Protocol

Zero-shot ClinVar noncoding non-SNVs, highly conserved classification (Evo 2 paper, Supplementary Data 1)

Zero-shot classification of pathogenic/likely pathogenic versus benign/likely benign variants in the ClinVar noncoding non-SNVs, highly conserved stratum, AUROC and AUPRC.

12 evaluations · 24 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.

12 recorded evaluations, 24 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

12 evaluations · 24 results. Different protocols are not a single leaderboard.

Protocol: Zero-shot ClinVar noncoding non-SNVs, highly conserved classification (Evo 2 paper, Supplementary Data 1) · Dataset: ClinVar October 2024 release, filtered (Brixi et al. 2026)

Sorted by AUPRC (zero-shot; ClinVar noncoding non-SNVs, highly conserved) (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 noncoding non-SNVs, highly conserved)	AUROC (zero-shot; ClinVar noncoding non-SNVs, highly conserved)
Evo 2 40B (Evo 2 paper variant effect evaluations)Evaluation	0.974 (best in column)	0.949 (best in column)
Evo 2 40B base (Evo 2 paper variant effect evaluations)Evaluation	0.974	0.943
Evo 2 7B base (Evo 2 paper variant effect evaluations)Evaluation	0.958	0.905
Evo 2 7B (Evo 2 paper variant effect evaluations)Evaluation	0.957	0.914
Pangolin (Evo 2 paper variant effect evaluations)Evaluation	0.941	0.85
PhyloP 470 (Evo 2 paper variant effect evaluations)Evaluation	0.936	0.835
PhyloP 447 (Evo 2 paper variant effect evaluations)Evaluation	0.92	0.801
PhyloP 100 (Evo 2 paper variant effect evaluations)Evaluation	0.911	0.761
PhyloP 241 (Evo 2 paper variant effect evaluations)Evaluation	0.91	0.8
Evo 1 (Evo 2 paper variant effect evaluations)Evaluation	0.778	0.569
RNA-FM (Evo 2 paper variant effect evaluations)Evaluation	0.746	0.517
NT (Evo 2 paper variant effect evaluations)Evaluation	0.732	0.503

