinVar', Genomic_Feature 'Low SpliceAI/Pangolin scores', Variant_Type 'SNV', Sub_category '', column 'AUPRC'
Configuration: CADD (Evo 2 paper variant effect evaluations)	Protocol: Zero-shot ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs classification (Evo 2 paper, Supplementary Data 1) Dataset: ClinVar October 2024 release, filtered (Brixi et al. 2026)	0.92 AUROC (zero-shot; ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source CADD on ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs (Evo 2 paper) gfm-guides-20261014-evo2-brixi2026-protocol-clinvar-low-spliceai-pangolin-scores-snv Aggregation: Not reported Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026) · Supplementary Data 1 (sheet 'Sheet1') cell I664, row 664: Model 'CADD', Data 'ClinVar', Genomic_Feature 'Low SpliceAI/Pangolin scores', Variant_Type 'SNV', Sub_category '', column 'AUROC'
Configuration: Evo 1 (Evo 2 paper variant effect evaluations)	Protocol: Zero-shot ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs classification (Evo 2 paper, Supplementary Data 1) Dataset: ClinVar October 2024 release, filtered (Brixi et al. 2026)	0.016 AUPRC (zero-shot; ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Evo 1 on ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs (Evo 2 paper) gfm-guides-20261014-evo2-brixi2026-protocol-clinvar-low-spliceai-pangolin-scores-snv Aggregation: Not reported Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026) · Supplementary Data 1 (sheet 'Sheet1') cell J674, row 674: Model 'Evo 1', Data 'ClinVar', Genomic_Feature 'Low SpliceAI/Pangolin scores', Variant_Type 'SNV', Sub_category '', column 'AUPRC'
Configuration: Evo 1 (Evo 2 paper variant effect evaluations)	Protocol: Zero-shot ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs classification (Evo 2 paper, Supplementary Data 1) Dataset: ClinVar October 2024 release, filtered (Brixi et al. 2026)	0.548 AUROC (zero-shot; ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Evo 1 on ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs (Evo 2 paper) gfm-guides-20261014-evo2-brixi2026-protocol-clinvar-low-spliceai-pangolin-scores-snv Aggregation: Not reported Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026) · Supplementary Data 1 (sheet 'Sheet1') cell I674, row 674: Model 'Evo 1', Data 'ClinVar', Genomic_Feature 'Low SpliceAI/Pangolin scores', Variant_Type 'SNV', Sub_category '', column 'AUROC'
Configuration: Evo 2 40B base (Evo 2 paper variant effect evaluations)	Protocol: Zero-shot ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs classification (Evo 2 paper, Supplementary Data 1) Dataset: ClinVar October 2024 release, filtered (Brixi et al. 2026)	0.283 AUPRC (zero-shot; ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Evo 2 40B base on ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs (Evo 2 paper) gfm-guides-20261014-evo2-brixi2026-protocol-clinvar-low-spliceai-pangolin-scores-snv Aggregation: Not reported Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026) · Supplementary Data 1 (sheet 'Sheet1') cell J667, row 667: Model 'Evo 2 40B base', Data 'ClinVar', Genomic_Feature 'Low SpliceAI/Pangolin scores', Variant_Type 'SNV', Sub_category '', column 'AUPRC'
Configuration: Evo 2 40B base (Evo 2 paper variant effect evaluations)	Protocol: Zero-shot ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs classification (Evo 2 paper, Supplementary Data 1) Dataset: ClinVar October 2024 release, filtered (Brixi et al. 2026)	0.899 AUROC (zero-shot; ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Evo 2 40B base on ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs (Evo 2 paper) gfm-guides-20261014-evo2-brixi2026-protocol-clinvar-low-spliceai-pangolin-scores-snv Aggregation: Not reported Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026) · Supplementary Data 1 (sheet 'Sheet1') cell I667, row 667: Model 'Evo 2 40B base', Data 'ClinVar', Genomic_Feature 'Low SpliceAI/Pangolin scores', Variant_Type 'SNV', Sub_category '', column 'AUROC'
Configuration: Evo 2 40B (Evo 2 paper variant effect evaluations)	Protocol: Zero-shot ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs classification (Evo 2 paper, Supplementary Data 1) Dataset: ClinVar October 2024 release, filtered (Brixi et al. 2026)	0.311 AUPRC (zero-shot; ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Evo 2 40B on ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs (Evo 2 paper) gfm-guides-20261014-evo2-brixi2026-protocol-clinvar-low-spliceai-pangolin-scores-snv Aggregation: Not reported Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026) · Supplementary Data 1 (sheet 'Sheet1') cell J665, row 665: Model 'Evo 2 40B', Data 'ClinVar', Genomic_Feature 'Low SpliceAI/Pangolin scores', Variant_Type 'SNV', Sub_category '', column 'AUPRC'
