| Configuration: GPT-4 (gpt-4-1106-preview), zero-shot prompt (Kafkas et al. 2025) | Protocol: Ranking the causative gene within synthetic candidate sets of 5 to 100 genes, ClinVar (Kafkas et al. 2025 Table 3)
Dataset: ClinVar variants added 2 July to 7 October 2023, 100 genes (Kafkas et al. 2025) | 0.622 AUPRC (candidate gene set of 100 genes including the causative gene) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceGPT-4 Zero shot on ClinVar candidate gene sets rare-ranking-20261009-protocol-kafkas2025-clinvar-gene-sets Aggregation: Not reported The application of Large Language Models to the phenotype-based prioritization of causative genes in rare disease patients · Table 3 row Size 100, 'AUPR', column 'ClinVar' 'GPT-4' 'Zero shot' |
|---|
| Configuration: GPT-4 (gpt-4-1106-preview), zero-shot prompt (Kafkas et al. 2025) | Protocol: Ranking the causative gene within synthetic candidate sets of 5 to 100 genes, ClinVar (Kafkas et al. 2025 Table 3)
Dataset: ClinVar variants added 2 July to 7 October 2023, 100 genes (Kafkas et al. 2025) | 0.911 AUROC (candidate gene set of 100 genes including the causative gene) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceGPT-4 Zero shot on ClinVar candidate gene sets rare-ranking-20261009-protocol-kafkas2025-clinvar-gene-sets Aggregation: Not reported The application of Large Language Models to the phenotype-based prioritization of causative genes in rare disease patients · Table 3 row Size 100, 'ROC AUC', column 'ClinVar' 'GPT-4' 'Zero shot' |
|---|
| Configuration: GPT-4 (gpt-4-1106-preview), zero-shot prompt (Kafkas et al. 2025) | Protocol: Ranking the causative gene within synthetic candidate sets of 5 to 100 genes, ClinVar (Kafkas et al. 2025 Table 3)
Dataset: ClinVar variants added 2 July to 7 October 2023, 100 genes (Kafkas et al. 2025) | 68% Top-1 accuracy (candidate gene set of 100 genes including the causative gene) percent · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceGPT-4 Zero shot on ClinVar candidate gene sets rare-ranking-20261009-protocol-kafkas2025-clinvar-gene-sets Aggregation: Not reported The application of Large Language Models to the phenotype-based prioritization of causative genes in rare disease patients · Table 3 row Size 100, 'Hits@1 (%)', column 'ClinVar' 'GPT-4' 'Zero shot' |
|---|
| Configuration: GPT-4 (gpt-4-1106-preview), zero-shot prompt (Kafkas et al. 2025) | Protocol: Ranking the causative gene within synthetic candidate sets of 5 to 100 genes, ClinVar (Kafkas et al. 2025 Table 3)
Dataset: ClinVar variants added 2 July to 7 October 2023, 100 genes (Kafkas et al. 2025) | 81% Top-10 accuracy (candidate gene set of 100 genes including the causative gene) percent · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceGPT-4 Zero shot on ClinVar candidate gene sets rare-ranking-20261009-protocol-kafkas2025-clinvar-gene-sets Aggregation: Not reported The application of Large Language Models to the phenotype-based prioritization of causative genes in rare disease patients · Table 3 row Size 100, 'Hits@10 (%)', column 'ClinVar' 'GPT-4' 'Zero shot' |
|---|
| Configuration: GPT-4 (gpt-4-1106-preview), zero-shot prompt (Kafkas et al. 2025) | Protocol: Ranking the causative gene within synthetic candidate sets of 5 to 100 genes, ClinVar (Kafkas et al. 2025 Table 3)
Dataset: ClinVar variants added 2 July to 7 October 2023, 100 genes (Kafkas et al. 2025) | 0.802 AUPRC (candidate gene set of 25 genes including the causative gene) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceGPT-4 Zero shot on ClinVar candidate gene sets rare-ranking-20261009-protocol-kafkas2025-clinvar-gene-sets Aggregation: Not reported The application of Large Language Models to the phenotype-based prioritization of causative genes in rare disease patients · Table 3 row Size 25, 'AUPR', column 'ClinVar' 'GPT-4' 'Zero shot' |
|---|