All 24 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: Evo 1 (Evo 2 paper variant effect evaluations)	Protocol: Zero-shot ClinVar noncoding non-SNVs, highly conserved classification (Evo 2 paper, Supplementary Data 1) Dataset: ClinVar October 2024 release, filtered (Brixi et al. 2026)	0.778 AUPRC (zero-shot; ClinVar noncoding non-SNVs, highly conserved) 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 noncoding non-SNVs, highly conserved (Evo 2 paper) gfm-guides-20261014-evo2-brixi2026-protocol-clinvar-noncoding-non-snv-highly-conserved 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 J362, row 362: Model 'Evo 1', Data 'ClinVar', Genomic_Feature 'Noncoding', Variant_Type 'non-SNV', Sub_category 'Highly conserved', column 'AUPRC'
Configuration: Evo 1 (Evo 2 paper variant effect evaluations)	Protocol: Zero-shot ClinVar noncoding non-SNVs, highly conserved classification (Evo 2 paper, Supplementary Data 1) Dataset: ClinVar October 2024 release, filtered (Brixi et al. 2026)	0.569 AUROC (zero-shot; ClinVar noncoding non-SNVs, highly conserved) 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 noncoding non-SNVs, highly conserved (Evo 2 paper) gfm-guides-20261014-evo2-brixi2026-protocol-clinvar-noncoding-non-snv-highly-conserved 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 I362, row 362: Model 'Evo 1', Data 'ClinVar', Genomic_Feature 'Noncoding', Variant_Type 'non-SNV', Sub_category 'Highly conserved', column 'AUROC'
Configuration: Evo 2 40B base (Evo 2 paper variant effect evaluations)	Protocol: Zero-shot ClinVar noncoding non-SNVs, highly conserved classification (Evo 2 paper, Supplementary Data 1) Dataset: ClinVar October 2024 release, filtered (Brixi et al. 2026)	0.974 AUPRC (zero-shot; ClinVar noncoding non-SNVs, highly conserved) 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 noncoding non-SNVs, highly conserved (Evo 2 paper) gfm-guides-20261014-evo2-brixi2026-protocol-clinvar-noncoding-non-snv-highly-conserved 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 J354, row 354: Model 'Evo 2 40B base', Data 'ClinVar', Genomic_Feature 'Noncoding', Variant_Type 'non-SNV', Sub_category 'Highly conserved', column 'AUPRC'
Configuration: Evo 2 40B base (Evo 2 paper variant effect evaluations)	Protocol: Zero-shot ClinVar noncoding non-SNVs, highly conserved classification (Evo 2 paper, Supplementary Data 1) Dataset: ClinVar October 2024 release, filtered (Brixi et al. 2026)	0.943 AUROC (zero-shot; ClinVar noncoding non-SNVs, highly conserved) 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 noncoding non-SNVs, highly conserved (Evo 2 paper) gfm-guides-20261014-evo2-brixi2026-protocol-clinvar-noncoding-non-snv-highly-conserved 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 I354, row 354: Model 'Evo 2 40B base', Data 'ClinVar', Genomic_Feature 'Noncoding', Variant_Type 'non-SNV', Sub_category 'Highly conserved', column 'AUROC'
Configuration: Evo 2 40B (Evo 2 paper variant effect evaluations)	Protocol: Zero-shot ClinVar noncoding non-SNVs, highly conserved classification (Evo 2 paper, Supplementary Data 1) Dataset: ClinVar October 2024 release, filtered (Brixi et al. 2026)	0.974 AUPRC (zero-shot; ClinVar noncoding non-SNVs, highly conserved) 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 noncoding non-SNVs, highly conserved (Evo 2 paper) gfm-guides-20261014-evo2-brixi2026-protocol-clinvar-noncoding-non-snv-highly-conserved 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 J353, row 353: Model 'Evo 2 40B', Data 'ClinVar', Genomic_Feature 'Noncoding', Variant_Type 'non-SNV', Sub_category 'Highly conserved', column 'AUPRC'
Configuration: Evo 2 40B (Evo 2 paper variant effect evaluations)	Protocol: Zero-shot ClinVar noncoding non-SNVs, highly conserved classification (Evo 2 paper, Supplementary Data 1) Dataset: ClinVar October 2024 release, filtered (Brixi et al. 2026)	0.949 AUROC (zero-shot; ClinVar noncoding non-SNVs, highly conserved) 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 noncoding non-SNVs, highly conserved (Evo 2 paper) gfm-guides-20261014-evo2-brixi2026-protocol-clinvar-noncoding-non-snv-highly-conserved 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 I353, row 353: Model 'Evo 2 40B', Data 'ClinVar', Genomic_Feature 'Noncoding', Variant_Type 'non-SNV', Sub_category 'Highly conserved', column 'AUROC'
