Configuration: Chroma (Scaffold-Lab unconditional generation) Protocol: Scaffold-Lab unconditional generation: Novelty(↓) Dataset: Scaffold-Lab generated backbones (100 per length group) 0.742 TM score (novelty as the pdb-TM of designable backbones against the PDB (lower is more novel); group mean without data preprocessing; length 1000)unitless · lower
Uncertainty: Not reported by the source
Coverage: Not reported scored / Not reported eligible
Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 3 Designability column: equation (1) defines a per-backbone success over 100 backbones per length, which gives two-decimal fractions, but the column prints three-decimal group means; the aggregation behind the column is not stated, and the criterion is sc-TM above 0.5, not the 2 Angstrom sc-RMSD in the store's designability concept. Do not compare these values with other designability results.Scaffold-Lab: Critical evaluation and ranking of protein backbone generation methods in a unified framework · Table 3, column 'Designability(↑)'; Metrics, equation (1)
Methods, coverage and source Chroma Novelty(↓) on Scaffold-Lab unconditional generation, length 1000
lit-structure-20261011-scaffoldlab-protocol-novelty
Aggregation: Not reported
Scaffold-Lab: Critical evaluation and ranking of protein backbone generation methods in a unified framework · Table 3, row 'Long' / 'Chroma' / length 1000, column 'Novelty(↓)' Configuration: Chroma (Scaffold-Lab unconditional generation) Protocol: Scaffold-Lab unconditional generation: Novelty(↓) Dataset: Scaffold-Lab generated backbones (100 per length group) 0.733 TM score (novelty as the pdb-TM of designable backbones against the PDB (lower is more novel); group mean without data preprocessing; length 600)unitless · lower
Uncertainty: Not reported by the source
Coverage: Not reported scored / Not reported eligible
Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 3 Designability column: equation (1) defines a per-backbone success over 100 backbones per length, which gives two-decimal fractions, but the column prints three-decimal group means; the aggregation behind the column is not stated, and the criterion is sc-TM above 0.5, not the 2 Angstrom sc-RMSD in the store's designability concept. Do not compare these values with other designability results.Scaffold-Lab: Critical evaluation and ranking of protein backbone generation methods in a unified framework · Table 3, column 'Designability(↑)'; Metrics, equation (1)
Methods, coverage and source Chroma Novelty(↓) on Scaffold-Lab unconditional generation, length 600
lit-structure-20261011-scaffoldlab-protocol-novelty
Aggregation: Not reported
Scaffold-Lab: Critical evaluation and ranking of protein backbone generation methods in a unified framework · Table 3, row 'Long' / 'Chroma' / length 600, column 'Novelty(↓)' Configuration: Chroma (Scaffold-Lab unconditional generation) Protocol: Scaffold-Lab unconditional generation: Novelty(↓) Dataset: Scaffold-Lab generated backbones (100 per length group) 0.746 TM score (novelty as the pdb-TM of designable backbones against the PDB (lower is more novel); group mean without data preprocessing; length 800)unitless · lower
Uncertainty: Not reported by the source
Coverage: Not reported scored / Not reported eligible
Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 3 Designability column: equation (1) defines a per-backbone success over 100 backbones per length, which gives two-decimal fractions, but the column prints three-decimal group means; the aggregation behind the column is not stated, and the criterion is sc-TM above 0.5, not the 2 Angstrom sc-RMSD in the store's designability concept. Do not compare these values with other designability results.Scaffold-Lab: Critical evaluation and ranking of protein backbone generation methods in a unified framework · Table 3, column 'Designability(↑)'; Metrics, equation (1)
Methods, coverage and source Chroma Novelty(↓) on Scaffold-Lab unconditional generation, length 800
lit-structure-20261011-scaffoldlab-protocol-novelty
Aggregation: Not reported
Scaffold-Lab: Critical evaluation and ranking of protein backbone generation methods in a unified framework · Table 3, row 'Long' / 'Chroma' / length 800, column 'Novelty(↓)' Configuration: Chroma (Scaffold-Lab unconditional generation) Protocol: Scaffold-Lab unconditional generation: Novelty(↓) Dataset: Scaffold-Lab generated backbones (100 per length group) 0.676 TM score (novelty as the pdb-TM of designable backbones against the PDB (lower is more novel); group mean without data preprocessing; length 200)unitless · lower
