rewirebio.iobenchmarks
Evidence claim

Relevance of Megascale held-out test split ddG prediction (Dieckhaus et al. 2024) to "Assess methods for protein stability experiments"

Use case
Assess methods for protein stability experiments
Assessed by
Megascale held-out test split ddG prediction (Dieckhaus et al. 2024 Table 2)
Relevance
Direct evidence
Endpoint
RMSE and correlation of predicted ddG on the Megascale held-out test split for the ThermoMPNN comparison set

Held-out proteins with no homologue in the training sets directly test generalisation to unseen proteins, the validation step the use case asks about.

12 reviewed evaluations

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.

20 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-11-21-adc15377fab2
Property and statementOriginal source and locationReview and provenance
Citation locations
1 values
  • source id
    protein-stability-20261009-source-dieckhaus2024
    locator
    Table 2 and footnotes; Methods 'Datasets'
Context-only references
Transfer learning to leverage larger datasets for improved prediction of protein stability changes

Original source ↗

protein-stability-20261009-source-dieckhaus2024: Table 2 and footnotes; Methods 'Datasets'

Version: PNAS 121(6):e2314853121, published 2024-01-29; PMC10861915 full-text XML
Retrieved: 2026-10-09T21:01:06Z

not individually reviewed

No individual claim review recorded

Audit details

Field: attributes.citation_locators

Source artifact SHA-256: ba9a763c388eeea47d70fd0d8e2fbf497f61fc8a88dc93d5dac261572daa8010

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

Inspected artifact

Comparison group
dieckhaus2024-thermompnn
Context-only references
Transfer learning to leverage larger datasets for improved prediction of protein stability changes

Original source ↗

protein-stability-20261009-source-dieckhaus2024: Table 2 and footnotes; Methods 'Datasets'

Version: PNAS 121(6):e2314853121, published 2024-01-29; PMC10861915 full-text XML
Retrieved: 2026-10-09T21:01:06Z

not individually reviewed

No individual claim review recorded

Audit details

Field: attributes.comparison_group

Source artifact SHA-256: ba9a763c388eeea47d70fd0d8e2fbf497f61fc8a88dc93d5dac261572daa8010

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

Inspected artifact

Comparison title
ThermoMPNN comparison sets (Dieckhaus et al. 2024)
Context-only references
Transfer learning to leverage larger datasets for improved prediction of protein stability changes

Original source ↗

protein-stability-20261009-source-dieckhaus2024: Table 2 and footnotes; Methods 'Datasets'

Version: PNAS 121(6):e2314853121, published 2024-01-29; PMC10861915 full-text XML
Retrieved: 2026-10-09T21:01:06Z

not individually reviewed

No individual claim review recorded

Audit details

Field: attributes.comparison_title

Source artifact SHA-256: ba9a763c388eeea47d70fd0d8e2fbf497f61fc8a88dc93d5dac261572daa8010

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

Inspected artifact

Constraints
2 values
  • Inspect every linked evaluation's source locator before citing a result.
  • Do not combine this mapping's evaluations with any other protocol's results; datasets, splits, structures and predictor versions differ between sources.
Context-only references
Transfer learning to leverage larger datasets for improved prediction of protein stability changes

Original source ↗

protein-stability-20261009-source-dieckhaus2024: Table 2 and footnotes; Methods 'Datasets'

Version: PNAS 121(6):e2314853121, published 2024-01-29; PMC10861915 full-text XML
Retrieved: 2026-10-09T21:01:06Z

not individually reviewed

No individual claim review recorded

Audit details

Field: attributes.constraints

Source artifact SHA-256: ba9a763c388eeea47d70fd0d8e2fbf497f61fc8a88dc93d5dac261572daa8010

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

Inspected artifact

Endpoint
RMSE and correlation of predicted ddG on the Megascale held-out test split for the ThermoMPNN comparison set
Context-only references
Transfer learning to leverage larger datasets for improved prediction of protein stability changes

Original source ↗

protein-stability-20261009-source-dieckhaus2024: Table 2 and footnotes; Methods 'Datasets'

Version: PNAS 121(6):e2314853121, published 2024-01-29; PMC10861915 full-text XML
Retrieved: 2026-10-09T21:01:06Z

not individually reviewed

No individual claim review recorded

Audit details

Field: attributes.endpoint

Source artifact SHA-256: ba9a763c388eeea47d70fd0d8e2fbf497f61fc8a88dc93d5dac261572daa8010

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

Inspected artifact

Claimed field
links:assessed_by:protein-stability-20261009-protocol-dieckhaus2024-megascale
Context-only references
Transfer learning to leverage larger datasets for improved prediction of protein stability changes

Original source ↗

protein-stability-20261009-source-dieckhaus2024: Table 2 and footnotes; Methods 'Datasets'

Version: PNAS 121(6):e2314853121, published 2024-01-29; PMC10861915 full-text XML
Retrieved: 2026-10-09T21:01:06Z

not individually reviewed

No individual claim review recorded

Audit details

Field: attributes.field

Source artifact SHA-256: ba9a763c388eeea47d70fd0d8e2fbf497f61fc8a88dc93d5dac261572daa8010

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

Inspected artifact

Headline metric
pearson-correlation
Context-only references
Transfer learning to leverage larger datasets for improved prediction of protein stability changes

Original source ↗

protein-stability-20261009-source-dieckhaus2024: Table 2 and footnotes; Methods 'Datasets'