Configuration: Evo 2 7B base (Evo 2 paper variant effect evaluations)	Protocol: Zero-shot ClinVar noncoding non-SNVs, highly conserved classification (Evo 2 paper, Supplementary Data 1) Dataset: ClinVar October 2024 release, filtered (Brixi et al. 2026)	0.958 AUPRC (zero-shot; ClinVar noncoding non-SNVs, highly conserved) 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 noncoding non-SNVs, highly conserved (Evo 2 paper) gfm-guides-20261014-evo2-brixi2026-protocol-clinvar-noncoding-non-snv-highly-conserved 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 J356, row 356: Model 'Evo 2 7B base', Data 'ClinVar', Genomic_Feature 'Noncoding', Variant_Type 'non-SNV', Sub_category 'Highly conserved', column 'AUPRC'
Configuration: Evo 2 7B base (Evo 2 paper variant effect evaluations)	Protocol: Zero-shot ClinVar noncoding non-SNVs, highly conserved classification (Evo 2 paper, Supplementary Data 1) Dataset: ClinVar October 2024 release, filtered (Brixi et al. 2026)	0.905 AUROC (zero-shot; ClinVar noncoding non-SNVs, highly conserved) 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 noncoding non-SNVs, highly conserved (Evo 2 paper) gfm-guides-20261014-evo2-brixi2026-protocol-clinvar-noncoding-non-snv-highly-conserved 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 I356, row 356: Model 'Evo 2 7B base', Data 'ClinVar', Genomic_Feature 'Noncoding', Variant_Type 'non-SNV', Sub_category 'Highly conserved', column 'AUROC'
Configuration: Evo 2 7B (Evo 2 paper variant effect evaluations)	Protocol: Zero-shot ClinVar noncoding non-SNVs, highly conserved classification (Evo 2 paper, Supplementary Data 1) Dataset: ClinVar October 2024 release, filtered (Brixi et al. 2026)	0.957 AUPRC (zero-shot; ClinVar noncoding non-SNVs, highly conserved) 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 noncoding non-SNVs, highly conserved (Evo 2 paper) gfm-guides-20261014-evo2-brixi2026-protocol-clinvar-noncoding-non-snv-highly-conserved 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 J355, row 355: Model 'Evo 2 7B', Data 'ClinVar', Genomic_Feature 'Noncoding', Variant_Type 'non-SNV', Sub_category 'Highly conserved', column 'AUPRC'
Configuration: Evo 2 7B (Evo 2 paper variant effect evaluations)	Protocol: Zero-shot ClinVar noncoding non-SNVs, highly conserved classification (Evo 2 paper, Supplementary Data 1) Dataset: ClinVar October 2024 release, filtered (Brixi et al. 2026)	0.914 AUROC (zero-shot; ClinVar noncoding non-SNVs, highly conserved) 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 noncoding non-SNVs, highly conserved (Evo 2 paper) gfm-guides-20261014-evo2-brixi2026-protocol-clinvar-noncoding-non-snv-highly-conserved 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 I355, row 355: Model 'Evo 2 7B', Data 'ClinVar', Genomic_Feature 'Noncoding', Variant_Type 'non-SNV', Sub_category 'Highly conserved', column 'AUROC'
Configuration: NT (Evo 2 paper variant effect evaluations)	Protocol: Zero-shot ClinVar noncoding non-SNVs, highly conserved classification (Evo 2 paper, Supplementary Data 1) Dataset: ClinVar October 2024 release, filtered (Brixi et al. 2026)	0.732 AUPRC (zero-shot; ClinVar noncoding non-SNVs, highly conserved) 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 noncoding non-SNVs, highly conserved (Evo 2 paper) gfm-guides-20261014-evo2-brixi2026-protocol-clinvar-noncoding-non-snv-highly-conserved 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 J364, row 364: Model 'NT', Data 'ClinVar', Genomic_Feature 'Noncoding', Variant_Type 'non-SNV', Sub_category 'Highly conserved', column 'AUPRC'
Configuration: NT (Evo 2 paper variant effect evaluations)	Protocol: Zero-shot ClinVar noncoding non-SNVs, highly conserved classification (Evo 2 paper, Supplementary Data 1) Dataset: ClinVar October 2024 release, filtered (Brixi et al. 2026)	0.503 AUROC (zero-shot; ClinVar noncoding non-SNVs, highly conserved) 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 noncoding non-SNVs, highly conserved (Evo 2 paper) gfm-guides-20261014-evo2-brixi2026-protocol-clinvar-noncoding-non-snv-highly-conserved 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 I364, row 364: Model 'NT', Data 'ClinVar', Genomic_Feature 'Noncoding', Variant_Type 'non-SNV', Sub_category 'Highly conserved', column 'AUROC'