Uncertainty: Not reported by the source
Coverage: Not reported scored / Not reported eligible
Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 3 Designability column: equation (1) defines a per-backbone success over 100 backbones per length, which gives two-decimal fractions, but the column prints three-decimal group means; the aggregation behind the column is not stated, and the criterion is sc-TM above 0.5, not the 2 Angstrom sc-RMSD in the store's designability concept. Do not compare these values with other designability results.Scaffold-Lab: Critical evaluation and ranking of protein backbone generation methods in a unified framework · Table 3, column 'Designability(↑)'; Metrics, equation (1)
Methods, coverage and source Chroma Novelty(↓) on Scaffold-Lab unconditional generation, length 200
lit-structure-20261011-scaffoldlab-protocol-novelty
Aggregation: Not reported
Scaffold-Lab: Critical evaluation and ranking of protein backbone generation methods in a unified framework · Table 3, row 'Medium' / 'Chroma' / length 200, column 'Novelty(↓)' Configuration: Chroma (Scaffold-Lab unconditional generation) Protocol: Scaffold-Lab unconditional generation: Novelty(↓) Dataset: Scaffold-Lab generated backbones (100 per length group) 0.637 TM score (novelty as the pdb-TM of designable backbones against the PDB (lower is more novel); group mean without data preprocessing; length 300)unitless · lower
Uncertainty: Not reported by the source
Coverage: Not reported scored / Not reported eligible
Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 3 Designability column: equation (1) defines a per-backbone success over 100 backbones per length, which gives two-decimal fractions, but the column prints three-decimal group means; the aggregation behind the column is not stated, and the criterion is sc-TM above 0.5, not the 2 Angstrom sc-RMSD in the store's designability concept. Do not compare these values with other designability results.Scaffold-Lab: Critical evaluation and ranking of protein backbone generation methods in a unified framework · Table 3, column 'Designability(↑)'; Metrics, equation (1)
Methods, coverage and source Chroma Novelty(↓) on Scaffold-Lab unconditional generation, length 300
lit-structure-20261011-scaffoldlab-protocol-novelty
Aggregation: Not reported
Scaffold-Lab: Critical evaluation and ranking of protein backbone generation methods in a unified framework · Table 3, row 'Medium' / 'Chroma' / length 300, column 'Novelty(↓)' Configuration: Chroma (Scaffold-Lab unconditional generation) Protocol: Scaffold-Lab unconditional generation: Novelty(↓) Dataset: Scaffold-Lab generated backbones (100 per length group) 0.668 TM score (novelty as the pdb-TM of designable backbones against the PDB (lower is more novel); group mean without data preprocessing; length 400)unitless · lower
Uncertainty: Not reported by the source
Coverage: Not reported scored / Not reported eligible
Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 3 Designability column: equation (1) defines a per-backbone success over 100 backbones per length, which gives two-decimal fractions, but the column prints three-decimal group means; the aggregation behind the column is not stated, and the criterion is sc-TM above 0.5, not the 2 Angstrom sc-RMSD in the store's designability concept. Do not compare these values with other designability results.Scaffold-Lab: Critical evaluation and ranking of protein backbone generation methods in a unified framework · Table 3, column 'Designability(↑)'; Metrics, equation (1)
Methods, coverage and source Chroma Novelty(↓) on Scaffold-Lab unconditional generation, length 400
lit-structure-20261011-scaffoldlab-protocol-novelty
Aggregation: Not reported
Scaffold-Lab: Critical evaluation and ranking of protein backbone generation methods in a unified framework · Table 3, row 'Medium' / 'Chroma' / length 400, column 'Novelty(↓)' Configuration: Chroma (Scaffold-Lab unconditional generation) Protocol: Scaffold-Lab unconditional generation: Novelty(↓) Dataset: Scaffold-Lab generated backbones (100 per length group) 0.685 TM score (novelty as the pdb-TM of designable backbones against the PDB (lower is more novel); group mean without data preprocessing; length 500)unitless · lower
Uncertainty: Not reported by the source