Version: PNAS 121(6):e2314853121, published 2024-01-29; PMC10861915 full-text XML
Retrieved: 2026-10-09T21:01:06Z

not individually reviewed

No individual claim review recorded

Audit details

Field: attributes.headline_metric

Source artifact SHA-256: ba9a763c388eeea47d70fd0d8e2fbf497f61fc8a88dc93d5dac261572daa8010

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

Inspected artifact

Limitations
4 values
  • Developer comparison: the authors built ThermoMPNN and chose the comparator set (methods with readily accessible code).
  • Megascale proteins are 40-72-residue domains, many de novo designed, measured by one proteolysis assay over a narrow ddG range (-3 to 5 kcal/mol).
  • RaSP and PROSTATA were retrained on Megascale data for this table; other comparators use their published training.
  • No uncertainty is printed in Table 2 (Table 1 ablations give seed SD for ThermoMPNN only).
Context-only references
Transfer learning to leverage larger datasets for improved prediction of protein stability changes

Original source ↗

protein-stability-20261009-source-dieckhaus2024: Table 2 and footnotes; Methods 'Datasets'

Version: PNAS 121(6):e2314853121, published 2024-01-29; PMC10861915 full-text XML
Retrieved: 2026-10-09T21:01:06Z

not individually reviewed

No individual claim review recorded

Audit details

Field: attributes.limitations

Source artifact SHA-256: ba9a763c388eeea47d70fd0d8e2fbf497f61fc8a88dc93d5dac261572daa8010