Configuration: Evo 2 40B (Evo 2 paper variant effect evaluations)	Protocol: Zero-shot ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs classification (Evo 2 paper, Supplementary Data 1) Dataset: ClinVar October 2024 release, filtered (Brixi et al. 2026)	0.92 AUROC (zero-shot; ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Evo 2 40B on ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs (Evo 2 paper) gfm-guides-20261014-evo2-brixi2026-protocol-clinvar-low-spliceai-pangolin-scores-snv Aggregation: Not reported Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026) · Supplementary Data 1 (sheet 'Sheet1') cell I665, row 665: Model 'Evo 2 40B', Data 'ClinVar', Genomic_Feature 'Low SpliceAI/Pangolin scores', Variant_Type 'SNV', Sub_category '', column 'AUROC'
Configuration: Evo 2 7B base (Evo 2 paper variant effect evaluations)	Protocol: Zero-shot ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs classification (Evo 2 paper, Supplementary Data 1) Dataset: ClinVar October 2024 release, filtered (Brixi et al. 2026)	0.277 AUPRC (zero-shot; ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Evo 2 7B base on ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs (Evo 2 paper) gfm-guides-20261014-evo2-brixi2026-protocol-clinvar-low-spliceai-pangolin-scores-snv Aggregation: Not reported Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026) · Supplementary Data 1 (sheet 'Sheet1') cell J669, row 669: Model 'Evo 2 7B base', Data 'ClinVar', Genomic_Feature 'Low SpliceAI/Pangolin scores', Variant_Type 'SNV', Sub_category '', column 'AUPRC'
Configuration: Evo 2 7B base (Evo 2 paper variant effect evaluations)	Protocol: Zero-shot ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs classification (Evo 2 paper, Supplementary Data 1) Dataset: ClinVar October 2024 release, filtered (Brixi et al. 2026)	0.889 AUROC (zero-shot; ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Evo 2 7B base on ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs (Evo 2 paper) gfm-guides-20261014-evo2-brixi2026-protocol-clinvar-low-spliceai-pangolin-scores-snv Aggregation: Not reported Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026) · Supplementary Data 1 (sheet 'Sheet1') cell I669, row 669: Model 'Evo 2 7B base', Data 'ClinVar', Genomic_Feature 'Low SpliceAI/Pangolin scores', Variant_Type 'SNV', Sub_category '', column 'AUROC'
Configuration: Evo 2 7B (Evo 2 paper variant effect evaluations)	Protocol: Zero-shot ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs classification (Evo 2 paper, Supplementary Data 1) Dataset: ClinVar October 2024 release, filtered (Brixi et al. 2026)	0.353 AUPRC (zero-shot; ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Evo 2 7B on ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs (Evo 2 paper) gfm-guides-20261014-evo2-brixi2026-protocol-clinvar-low-spliceai-pangolin-scores-snv Aggregation: Not reported Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026) · Supplementary Data 1 (sheet 'Sheet1') cell J672, row 672: Model 'Evo 2 7B', Data 'ClinVar', Genomic_Feature 'Low SpliceAI/Pangolin scores', Variant_Type 'SNV', Sub_category '', column 'AUPRC'
Configuration: Evo 2 7B (Evo 2 paper variant effect evaluations)	Protocol: Zero-shot ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs classification (Evo 2 paper, Supplementary Data 1) Dataset: ClinVar October 2024 release, filtered (Brixi et al. 2026)	0.881 AUROC (zero-shot; ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Evo 2 7B on ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs (Evo 2 paper) gfm-guides-20261014-evo2-brixi2026-protocol-clinvar-low-spliceai-pangolin-scores-snv Aggregation: Not reported Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026) · Supplementary Data 1 (sheet 'Sheet1') cell I672, row 672: Model 'Evo 2 7B', Data 'ClinVar', Genomic_Feature 'Low SpliceAI/Pangolin scores', Variant_Type 'SNV', Sub_category '', column 'AUROC'
Configuration: GPN-MSA (Evo 2 paper variant effect evaluations)	Protocol: Zero-shot ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs classification (Evo 2 paper, Supplementary Data 1) Dataset: ClinVar October 2024 release, filtered (Brixi et al. 2026)	0.36 AUPRC (zero-shot; ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source GPN-MSA on ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs (Evo 2 paper) gfm-guides-20261014-evo2-brixi2026-protocol-clinvar-low-spliceai-pangolin-scores-snv Aggregation: Not reported Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026) · Supplementary Data 1 (sheet 'Sheet1') cell J666, row 666: Model 'GPN-MSA', Data 'ClinVar', Genomic_Feature 'Low SpliceAI/Pangolin scores', Variant_Type 'SNV', Sub_category '', column 'AUPRC'