Coverage: Not reported scored / Not reported eligible
Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 3 Designability column: equation (1) defines a per-backbone success over 100 backbones per length, which gives two-decimal fractions, but the column prints three-decimal group means; the aggregation behind the column is not stated, and the criterion is sc-TM above 0.5, not the 2 Angstrom sc-RMSD in the store's designability concept. Do not compare these values with other designability results.Scaffold-Lab: Critical evaluation and ranking of protein backbone generation methods in a unified framework · Table 3, column 'Designability(↑)'; Metrics, equation (1)
Methods, coverage and source Chroma Novelty(↓) on Scaffold-Lab unconditional generation, length 500
lit-structure-20261011-scaffoldlab-protocol-novelty
Aggregation: Not reported
Scaffold-Lab: Critical evaluation and ranking of protein backbone generation methods in a unified framework · Table 3, row 'Medium' / 'Chroma' / length 500, column 'Novelty(↓)' Configuration: Chroma (Scaffold-Lab unconditional generation) Protocol: Scaffold-Lab unconditional generation: Novelty(↓) Dataset: Scaffold-Lab generated backbones (100 per length group) 0.682 TM score (novelty as the pdb-TM of designable backbones against the PDB (lower is more novel); group mean without data preprocessing; length 100)unitless · lower
Uncertainty: Not reported by the source
Coverage: Not reported scored / Not reported eligible
Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 3 Designability column: equation (1) defines a per-backbone success over 100 backbones per length, which gives two-decimal fractions, but the column prints three-decimal group means; the aggregation behind the column is not stated, and the criterion is sc-TM above 0.5, not the 2 Angstrom sc-RMSD in the store's designability concept. Do not compare these values with other designability results.Scaffold-Lab: Critical evaluation and ranking of protein backbone generation methods in a unified framework · Table 3, column 'Designability(↑)'; Metrics, equation (1)
Methods, coverage and source Chroma Novelty(↓) on Scaffold-Lab unconditional generation, length 100
lit-structure-20261011-scaffoldlab-protocol-novelty
Aggregation: Not reported
Scaffold-Lab: Critical evaluation and ranking of protein backbone generation methods in a unified framework · Table 3, row 'Short' / 'Chroma' / length 100, column 'Novelty(↓)' Configuration: Chroma (Scaffold-Lab unconditional generation) Protocol: Scaffold-Lab unconditional generation: Novelty(↓) Dataset: Scaffold-Lab generated backbones (100 per length group) 0.715 TM score (novelty as the pdb-TM of designable backbones against the PDB (lower is more novel); group mean without data preprocessing; length 50)unitless · lower
Uncertainty: Not reported by the source
Coverage: Not reported scored / Not reported eligible
Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 3 Designability column: equation (1) defines a per-backbone success over 100 backbones per length, which gives two-decimal fractions, but the column prints three-decimal group means; the aggregation behind the column is not stated, and the criterion is sc-TM above 0.5, not the 2 Angstrom sc-RMSD in the store's designability concept. Do not compare these values with other designability results.Scaffold-Lab: Critical evaluation and ranking of protein backbone generation methods in a unified framework · Table 3, column 'Designability(↑)'; Metrics, equation (1)
Methods, coverage and source Chroma Novelty(↓) on Scaffold-Lab unconditional generation, length 50
lit-structure-20261011-scaffoldlab-protocol-novelty
Aggregation: Not reported
Scaffold-Lab: Critical evaluation and ranking of protein backbone generation methods in a unified framework · Table 3, row 'Short' / 'Chroma' / length 50, column 'Novelty(↓)' Configuration: FrameDiff (Scaffold-Lab unconditional generation) Protocol: Scaffold-Lab unconditional generation: Novelty(↓) Dataset: Scaffold-Lab generated backbones (100 per length group) 0.666 TM score (novelty as the pdb-TM of designable backbones against the PDB (lower is more novel); group mean without data preprocessing; length 200)unitless · lower
Uncertainty: Not reported by the source
Coverage: Not reported scored / Not reported eligible
Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 3 Designability column: equation (1) defines a per-backbone success over 100 backbones per length, which gives two-decimal fractions, but the column prints three-decimal group means; the aggregation behind the column is not stated, and the criterion is sc-TM above 0.5, not the 2 Angstrom sc-RMSD in the store's designability concept. Do not compare these values with other designability results.Scaffold-Lab: Critical evaluation and ranking of protein backbone generation methods in a unified framework · Table 3, column 'Designability(↑)'; Metrics, equation (1)
Methods, coverage and source FrameDiff Novelty(↓) on Scaffold-Lab unconditional generation, length 200
lit-structure-20261011-scaffoldlab-protocol-novelty
Aggregation: Not reported
Scaffold-Lab: Critical evaluation and ranking of protein backbone generation methods in a unified framework · Table 3, row 'Medium' / 'FrameDiff' / length 200, column 'Novelty(↓)' Configuration: FrameDiff (Scaffold-Lab unconditional generation) Protocol: Scaffold-Lab unconditional generation: Novelty(↓) Dataset: Scaffold-Lab generated backbones (100 per length group) 0.656 TM score (novelty as the pdb-TM of designable backbones against the PDB (lower is more novel); group mean without data preprocessing; length 300)unitless · lower
Uncertainty: Not reported by the source
Coverage: Not reported scored / Not reported eligible
Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 3 Designability column: equation (1) defines a per-backbone success over 100 backbones per length, which gives two-decimal fractions, but the column prints three-decimal group means; the aggregation behind the column is not stated, and the criterion is sc-TM above 0.5, not the 2 Angstrom sc-RMSD in the store's designability concept. Do not compare these values with other designability results.Scaffold-Lab: Critical evaluation and ranking of protein backbone generation methods in a unified framework · Table 3, column 'Designability(↑)'; Metrics, equation (1)
Methods, coverage and source FrameDiff Novelty(↓) on Scaffold-Lab unconditional generation, length 300
lit-structure-20261011-scaffoldlab-protocol-novelty
Aggregation: Not reported
Scaffold-Lab: Critical evaluation and ranking of protein backbone generation methods in a unified framework · Table 3, row 'Medium' / 'FrameDiff' / length 300, column 'Novelty(↓)' Configuration: FrameDiff (Scaffold-Lab unconditional generation) Protocol: Scaffold-Lab unconditional generation: Novelty(↓) Dataset: Scaffold-Lab generated backbones (100 per length group) 0.654 TM score (novelty as the pdb-TM of designable backbones against the PDB (lower is more novel); group mean without data preprocessing; length 400)unitless · lower
Uncertainty: Not reported by the source
Coverage: Not reported scored / Not reported eligible
Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 3 Designability column: equation (1) defines a per-backbone success over 100 backbones per length, which gives two-decimal fractions, but the column prints three-decimal group means; the aggregation behind the column is not stated, and the criterion is sc-TM above 0.5, not the 2 Angstrom sc-RMSD in the store's designability concept. Do not compare these values with other designability results.Scaffold-Lab: Critical evaluation and ranking of protein backbone generation methods in a unified framework · Table 3, column 'Designability(↑)'; Metrics, equation (1)
Methods, coverage and source FrameDiff Novelty(↓) on Scaffold-Lab unconditional generation, length 400
lit-structure-20261011-scaffoldlab-protocol-novelty
Aggregation: Not reported
Scaffold-Lab: Critical evaluation and ranking of protein backbone generation methods in a unified framework · Table 3, row 'Medium' / 'FrameDiff' / length 400, column 'Novelty(↓)' Configuration: FrameDiff (Scaffold-Lab unconditional generation) Protocol: Scaffold-Lab unconditional generation: Novelty(↓) Dataset: Scaffold-Lab generated backbones (100 per length group) 0.69 TM score (novelty as the pdb-TM of designable backbones against the PDB (lower is more novel); group mean without data preprocessing; length 500)unitless · lower
Uncertainty: Not reported by the source
Coverage: Not reported scored / Not reported eligible
Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 3 Designability column: equation (1) defines a per-backbone success over 100 backbones per length, which gives two-decimal fractions, but the column prints three-decimal group means; the aggregation behind the column is not stated, and the criterion is sc-TM above 0.5, not the 2 Angstrom sc-RMSD in the store's designability concept. Do not compare these values with other designability results.Scaffold-Lab: Critical evaluation and ranking of protein backbone generation methods in a unified framework · Table 3, column 'Designability(↑)'; Metrics, equation (1)