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

Inspected artifact

Pinned records
51 values
  • record id
    protein-stability-20261009-eval-dieckhaus2024-acdc-nn-megascale
    fields
    • status
    • links
    • attributes.origin
    • attributes.comparison
    sha256
    287a7c4e3e62c8d79821e5bd13874dd2a1f798e537a1b1e8d663b0e10282b8e0
  • record id
    protein-stability-20261009-eval-dieckhaus2024-acdc-nn-seq-megascale
    fields
    • status
    • links
    • attributes.origin
    • attributes.comparison
    sha256
    c14e739c1ce0e22d50c772e4fc945dffa13ad952692a71c480c3ebf865a110ab
  • record id
    protein-stability-20261009-eval-dieckhaus2024-foldx-megascale
    fields
    • status
    • links
    • attributes.origin
    • attributes.comparison
    sha256
    180ca704552900d4069da812c5cc0e893cd1b926ebbb69abf0f740cbde384226
  • record id
    protein-stability-20261009-eval-dieckhaus2024-maestro-megascale
    fields
    • status
    • links
    • attributes.origin
    • attributes.comparison
    sha256
    4e5e5f97102f6f81aaac1df6986a011fb8d59af424572eef8d2cff063da4b534
  • record id
    protein-stability-20261009-eval-dieckhaus2024-mcsm-megascale
    fields
    • status
    • links
    • attributes.origin
    • attributes.comparison
    sha256
    5d64b199f8adc17ec2ee47bd1053aedfb7d672d4a7cd69bcf2ac365541575cf4
  • record id
    protein-stability-20261009-eval-dieckhaus2024-mupro-megascale
    fields
    • status
    • links
    • attributes.origin
    • attributes.comparison
    sha256
    5195abea5101b76ba1e65c1b5d0c9f781ef0e472f7f1029217b2b398ed45f6fa
  • record id
    protein-stability-20261009-eval-dieckhaus2024-prostata-megascale
    fields
    • status
    • links
    • attributes.origin
    • attributes.comparison
    sha256
    787935164f21748d120ca515fb57a3d6865bd8c31314b73af588597570a89d32
  • record id
    protein-stability-20261009-eval-dieckhaus2024-proteinmpnn-megascale
    fields
    • status
    • links
    • attributes.origin
    • attributes.comparison
    sha256
    830e66505079613f56593392257e7f625f7351796b9166f2f1c30e08aced8d9c
  • record id
    protein-stability-20261009-eval-dieckhaus2024-rasp-megascale
    fields
    • status
    • links
    • attributes.origin
    • attributes.comparison
    sha256
    f6beb9657ab5b7a901b79aab74eefa5b3a21a1cc4a2c918ad58afc6868006b90
  • record id
    protein-stability-20261009-eval-dieckhaus2024-rosetta-megascale
    fields
    • status
    • links
    • attributes.origin
    • attributes.comparison
    sha256
    7c954b55c996249945af180067cc2e77dc12136c30b4f30b14200f0456d0fda4
  • record id
    protein-stability-20261009-eval-dieckhaus2024-thermompnn-megascale
    fields
    • status
    • links
    • attributes.origin
    • attributes.comparison
    sha256
    3e4a54297a11196c6d43e7e44ce003ec91ca4ad81705999f5fa529ce40e4d6f5
  • record id
    protein-stability-20261009-eval-dieckhaus2024-thermonet-megascale
    fields
    • status
    • links
    • attributes.origin
    • attributes.comparison
    sha256
    ce754f91c7f4ea168dda505ecd8f12882733e44d4b98b32e356048e64ea8ce57
  • record id
    protein-stability-20261009-protocol-dieckhaus2024-megascale
    fields
    • status
    • name
    • description
    • facets
    • source_ids
    • links
    • attributes
    sha256
    514fb78a1423694d42b4bbaad1c2ed3dff6516f98aaf0f3548904416d0c66bd3
  • record id
    protein-stability-20261009-result-dieckhaus2024-acdc-nn-megascale-pearson-correlation
    fields
    • status
    • attributes.metric
    • attributes.metric_qualifier
    • attributes.printed_value
    • attributes.numeric_value
    sha256
    d74e51b8b16f2605635582f9a85ee20573175a09aa8660bb7a3f0ce152261948
  • record id
    protein-stability-20261009-result-dieckhaus2024-acdc-nn-megascale-root-mean-squared-error
    fields
    • status
    • attributes.metric
    • attributes.metric_qualifier
    • attributes.printed_value
    • attributes.numeric_value
    sha256
    a6196b0142b14d420934193d74a5033f73feb253bb81bf713e475e72eddc9723
  • record id
    protein-stability-20261009-result-dieckhaus2024-acdc-nn-megascale-spearman-correlation
    fields
    • status
    • attributes.metric
    • attributes.metric_qualifier
    • attributes.printed_value
    • attributes.numeric_value
    sha256
    97aec9e5d12e6ae26bf4258ee1c7c52b412a800cb2f477d16a22d3fc4ddfda4f
  • record id
    protein-stability-20261009-result-dieckhaus2024-acdc-nn-seq-megascale-pearson-correlation
    fields
    • status
    • attributes.metric
    • attributes.metric_qualifier
    • attributes.printed_value
    • attributes.numeric_value
    sha256
    2eaa50a14056a709a7d3730ca311db32853d0fa63db46b5ed33266dcbd60379f
  • record id
    protein-stability-20261009-result-dieckhaus2024-acdc-nn-seq-megascale-root-mean-squared-error
    fields
    • status
    • attributes.metric
    • attributes.metric_qualifier
    • attributes.printed_value
    • attributes.numeric_value
    sha256
    0396614c9897ddefbaf901615c478fa214b27ba5a264b59c3c88a98995c64b67
  • record id
    protein-stability-20261009-result-dieckhaus2024-acdc-nn-seq-megascale-spearman-correlation
    fields
    • status
    • attributes.metric
    • attributes.metric_qualifier
    • attributes.printed_value
    • attributes.numeric_value
    sha256
    f27db5485a9fda120067fdb923d4279cda7356241dad6a559715e1386e67cf03
  • record id
    protein-stability-20261009-result-dieckhaus2024-foldx-megascale-pearson-correlation
    fields
    • status
    • attributes.metric
    • attributes.metric_qualifier
    • attributes.printed_value
    • attributes.numeric_value
    sha256
    933d7334d37930314272e82c33ef066e3a2844784ad4338253b5359a7380d0b0
  • record id
    protein-stability-20261009-result-dieckhaus2024-foldx-megascale-root-mean-squared-error
    fields
    • status
    • attributes.metric
    • attributes.metric_qualifier
    • attributes.printed_value
    • attributes.numeric_value
    sha256
    24d3acf6e8a3efbf88e527c7d14a679b882db20028dfce28b94fdad1b7cd38de
  • record id
    protein-stability-20261009-result-dieckhaus2024-foldx-megascale-spearman-correlation
    fields
    • status
    • attributes.metric
    • attributes.metric_qualifier
    • attributes.printed_value
    • attributes.numeric_value
    sha256
    a80779f6abfdba2b0456e1310546ea7cfe15e6c7f416722dc64a4a196001768e
  • record id
    protein-stability-20261009-result-dieckhaus2024-maestro-megascale-pearson-correlation
    fields
    • status
    • attributes.metric
    • attributes.metric_qualifier
    • attributes.printed_value
    • attributes.numeric_value
    sha256
    d5e3f2ec0236b5761e07a4d30b8fee965d30911bb6cc94bd4b8da99f739c5de6
  • record id
    protein-stability-20261009-result-dieckhaus2024-maestro-megascale-root-mean-squared-error
    fields
    • status
    • attributes.metric
    • attributes.metric_qualifier
    • attributes.printed_value
    • attributes.numeric_value
    sha256
    49e2bf233e57fb85c53eb0e9b9bdee2d3948ee4ed9340abd7f1d762af5adb5d8
  • record id
    protein-stability-20261009-result-dieckhaus2024-maestro-megascale-spearman-correlation
    fields
    • status
    • attributes.metric
    • attributes.metric_qualifier
    • attributes.printed_value
    • attributes.numeric_value
    sha256
    86e1bc0d9faba47233649a18e7d94db12e5ad46d39d080646880393752a36eff
  • record id
    protein-stability-20261009-result-dieckhaus2024-mcsm-megascale-pearson-correlation
    fields
    • status
    • attributes.metric
    • attributes.metric_qualifier
    • attributes.printed_value
    • attributes.numeric_value
    sha256
    75b3fafbe9d49f54450d5c0f357f65089c2f06cd9efe195d62aee1eefc1258d5
  • record id
    protein-stability-20261009-result-dieckhaus2024-mcsm-megascale-root-mean-squared-error
    fields
    • status
    • attributes.metric
    • attributes.metric_qualifier
    • attributes.printed_value
    • attributes.numeric_value
    sha256
    9aaaa40fbe84d291c65aecb22fa05953a48cb5b1c4527ca73426e247a81333bc
