| Configuration: SMILES Transformer (main) | Protocol: MassSpecGym · main (MassSpecGym De novo molecule generation) Dataset: MassSpecGym · main | 0 Top-1 accuracy (de novo, exact match) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceSMILES Transformer (main): MassSpecGym · main Generate candidate molecules from an input spectrum. Compare within the same main/formula challenge and metric. Main random generation uses precursor mass; the Transformer consumes the spectrum. MCES single-linkage molecular clustering at threshold 10; fixed held-out test split Aggregation: Not reported MassSpecGym: A benchmark for the discovery and identification of molecules · Table 2, main challenge, SMILES Transformer, Top-1 accuracy |
|---|
| Configuration: SELFIES Transformer (main) | Protocol: MassSpecGym · main (MassSpecGym De novo molecule generation) Dataset: MassSpecGym · main | 0 Top-1 accuracy (de novo, exact match) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceSELFIES Transformer (main): MassSpecGym · main Generate candidate molecules from an input spectrum. Compare within the same main/formula challenge and metric. Main random generation uses precursor mass; the Transformer consumes the spectrum. MCES single-linkage molecular clustering at threshold 10; fixed held-out test split Aggregation: Not reported MassSpecGym: A benchmark for the discovery and identification of molecules · Table 2, main challenge, SELFIES Transformer, Top-1 accuracy |
|---|
| Configuration: SELFIES Transformer (main) | Protocol: MassSpecGym · main (MassSpecGym De novo molecule generation) Dataset: MassSpecGym · main | 21.84 (21.67-22.00) Top-10 MCES unitless · lower Uncertainty: 99.9% CI 21.67 to 22.00 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceSELFIES Transformer (main): MassSpecGym · main Generate candidate molecules from an input spectrum. Compare within the same main/formula challenge and metric. Main random generation uses precursor mass; the Transformer consumes the spectrum. MCES single-linkage molecular clustering at threshold 10; fixed held-out test split Aggregation: Not reported MassSpecGym: A benchmark for the discovery and identification of molecules · Table 2, main challenge, SELFIES Transformer, Top-10 MCES |
|---|
| Configuration: SELFIES Transformer (main) | Protocol: MassSpecGym · main (MassSpecGym De novo molecule generation) Dataset: MassSpecGym · main | 0 Top-10 accuracy (de novo, exact match) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceSELFIES Transformer (main): MassSpecGym · main Generate candidate molecules from an input spectrum. Compare within the same main/formula challenge and metric. Main random generation uses precursor mass; the Transformer consumes the spectrum. MCES single-linkage molecular clustering at threshold 10; fixed held-out test split Aggregation: Not reported MassSpecGym: A benchmark for the discovery and identification of molecules · Table 2, main challenge, SELFIES Transformer, Top-10 accuracy |
|---|
| Configuration: SELFIES Transformer (main) | Protocol: MassSpecGym · main (MassSpecGym De novo molecule generation) Dataset: MassSpecGym · main | 33.28 (33.00-33.57) Top-1 MCES (de novo; best of top-1 generated) unitless · lower Uncertainty: 99.9% CI 33.00 to 33.57 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceSELFIES Transformer (main): MassSpecGym · main Generate candidate molecules from an input spectrum. Compare within the same main/formula challenge and metric. Main random generation uses precursor mass; the Transformer consumes the spectrum. MCES single-linkage molecular clustering at threshold 10; fixed held-out test split Aggregation: Not reported MassSpecGym: A benchmark for the discovery and identification of molecules · Table 2, main challenge, SELFIES Transformer, Top-1 MCES |
|---|
| Configuration: SMILES Transformer (main) | Protocol: MassSpecGym · main (MassSpecGym De novo molecule generation) Dataset: MassSpecGym · main | 53.80 (52.95-54.61) Top-1 MCES (de novo; best of top-1 generated) unitless · lower Uncertainty: 99.9% CI 52.95 to 54.61 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceSMILES Transformer (main): MassSpecGym · main Generate candidate molecules from an input spectrum. Compare within the same main/formula challenge and metric. Main random generation uses precursor mass; the Transformer consumes the spectrum. MCES single-linkage molecular clustering at threshold 10; fixed held-out test split Aggregation: Not reported MassSpecGym: A benchmark for the discovery and identification of molecules · Table 2, main challenge, SMILES Transformer, Top-1 MCES |
|---|