| Configuration: GPT-4 (gpt-4-1106-preview), zero-shot prompt (Kafkas et al. 2025) | Protocol: Ranking the causative gene within synthetic candidate sets of 5 to 100 genes, ClinVar (Kafkas et al. 2025 Table 3)
Dataset: ClinVar variants added 2 July to 7 October 2023, 100 genes (Kafkas et al. 2025) | 0.964 AUROC (candidate gene set of 25 genes including the causative gene) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceGPT-4 Zero shot on ClinVar candidate gene sets rare-ranking-20261009-protocol-kafkas2025-clinvar-gene-sets Aggregation: Not reported The application of Large Language Models to the phenotype-based prioritization of causative genes in rare disease patients · Table 3 row Size 25, 'ROC AUC', column 'ClinVar' 'GPT-4' 'Zero shot' |
|---|
| Configuration: GPT-4 (gpt-4-1106-preview), zero-shot prompt (Kafkas et al. 2025) | Protocol: Ranking the causative gene within synthetic candidate sets of 5 to 100 genes, ClinVar (Kafkas et al. 2025 Table 3)
Dataset: ClinVar variants added 2 July to 7 October 2023, 100 genes (Kafkas et al. 2025) | 82% Top-1 accuracy (candidate gene set of 25 genes including the causative gene) percent · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceGPT-4 Zero shot on ClinVar candidate gene sets rare-ranking-20261009-protocol-kafkas2025-clinvar-gene-sets Aggregation: Not reported The application of Large Language Models to the phenotype-based prioritization of causative genes in rare disease patients · Table 3 row Size 25, 'Hits@1 (%)', column 'ClinVar' 'GPT-4' 'Zero shot' |
|---|
| Configuration: GPT-4 (gpt-4-1106-preview), zero-shot prompt (Kafkas et al. 2025) | Protocol: Ranking the causative gene within synthetic candidate sets of 5 to 100 genes, ClinVar (Kafkas et al. 2025 Table 3)
Dataset: ClinVar variants added 2 July to 7 October 2023, 100 genes (Kafkas et al. 2025) | 94% Top-10 accuracy (candidate gene set of 25 genes including the causative gene) percent · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceGPT-4 Zero shot on ClinVar candidate gene sets rare-ranking-20261009-protocol-kafkas2025-clinvar-gene-sets Aggregation: Not reported The application of Large Language Models to the phenotype-based prioritization of causative genes in rare disease patients · Table 3 row Size 25, 'Hits@10 (%)', column 'ClinVar' 'GPT-4' 'Zero shot' |
|---|
| Configuration: GPT-4 (gpt-4-1106-preview), zero-shot prompt (Kafkas et al. 2025) | Protocol: Ranking the causative gene within synthetic candidate sets of 5 to 100 genes, ClinVar (Kafkas et al. 2025 Table 3)
Dataset: ClinVar variants added 2 July to 7 October 2023, 100 genes (Kafkas et al. 2025) | 0.944 AUPRC (candidate gene set of 5 genes including the causative gene) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceGPT-4 Zero shot on ClinVar candidate gene sets rare-ranking-20261009-protocol-kafkas2025-clinvar-gene-sets Aggregation: Not reported The application of Large Language Models to the phenotype-based prioritization of causative genes in rare disease patients · Table 3 row Size 5, 'AUPR', column 'ClinVar' 'GPT-4' 'Zero shot' |
|---|
| Configuration: GPT-4 (gpt-4-1106-preview), zero-shot prompt (Kafkas et al. 2025) | Protocol: Ranking the causative gene within synthetic candidate sets of 5 to 100 genes, ClinVar (Kafkas et al. 2025 Table 3)
Dataset: ClinVar variants added 2 July to 7 October 2023, 100 genes (Kafkas et al. 2025) | 0.991 AUROC (candidate gene set of 5 genes including the causative gene) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceGPT-4 Zero shot on ClinVar candidate gene sets rare-ranking-20261009-protocol-kafkas2025-clinvar-gene-sets Aggregation: Not reported The application of Large Language Models to the phenotype-based prioritization of causative genes in rare disease patients · Table 3 row Size 5, 'ROC AUC', column 'ClinVar' 'GPT-4' 'Zero shot' |
|---|