  • record id
    protein-stability-20261009-result-dieckhaus2024-mcsm-megascale-spearman-correlation
    fields
    • status
    • attributes.metric
    • attributes.metric_qualifier
    • attributes.printed_value
    • attributes.numeric_value
    sha256
    65541cae7a6c489a60d196fc14ea32ee5becc4a8ae2f97b49a79c5999e00d24a
  • record id
    protein-stability-20261009-result-dieckhaus2024-mupro-megascale-pearson-correlation
    fields
    • status
    • attributes.metric
    • attributes.metric_qualifier
    • attributes.printed_value
    • attributes.numeric_value
    sha256
    fe0e1366fdd2fbf7594aa953609978ebdcb5382fb03b8adca78792f85a1d8976
  • record id
    protein-stability-20261009-result-dieckhaus2024-mupro-megascale-root-mean-squared-error
    fields
    • status
    • attributes.metric
    • attributes.metric_qualifier
    • attributes.printed_value
    • attributes.numeric_value
    sha256
    0396614c9897ddefbaf901615c478fa214b27ba5a264b59c3c88a98995c64b67
  • record id
    protein-stability-20261009-result-dieckhaus2024-mupro-megascale-spearman-correlation
    fields
    • status
    • attributes.metric
    • attributes.metric_qualifier
    • attributes.printed_value
    • attributes.numeric_value
    sha256
    a7eb3b1a7c33d704b682b322921f56e6fd906432b59d8acc9ee9f16a5a2bfe21
  • record id
    protein-stability-20261009-result-dieckhaus2024-prostata-megascale-pearson-correlation
    fields
    • status
    • attributes.metric
    • attributes.metric_qualifier
    • attributes.printed_value
    • attributes.numeric_value
    sha256
    f95f71880bdf155e2e728ae6a5c2e01897a7bb18580084bf951af98ad1d84234
  • record id
    protein-stability-20261009-result-dieckhaus2024-prostata-megascale-root-mean-squared-error
    fields
    • status
    • attributes.metric
    • attributes.metric_qualifier
    • attributes.printed_value
    • attributes.numeric_value
    sha256
    ae8ffcd5770d2540945d4ec296963c891f8b4355b97d2614062b46c99b2fcae3
  • record id
    protein-stability-20261009-result-dieckhaus2024-prostata-megascale-spearman-correlation
    fields
    • status
    • attributes.metric
    • attributes.metric_qualifier
    • attributes.printed_value
    • attributes.numeric_value
    sha256
    c8b2bde7f8528dcb027c8b5ea5b9b494d446dacff65c8e870483f4d36acc8a33
  • record id
    protein-stability-20261009-result-dieckhaus2024-proteinmpnn-megascale-pearson-correlation
    fields
    • status
    • attributes.metric
    • attributes.metric_qualifier
    • attributes.printed_value
    • attributes.numeric_value
    sha256
    303811688435b5667c2a6ff86c90a8e7237a37a250cfc5e1030e56c21d91b526
  • record id
    protein-stability-20261009-result-dieckhaus2024-proteinmpnn-megascale-root-mean-squared-error
    fields
    • status
    • attributes.metric
    • attributes.metric_qualifier
    • attributes.printed_value
    • attributes.numeric_value
    sha256
    58589860ca9d8502725295065be893f4f42ef0d92d3582e2f45bf87dcaa669c4
  • record id
    protein-stability-20261009-result-dieckhaus2024-proteinmpnn-megascale-spearman-correlation
    fields
    • status
    • attributes.metric
    • attributes.metric_qualifier
    • attributes.printed_value
    • attributes.numeric_value
    sha256
    19399e6833b943b6ccb358a10e3e5d592a16c9ca872197968c0ef4f690f2b32e
  • record id
    protein-stability-20261009-result-dieckhaus2024-rasp-megascale-pearson-correlation
    fields
    • status
    • attributes.metric
    • attributes.metric_qualifier
    • attributes.printed_value
    • attributes.numeric_value
    sha256
    88e9bbdad3112d1ef4196cdb4744349e3d9117f8b273e5b1d16e98ed957d15ae
  • record id
    protein-stability-20261009-result-dieckhaus2024-rasp-megascale-root-mean-squared-error
    fields
    • status
    • attributes.metric
    • attributes.metric_qualifier
    • attributes.printed_value
    • attributes.numeric_value
    sha256
    0396614c9897ddefbaf901615c478fa214b27ba5a264b59c3c88a98995c64b67
  • record id
    protein-stability-20261009-result-dieckhaus2024-rasp-megascale-spearman-correlation
    fields
    • status
    • attributes.metric
    • attributes.metric_qualifier
    • attributes.printed_value
    • attributes.numeric_value
    sha256
    b33852b72433f0fd41f59a8551a98268a4c939a6e2d5a2ddf710f4262d0a1562
  • record id
    protein-stability-20261009-result-dieckhaus2024-rosetta-megascale-pearson-correlation
    fields
    • status
    • attributes.metric
    • attributes.metric_qualifier
    • attributes.printed_value
    • attributes.numeric_value
    sha256
    7b93e113912b4c4e86c86e121751ff37647cd2e79b87ef39e5984ea97e0941ca
  • record id
    protein-stability-20261009-result-dieckhaus2024-rosetta-megascale-root-mean-squared-error
    fields
    • status
    • attributes.metric
    • attributes.metric_qualifier
    • attributes.printed_value
    • attributes.numeric_value
    sha256
    ce5d683ef3e495d347383c02b01b33446e4336bfea645f3b9496cb84e6f59d23
  • record id
    protein-stability-20261009-result-dieckhaus2024-rosetta-megascale-spearman-correlation
    fields
    • status
    • attributes.metric
    • attributes.metric_qualifier
    • attributes.printed_value
    • attributes.numeric_value
    sha256
    8227da073862d54c3756c6c94dbb082b96a20c648adeb8f5aa37f00da4eb504e
  • record id
    protein-stability-20261009-result-dieckhaus2024-thermompnn-megascale-pearson-correlation
    fields
    • status
    • attributes.metric
    • attributes.metric_qualifier
    • attributes.printed_value
    • attributes.numeric_value
    sha256
    e12650b15fe79a156ea4e7d09fdbc58e2643615e1904ecd323b2c91d3681c1b1
  • record id
    protein-stability-20261009-result-dieckhaus2024-thermompnn-megascale-root-mean-squared-error
    fields
    • status
    • attributes.metric
    • attributes.metric_qualifier
    • attributes.printed_value
    • attributes.numeric_value
    sha256
    4ebfa3708d40edec684bf55f7dc12a1786bfe4fa7e0107dea106be42d0fc567b
  • record id
    protein-stability-20261009-result-dieckhaus2024-thermompnn-megascale-spearman-correlation
    fields
    • status
    • attributes.metric
    • attributes.metric_qualifier
    • attributes.printed_value
    • attributes.numeric_value
    sha256
    400acde872ece89a4dcd1b92aeaa7ec160503cc2aa4bc9c790b7eb1ee6f8710c
  • record id
    protein-stability-20261009-result-dieckhaus2024-thermonet-megascale-pearson-correlation
    fields
    • status
    • attributes.metric
    • attributes.metric_qualifier
    • attributes.printed_value
    • attributes.numeric_value
    sha256
    a10e5352208093693cc2ccca89713399f01148a7a0189d0dd49728761d232e74
  • record id
    protein-stability-20261009-result-dieckhaus2024-thermonet-megascale-root-mean-squared-error
    fields
    • status
    • attributes.metric
    • attributes.metric_qualifier
    • attributes.printed_value
    • attributes.numeric_value
    sha256
    192f491a91b10c127d1a0cd2d73edce20d2429edd239022837849c407a234f99
  • record id
    protein-stability-20261009-result-dieckhaus2024-thermonet-megascale-spearman-correlation
    fields
    • status
    • attributes.metric
    • attributes.metric_qualifier
    • attributes.printed_value
    • attributes.numeric_value
    sha256
    8845c52c86fb441a39039a17a7edb15ae7d494e2f4519e77433887a7bf3e0fac
  • record id
    protein-stability-20261009-source-dieckhaus2024
    fields
    • status
    • attributes.artifact_sha256
    sha256
    e4c02837eab159fbef7943f8346e38196625d3a62702c961e9e1e54d1d61464e
  • record id
    use-case-protein-stability
    fields
    • status
    • name
    • description
    • facets
    • attributes.question
    • attributes.decision
    • attributes.inputs
    • attributes.output
    • attributes.exclusions
    • attributes.setting
    • attributes.clinical_scope
    • attributes.intended_users
    sha256
    2dd1d0e139a17e51ae72cc5945196ffbb366fe4daa4c20c4efd950346a30a54f
Context-only references
Transfer learning to leverage larger datasets for improved prediction of protein stability changes