Configuration: Pangolin (Evo 2 paper variant effect evaluations)	Protocol: Zero-shot ClinVar noncoding non-SNVs, highly conserved classification (Evo 2 paper, Supplementary Data 1) Dataset: ClinVar October 2024 release, filtered (Brixi et al. 2026)	0.941 AUPRC (zero-shot; ClinVar noncoding non-SNVs, highly conserved) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Pangolin on ClinVar noncoding non-SNVs, highly conserved (Evo 2 paper) gfm-guides-20261014-evo2-brixi2026-protocol-clinvar-noncoding-non-snv-highly-conserved 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 J357, row 357: Model 'Pangolin', Data 'ClinVar', Genomic_Feature 'Noncoding', Variant_Type 'non-SNV', Sub_category 'Highly conserved', column 'AUPRC'
Configuration: Pangolin (Evo 2 paper variant effect evaluations)	Protocol: Zero-shot ClinVar noncoding non-SNVs, highly conserved classification (Evo 2 paper, Supplementary Data 1) Dataset: ClinVar October 2024 release, filtered (Brixi et al. 2026)	0.85 AUROC (zero-shot; ClinVar noncoding non-SNVs, highly conserved) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Pangolin on ClinVar noncoding non-SNVs, highly conserved (Evo 2 paper) gfm-guides-20261014-evo2-brixi2026-protocol-clinvar-noncoding-non-snv-highly-conserved 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 I357, row 357: Model 'Pangolin', Data 'ClinVar', Genomic_Feature 'Noncoding', Variant_Type 'non-SNV', Sub_category 'Highly conserved', column 'AUROC'
Configuration: PhyloP 100 (Evo 2 paper variant effect evaluations)	Protocol: Zero-shot ClinVar noncoding non-SNVs, highly conserved classification (Evo 2 paper, Supplementary Data 1) Dataset: ClinVar October 2024 release, filtered (Brixi et al. 2026)	0.911 AUPRC (zero-shot; ClinVar noncoding non-SNVs, highly conserved) 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 noncoding non-SNVs, highly conserved (Evo 2 paper) gfm-guides-20261014-evo2-brixi2026-protocol-clinvar-noncoding-non-snv-highly-conserved 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 J361, row 361: Model 'PhyloP 100', Data 'ClinVar', Genomic_Feature 'Noncoding', Variant_Type 'non-SNV', Sub_category 'Highly conserved', column 'AUPRC'
Configuration: PhyloP 100 (Evo 2 paper variant effect evaluations)	Protocol: Zero-shot ClinVar noncoding non-SNVs, highly conserved classification (Evo 2 paper, Supplementary Data 1) Dataset: ClinVar October 2024 release, filtered (Brixi et al. 2026)	0.761 AUROC (zero-shot; ClinVar noncoding non-SNVs, highly conserved) 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 noncoding non-SNVs, highly conserved (Evo 2 paper) gfm-guides-20261014-evo2-brixi2026-protocol-clinvar-noncoding-non-snv-highly-conserved 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 I361, row 361: Model 'PhyloP 100', Data 'ClinVar', Genomic_Feature 'Noncoding', Variant_Type 'non-SNV', Sub_category 'Highly conserved', column 'AUROC'
Configuration: PhyloP 241 (Evo 2 paper variant effect evaluations)	Protocol: Zero-shot ClinVar noncoding non-SNVs, highly conserved classification (Evo 2 paper, Supplementary Data 1) Dataset: ClinVar October 2024 release, filtered (Brixi et al. 2026)	0.91 AUPRC (zero-shot; ClinVar noncoding non-SNVs, highly conserved) 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 noncoding non-SNVs, highly conserved (Evo 2 paper) gfm-guides-20261014-evo2-brixi2026-protocol-clinvar-noncoding-non-snv-highly-conserved 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 J360, row 360: Model 'PhyloP 241', Data 'ClinVar', Genomic_Feature 'Noncoding', Variant_Type 'non-SNV', Sub_category 'Highly conserved', column 'AUPRC'
Configuration: PhyloP 241 (Evo 2 paper variant effect evaluations)	Protocol: Zero-shot ClinVar noncoding non-SNVs, highly conserved classification (Evo 2 paper, Supplementary Data 1) Dataset: ClinVar October 2024 release, filtered (Brixi et al. 2026)	0.8 AUROC (zero-shot; ClinVar noncoding non-SNVs, highly conserved) 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 noncoding non-SNVs, highly conserved (Evo 2 paper) gfm-guides-20261014-evo2-brixi2026-protocol-clinvar-noncoding-non-snv-highly-conserved 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 I360, row 360: Model 'PhyloP 241', Data 'ClinVar', Genomic_Feature 'Noncoding', Variant_Type 'non-SNV', Sub_category 'Highly conserved', column 'AUROC'
