rewirebio.iobenchmarks
← Browse all sources
Source

Scaffold-Lab: Critical evaluation and ranking of protein backbone generation methods in a unified framework

PLoS Computational Biology · 2026 · Version of record, PLoS Computational Biology 2026 (PMC13225634 JATS full text) · Peer-reviewed

DOI: 10.1371/journal.pcbi.1014290Original source

What this source contributed

Records in this release that cite this source. A record can cite several sources.

Results

Values as the source printed them. Compare results only under compatible protocols, datasets and metrics.

Model or configurationMetricValueDatasetEvaluation
Chroma (Scaffold-Lab unconditional generation)Topsis relative closeness (TOPSIS relative closeness with CRITIC weights, per length; length 50)0.368 unitlessScaffold-Lab generated backbones (100 per length group)Chroma Ci on Scaffold-Lab unconditional generation, length 50
Chroma (Scaffold-Lab unconditional generation)Topsis relative closeness (TOPSIS relative closeness with CRITIC weights, per length; length 100)0.437 unitlessScaffold-Lab generated backbones (100 per length group)Chroma Ci on Scaffold-Lab unconditional generation, length 100
Chroma (Scaffold-Lab unconditional generation)Topsis relative closeness (TOPSIS relative closeness with CRITIC weights, per length; length 200)0.275 unitlessScaffold-Lab generated backbones (100 per length group)Chroma Ci on Scaffold-Lab unconditional generation, length 200
Chroma (Scaffold-Lab unconditional generation)Topsis relative closeness (TOPSIS relative closeness with CRITIC weights, per length; length 300)0.398 unitlessScaffold-Lab generated backbones (100 per length group)Chroma Ci on Scaffold-Lab unconditional generation, length 300
Chroma (Scaffold-Lab unconditional generation)Topsis relative closeness (TOPSIS relative closeness with CRITIC weights, per length; length 400)0.262 unitlessScaffold-Lab generated backbones (100 per length group)Chroma Ci on Scaffold-Lab unconditional generation, length 400
Chroma (Scaffold-Lab unconditional generation)Topsis relative closeness (TOPSIS relative closeness with CRITIC weights, per length; length 500)0.249 unitlessScaffold-Lab generated backbones (100 per length group)Chroma Ci on Scaffold-Lab unconditional generation, length 500
Chroma (Scaffold-Lab unconditional generation)Topsis relative closeness (TOPSIS relative closeness with CRITIC weights, per length; length 600)0.516 unitlessScaffold-Lab generated backbones (100 per length group)Chroma Ci on Scaffold-Lab unconditional generation, length 600
Chroma (Scaffold-Lab unconditional generation)Topsis relative closeness (TOPSIS relative closeness with CRITIC weights, per length; length 800)0.325 unitlessScaffold-Lab generated backbones (100 per length group)Chroma Ci on Scaffold-Lab unconditional generation, length 800
Chroma (Scaffold-Lab unconditional generation)Topsis relative closeness (TOPSIS relative closeness with CRITIC weights, per length; length 1000)0.222 unitlessScaffold-Lab generated backbones (100 per length group)Chroma Ci on Scaffold-Lab unconditional generation, length 1000
Chroma (Scaffold-Lab unconditional generation)Designability (Table 3 'Designability' column, printed as a group mean without data preprocessing; the Metrics section counts a backbone as designable when the mean sc-TM of its top 3 ProteinMPNN sequences refolded with ESMFold exceeds 0.5 (equation 1); the table does not state whether the value is the share of designable backbones or a mean sc-TM; not comparable with the 2 Angstrom sc-RMSD criterion in the concept definition; length 50)0.691 fractionScaffold-Lab generated backbones (100 per length group)Chroma Designability(↑) on Scaffold-Lab unconditional generation, length 50
Chroma (Scaffold-Lab unconditional generation)Designability (Table 3 'Designability' column, printed as a group mean without data preprocessing; the Metrics section counts a backbone as designable when the mean sc-TM of its top 3 ProteinMPNN sequences refolded with ESMFold exceeds 0.5 (equation 1); the table does not state whether the value is the share of designable backbones or a mean sc-TM; not comparable with the 2 Angstrom sc-RMSD criterion in the concept definition; length 100)0.763 fractionScaffold-Lab generated backbones (100 per length group)Chroma Designability(↑) on Scaffold-Lab unconditional generation, length 100
Chroma (Scaffold-Lab unconditional generation)Designability (Table 3 'Designability' column, printed as a group mean without data preprocessing; the Metrics section counts a backbone as designable when the mean sc-TM of its top 3 ProteinMPNN sequences refolded with ESMFold exceeds 0.5 (equation 1); the table does not state whether the value is the share of designable backbones or a mean sc-TM; not comparable with the 2 Angstrom sc-RMSD criterion in the concept definition; length 200)0.76 fractionScaffold-Lab generated backbones (100 per length group)Chroma Designability(↑) on Scaffold-Lab unconditional generation, length 200