Original source ↗

protein-stability-20261009-source-dieckhaus2024: Table 2 and footnotes; Methods 'Datasets'

Version: PNAS 121(6):e2314853121, published 2024-01-29; PMC10861915 full-text XML
Retrieved: 2026-10-09T21:01:06Z

not individually reviewed

No individual claim review recorded

Audit details

Field: attributes.pins

Source artifact SHA-256: ba9a763c388eeea47d70fd0d8e2fbf497f61fc8a88dc93d5dac261572daa8010

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

Inspected artifact

Rationale
Held-out proteins with no homologue in the training sets directly test generalisation to unseen proteins, the validation step the use case asks about.
Context-only references
Transfer learning to leverage larger datasets for improved prediction of protein stability changes

Original source ↗

protein-stability-20261009-source-dieckhaus2024: Table 2 and footnotes; Methods 'Datasets'

Version: PNAS 121(6):e2314853121, published 2024-01-29; PMC10861915 full-text XML
Retrieved: 2026-10-09T21:01:06Z

not individually reviewed

No individual claim review recorded

Audit details

Field: attributes.rationale

Source artifact SHA-256: ba9a763c388eeea47d70fd0d8e2fbf497f61fc8a88dc93d5dac261572daa8010

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

Inspected artifact

How to read the evidence

Sources and history

Release 2026-11-21-adc15377fab2 · Record review: source checked

1 source record and release historyDownload this release (gzip)
Technical metadata and extraction receipts