| Configuration: Random chemical generation (main) | Protocol: MassSpecGym · main (MassSpecGym De novo molecule generation) Dataset: MassSpecGym · main | 28.59 (28.33-28.84) Top-1 MCES (de novo; best of top-1 generated) unitless · lower Uncertainty: 99.9% CI 28.33 to 28.84 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceRandom chemical generation (main): MassSpecGym · main Generate candidate molecules from an input spectrum. Compare within the same main/formula challenge and metric. Main random generation uses precursor mass; the Transformer consumes the spectrum. MCES single-linkage molecular clustering at threshold 10; fixed held-out test split Aggregation: Not reported MassSpecGym: A benchmark for the discovery and identification of molecules · Table 2, main challenge, Random chemical generation, Top-1 MCES |
|---|
| Configuration: SELFIES Transformer (main) | Protocol: MassSpecGym · main (MassSpecGym De novo molecule generation) Dataset: MassSpecGym · main | 0.15 (0.15 - 0.15) Top-10 tanimoto unitless · higher Uncertainty: 99.9% CI 0.15 to 0.15 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceSELFIES Transformer (main): MassSpecGym · main Generate candidate molecules from an input spectrum. Compare within the same main/formula challenge and metric. Main random generation uses precursor mass; the Transformer consumes the spectrum. MCES single-linkage molecular clustering at threshold 10; fixed held-out test split Aggregation: Not reported MassSpecGym: A benchmark for the discovery and identification of molecules · Table 2, main challenge, SELFIES Transformer, Top-10 Tanimoto |
|---|
| Configuration: SELFIES Transformer (main) | Protocol: MassSpecGym · main (MassSpecGym De novo molecule generation) Dataset: MassSpecGym · main | 0.10 (0.10 - 0.10) Top-1 tanimoto unitless · higher Uncertainty: 99.9% CI 0.10 to 0.10 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceSELFIES Transformer (main): MassSpecGym · main Generate candidate molecules from an input spectrum. Compare within the same main/formula challenge and metric. Main random generation uses precursor mass; the Transformer consumes the spectrum. MCES single-linkage molecular clustering at threshold 10; fixed held-out test split Aggregation: Not reported MassSpecGym: A benchmark for the discovery and identification of molecules · Table 2, main challenge, SELFIES Transformer, Top-1 Tanimoto |
|---|
| Configuration: SMILES Transformer (main) | Protocol: MassSpecGym · main (MassSpecGym De novo molecule generation) Dataset: MassSpecGym · main | 0 Top-10 accuracy (de novo, exact match) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceSMILES Transformer (main): MassSpecGym · main Generate candidate molecules from an input spectrum. Compare within the same main/formula challenge and metric. Main random generation uses precursor mass; the Transformer consumes the spectrum. MCES single-linkage molecular clustering at threshold 10; fixed held-out test split Aggregation: Not reported MassSpecGym: A benchmark for the discovery and identification of molecules · Table 2, main challenge, SMILES Transformer, Top-10 accuracy |
|---|
| Configuration: Random chemical generation (main) | Protocol: MassSpecGym · main (MassSpecGym De novo molecule generation) Dataset: MassSpecGym · main | 0 Top-10 accuracy (de novo, exact match) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceRandom chemical generation (main): MassSpecGym · main Generate candidate molecules from an input spectrum. Compare within the same main/formula challenge and metric. Main random generation uses precursor mass; the Transformer consumes the spectrum. MCES single-linkage molecular clustering at threshold 10; fixed held-out test split Aggregation: Not reported MassSpecGym: A benchmark for the discovery and identification of molecules · Table 2, main challenge, Random chemical generation, Top-10 accuracy |
|---|
| Configuration: Random chemical generation (main) | Protocol: MassSpecGym · main (MassSpecGym De novo molecule generation) Dataset: MassSpecGym · main | 25.72 (25.49-25.95) Top-10 MCES unitless · lower Uncertainty: 99.9% CI 25.49 to 25.95 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceRandom chemical generation (main): MassSpecGym · main Generate candidate molecules from an input spectrum. Compare within the same main/formula challenge and metric. Main random generation uses precursor mass; the Transformer consumes the spectrum. MCES single-linkage molecular clustering at threshold 10; fixed held-out test split Aggregation: Not reported MassSpecGym: A benchmark for the discovery and identification of molecules · Table 2, main challenge, Random chemical generation, Top-10 MCES |
|---|