Chroma (Scaffold-Lab unconditional generation)Designability (Table 3 'Designability' column, printed as a group mean without data preprocessing; the Metrics section counts a backbone as designable when the mean sc-TM of its top 3 ProteinMPNN sequences refolded with ESMFold exceeds 0.5 (equation 1); the table does not state whether the value is the share of designable backbones or a mean sc-TM; not comparable with the 2 Angstrom sc-RMSD criterion in the concept definition; length 300)0.684 fractionScaffold-Lab generated backbones (100 per length group)Chroma Designability(↑) on Scaffold-Lab unconditional generation, length 300
Chroma (Scaffold-Lab unconditional generation)Designability (Table 3 'Designability' column, printed as a group mean without data preprocessing; the Metrics section counts a backbone as designable when the mean sc-TM of its top 3 ProteinMPNN sequences refolded with ESMFold exceeds 0.5 (equation 1); the table does not state whether the value is the share of designable backbones or a mean sc-TM; not comparable with the 2 Angstrom sc-RMSD criterion in the concept definition; length 400)0.545 fractionScaffold-Lab generated backbones (100 per length group)Chroma Designability(↑) on Scaffold-Lab unconditional generation, length 400
Chroma (Scaffold-Lab unconditional generation)Designability (Table 3 'Designability' column, printed as a group mean without data preprocessing; the Metrics section counts a backbone as designable when the mean sc-TM of its top 3 ProteinMPNN sequences refolded with ESMFold exceeds 0.5 (equation 1); the table does not state whether the value is the share of designable backbones or a mean sc-TM; not comparable with the 2 Angstrom sc-RMSD criterion in the concept definition; length 500)0.48 fractionScaffold-Lab generated backbones (100 per length group)Chroma Designability(↑) on Scaffold-Lab unconditional generation, length 500
Chroma (Scaffold-Lab unconditional generation)Designability (Table 3 'Designability' column, printed as a group mean without data preprocessing; the Metrics section counts a backbone as designable when the mean sc-TM of its top 3 ProteinMPNN sequences refolded with ESMFold exceeds 0.5 (equation 1); the table does not state whether the value is the share of designable backbones or a mean sc-TM; not comparable with the 2 Angstrom sc-RMSD criterion in the concept definition; length 600)0.432 fractionScaffold-Lab generated backbones (100 per length group)Chroma Designability(↑) on Scaffold-Lab unconditional generation, length 600
Chroma (Scaffold-Lab unconditional generation)Designability (Table 3 'Designability' column, printed as a group mean without data preprocessing; the Metrics section counts a backbone as designable when the mean sc-TM of its top 3 ProteinMPNN sequences refolded with ESMFold exceeds 0.5 (equation 1); the table does not state whether the value is the share of designable backbones or a mean sc-TM; not comparable with the 2 Angstrom sc-RMSD criterion in the concept definition; length 800)0.434 fractionScaffold-Lab generated backbones (100 per length group)Chroma Designability(↑) on Scaffold-Lab unconditional generation, length 800
Chroma (Scaffold-Lab unconditional generation)Designability (Table 3 'Designability' column, printed as a group mean without data preprocessing; the Metrics section counts a backbone as designable when the mean sc-TM of its top 3 ProteinMPNN sequences refolded with ESMFold exceeds 0.5 (equation 1); the table does not state whether the value is the share of designable backbones or a mean sc-TM; not comparable with the 2 Angstrom sc-RMSD criterion in the concept definition; length 1000)0.427 fractionScaffold-Lab generated backbones (100 per length group)Chroma Designability(↑) on Scaffold-Lab unconditional generation, length 1000
Chroma (Scaffold-Lab unconditional generation)Proportion (unique Foldseek-Cluster clusters divided by the number of backbones in the group, clustering TM-score threshold 0.5; group mean without data preprocessing; length 50)0.54 fractionScaffold-Lab generated backbones (100 per length group)Chroma Diversity (↑) on Scaffold-Lab unconditional generation, length 50
Chroma (Scaffold-Lab unconditional generation)Proportion (unique Foldseek-Cluster clusters divided by the number of backbones in the group, clustering TM-score threshold 0.5; group mean without data preprocessing; length 100)0.66 fractionScaffold-Lab generated backbones (100 per length group)Chroma Diversity (↑) on Scaffold-Lab unconditional generation, length 100