Configuration: GPN-MSA (Evo 2 paper variant effect evaluations)	Protocol: Zero-shot ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs classification (Evo 2 paper, Supplementary Data 1) Dataset: ClinVar October 2024 release, filtered (Brixi et al. 2026)	0.915 AUROC (zero-shot; ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source GPN-MSA on ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs (Evo 2 paper) gfm-guides-20261014-evo2-brixi2026-protocol-clinvar-low-spliceai-pangolin-scores-snv Aggregation: Not reported Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026) · Supplementary Data 1 (sheet 'Sheet1') cell I666, row 666: Model 'GPN-MSA', Data 'ClinVar', Genomic_Feature 'Low SpliceAI/Pangolin scores', Variant_Type 'SNV', Sub_category '', column 'AUROC'
Configuration: NT (Evo 2 paper variant effect evaluations)	Protocol: Zero-shot ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs classification (Evo 2 paper, Supplementary Data 1) Dataset: ClinVar October 2024 release, filtered (Brixi et al. 2026)	0.005 AUPRC (zero-shot; ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source NT on ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs (Evo 2 paper) gfm-guides-20261014-evo2-brixi2026-protocol-clinvar-low-spliceai-pangolin-scores-snv Aggregation: Not reported Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026) · Supplementary Data 1 (sheet 'Sheet1') cell J676, row 676: Model 'NT', Data 'ClinVar', Genomic_Feature 'Low SpliceAI/Pangolin scores', Variant_Type 'SNV', Sub_category '', column 'AUPRC'
Configuration: NT (Evo 2 paper variant effect evaluations)	Protocol: Zero-shot ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs classification (Evo 2 paper, Supplementary Data 1) Dataset: ClinVar October 2024 release, filtered (Brixi et al. 2026)	0.52 AUROC (zero-shot; ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source NT on ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs (Evo 2 paper) gfm-guides-20261014-evo2-brixi2026-protocol-clinvar-low-spliceai-pangolin-scores-snv Aggregation: Not reported Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026) · Supplementary Data 1 (sheet 'Sheet1') cell I676, row 676: Model 'NT', Data 'ClinVar', Genomic_Feature 'Low SpliceAI/Pangolin scores', Variant_Type 'SNV', Sub_category '', column 'AUROC'
Configuration: PhyloP 100 (Evo 2 paper variant effect evaluations)	Protocol: Zero-shot ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs classification (Evo 2 paper, Supplementary Data 1) Dataset: ClinVar October 2024 release, filtered (Brixi et al. 2026)	0.341 AUPRC (zero-shot; ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source PhyloP 100 on ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs (Evo 2 paper) gfm-guides-20261014-evo2-brixi2026-protocol-clinvar-low-spliceai-pangolin-scores-snv Aggregation: Not reported Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026) · Supplementary Data 1 (sheet 'Sheet1') cell J673, row 673: Model 'PhyloP 100', Data 'ClinVar', Genomic_Feature 'Low SpliceAI/Pangolin scores', Variant_Type 'SNV', Sub_category '', column 'AUPRC'
Configuration: PhyloP 100 (Evo 2 paper variant effect evaluations)	Protocol: Zero-shot ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs classification (Evo 2 paper, Supplementary Data 1) Dataset: ClinVar October 2024 release, filtered (Brixi et al. 2026)	0.876 AUROC (zero-shot; ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source PhyloP 100 on ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs (Evo 2 paper) gfm-guides-20261014-evo2-brixi2026-protocol-clinvar-low-spliceai-pangolin-scores-snv Aggregation: Not reported Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026) · Supplementary Data 1 (sheet 'Sheet1') cell I673, row 673: Model 'PhyloP 100', Data 'ClinVar', Genomic_Feature 'Low SpliceAI/Pangolin scores', Variant_Type 'SNV', Sub_category '', column 'AUROC'
Configuration: PhyloP 241 (Evo 2 paper variant effect evaluations)	Protocol: Zero-shot ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs classification (Evo 2 paper, Supplementary Data 1) Dataset: ClinVar October 2024 release, filtered (Brixi et al. 2026)	0.214 AUPRC (zero-shot; ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source PhyloP 241 on ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs (Evo 2 paper) gfm-guides-20261014-evo2-brixi2026-protocol-clinvar-low-spliceai-pangolin-scores-snv Aggregation: Not reported Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026) · Supplementary Data 1 (sheet 'Sheet1') cell J668, row 668: Model 'PhyloP 241', Data 'ClinVar', Genomic_Feature 'Low SpliceAI/Pangolin scores', Variant_Type 'SNV', Sub_category '', column 'AUPRC'