Stable ID: use-case-mapping-protein-stability-20261009-dieckhaus2024-megascale

field
links:assessed_by:protein-stability-20261009-protocol-dieckhaus2024-megascale
value
protein-stability-20261009-protocol-dieckhaus2024-megascale
relevance
direct
endpoint
RMSE and correlation of predicted ddG on the Megascale held-out test split for the ThermoMPNN comparison set
rationale
Held-out proteins with no homologue in the training sets directly test generalisation to unseen proteins, the validation step the use case asks about.
constraints
Inspect every linked evaluation's source locator before citing a result.; Do not combine this mapping's evaluations with any other protocol's results; datasets, splits, structures and predictor versions differ between sources.
limitations
Developer comparison: the authors built ThermoMPNN and chose the comparator set (methods with readily accessible code).; Megascale proteins are 40-72-residue domains, many de novo designed, measured by one proteolysis assay over a narrow ddG range (-3 to 5 kcal/mol).; RaSP and PROSTATA were retrained on Megascale data for this table; other comparators use their published training.; No uncertainty is printed in Table 2 (Table 1 ablations give seed SD for ThermoMPNN only).
revision
1
reason
Add primary-source stability predictor comparison evidence from the protein stability use-case pass (2026-10-09).
citation locators
source id: protein-stability-20261009-source-dieckhaus2024; locator: Table 2 and footnotes; Methods 'Datasets'
source locator
protein-stability-20261009-source-dieckhaus2024: Table 2 and footnotes; Methods 'Datasets'
comparison group
dieckhaus2024-thermompnn
comparison title
ThermoMPNN comparison sets (Dieckhaus et al. 2024)
headline metric
pearson-correlation
stratum label
Megascale held-out test split
stratum order
1
reviewed evaluations
protein-stability-20261009-eval-dieckhaus2024-acdc-nn-megascale; protein-stability-20261009-eval-dieckhaus2024-acdc-nn-seq-megascale; protein-stability-20261009-eval-dieckhaus2024-foldx-megascale; protein-stability-20261009-eval-dieckhaus2024-maestro-megascale; protein-stability-20261009-eval-dieckhaus2024-mcsm-megascale; protein-stability-20261009-eval-dieckhaus2024-mupro-megascale; protein-stability-20261009-eval-dieckhaus2024-prostata-megascale; protein-stability-20261009-eval-dieckhaus2024-proteinmpnn-megascale; protein-stability-20261009-eval-dieckhaus2024-rasp-megascale; protein-stability-20261009-eval-dieckhaus2024-rosetta-megascale; protein-stability-20261009-eval-dieckhaus2024-thermompnn-megascale; protein-stability-20261009-eval-dieckhaus2024-thermonet-megascale
review
method: automated-source-review; reviewer: claude; reviewer note: Separate Claude review agent, independent of the extractor; no human review claimed; reviewed at: 2026-10-09T23:59:00Z; note: Independent review of endpoint fit, relevance grade, limitations, exclusions and grouping against the use case and the source; every value of the listed evaluations was checked against the source table. No execution, reproduction, human scientific review or clinical validation.
pins
record id: protein-stability-20261009-eval-dieckhaus2024-acdc-nn-megascale; fields: status; links; attributes.origin; attributes.comparison; sha256: 287a7c4e3e62c8d79821e5bd13874dd2a1f798e537a1b1e8d663b0e10282b8e0; record id: protein-stability-20261009-eval-dieckhaus2024-acdc-nn-seq-megascale; fields: status; links; attributes.origin; attributes.comparison; sha256: c14e739c1ce0e22d50c772e4fc945dffa13ad952692a71c480c3ebf865a110ab; record id: protein-stability-20261009-eval-dieckhaus2024-foldx-megascale; fields: status; links; attributes.origin; attributes.comparison; sha256: 180ca704552900d4069da812c5cc0e893cd1b926ebbb69abf0f740cbde384226; record id: protein-stability-20261009-eval-dieckhaus2024-maestro-megascale; fields: status; links; attributes.origin; attributes.comparison; sha256: 4e5e5f97102f6f81aaac1df6986a011fb8d59af424572eef8d2cff063da4b534; record id: protein-stability-20261009-eval-dieckhaus2024-mcsm-megascale; fields: status; links; attributes.origin; attributes.comparison; sha256: 5d64b199f8adc17ec2ee47bd1053aedfb7d672d4a7cd69bcf2ac365541575cf4; record id: protein-stability-20261009-eval-dieckhaus2024-mupro-megascale; fields: status; links; attributes.origin; attributes.comparison; sha256: 5195abea5101b76ba1e65c1b5d0c9f781ef0e472f7f1029217b2b398ed45f6fa; record id: protein-stability-20261009-eval-dieckhaus2024-prostata-megascale; fields: status; links; attributes.origin; attributes.comparison; sha256: 787935164f21748d120ca515fb57a3d6865bd8c31314b73af588597570a89d32; record id: protein-stability-20261009-eval-dieckhaus2024-proteinmpnn-megascale; fields: status; links; attributes.origin; attributes.comparison; sha256: 830e66505079613f56593392257e7f625f7351796b9166f2f1c30e08aced8d9c; record id: protein-stability-20261009-eval-dieckhaus2024-rasp-megascale; fields: status; links; attributes.origin; attributes.comparison; sha256: f6beb9657ab5b7a901b79aab74eefa5b3a21a1cc4a2c918ad58afc6868006b90; record id: protein-stability-20261009-eval-dieckhaus2024-rosetta-megascale; fields: status; links; attributes.origin; attributes.comparison; sha256: 7c954b55c996249945af180067cc2e77dc12136c30b4f30b14200f0456d0fda4; record id: protein-stability-20261009-eval-dieckhaus2024-thermompnn-megascale; fields: status; links; attributes.origin; attributes.comparison; sha256: 