Chroma (Scaffold-Lab unconditional generation)Proportion (unique Foldseek-Cluster clusters divided by the number of backbones in the group, clustering TM-score threshold 0.5; group mean without data preprocessing; length 200)0.48 fractionScaffold-Lab generated backbones (100 per length group)Chroma Diversity (↑) on Scaffold-Lab unconditional generation, length 200
Chroma (Scaffold-Lab unconditional generation)Proportion (unique Foldseek-Cluster clusters divided by the number of backbones in the group, clustering TM-score threshold 0.5; group mean without data preprocessing; length 300)0.67 fractionScaffold-Lab generated backbones (100 per length group)Chroma Diversity (↑) on Scaffold-Lab unconditional generation, length 300
Chroma (Scaffold-Lab unconditional generation)Proportion (unique Foldseek-Cluster clusters divided by the number of backbones in the group, clustering TM-score threshold 0.5; group mean without data preprocessing; length 400)0.74 fractionScaffold-Lab generated backbones (100 per length group)Chroma Diversity (↑) on Scaffold-Lab unconditional generation, length 400
Chroma (Scaffold-Lab unconditional generation)Proportion (unique Foldseek-Cluster clusters divided by the number of backbones in the group, clustering TM-score threshold 0.5; group mean without data preprocessing; length 500)0.84 fractionScaffold-Lab generated backbones (100 per length group)Chroma Diversity (↑) on Scaffold-Lab unconditional generation, length 500
Chroma (Scaffold-Lab unconditional generation)Proportion (unique Foldseek-Cluster clusters divided by the number of backbones in the group, clustering TM-score threshold 0.5; group mean without data preprocessing; length 600)0.88 fractionScaffold-Lab generated backbones (100 per length group)Chroma Diversity (↑) on Scaffold-Lab unconditional generation, length 600
Chroma (Scaffold-Lab unconditional generation)Proportion (unique Foldseek-Cluster clusters divided by the number of backbones in the group, clustering TM-score threshold 0.5; group mean without data preprocessing; length 800)0.84 fractionScaffold-Lab generated backbones (100 per length group)Chroma Diversity (↑) on Scaffold-Lab unconditional generation, length 800
Chroma (Scaffold-Lab unconditional generation)Proportion (unique Foldseek-Cluster clusters divided by the number of backbones in the group, clustering TM-score threshold 0.5; group mean without data preprocessing; length 1000)0.7 fractionScaffold-Lab generated backbones (100 per length group)Chroma Diversity (↑) on Scaffold-Lab unconditional generation, length 1000
Chroma (Scaffold-Lab unconditional generation)Runtime (average time taken to generate each backbone over 100 backbones per group, on identical hardware; length 50)1.17 unit-unreportedScaffold-Lab generated backbones (100 per length group)Chroma Efficiency (↓) on Scaffold-Lab unconditional generation, length 50
Chroma (Scaffold-Lab unconditional generation)Runtime (average time taken to generate each backbone over 100 backbones per group, on identical hardware; length 100)2.73 unit-unreportedScaffold-Lab generated backbones (100 per length group)Chroma Efficiency (↓) on Scaffold-Lab unconditional generation, length 100
Chroma (Scaffold-Lab unconditional generation)Runtime (average time taken to generate each backbone over 100 backbones per group, on identical hardware; length 200)4.68 unit-unreportedScaffold-Lab generated backbones (100 per length group)Chroma Efficiency (↓) on Scaffold-Lab unconditional generation, length 200
Chroma (Scaffold-Lab unconditional generation)Runtime (average time taken to generate each backbone over 100 backbones per group, on identical hardware; length 300)5.73 unit-unreportedScaffold-Lab generated backbones (100 per length group)Chroma Efficiency (↓) on Scaffold-Lab unconditional generation, length 300
Chroma (Scaffold-Lab unconditional generation)Runtime (average time taken to generate each backbone over 100 backbones per group, on identical hardware; length 400)6.92 unit-unreportedScaffold-Lab generated backbones (100 per length group)Chroma Efficiency (↓) on Scaffold-Lab unconditional generation, length 400
Chroma (Scaffold-Lab unconditional generation)Runtime (average time taken to generate each backbone over 100 backbones per group, on identical hardware; length 500)8.56 unit-unreportedScaffold-Lab generated backbones (100 per length group)Chroma Efficiency (↓) on Scaffold-Lab unconditional generation, length 500
Chroma (Scaffold-Lab unconditional generation)Runtime (average time taken to generate each backbone over 100 backbones per group, on identical hardware; length 600)12.2 unit-unreportedScaffold-Lab generated backbones (100 per length group)Chroma Efficiency (↓) on Scaffold-Lab unconditional generation, length 600
Chroma (Scaffold-Lab unconditional generation)Runtime (average time taken to generate each backbone over 100 backbones per group, on identical hardware; length 800)19.27 unit-unreportedScaffold-Lab generated backbones (100 per length group)Chroma Efficiency (↓) on Scaffold-Lab unconditional generation, length 800