Configuration: PhyloP 447 (Evo 2 paper variant effect evaluations)	Protocol: Zero-shot ClinVar noncoding non-SNVs, highly conserved classification (Evo 2 paper, Supplementary Data 1) Dataset: ClinVar October 2024 release, filtered (Brixi et al. 2026)	0.92 AUPRC (zero-shot; ClinVar noncoding non-SNVs, highly conserved) 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 noncoding non-SNVs, highly conserved (Evo 2 paper) gfm-guides-20261014-evo2-brixi2026-protocol-clinvar-noncoding-non-snv-highly-conserved 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 J359, row 359: Model 'PhyloP 447', Data 'ClinVar', Genomic_Feature 'Noncoding', Variant_Type 'non-SNV', Sub_category 'Highly conserved', column 'AUPRC'
Configuration: PhyloP 447 (Evo 2 paper variant effect evaluations)	Protocol: Zero-shot ClinVar noncoding non-SNVs, highly conserved classification (Evo 2 paper, Supplementary Data 1) Dataset: ClinVar October 2024 release, filtered (Brixi et al. 2026)	0.801 AUROC (zero-shot; ClinVar noncoding non-SNVs, highly conserved) 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 noncoding non-SNVs, highly conserved (Evo 2 paper) gfm-guides-20261014-evo2-brixi2026-protocol-clinvar-noncoding-non-snv-highly-conserved 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 I359, row 359: Model 'PhyloP 447', Data 'ClinVar', Genomic_Feature 'Noncoding', Variant_Type 'non-SNV', Sub_category 'Highly conserved', column 'AUROC'
Configuration: PhyloP 470 (Evo 2 paper variant effect evaluations)	Protocol: Zero-shot ClinVar noncoding non-SNVs, highly conserved classification (Evo 2 paper, Supplementary Data 1) Dataset: ClinVar October 2024 release, filtered (Brixi et al. 2026)	0.936 AUPRC (zero-shot; ClinVar noncoding non-SNVs, highly conserved) 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 noncoding non-SNVs, highly conserved (Evo 2 paper) gfm-guides-20261014-evo2-brixi2026-protocol-clinvar-noncoding-non-snv-highly-conserved 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 J358, row 358: Model 'PhyloP 470', Data 'ClinVar', Genomic_Feature 'Noncoding', Variant_Type 'non-SNV', Sub_category 'Highly conserved', column 'AUPRC'
Configuration: PhyloP 470 (Evo 2 paper variant effect evaluations)	Protocol: Zero-shot ClinVar noncoding non-SNVs, highly conserved classification (Evo 2 paper, Supplementary Data 1) Dataset: ClinVar October 2024 release, filtered (Brixi et al. 2026)	0.835 AUROC (zero-shot; ClinVar noncoding non-SNVs, highly conserved) 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 noncoding non-SNVs, highly conserved (Evo 2 paper) gfm-guides-20261014-evo2-brixi2026-protocol-clinvar-noncoding-non-snv-highly-conserved 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 I358, row 358: Model 'PhyloP 470', Data 'ClinVar', Genomic_Feature 'Noncoding', Variant_Type 'non-SNV', Sub_category 'Highly conserved', column 'AUROC'
Configuration: RNA-FM (Evo 2 paper variant effect evaluations)	Protocol: Zero-shot ClinVar noncoding non-SNVs, highly conserved classification (Evo 2 paper, Supplementary Data 1) Dataset: ClinVar October 2024 release, filtered (Brixi et al. 2026)	0.746 AUPRC (zero-shot; ClinVar noncoding non-SNVs, highly conserved) 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 noncoding non-SNVs, highly conserved (Evo 2 paper) gfm-guides-20261014-evo2-brixi2026-protocol-clinvar-noncoding-non-snv-highly-conserved 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 J363, row 363: Model 'RNA-FM', Data 'ClinVar', Genomic_Feature 'Noncoding', Variant_Type 'non-SNV', Sub_category 'Highly conserved', column 'AUPRC'
Configuration: RNA-FM (Evo 2 paper variant effect evaluations)	Protocol: Zero-shot ClinVar noncoding non-SNVs, highly conserved classification (Evo 2 paper, Supplementary Data 1) Dataset: ClinVar October 2024 release, filtered (Brixi et al. 2026)	0.517 AUROC (zero-shot; ClinVar noncoding non-SNVs, highly conserved) 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 noncoding non-SNVs, highly conserved (Evo 2 paper) gfm-guides-20261014-evo2-brixi2026-protocol-clinvar-noncoding-non-snv-highly-conserved 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 I363, row 363: Model 'RNA-FM', Data 'ClinVar', Genomic_Feature 'Noncoding', Variant_Type 'non-SNV', Sub_category 'Highly conserved', column 'AUROC'