Configuration: PhyloP 241 (Evo 2 paper variant effect evaluations)	Protocol: Zero-shot ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs classification (Evo 2 paper, Supplementary Data 1) Dataset: ClinVar October 2024 release, filtered (Brixi et al. 2026)	0.897 AUROC (zero-shot; ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source PhyloP 241 on ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs (Evo 2 paper) gfm-guides-20261014-evo2-brixi2026-protocol-clinvar-low-spliceai-pangolin-scores-snv Aggregation: Not reported Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026) · Supplementary Data 1 (sheet 'Sheet1') cell I668, row 668: Model 'PhyloP 241', Data 'ClinVar', Genomic_Feature 'Low SpliceAI/Pangolin scores', Variant_Type 'SNV', Sub_category '', column 'AUROC'
Configuration: PhyloP 447 (Evo 2 paper variant effect evaluations)	Protocol: Zero-shot ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs classification (Evo 2 paper, Supplementary Data 1) Dataset: ClinVar October 2024 release, filtered (Brixi et al. 2026)	0.269 AUPRC (zero-shot; ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source PhyloP 447 on ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs (Evo 2 paper) gfm-guides-20261014-evo2-brixi2026-protocol-clinvar-low-spliceai-pangolin-scores-snv Aggregation: Not reported Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026) · Supplementary Data 1 (sheet 'Sheet1') cell J671, row 671: Model 'PhyloP 447', Data 'ClinVar', Genomic_Feature 'Low SpliceAI/Pangolin scores', Variant_Type 'SNV', Sub_category '', column 'AUPRC'
Configuration: PhyloP 447 (Evo 2 paper variant effect evaluations)	Protocol: Zero-shot ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs classification (Evo 2 paper, Supplementary Data 1) Dataset: ClinVar October 2024 release, filtered (Brixi et al. 2026)	0.883 AUROC (zero-shot; ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source PhyloP 447 on ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs (Evo 2 paper) gfm-guides-20261014-evo2-brixi2026-protocol-clinvar-low-spliceai-pangolin-scores-snv Aggregation: Not reported Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026) · Supplementary Data 1 (sheet 'Sheet1') cell I671, row 671: Model 'PhyloP 447', Data 'ClinVar', Genomic_Feature 'Low SpliceAI/Pangolin scores', Variant_Type 'SNV', Sub_category '', column 'AUROC'
Configuration: PhyloP 470 (Evo 2 paper variant effect evaluations)	Protocol: Zero-shot ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs classification (Evo 2 paper, Supplementary Data 1) Dataset: ClinVar October 2024 release, filtered (Brixi et al. 2026)	0.262 AUPRC (zero-shot; ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source PhyloP 470 on ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs (Evo 2 paper) gfm-guides-20261014-evo2-brixi2026-protocol-clinvar-low-spliceai-pangolin-scores-snv Aggregation: Not reported Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026) · Supplementary Data 1 (sheet 'Sheet1') cell J670, row 670: Model 'PhyloP 470', Data 'ClinVar', Genomic_Feature 'Low SpliceAI/Pangolin scores', Variant_Type 'SNV', Sub_category '', column 'AUPRC'
Configuration: PhyloP 470 (Evo 2 paper variant effect evaluations)	Protocol: Zero-shot ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs classification (Evo 2 paper, Supplementary Data 1) Dataset: ClinVar October 2024 release, filtered (Brixi et al. 2026)	0.886 AUROC (zero-shot; ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source PhyloP 470 on ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs (Evo 2 paper) gfm-guides-20261014-evo2-brixi2026-protocol-clinvar-low-spliceai-pangolin-scores-snv Aggregation: Not reported Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026) · Supplementary Data 1 (sheet 'Sheet1') cell I670, row 670: Model 'PhyloP 470', Data 'ClinVar', Genomic_Feature 'Low SpliceAI/Pangolin scores', Variant_Type 'SNV', Sub_category '', column 'AUROC'
Configuration: RNA-FM (Evo 2 paper variant effect evaluations)	Protocol: Zero-shot ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs classification (Evo 2 paper, Supplementary Data 1) Dataset: ClinVar October 2024 release, filtered (Brixi et al. 2026)	0.004 AUPRC (zero-shot; ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source RNA-FM on ClinVar low SpliceAI and Pangolin scores (both below 0.1) SNVs (Evo 2 paper) gfm-guides-20261014-evo2-brixi2026-protocol-clinvar-low-spliceai-pangolin-scores-snv Aggregation: Not reported Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026); Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026) · Supplementary Data 1 (sheet 'Sheet1') cell J675, row 675: Model 'RNA-FM', Data 'ClinVar', Genomic_Feature 'Low SpliceAI/Pangolin scores', Variant_Type 'SNV', Sub_category '', column 'AUPRC'