Chroma (Scaffold-Lab unconditional generation)Runtime (average time taken to generate each backbone over 100 backbones per group, on identical hardware; length 1000)24.67 unit-unreportedScaffold-Lab generated backbones (100 per length group)Chroma Efficiency (↓) on Scaffold-Lab unconditional generation, length 1000
Chroma (Scaffold-Lab unconditional generation)Topsis relative closeness (TOPSIS relative closeness with CRITIC weights, mean over the lengths in the group; Long group)0.354 unitlessScaffold-Lab generated backbones (100 per length group)Chroma Mean Ci on Scaffold-Lab unconditional generation, Long group
Chroma (Scaffold-Lab unconditional generation)Topsis relative closeness (TOPSIS relative closeness with CRITIC weights, mean over the lengths in the group; Medium group)0.296 unitlessScaffold-Lab generated backbones (100 per length group)Chroma Mean Ci on Scaffold-Lab unconditional generation, Medium group
Chroma (Scaffold-Lab unconditional generation)Topsis relative closeness (TOPSIS relative closeness with CRITIC weights, mean over the lengths in the group; Short group)0.403 unitlessScaffold-Lab generated backbones (100 per length group)Chroma Mean Ci on Scaffold-Lab unconditional generation, Short group
Chroma (Scaffold-Lab unconditional generation)TM score (novelty as the pdb-TM of designable backbones against the PDB (lower is more novel); group mean without data preprocessing; length 50)0.715 unitlessScaffold-Lab generated backbones (100 per length group)Chroma Novelty(↓) on Scaffold-Lab unconditional generation, length 50
Chroma (Scaffold-Lab unconditional generation)TM score (novelty as the pdb-TM of designable backbones against the PDB (lower is more novel); group mean without data preprocessing; length 100)0.682 unitlessScaffold-Lab generated backbones (100 per length group)Chroma Novelty(↓) on Scaffold-Lab unconditional generation, length 100
Chroma (Scaffold-Lab unconditional generation)TM score (novelty as the pdb-TM of designable backbones against the PDB (lower is more novel); group mean without data preprocessing; length 200)0.676 unitlessScaffold-Lab generated backbones (100 per length group)Chroma Novelty(↓) on Scaffold-Lab unconditional generation, length 200
Chroma (Scaffold-Lab unconditional generation)TM score (novelty as the pdb-TM of designable backbones against the PDB (lower is more novel); group mean without data preprocessing; length 300)0.637 unitlessScaffold-Lab generated backbones (100 per length group)Chroma Novelty(↓) on Scaffold-Lab unconditional generation, length 300
Chroma (Scaffold-Lab unconditional generation)TM score (novelty as the pdb-TM of designable backbones against the PDB (lower is more novel); group mean without data preprocessing; length 400)0.668 unitlessScaffold-Lab generated backbones (100 per length group)Chroma Novelty(↓) on Scaffold-Lab unconditional generation, length 400
Chroma (Scaffold-Lab unconditional generation)TM score (novelty as the pdb-TM of designable backbones against the PDB (lower is more novel); group mean without data preprocessing; length 500)0.685 unitlessScaffold-Lab generated backbones (100 per length group)Chroma Novelty(↓) on Scaffold-Lab unconditional generation, length 500
Chroma (Scaffold-Lab unconditional generation)TM score (novelty as the pdb-TM of designable backbones against the PDB (lower is more novel); group mean without data preprocessing; length 600)0.733 unitlessScaffold-Lab generated backbones (100 per length group)Chroma Novelty(↓) on Scaffold-Lab unconditional generation, length 600
Chroma (Scaffold-Lab unconditional generation)TM score (novelty as the pdb-TM of designable backbones against the PDB (lower is more novel); group mean without data preprocessing; length 800)0.746 unitlessScaffold-Lab generated backbones (100 per length group)Chroma Novelty(↓) on Scaffold-Lab unconditional generation, length 800
Chroma (Scaffold-Lab unconditional generation)TM score (novelty as the pdb-TM of designable backbones against the PDB (lower is more novel); group mean without data preprocessing; length 1000)0.742 unitlessScaffold-Lab generated backbones (100 per length group)Chroma Novelty(↓) on Scaffold-Lab unconditional generation, length 1000
Chroma (Scaffold-Lab unconditional generation)Rank (rank within the length group by mean TOPSIS relative closeness; Long group)2 unitlessScaffold-Lab generated backbones (100 per length group)Chroma Rank on Scaffold-Lab unconditional generation, Long group
Chroma (Scaffold-Lab unconditional generation)Rank (rank within the length group by mean TOPSIS relative closeness; Medium group)3 unitlessScaffold-Lab generated backbones (100 per length group)Chroma Rank on Scaffold-Lab unconditional generation, Medium group