3e4a54297a11196c6d43e7e44ce003ec91ca4ad81705999f5fa529ce40e4d6f5; record id: protein-stability-20261009-eval-dieckhaus2024-thermonet-megascale; fields: status; links; attributes.origin; attributes.comparison; sha256: ce754f91c7f4ea168dda505ecd8f12882733e44d4b98b32e356048e64ea8ce57; record id: protein-stability-20261009-protocol-dieckhaus2024-megascale; fields: status; name; description; facets; source_ids; links; attributes; sha256: 514fb78a1423694d42b4bbaad1c2ed3dff6516f98aaf0f3548904416d0c66bd3; record id: protein-stability-20261009-result-dieckhaus2024-acdc-nn-megascale-pearson-correlation; fields: status; attributes.metric; attributes.metric_qualifier; attributes.printed_value; attributes.numeric_value; sha256: d74e51b8b16f2605635582f9a85ee20573175a09aa8660bb7a3f0ce152261948; record id: protein-stability-20261009-result-dieckhaus2024-acdc-nn-megascale-root-mean-squared-error; fields: status; attributes.metric; attributes.metric_qualifier; attributes.printed_value; attributes.numeric_value; sha256: a6196b0142b14d420934193d74a5033f73feb253bb81bf713e475e72eddc9723; record id: protein-stability-20261009-result-dieckhaus2024-acdc-nn-megascale-spearman-correlation; fields: status; attributes.metric; attributes.metric_qualifier; attributes.printed_value; attributes.numeric_value; sha256: 97aec9e5d12e6ae26bf4258ee1c7c52b412a800cb2f477d16a22d3fc4ddfda4f; record id: protein-stability-20261009-result-dieckhaus2024-acdc-nn-seq-megascale-pearson-correlation; fields: status; attributes.metric; attributes.metric_qualifier; attributes.printed_value; attributes.numeric_value; sha256: 2eaa50a14056a709a7d3730ca311db32853d0fa63db46b5ed33266dcbd60379f; record id: protein-stability-20261009-result-dieckhaus2024-acdc-nn-seq-megascale-root-mean-squared-error; fields: status; attributes.metric; attributes.metric_qualifier; attributes.printed_value; attributes.numeric_value; sha256: 0396614c9897ddefbaf901615c478fa214b27ba5a264b59c3c88a98995c64b67; record id: protein-stability-20261009-result-dieckhaus2024-acdc-nn-seq-megascale-spearman-correlation; fields: status; attributes.metric; attributes.metric_qualifier; attributes.printed_value; attributes.numeric_value; sha256: f27db5485a9fda120067fdb923d4279cda7356241dad6a559715e1386e67cf03; record id: protein-stability-20261009-result-dieckhaus2024-foldx-megascale-pearson-correlation; fields: status; attributes.metric; attributes.metric_qualifier; attributes.printed_value; attributes.numeric_value; sha256: 933d7334d37930314272e82c33ef066e3a2844784ad4338253b5359a7380d0b0; record id: protein-stability-20261009-result-dieckhaus2024-foldx-megascale-root-mean-squared-error; fields: status; attributes.metric; attributes.metric_qualifier; attributes.printed_value; attributes.numeric_value; sha256: 24d3acf6e8a3efbf88e527c7d14a679b882db20028dfce28b94fdad1b7cd38de; record id: protein-stability-20261009-result-dieckhaus2024-foldx-megascale-spearman-correlation; fields: status; attributes.metric; attributes.metric_qualifier; attributes.printed_value; attributes.numeric_value; sha256: a80779f6abfdba2b0456e1310546ea7cfe15e6c7f416722dc64a4a196001768e; record id: protein-stability-20261009-result-dieckhaus2024-maestro-megascale-pearson-correlation; fields: status; attributes.metric; attributes.metric_qualifier; attributes.printed_value; attributes.numeric_value; sha256: d5e3f2ec0236b5761e07a4d30b8fee965d30911bb6cc94bd4b8da99f739c5de6; record id: protein-stability-20261009-result-dieckhaus2024-maestro-megascale-root-mean-squared-error; fields: status; attributes.metric; attributes.metric_qualifier; attributes.printed_value; attributes.numeric_value; sha256: 49e2bf233e57fb85c53eb0e9b9bdee2d3948ee4ed9340abd7f1d762af5adb5d8; record id: protein-stability-20261009-result-dieckhaus2024-maestro-megascale-spearman-correlation; fields: status; attributes.metric; attributes.metric_qualifier; attributes.printed_value; attributes.numeric_value; sha256: 86e1bc0d9faba47233649a18e7d94db12e5ad46d39d080646880393752a36eff; record id: protein-stability-20261009-result-dieckhaus2024-mcsm-megascale-pearson-correlation; fields: status; attributes.metric; attributes.metric_qualifier; attributes.printed_value; attributes.numeric_value; sha256: 75b3fafbe9d49f54450d5c0f357f65089c2f06cd9efe195d62aee1eefc1258d5; record id: protein-stability-20261009-result-dieckhaus2024-mcsm-megascale-root-mean-squared-error; fields: status; attributes.metric; attributes.metric_qualifier; attributes.printed_value; attributes.numeric_value; sha256: 9aaaa40fbe84d291c65aecb22fa05953a48cb5b1c4527ca73426e247a81333bc; record id: protein-stability-20261009-result-dieckhaus2024-mcsm-megascale-spearman-correlation; fields: status; attributes.metric; attributes.metric_qualifier; attributes.printed_value; attributes.numeric_value; sha256: 65541cae7a6c489a60d196fc14ea32ee5becc4a8ae2f97b49a79c5999e00d24a; record id: protein-stability-20261009-result-dieckhaus2024-mupro-megascale-pearson-correlation; fields: status; attributes.metric; attributes.metric_qualifier; attributes.printed_value; attributes.numeric_value; sha256: fe0e1366fdd2fbf7594aa953609978ebdcb5382fb03b8adca78792f85a1d8976; record id: protein-stability-20261009-result-dieckhaus2024-mupro-megascale-root-mean-squared-error; fields: status; attributes.metric; attributes.metric_qualifier; attributes.printed_value; attributes.numeric_value; sha256: 0396614c9897ddefbaf901615c478fa214b27ba5a264b59c3c88a98995c64b67; record