Methods, coverage and source FrameDiff Novelty(↓) on Scaffold-Lab unconditional generation, length 500
lit-structure-20261011-scaffoldlab-protocol-novelty
Aggregation: Not reported
Scaffold-Lab: Critical evaluation and ranking of protein backbone generation methods in a unified framework · Table 3, row 'Medium' / 'FrameDiff' / length 500, column 'Novelty(↓)' Configuration: FrameDiff (Scaffold-Lab unconditional generation) Protocol: Scaffold-Lab unconditional generation: Novelty(↓) Dataset: Scaffold-Lab generated backbones (100 per length group) 0.711 TM score (novelty as the pdb-TM of designable backbones against the PDB (lower is more novel); group mean without data preprocessing; length 100)unitless · lower
Uncertainty: Not reported by the source
Coverage: Not reported scored / Not reported eligible
Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 3 Designability column: equation (1) defines a per-backbone success over 100 backbones per length, which gives two-decimal fractions, but the column prints three-decimal group means; the aggregation behind the column is not stated, and the criterion is sc-TM above 0.5, not the 2 Angstrom sc-RMSD in the store's designability concept. Do not compare these values with other designability results.Scaffold-Lab: Critical evaluation and ranking of protein backbone generation methods in a unified framework · Table 3, column 'Designability(↑)'; Metrics, equation (1)
Methods, coverage and source FrameDiff Novelty(↓) on Scaffold-Lab unconditional generation, length 100
lit-structure-20261011-scaffoldlab-protocol-novelty
Aggregation: Not reported
Scaffold-Lab: Critical evaluation and ranking of protein backbone generation methods in a unified framework · Table 3, row 'Short' / 'FrameDiff' / length 100, column 'Novelty(↓)' Configuration: FrameDiff (Scaffold-Lab unconditional generation) Protocol: Scaffold-Lab unconditional generation: Novelty(↓) Dataset: Scaffold-Lab generated backbones (100 per length group) 0.731 TM score (novelty as the pdb-TM of designable backbones against the PDB (lower is more novel); group mean without data preprocessing; length 50)unitless · lower
Uncertainty: Not reported by the source
Coverage: Not reported scored / Not reported eligible
Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 3 Designability column: equation (1) defines a per-backbone success over 100 backbones per length, which gives two-decimal fractions, but the column prints three-decimal group means; the aggregation behind the column is not stated, and the criterion is sc-TM above 0.5, not the 2 Angstrom sc-RMSD in the store's designability concept. Do not compare these values with other designability results.Scaffold-Lab: Critical evaluation and ranking of protein backbone generation methods in a unified framework · Table 3, column 'Designability(↑)'; Metrics, equation (1)
Methods, coverage and source FrameDiff Novelty(↓) on Scaffold-Lab unconditional generation, length 50
lit-structure-20261011-scaffoldlab-protocol-novelty
Aggregation: Not reported
Scaffold-Lab: Critical evaluation and ranking of protein backbone generation methods in a unified framework · Table 3, row 'Short' / 'FrameDiff' / length 50, column 'Novelty(↓)' Configuration: FrameFlow (Scaffold-Lab unconditional generation) Protocol: Scaffold-Lab unconditional generation: Novelty(↓) Dataset: Scaffold-Lab generated backbones (100 per length group) 0.721 TM score (novelty as the pdb-TM of designable backbones against the PDB (lower is more novel); group mean without data preprocessing; length 100)unitless · lower
Uncertainty: Not reported by the source
Coverage: Not reported scored / Not reported eligible
Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 3 Designability column: equation (1) defines a per-backbone success over 100 backbones per length, which gives two-decimal fractions, but the column prints three-decimal group means; the aggregation behind the column is not stated, and the criterion is sc-TM above 0.5, not the 2 Angstrom sc-RMSD in the store's designability concept. Do not compare these values with other designability results.Scaffold-Lab: Critical evaluation and ranking of protein backbone generation methods in a unified framework · Table 3, column 'Designability(↑)'; Metrics, equation (1)