Models, benchmarks and other records

Models (4)

Configurations (5)

Benchmarks (1)

Protocols (7)

Datasets (1)

Evaluations (160)

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.

26 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-10-23-5347695500ed
Property and statementOriginal source and locationReview and provenance
Artifact SHA-256
9ff68ef80dc57d6ef85920d4d2104e86d071215ac9c74367a72b2a85669840d0
Source metadata		Scaffold-Lab: Critical evaluation and ranking of protein backbone generation methods in a unified framework

Original source ↗

No field-specific location recorded

Version: Version of record, PLoS Computational Biology 2026 (PMC13225634 JATS full text)
Retrieved: 2026-10-11T21:30:00Z

catalogued

No individual claim review recorded

Source has a recorded evidence concern. Consult its source page before using the claim.

Audit details

Field: attributes.artifact_sha256

Source artifact SHA-256: 9ff68ef80dc57d6ef85920d4d2104e86d071215ac9c74367a72b2a85669840d0

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Artifact url
https://www.ebi.ac.uk/europepmc/webservices/rest/PMC13225634/fullTextXML
Source metadata		Scaffold-Lab: Critical evaluation and ranking of protein backbone generation methods in a unified framework

Original source ↗

No field-specific location recorded

Version: Version of record, PLoS Computational Biology 2026 (PMC13225634 JATS full text)
Retrieved: 2026-10-11T21:30:00Z

catalogued

No individual claim review recorded

Source has a recorded evidence concern. Consult its source page before using the claim.