| Configuration: GPT-4 (gpt-4-1106-preview), zero-shot prompt (Kafkas et al. 2025) | Protocol: Ranking the causative gene within synthetic candidate sets of 5 to 100 genes, ClinVar (Kafkas et al. 2025 Table 3)
Dataset: ClinVar variants added 2 July to 7 October 2023, 100 genes (Kafkas et al. 2025) | 93% Top-1 accuracy (candidate gene set of 5 genes including the causative gene) percent · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceGPT-4 Zero shot on ClinVar candidate gene sets rare-ranking-20261009-protocol-kafkas2025-clinvar-gene-sets Aggregation: Not reported The application of Large Language Models to the phenotype-based prioritization of causative genes in rare disease patients · Table 3 row Size 5, 'Hits@1 (%)', column 'ClinVar' 'GPT-4' 'Zero shot' |
|---|
| Configuration: GPT-4 (gpt-4-1106-preview), zero-shot prompt (Kafkas et al. 2025) | Protocol: Ranking the causative gene within synthetic candidate sets of 5 to 100 genes, ClinVar (Kafkas et al. 2025 Table 3)
Dataset: ClinVar variants added 2 July to 7 October 2023, 100 genes (Kafkas et al. 2025) | 100% Top-10 accuracy (candidate gene set of 5 genes including the causative gene) percent · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceGPT-4 Zero shot on ClinVar candidate gene sets rare-ranking-20261009-protocol-kafkas2025-clinvar-gene-sets Aggregation: Not reported The application of Large Language Models to the phenotype-based prioritization of causative genes in rare disease patients · Table 3 row Size 5, 'Hits@10 (%)', column 'ClinVar' 'GPT-4' 'Zero shot' |
|---|
| Configuration: GPT-4 (gpt-4-1106-preview), zero-shot prompt (Kafkas et al. 2025) | Protocol: Ranking the causative gene within synthetic candidate sets of 5 to 100 genes, ClinVar (Kafkas et al. 2025 Table 3)
Dataset: ClinVar variants added 2 July to 7 October 2023, 100 genes (Kafkas et al. 2025) | 0.806 AUPRC (candidate gene set of 50 genes including the causative gene) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceGPT-4 Zero shot on ClinVar candidate gene sets rare-ranking-20261009-protocol-kafkas2025-clinvar-gene-sets Aggregation: Not reported The application of Large Language Models to the phenotype-based prioritization of causative genes in rare disease patients · Table 3 row Size 50, 'AUPR', column 'ClinVar' 'GPT-4' 'Zero shot' |
|---|
| Configuration: GPT-4 (gpt-4-1106-preview), zero-shot prompt (Kafkas et al. 2025) | Protocol: Ranking the causative gene within synthetic candidate sets of 5 to 100 genes, ClinVar (Kafkas et al. 2025 Table 3)
Dataset: ClinVar variants added 2 July to 7 October 2023, 100 genes (Kafkas et al. 2025) | 0.971 AUROC (candidate gene set of 50 genes including the causative gene) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceGPT-4 Zero shot on ClinVar candidate gene sets rare-ranking-20261009-protocol-kafkas2025-clinvar-gene-sets Aggregation: Not reported The application of Large Language Models to the phenotype-based prioritization of causative genes in rare disease patients · Table 3 row Size 50, 'ROC AUC', column 'ClinVar' 'GPT-4' 'Zero shot' |
|---|
| Configuration: GPT-4 (gpt-4-1106-preview), zero-shot prompt (Kafkas et al. 2025) | Protocol: Ranking the causative gene within synthetic candidate sets of 5 to 100 genes, ClinVar (Kafkas et al. 2025 Table 3)
Dataset: ClinVar variants added 2 July to 7 October 2023, 100 genes (Kafkas et al. 2025) | 81% Top-1 accuracy (candidate gene set of 50 genes including the causative gene) percent · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceGPT-4 Zero shot on ClinVar candidate gene sets rare-ranking-20261009-protocol-kafkas2025-clinvar-gene-sets Aggregation: Not reported The application of Large Language Models to the phenotype-based prioritization of causative genes in rare disease patients · Table 3 row Size 50, 'Hits@1 (%)', column 'ClinVar' 'GPT-4' 'Zero shot' |