Methods, coverage and source FrameFlow Novelty(↓) on Scaffold-Lab unconditional generation, length 100
lit-structure-20261011-scaffoldlab-protocol-novelty
Aggregation: Not reported
Scaffold-Lab: Critical evaluation and ranking of protein backbone generation methods in a unified framework · Table 3, row 'Short' / 'FrameFlow' / length 100, column 'Novelty(↓)' Configuration: FrameFlow (Scaffold-Lab unconditional generation) Protocol: Scaffold-Lab unconditional generation: Novelty(↓) Dataset: Scaffold-Lab generated backbones (100 per length group) 0.812 TM score (novelty as the pdb-TM of designable backbones against the PDB (lower is more novel); group mean without data preprocessing; length 50)unitless · lower
Uncertainty: Not reported by the source
Coverage: Not reported scored / Not reported eligible
Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 3 Designability column: equation (1) defines a per-backbone success over 100 backbones per length, which gives two-decimal fractions, but the column prints three-decimal group means; the aggregation behind the column is not stated, and the criterion is sc-TM above 0.5, not the 2 Angstrom sc-RMSD in the store's designability concept. Do not compare these values with other designability results.Scaffold-Lab: Critical evaluation and ranking of protein backbone generation methods in a unified framework · Table 3, column 'Designability(↑)'; Metrics, equation (1)
Methods, coverage and source FrameFlow Novelty(↓) on Scaffold-Lab unconditional generation, length 50
lit-structure-20261011-scaffoldlab-protocol-novelty
Aggregation: Not reported
Scaffold-Lab: Critical evaluation and ranking of protein backbone generation methods in a unified framework · Table 3, row 'Short' / 'FrameFlow' / length 50, column 'Novelty(↓)' Configuration: Genie (Scaffold-Lab unconditional generation) Protocol: Scaffold-Lab unconditional generation: Novelty(↓) Dataset: Scaffold-Lab generated backbones (100 per length group) 0.607 TM score (novelty as the pdb-TM of designable backbones against the PDB (lower is more novel); group mean without data preprocessing; length 100)unitless · lower
Uncertainty: Not reported by the source
Coverage: Not reported scored / Not reported eligible
Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 3 Designability column: equation (1) defines a per-backbone success over 100 backbones per length, which gives two-decimal fractions, but the column prints three-decimal group means; the aggregation behind the column is not stated, and the criterion is sc-TM above 0.5, not the 2 Angstrom sc-RMSD in the store's designability concept. Do not compare these values with other designability results.Scaffold-Lab: Critical evaluation and ranking of protein backbone generation methods in a unified framework · Table 3, column 'Designability(↑)'; Metrics, equation (1)
Methods, coverage and source Genie Novelty(↓) on Scaffold-Lab unconditional generation, length 100
lit-structure-20261011-scaffoldlab-protocol-novelty
Aggregation: Not reported
Scaffold-Lab: Critical evaluation and ranking of protein backbone generation methods in a unified framework · Table 3, row 'Short' / 'Genie' / length 100, column 'Novelty(↓)' Configuration: Genie (Scaffold-Lab unconditional generation) Protocol: Scaffold-Lab unconditional generation: Novelty(↓) Dataset: Scaffold-Lab generated backbones (100 per length group) 0.715 TM score (novelty as the pdb-TM of designable backbones against the PDB (lower is more novel); group mean without data preprocessing; length 50)unitless · lower
Uncertainty: Not reported by the source
Coverage: Not reported scored / Not reported eligible
Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 3 Designability column: equation (1) defines a per-backbone success over 100 backbones per length, which gives two-decimal fractions, but the column prints three-decimal group means; the aggregation behind the column is not stated, and the criterion is sc-TM above 0.5, not the 2 Angstrom sc-RMSD in the store's designability concept. Do not compare these values with other designability results.Scaffold-Lab: Critical evaluation and ranking of protein backbone generation methods in a unified framework · Table 3, column 'Designability(↑)'; Metrics, equation (1)
Methods, coverage and source Genie Novelty(↓) on Scaffold-Lab unconditional generation, length 50