Audit details

Field: attributes.artifact_url

Source artifact SHA-256: 9ff68ef80dc57d6ef85920d4d2104e86d071215ac9c74367a72b2a85669840d0

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Doi
10.1371/journal.pcbi.1014290
Source metadata		Scaffold-Lab: Critical evaluation and ranking of protein backbone generation methods in a unified framework

Original source ↗

No field-specific location recorded

Version: Version of record, PLoS Computational Biology 2026 (PMC13225634 JATS full text)
Retrieved: 2026-10-11T21:30:00Z

catalogued

No individual claim review recorded

Source has a recorded evidence concern. Consult its source page before using the claim.

Audit details

Field: attributes.doi

Source artifact SHA-256: 9ff68ef80dc57d6ef85920d4d2104e86d071215ac9c74367a72b2a85669840d0

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Evidence concerns
1 values
  • source id
    lit-structure-20261011-scaffoldlab-source-zheng2026
    message
    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.
    source locator
    Table 3, column 'Designability(↑)'; Metrics, equation (1)
    artifact sha256
    9ff68ef80dc57d6ef85920d4d2104e86d071215ac9c74367a72b2a85669840d0
    review date
    2026-10-11
Source metadata		Scaffold-Lab: Critical evaluation and ranking of protein backbone generation methods in a unified framework

Original source ↗

No field-specific location recorded

Version: Version of record, PLoS Computational Biology 2026 (PMC13225634 JATS full text)
Retrieved: 2026-10-11T21:30:00Z

catalogued

No individual claim review recorded

Source has a recorded evidence concern. Consult its source page before using the claim.

Audit details

Field: attributes.evidence_concerns

Source artifact SHA-256: 9ff68ef80dc57d6ef85920d4d2104e86d071215ac9c74367a72b2a85669840d0

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Licence
CC BY 4.0
Source metadata		Scaffold-Lab: Critical evaluation and ranking of protein backbone generation methods in a unified framework

Original source ↗

No field-specific location recorded

Version: Version of record, PLoS Computational Biology 2026 (PMC13225634 JATS full text)
Retrieved: 2026-10-11T21:30:00Z

catalogued

No individual claim review recorded

Source has a recorded evidence concern. Consult its source page before using the claim.

Audit details

Field: attributes.licence

Source artifact SHA-256: 9ff68ef80dc57d6ef85920d4d2104e86d071215ac9c74367a72b2a85669840d0

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Limitations
4 values
  • Table 3 only: the unconditional-generation summary. The motif-scaffolding results, the secondary-structure composition, the structural-validity checks and the dynamic-threshold analyses are figures and were not extracted.
  • Table 3 prints no unit for the efficiency column; the text says it is the average time to generate each backbone and that current methods take several minutes, so the unit is recorded as unreported.
  • The table prints group means without data preprocessing; the per-backbone values behind them are not published in the article.
  • The acknowledgements thank Brian L. Trippe, an author of FrameDiff, for contributing to the Scaffold-Lab codebase; he is not an author of this paper.
Source metadata		Scaffold-Lab: Critical evaluation and ranking of protein backbone generation methods in a unified framework

Original source ↗

No field-specific location recorded

Version: Version of record, PLoS Computational Biology 2026 (PMC13225634 JATS full text)
Retrieved: 2026-10-11T21:30:00Z

catalogued

No individual claim review recorded

Source has a recorded evidence concern. Consult its source page before using the claim.

Audit details

Field: attributes.limitations

Source artifact SHA-256: 9ff68ef80dc57d6ef85920d4d2104e86d071215ac9c74367a72b2a85669840d0

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Media type
application/xml
Source metadata		Scaffold-Lab: Critical evaluation and ranking of protein backbone generation methods in a unified framework

Original source ↗

No field-specific location recorded

Version: Version of record, PLoS Computational Biology 2026 (PMC13225634 JATS full text)
Retrieved: 2026-10-11T21:30:00Z

catalogued

No individual claim review recorded

Source has a recorded evidence concern. Consult its source page before using the claim.