|---|
| Configuration: GPT-4 (gpt-4-1106-preview), zero-shot prompt (Kafkas et al. 2025) | Protocol: Ranking the causative gene within synthetic candidate sets of 5 to 100 genes, ClinVar (Kafkas et al. 2025 Table 3)
Dataset: ClinVar variants added 2 July to 7 October 2023, 100 genes (Kafkas et al. 2025) | 96% Top-10 accuracy (candidate gene set of 50 genes including the causative gene) percent · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceGPT-4 Zero shot on ClinVar candidate gene sets rare-ranking-20261009-protocol-kafkas2025-clinvar-gene-sets Aggregation: Not reported The application of Large Language Models to the phenotype-based prioritization of causative genes in rare disease patients · Table 3 row Size 50, 'Hits@10 (%)', column 'ClinVar' 'GPT-4' 'Zero shot' |
|---|
| Configuration: GPT-4 (gpt-4-1106-preview), zero-shot prompt (Kafkas et al. 2025) | Protocol: Ranking the causative gene within synthetic candidate sets of 5 to 100 genes, ClinVar (Kafkas et al. 2025 Table 3)
Dataset: ClinVar variants added 2 July to 7 October 2023, 100 genes (Kafkas et al. 2025) | 0.663 AUPRC (candidate gene set of 75 genes including the causative gene) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceGPT-4 Zero shot on ClinVar candidate gene sets rare-ranking-20261009-protocol-kafkas2025-clinvar-gene-sets Aggregation: Not reported The application of Large Language Models to the phenotype-based prioritization of causative genes in rare disease patients · Table 3 row Size 75, 'AUPR', column 'ClinVar' 'GPT-4' 'Zero shot' |
|---|
| Configuration: GPT-4 (gpt-4-1106-preview), zero-shot prompt (Kafkas et al. 2025) | Protocol: Ranking the causative gene within synthetic candidate sets of 5 to 100 genes, ClinVar (Kafkas et al. 2025 Table 3)
Dataset: ClinVar variants added 2 July to 7 October 2023, 100 genes (Kafkas et al. 2025) | 0.925 AUROC (candidate gene set of 75 genes including the causative gene) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceGPT-4 Zero shot on ClinVar candidate gene sets rare-ranking-20261009-protocol-kafkas2025-clinvar-gene-sets Aggregation: Not reported The application of Large Language Models to the phenotype-based prioritization of causative genes in rare disease patients · Table 3 row Size 75, 'ROC AUC', column 'ClinVar' 'GPT-4' 'Zero shot' |
|---|
| Configuration: GPT-4 (gpt-4-1106-preview), zero-shot prompt (Kafkas et al. 2025) | Protocol: Ranking the causative gene within synthetic candidate sets of 5 to 100 genes, ClinVar (Kafkas et al. 2025 Table 3)
Dataset: ClinVar variants added 2 July to 7 October 2023, 100 genes (Kafkas et al. 2025) | 71% Top-1 accuracy (candidate gene set of 75 genes including the causative gene) percent · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceGPT-4 Zero shot on ClinVar candidate gene sets rare-ranking-20261009-protocol-kafkas2025-clinvar-gene-sets Aggregation: Not reported The application of Large Language Models to the phenotype-based prioritization of causative genes in rare disease patients · Table 3 row Size 75, 'Hits@1 (%)', column 'ClinVar' 'GPT-4' 'Zero shot' |
|---|
| Configuration: GPT-4 (gpt-4-1106-preview), zero-shot prompt (Kafkas et al. 2025) | Protocol: Ranking the causative gene within synthetic candidate sets of 5 to 100 genes, ClinVar (Kafkas et al. 2025 Table 3)
Dataset: ClinVar variants added 2 July to 7 October 2023, 100 genes (Kafkas et al. 2025) | 82% Top-10 accuracy (candidate gene set of 75 genes including the causative gene) percent · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceGPT-4 Zero shot on ClinVar candidate gene sets rare-ranking-20261009-protocol-kafkas2025-clinvar-gene-sets Aggregation: Not reported The application of Large Language Models to the phenotype-based prioritization of causative genes in rare disease patients · Table 3 row Size 75, 'Hits@10 (%)', column 'ClinVar' 'GPT-4' 'Zero shot' |