Source checking is not independent reproduction. Release 2026-10-22-1b7cf027e4f6.

Methods and evaluation design

Procedure, tasks and evaluated configurations

Recorded evaluations

Each evaluation records what was tested and under which conditions.

Explore all linked results

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.

Author-reported evaluations: 13

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

Null control

Proposed control: requires review

Protocol-valid seeded random ranking; no fitting on assay labels

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

Established label-free reference with explicitly permitted sequence/MSA inputs

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 2026-10-22-1b7cf027e4f6. 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 2026-10-22-1b7cf027e4f6
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 2026-10-22-1b7cf027e4f6 · Record review: source checked

3 source records and release history

evo2: Journal full-text XML · Original source · Retrieved page snapshot; no immutable publisher revision supplied
Genome modelling and design across all domains of life with Evo 2: Supplementary Information (Nature 2026) · Original source · Nature 652 (2026), published 2026-03-04; Supplementary Information file 41586_2026_10176_MOESM1_ESM.pdf (73 pages)
Genome modelling and design across all domains of life with Evo 2: Supplementary Data 1, human variant effect prediction results (Nature 2026) · Original source · Nature 652 (2026), published 2026-03-04; Supplementary Data 1 file 41586_2026_10176_MOESM3_ESM.xlsx

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: gfm-guides-20261014-evo2-brixi2026-protocol-clinvar-low-spliceai-pangolin-scores-snv

areas: dna-genomes
contexts: research
protocol: Score each variant zero-shot (for Evo 2, the log-likelihood of the variant sequence minus that of the reference over an 8,192-bp genomic window around the variant) and compute AUROC and AUPRC for pathogenic/likely pathogenic versus benign/likely benign variants in the stratum Data 'ClinVar', Genomic_Feature 'Low SpliceAI/Pangolin scores', Variant_Type 'SNV'.
version: As published, Nature 652 (2026), Supplementary Data 1
source locator: Supplementary Data 1 rows with Data 'ClinVar', Genomic_Feature 'Low SpliceAI/Pangolin scores', Variant_Type 'SNV', Sub_category ''; SI A.3.12 and A.3.13 (page 13)
limitations: Positives: 102 pathogenic/likely pathogenic; negatives: 24146 benign/likely benign; total 24248 variants (Supplementary Data 1).; No split: every model scores the same variants zero-shot (SI A.3.12: 'For each benchmark, we score the same variants with all models').; Supervised comparators (AlphaMissense, CADD, SpliceAI, Pangolin) may have been trained on overlapping variants; training overlap is not reported.; No uncertainty is reported.

Related records

Suggest a correction