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.

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: 12

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-noncoding-non-snv-highly-conserved

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 'Noncoding', Variant_Type 'non-SNV', Sub_category 'Highly conserved'.
version: As published, Nature 652 (2026), Supplementary Data 1
source locator: Supplementary Data 1 rows with Data 'ClinVar', Genomic_Feature 'Noncoding', Variant_Type 'non-SNV', Sub_category 'Highly conserved'; SI A.3.12 and A.3.13 (page 13); Extended Data Fig. 4
limitations: Positives: 524 pathogenic/likely pathogenic; negatives: 182 benign/likely benign; total 706 variants (Supplementary Data 1).; phyloP 100-way > 2 (SI A.3.13).; 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

part of: Evo 2 paper zero-shot human variant effect evaluations (Brixi et al. 2026)
uses data: ClinVar October 2024 release, filtered (Brixi et al. 2026)
assessment: Evo 1 on ClinVar noncoding non-SNVs, highly conserved (Evo 2 paper)
assessment: Evo 2 40B base on ClinVar noncoding non-SNVs, highly conserved (Evo 2 paper)
assessment: Evo 2 40B on ClinVar noncoding non-SNVs, highly conserved (Evo 2 paper)
assessment: Evo 2 7B base on ClinVar noncoding non-SNVs, highly conserved (Evo 2 paper)
assessment: Evo 2 7B on ClinVar noncoding non-SNVs, highly conserved (Evo 2 paper)
assessment: NT on ClinVar noncoding non-SNVs, highly conserved (Evo 2 paper)
assessment: Pangolin on ClinVar noncoding non-SNVs, highly conserved (Evo 2 paper)
assessment: PhyloP 100 on ClinVar noncoding non-SNVs, highly conserved (Evo 2 paper)
assessment: PhyloP 241 on ClinVar noncoding non-SNVs, highly conserved (Evo 2 paper)
assessment: PhyloP 447 on ClinVar noncoding non-SNVs, highly conserved (Evo 2 paper)
assessment: PhyloP 470 on ClinVar noncoding non-SNVs, highly conserved (Evo 2 paper)
assessment: RNA-FM on ClinVar noncoding non-SNVs, highly conserved (Evo 2 paper)

Suggest a correction