lit-structure-20261011-scaffoldlab-protocol-novelty
Aggregation: Not reported
Scaffold-Lab: Critical evaluation and ranking of protein backbone generation methods in a unified framework · Table 3, row 'Short' / 'Genie' / length 50, column 'Novelty(↓)' Configuration: RFdiffusion (Scaffold-Lab unconditional generation) Protocol: Scaffold-Lab unconditional generation: Novelty(↓) Dataset: Scaffold-Lab generated backbones (100 per length group) 0.738 TM score (novelty as the pdb-TM of designable backbones against the PDB (lower is more novel); group mean without data preprocessing; length 1000)unitless · lower
Uncertainty: Not reported by the source
Coverage: Not reported scored / Not reported eligible
Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 3 Designability column: equation (1) defines a per-backbone success over 100 backbones per length, which gives two-decimal fractions, but the column prints three-decimal group means; the aggregation behind the column is not stated, and the criterion is sc-TM above 0.5, not the 2 Angstrom sc-RMSD in the store's designability concept. Do not compare these values with other designability results.Scaffold-Lab: Critical evaluation and ranking of protein backbone generation methods in a unified framework · Table 3, column 'Designability(↑)'; Metrics, equation (1)
Methods, coverage and source RFdiffusion Novelty(↓) on Scaffold-Lab unconditional generation, length 1000
lit-structure-20261011-scaffoldlab-protocol-novelty
Aggregation: Not reported
Scaffold-Lab: Critical evaluation and ranking of protein backbone generation methods in a unified framework · Table 3, row 'Long' / 'RFdiffusion' / length 1000, column 'Novelty(↓)' Configuration: RFdiffusion (Scaffold-Lab unconditional generation) Protocol: Scaffold-Lab unconditional generation: Novelty(↓) Dataset: Scaffold-Lab generated backbones (100 per length group) 0.609 TM score (novelty as the pdb-TM of designable backbones against the PDB (lower is more novel); group mean without data preprocessing; length 600)unitless · lower
Uncertainty: Not reported by the source
Coverage: Not reported scored / Not reported eligible
Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 3 Designability column: equation (1) defines a per-backbone success over 100 backbones per length, which gives two-decimal fractions, but the column prints three-decimal group means; the aggregation behind the column is not stated, and the criterion is sc-TM above 0.5, not the 2 Angstrom sc-RMSD in the store's designability concept. Do not compare these values with other designability results.Scaffold-Lab: Critical evaluation and ranking of protein backbone generation methods in a unified framework · Table 3, column 'Designability(↑)'; Metrics, equation (1)
Methods, coverage and source RFdiffusion Novelty(↓) on Scaffold-Lab unconditional generation, length 600
lit-structure-20261011-scaffoldlab-protocol-novelty
Aggregation: Not reported
Scaffold-Lab: Critical evaluation and ranking of protein backbone generation methods in a unified framework · Table 3, row 'Long' / 'RFdiffusion' / length 600, column 'Novelty(↓)' Configuration: RFdiffusion (Scaffold-Lab unconditional generation) Protocol: Scaffold-Lab unconditional generation: Novelty(↓) Dataset: Scaffold-Lab generated backbones (100 per length group) 0.677 TM score (novelty as the pdb-TM of designable backbones against the PDB (lower is more novel); group mean without data preprocessing; length 800)unitless · lower
Uncertainty: Not reported by the source
Coverage: Not reported scored / Not reported eligible
Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 3 Designability column: equation (1) defines a per-backbone success over 100 backbones per length, which gives two-decimal fractions, but the column prints three-decimal group means; the aggregation behind the column is not stated, and the criterion is sc-TM above 0.5, not the 2 Angstrom sc-RMSD in the store's designability concept. Do not compare these values with other designability results.Scaffold-Lab: Critical evaluation and ranking of protein backbone generation methods in a unified framework · Table 3, column 'Designability(↑)'; Metrics, equation (1)
Methods, coverage and source RFdiffusion Novelty(↓) on Scaffold-Lab unconditional generation, length 800
lit-structure-20261011-scaffoldlab-protocol-novelty
Aggregation: Not reported