| Configuration: Random chemical generation (main) | Protocol: MassSpecGym · main (MassSpecGym De novo molecule generation) Dataset: MassSpecGym · main | 0.10 (0.10 - 0.10) Top-10 tanimoto unitless · higher Uncertainty: 99.9% CI 0.10 to 0.10 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceRandom chemical generation (main): MassSpecGym · main Generate candidate molecules from an input spectrum. Compare within the same main/formula challenge and metric. Main random generation uses precursor mass; the Transformer consumes the spectrum. MCES single-linkage molecular clustering at threshold 10; fixed held-out test split Aggregation: Not reported MassSpecGym: A benchmark for the discovery and identification of molecules · Table 2, main challenge, Random chemical generation, Top-10 Tanimoto |
|---|
| Configuration: Random chemical generation (main) | Protocol: MassSpecGym · main (MassSpecGym De novo molecule generation) Dataset: MassSpecGym · main | 0 Top-1 accuracy (de novo, exact match) fraction · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceRandom chemical generation (main): MassSpecGym · main Generate candidate molecules from an input spectrum. Compare within the same main/formula challenge and metric. Main random generation uses precursor mass; the Transformer consumes the spectrum. MCES single-linkage molecular clustering at threshold 10; fixed held-out test split Aggregation: Not reported MassSpecGym: A benchmark for the discovery and identification of molecules · Table 2, main challenge, Random chemical generation, Top-1 accuracy |
|---|
| Configuration: SMILES Transformer (main) | Protocol: MassSpecGym · main (MassSpecGym De novo molecule generation) Dataset: MassSpecGym · main | 0.07 (0.07 - 0.08) Top-1 tanimoto unitless · higher Uncertainty: 99.9% CI 0.07 to 0.08 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceSMILES Transformer (main): MassSpecGym · main Generate candidate molecules from an input spectrum. Compare within the same main/formula challenge and metric. Main random generation uses precursor mass; the Transformer consumes the spectrum. MCES single-linkage molecular clustering at threshold 10; fixed held-out test split Aggregation: Not reported MassSpecGym: A benchmark for the discovery and identification of molecules · Table 2, main challenge, SMILES Transformer, Top-1 Tanimoto |
|---|
| Configuration: SMILES Transformer (main) | Protocol: MassSpecGym · main (MassSpecGym De novo molecule generation) Dataset: MassSpecGym · main | 0.17 (0.17 - 0.17) Top-10 tanimoto unitless · higher Uncertainty: 99.9% CI 0.17 to 0.17 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceSMILES Transformer (main): MassSpecGym · main Generate candidate molecules from an input spectrum. Compare within the same main/formula challenge and metric. Main random generation uses precursor mass; the Transformer consumes the spectrum. MCES single-linkage molecular clustering at threshold 10; fixed held-out test split Aggregation: Not reported MassSpecGym: A benchmark for the discovery and identification of molecules · Table 2, main challenge, SMILES Transformer, Top-10 Tanimoto |
|---|
| Configuration: SMILES Transformer (main) | Protocol: MassSpecGym · main (MassSpecGym De novo molecule generation) Dataset: MassSpecGym · main | 21.97 (21.79-22.16) Top-10 MCES unitless · lower Uncertainty: 99.9% CI 21.79 to 22.16 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceSMILES Transformer (main): MassSpecGym · main Generate candidate molecules from an input spectrum. Compare within the same main/formula challenge and metric. Main random generation uses precursor mass; the Transformer consumes the spectrum. MCES single-linkage molecular clustering at threshold 10; fixed held-out test split Aggregation: Not reported MassSpecGym: A benchmark for the discovery and identification of molecules · Table 2, main challenge, SMILES Transformer, Top-10 MCES |
|---|
| Configuration: Random chemical generation (main) | Protocol: MassSpecGym · main (MassSpecGym De novo molecule generation) Dataset: MassSpecGym · main | 0.07 (0.07 - 0.07) Top-1 tanimoto unitless · higher Uncertainty: 99.9% CI 0.07 to 0.07 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceRandom chemical generation (main): MassSpecGym · main Generate candidate molecules from an input spectrum. Compare within the same main/formula challenge and metric. Main random generation uses precursor mass; the Transformer consumes the spectrum. MCES single-linkage molecular clustering at threshold 10; fixed held-out test split Aggregation: Not reported MassSpecGym: A benchmark for the discovery and identification of molecules · Table 2, main challenge, Random chemical generation, Top-1 Tanimoto |
|---|