|---|
| Configuration: GPT-4 (gpt-4-1106-preview), zero-shot prompt (Kafkas et al. 2025) | Protocol: Ranking the causative gene within synthetic candidate sets of 5 to 100 genes, GPCards (Kafkas et al. 2025 Table 3)
Dataset: GPCards gene-phenotype cases (free-text phenotypes) (Kafkas et al. 2025) | 0.343 AUPRC (candidate gene set of 100 genes including the causative gene) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceGPT-4 Zero shot on GP-Cards candidate gene sets rare-ranking-20261009-protocol-kafkas2025-gpcards-gene-sets Aggregation: Not reported The application of Large Language Models to the phenotype-based prioritization of causative genes in rare disease patients · Table 3 row Size 100, 'AUPR', column 'GP-Cards' 'GPT-4' 'Zero shot' |
|---|
| Configuration: GPT-4 (gpt-4-1106-preview), zero-shot prompt (Kafkas et al. 2025) | Protocol: Ranking the causative gene within synthetic candidate sets of 5 to 100 genes, GPCards (Kafkas et al. 2025 Table 3)
Dataset: GPCards gene-phenotype cases (free-text phenotypes) (Kafkas et al. 2025) | 0.928 AUROC (candidate gene set of 100 genes including the causative gene) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceGPT-4 Zero shot on GP-Cards candidate gene sets rare-ranking-20261009-protocol-kafkas2025-gpcards-gene-sets Aggregation: Not reported The application of Large Language Models to the phenotype-based prioritization of causative genes in rare disease patients · Table 3 row Size 100, 'ROC AUC', column 'GP-Cards' 'GPT-4' 'Zero shot' |
|---|
| Configuration: GPT-4 (gpt-4-1106-preview), zero-shot prompt (Kafkas et al. 2025) | Protocol: Ranking the causative gene within synthetic candidate sets of 5 to 100 genes, GPCards (Kafkas et al. 2025 Table 3)
Dataset: GPCards gene-phenotype cases (free-text phenotypes) (Kafkas et al. 2025) | 60% Top-1 accuracy (candidate gene set of 100 genes including the causative gene) percent · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceGPT-4 Zero shot on GP-Cards candidate gene sets rare-ranking-20261009-protocol-kafkas2025-gpcards-gene-sets Aggregation: Not reported The application of Large Language Models to the phenotype-based prioritization of causative genes in rare disease patients · Table 3 row Size 100, 'Hits@1 (%)', column 'GP-Cards' 'GPT-4' 'Zero shot' |
|---|
| Configuration: GPT-4 (gpt-4-1106-preview), zero-shot prompt (Kafkas et al. 2025) | Protocol: Ranking the causative gene within synthetic candidate sets of 5 to 100 genes, GPCards (Kafkas et al. 2025 Table 3)
Dataset: GPCards gene-phenotype cases (free-text phenotypes) (Kafkas et al. 2025) | 86% Top-10 accuracy (candidate gene set of 100 genes including the causative gene) percent · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceGPT-4 Zero shot on GP-Cards candidate gene sets rare-ranking-20261009-protocol-kafkas2025-gpcards-gene-sets Aggregation: Not reported The application of Large Language Models to the phenotype-based prioritization of causative genes in rare disease patients · Table 3 row Size 100, 'Hits@10 (%)', column 'GP-Cards' 'GPT-4' 'Zero shot' |
|---|
| Configuration: GPT-4 (gpt-4-1106-preview), zero-shot prompt (Kafkas et al. 2025) | Protocol: Ranking the causative gene within synthetic candidate sets of 5 to 100 genes, GPCards (Kafkas et al. 2025 Table 3)
Dataset: GPCards gene-phenotype cases (free-text phenotypes) (Kafkas et al. 2025) | 0.77 AUPRC (candidate gene set of 25 genes including the causative gene) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceGPT-4 Zero shot on GP-Cards candidate gene sets rare-ranking-20261009-protocol-kafkas2025-gpcards-gene-sets Aggregation: Not reported The application of Large Language Models to the phenotype-based prioritization of causative genes in rare disease patients · Table 3 row Size 25, 'AUPR', column 'GP-Cards' 'GPT-4' 'Zero shot' |
|---|