Audit details

Field: attributes.media_type

Source artifact SHA-256: 9ff68ef80dc57d6ef85920d4d2104e86d071215ac9c74367a72b2a85669840d0

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Publication status
peer_reviewed
Source metadata		Scaffold-Lab: Critical evaluation and ranking of protein backbone generation methods in a unified framework

Original source ↗

No field-specific location recorded

Version: Version of record, PLoS Computational Biology 2026 (PMC13225634 JATS full text)
Retrieved: 2026-10-11T21:30:00Z

catalogued

No individual claim review recorded

Source has a recorded evidence concern. Consult its source page before using the claim.

Audit details

Field: attributes.publication_status

Source artifact SHA-256: 9ff68ef80dc57d6ef85920d4d2104e86d071215ac9c74367a72b2a85669840d0

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Retrieved at
2026-10-11T21:30:00Z
Source metadata		Scaffold-Lab: Critical evaluation and ranking of protein backbone generation methods in a unified framework

Original source ↗

No field-specific location recorded

Version: Version of record, PLoS Computational Biology 2026 (PMC13225634 JATS full text)
Retrieved: 2026-10-11T21:30:00Z

catalogued

No individual claim review recorded

Source has a recorded evidence concern. Consult its source page before using the claim.

Audit details

Field: attributes.retrieved_at

Source artifact SHA-256: 9ff68ef80dc57d6ef85920d4d2104e86d071215ac9c74367a72b2a85669840d0

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Review: date
2026-10-11
Source metadata		Scaffold-Lab: Critical evaluation and ranking of protein backbone generation methods in a unified framework

Original source ↗

No field-specific location recorded

Version: Version of record, PLoS Computational Biology 2026 (PMC13225634 JATS full text)
Retrieved: 2026-10-11T21:30:00Z

catalogued

No individual claim review recorded

Source has a recorded evidence concern. Consult its source page before using the claim.

Audit details

Field: attributes.review.date

Source artifact SHA-256: 9ff68ef80dc57d6ef85920d4d2104e86d071215ac9c74367a72b2a85669840d0

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

How to read the evidence

Sources and history

Release 2026-10-23-5347695500ed · Record review: source checked

Primary source retrieved and hashed for the 2026-10-11 protein and structure literature pass.

Release history

No supporting source is linked yet.

Read original source

Download this release (gzip)
Technical metadata and extraction receipts

Stable ID: lit-structure-20261011-scaffoldlab-source-zheng2026

areas
protein-structure
contexts
research
url
https://pmc.ncbi.nlm.nih.gov/articles/PMC13225634/
artifact url
https://www.ebi.ac.uk/europepmc/webservices/rest/PMC13225634/fullTextXML
doi
10.1371/journal.pcbi.1014290
version
Version of record, PLoS Computational Biology 2026 (PMC13225634 JATS full text)
retrieved at
2026-10-11T21:30:00Z
artifact sha256
9ff68ef80dc57d6ef85920d4d2104e86d071215ac9c74367a72b2a85669840d0
publication status
peer_reviewed
licence
CC BY 4.0
media type
application/xml
venue
PLoS Computational Biology
year
2026
limitations
Table 3 only: the unconditional-generation summary. The motif-scaffolding results, the secondary-structure composition, the structural-validity checks and the dynamic-threshold analyses are figures and were not extracted.; Table 3 prints no unit for the efficiency column; the text says it is the average time to generate each backbone and that current methods take several minutes, so the unit is recorded as unreported.; The table prints group means without data preprocessing; the per-backbone values behind them are not published in the article.; The acknowledgements thank Brian L. Trippe, an author of FrameDiff, for contributing to the Scaffold-Lab codebase; he is not an author of this paper.
evidence concerns
source id: lit-structure-20261011-scaffoldlab-source-zheng2026; message: 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.; source locator: Table 3, column 'Designability(↑)'; Metrics, equation (1); artifact sha256: 9ff68ef80dc57d6ef85920d4d2104e86d071215ac9c74367a72b2a85669840d0; review date: 2026-10-11
review
method: source-hash-verification; method note: Artifact re-retrieved from Europe PMC and SHA-256 matched.; reviewer: claude; reviewer note: Claude review agent reviewer-ps-2, independent of the extractor lit-protein-structure; no human review claimed; date: 2026-10-11
Related records

    Suggest a correction