Scaffold-Lab: Critical evaluation and ranking of protein backbone generation methods in a unified framework · Table 3, row 'Long' / 'RFdiffusion' / length 800, column 'Novelty(↓)' Configuration: RFdiffusion (Scaffold-Lab unconditional generation) Protocol: Scaffold-Lab unconditional generation: Novelty(↓) Dataset: Scaffold-Lab generated backbones (100 per length group) 0.65 TM score (novelty as the pdb-TM of designable backbones against the PDB (lower is more novel); group mean without data preprocessing; length 200)unitless · lower
Uncertainty: Not reported by the source
Coverage: Not reported scored / Not reported eligible
Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 3 Designability column: equation (1) defines a per-backbone success over 100 backbones per length, which gives two-decimal fractions, but the column prints three-decimal group means; the aggregation behind the column is not stated, and the criterion is sc-TM above 0.5, not the 2 Angstrom sc-RMSD in the store's designability concept. Do not compare these values with other designability results.Scaffold-Lab: Critical evaluation and ranking of protein backbone generation methods in a unified framework · Table 3, column 'Designability(↑)'; Metrics, equation (1)
Methods, coverage and source RFdiffusion Novelty(↓) on Scaffold-Lab unconditional generation, length 200
lit-structure-20261011-scaffoldlab-protocol-novelty
Aggregation: Not reported
Scaffold-Lab: Critical evaluation and ranking of protein backbone generation methods in a unified framework · Table 3, row 'Medium' / 'RFdiffusion' / length 200, column 'Novelty(↓)' Configuration: RFdiffusion (Scaffold-Lab unconditional generation) Protocol: Scaffold-Lab unconditional generation: Novelty(↓) Dataset: Scaffold-Lab generated backbones (100 per length group) 0.614 TM score (novelty as the pdb-TM of designable backbones against the PDB (lower is more novel); group mean without data preprocessing; length 300)unitless · lower
Uncertainty: Not reported by the source
Coverage: Not reported scored / Not reported eligible
Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 3 Designability column: equation (1) defines a per-backbone success over 100 backbones per length, which gives two-decimal fractions, but the column prints three-decimal group means; the aggregation behind the column is not stated, and the criterion is sc-TM above 0.5, not the 2 Angstrom sc-RMSD in the store's designability concept. Do not compare these values with other designability results.Scaffold-Lab: Critical evaluation and ranking of protein backbone generation methods in a unified framework · Table 3, column 'Designability(↑)'; Metrics, equation (1)
Methods, coverage and source RFdiffusion Novelty(↓) on Scaffold-Lab unconditional generation, length 300
lit-structure-20261011-scaffoldlab-protocol-novelty
Aggregation: Not reported
Scaffold-Lab: Critical evaluation and ranking of protein backbone generation methods in a unified framework · Table 3, row 'Medium' / 'RFdiffusion' / length 300, column 'Novelty(↓)' Configuration: RFdiffusion (Scaffold-Lab unconditional generation) Protocol: Scaffold-Lab unconditional generation: Novelty(↓) Dataset: Scaffold-Lab generated backbones (100 per length group) 0.591 TM score (novelty as the pdb-TM of designable backbones against the PDB (lower is more novel); group mean without data preprocessing; length 400)unitless · lower
Uncertainty: Not reported by the source
Coverage: Not reported scored / Not reported eligible
Independent external evaluation · Source checked Evidence concern: excluded from comparisons Table 3 Designability column: equation (1) defines a per-backbone success over 100 backbones per length, which gives two-decimal fractions, but the column prints three-decimal group means; the aggregation behind the column is not stated, and the criterion is sc-TM above 0.5, not the 2 Angstrom sc-RMSD in the store's designability concept. Do not compare these values with other designability results.Scaffold-Lab: Critical evaluation and ranking of protein backbone generation methods in a unified framework · Table 3, column 'Designability(↑)'; Metrics, equation (1)
Methods, coverage and source RFdiffusion Novelty(↓) on Scaffold-Lab unconditional generation, length 400
lit-structure-20261011-scaffoldlab-protocol-novelty
Aggregation: Not reported
Scaffold-Lab: Critical evaluation and ranking of protein backbone generation methods in a unified framework · Table 3, row 'Medium' / 'RFdiffusion' / length 400, column 'Novelty(↓)'