| Configuration: Random chemical generation (formula) | Protocol: MassSpecGym · formula (MassSpecGym De novo molecule generation) Dataset: MassSpecGym · formula | 18.25 (18.14-18.35) Top-10 MCES unitless · lower Uncertainty: 99.9% CI 18.14 to 18.35 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceRandom chemical generation (formula): MassSpecGym · formula 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, bonus formula challenge, Random chemical generation, Top-10 MCES |
|---|
| Configuration: SMILES Transformer (formula) | Protocol: MassSpecGym · formula (MassSpecGym De novo molecule generation) Dataset: MassSpecGym · formula | 0.03 (0.03 - 0.04) Top-1 tanimoto unitless · higher Uncertainty: 99.9% CI 0.03 to 0.04 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceSMILES Transformer (formula): MassSpecGym · formula 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, bonus formula challenge, SMILES Transformer, Top-1 Tanimoto |
|---|
| Configuration: SELFIES Transformer (formula) | Protocol: MassSpecGym · formula (MassSpecGym De novo molecule generation) Dataset: MassSpecGym · formula | 26.87 (26.66-27.11) Top-10 MCES unitless · lower Uncertainty: 99.9% CI 26.66 to 27.11 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceSELFIES Transformer (formula): MassSpecGym · formula 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, bonus formula challenge, SELFIES Transformer, Top-10 MCES |
|---|
| Configuration: SMILES Transformer (formula) | Protocol: MassSpecGym · formula (MassSpecGym De novo molecule generation) Dataset: MassSpecGym · formula | 0.10 (0.09 - 0.10) Top-10 tanimoto unitless · higher Uncertainty: 99.9% CI 0.09 to 0.10 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceSMILES Transformer (formula): MassSpecGym · formula 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, bonus formula challenge, SMILES Transformer, Top-10 Tanimoto |
|---|
| Configuration: Random chemical generation (formula) | Protocol: MassSpecGym · formula (MassSpecGym De novo molecule generation) Dataset: MassSpecGym · formula | 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 (formula): MassSpecGym · formula 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, bonus formula challenge, Random chemical generation, Top-10 accuracy |
|---|
| Configuration: SELFIES Transformer (formula) | Protocol: MassSpecGym · formula (MassSpecGym De novo molecule generation) Dataset: MassSpecGym · formula | 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 (formula): MassSpecGym · formula 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, bonus formula challenge, SELFIES Transformer, Top-10 accuracy |
|---|
| Configuration: Random chemical generation (formula) | Protocol: MassSpecGym · formula (MassSpecGym De novo molecule generation) Dataset: MassSpecGym · formula | 21.11 (20.97-21.26) Top-1 MCES (de novo; best of top-1 generated) unitless · lower Uncertainty: 99.9% CI 20.97 to 21.26 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceRandom chemical generation (formula): MassSpecGym · formula 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, bonus formula challenge, Random chemical generation, Top-1 MCES |
|---|
| Configuration: Random chemical generation (formula) | Protocol: MassSpecGym · formula (MassSpecGym De novo molecule generation) Dataset: MassSpecGym · formula | 0.11 (0.11 - 0.11) Top-10 tanimoto unitless · higher Uncertainty: 99.9% CI 0.11 to 0.11 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceRandom chemical generation (formula): MassSpecGym · formula 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, bonus formula challenge, Random chemical generation, Top-10 Tanimoto |
|---|
| Configuration: Random chemical generation (formula) | Protocol: MassSpecGym · formula (MassSpecGym De novo molecule generation) Dataset: MassSpecGym · formula | 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 (formula): MassSpecGym · formula 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, bonus formula challenge, Random chemical generation, Top-1 accuracy |
|---|
| Configuration: SMILES Transformer (formula) | Protocol: MassSpecGym · formula (MassSpecGym De novo molecule generation) Dataset: MassSpecGym · formula | 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 (formula): MassSpecGym · formula 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, bonus formula challenge, SMILES Transformer, Top-10 accuracy |
|---|
| Configuration: SELFIES Transformer (formula) | Protocol: MassSpecGym · formula (MassSpecGym De novo molecule generation) Dataset: MassSpecGym · formula | 0.08 (0.08 - 0.08) Top-1 tanimoto unitless · higher Uncertainty: 99.9% CI 0.08 to 0.08 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceSELFIES Transformer (formula): MassSpecGym · formula 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, bonus formula challenge, SELFIES Transformer, Top-1 Tanimoto |
|---|
| Configuration: Random chemical generation (formula) | Protocol: MassSpecGym · formula (MassSpecGym De novo molecule generation) Dataset: MassSpecGym · formula | 0.08 (0.08 - 0.08) Top-1 tanimoto unitless · higher Uncertainty: 99.9% CI 0.08 to 0.08 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceRandom chemical generation (formula): MassSpecGym · formula 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, bonus formula challenge, Random chemical generation, Top-1 Tanimoto |
|---|
| Configuration: SMILES Transformer (formula) | Protocol: MassSpecGym · formula (MassSpecGym De novo molecule generation) Dataset: MassSpecGym · formula | 79.39 (78.64-80.08) Top-1 MCES (de novo; best of top-1 generated) unitless · lower Uncertainty: 99.9% CI 78.64 to 80.08 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceSMILES Transformer (formula): MassSpecGym · formula 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, bonus formula challenge, SMILES Transformer, Top-1 MCES |
|---|
| Configuration: SMILES Transformer (formula) | Protocol: MassSpecGym · formula (MassSpecGym De novo molecule generation) Dataset: MassSpecGym · formula | 52.13 (51.45-52.81) Top-10 MCES unitless · lower Uncertainty: 99.9% CI 51.45 to 52.81 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceSMILES Transformer (formula): MassSpecGym · formula 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, bonus formula challenge, SMILES Transformer, Top-10 MCES |
|---|
| Configuration: SMILES Transformer (formula) | Protocol: MassSpecGym · formula (MassSpecGym De novo molecule generation) Dataset: MassSpecGym · formula | 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 (formula): MassSpecGym · formula 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, bonus formula challenge, SMILES Transformer, Top-1 accuracy |
|---|
| Configuration: SELFIES Transformer (formula) | Protocol: MassSpecGym · formula (MassSpecGym De novo molecule generation) Dataset: MassSpecGym · formula | 0.13 (0.13 - 0.13) Top-10 tanimoto unitless · higher Uncertainty: 99.9% CI 0.13 to 0.13 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceSELFIES Transformer (formula): MassSpecGym · formula 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, bonus formula challenge, SELFIES Transformer, Top-10 Tanimoto |
|---|
| Configuration: SELFIES Transformer (formula) | Protocol: MassSpecGym · formula (MassSpecGym De novo molecule generation) Dataset: MassSpecGym · formula | 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 (formula): MassSpecGym · formula 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, bonus formula challenge, SELFIES Transformer, Top-1 accuracy |
|---|
| Configuration: SELFIES Transformer (formula) | Protocol: MassSpecGym · formula (MassSpecGym De novo molecule generation) Dataset: MassSpecGym · formula | 38.88 (38.57-39.20) Top-1 MCES (de novo; best of top-1 generated) unitless · lower Uncertainty: 99.9% CI 38.57 to 39.20 Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceSELFIES Transformer (formula): MassSpecGym · formula 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, bonus formula challenge, SELFIES Transformer, Top-1 MCES |
|---|