id: protein-stability-20261009-result-dieckhaus2024-mupro-megascale-spearman-correlation; fields: status; attributes.metric; attributes.metric_qualifier; attributes.printed_value; attributes.numeric_value; sha256: a7eb3b1a7c33d704b682b322921f56e6fd906432b59d8acc9ee9f16a5a2bfe21; record id: protein-stability-20261009-result-dieckhaus2024-prostata-megascale-pearson-correlation; fields: status; attributes.metric; attributes.metric_qualifier; attributes.printed_value; attributes.numeric_value; sha256: f95f71880bdf155e2e728ae6a5c2e01897a7bb18580084bf951af98ad1d84234; record id: protein-stability-20261009-result-dieckhaus2024-prostata-megascale-root-mean-squared-error; fields: status; attributes.metric; attributes.metric_qualifier; attributes.printed_value; attributes.numeric_value; sha256: ae8ffcd5770d2540945d4ec296963c891f8b4355b97d2614062b46c99b2fcae3; record id: protein-stability-20261009-result-dieckhaus2024-prostata-megascale-spearman-correlation; fields: status; attributes.metric; attributes.metric_qualifier; attributes.printed_value; attributes.numeric_value; sha256: c8b2bde7f8528dcb027c8b5ea5b9b494d446dacff65c8e870483f4d36acc8a33; record id: protein-stability-20261009-result-dieckhaus2024-proteinmpnn-megascale-pearson-correlation; fields: status; attributes.metric; attributes.metric_qualifier; attributes.printed_value; attributes.numeric_value; sha256: 303811688435b5667c2a6ff86c90a8e7237a37a250cfc5e1030e56c21d91b526; record id: protein-stability-20261009-result-dieckhaus2024-proteinmpnn-megascale-root-mean-squared-error; fields: status; attributes.metric; attributes.metric_qualifier; attributes.printed_value; attributes.numeric_value; sha256: 58589860ca9d8502725295065be893f4f42ef0d92d3582e2f45bf87dcaa669c4; record id: protein-stability-20261009-result-dieckhaus2024-proteinmpnn-megascale-spearman-correlation; fields: status; attributes.metric; attributes.metric_qualifier; attributes.printed_value; attributes.numeric_value; sha256: 19399e6833b943b6ccb358a10e3e5d592a16c9ca872197968c0ef4f690f2b32e; record id: protein-stability-20261009-result-dieckhaus2024-rasp-megascale-pearson-correlation; fields: status; attributes.metric; attributes.metric_qualifier; attributes.printed_value; attributes.numeric_value; sha256: 88e9bbdad3112d1ef4196cdb4744349e3d9117f8b273e5b1d16e98ed957d15ae; record id: protein-stability-20261009-result-dieckhaus2024-rasp-megascale-root-mean-squared-error; fields: status; attributes.metric; attributes.metric_qualifier; attributes.printed_value; attributes.numeric_value; sha256: 0396614c9897ddefbaf901615c478fa214b27ba5a264b59c3c88a98995c64b67; record id: protein-stability-20261009-result-dieckhaus2024-rasp-megascale-spearman-correlation; fields: status; attributes.metric; attributes.metric_qualifier; attributes.printed_value; attributes.numeric_value; sha256: b33852b72433f0fd41f59a8551a98268a4c939a6e2d5a2ddf710f4262d0a1562; record id: protein-stability-20261009-result-dieckhaus2024-rosetta-megascale-pearson-correlation; fields: status; attributes.metric; attributes.metric_qualifier; attributes.printed_value; attributes.numeric_value; sha256: 7b93e113912b4c4e86c86e121751ff37647cd2e79b87ef39e5984ea97e0941ca; record id: protein-stability-20261009-result-dieckhaus2024-rosetta-megascale-root-mean-squared-error; fields: status; attributes.metric; attributes.metric_qualifier; attributes.printed_value; attributes.numeric_value; sha256: ce5d683ef3e495d347383c02b01b33446e4336bfea645f3b9496cb84e6f59d23; record id: protein-stability-20261009-result-dieckhaus2024-rosetta-megascale-spearman-correlation; fields: status; attributes.metric; attributes.metric_qualifier; attributes.printed_value; attributes.numeric_value; sha256: 8227da073862d54c3756c6c94dbb082b96a20c648adeb8f5aa37f00da4eb504e; record id: protein-stability-20261009-result-dieckhaus2024-thermompnn-megascale-pearson-correlation; fields: status; attributes.metric; attributes.metric_qualifier; attributes.printed_value; attributes.numeric_value; sha256: e12650b15fe79a156ea4e7d09fdbc58e2643615e1904ecd323b2c91d3681c1b1; record id: protein-stability-20261009-result-dieckhaus2024-thermompnn-megascale-root-mean-squared-error; fields: status; attributes.metric; attributes.metric_qualifier; attributes.printed_value; attributes.numeric_value; sha256: 4ebfa3708d40edec684bf55f7dc12a1786bfe4fa7e0107dea106be42d0fc567b; record id: protein-stability-20261009-result-dieckhaus2024-thermompnn-megascale-spearman-correlation; fields: status; attributes.metric; attributes.metric_qualifier; attributes.printed_value; attributes.numeric_value; sha256: 400acde872ece89a4dcd1b92aeaa7ec160503cc2aa4bc9c790b7eb1ee6f8710c; record id: protein-stability-20261009-result-dieckhaus2024-thermonet-megascale-pearson-correlation; fields: status; attributes.metric; attributes.metric_qualifier; attributes.printed_value; attributes.numeric_value; sha256: a10e5352208093693cc2ccca89713399f01148a7a0189d0dd49728761d232e74; record id: protein-stability-20261009-result-dieckhaus2024-thermonet-megascale-root-mean-squared-error; fields: status; attributes.metric; attributes.metric_qualifier; attributes.printed_value; attributes.numeric_value; sha256: 192f491a91b10c127d1a0cd2d73edce20d2429edd239022837849c407a234f99; record id: protein-stability-20261009-result-dieckhaus2024-thermonet-megascale-spearman-correlation; fields: status; attributes.metric; attributes.metric_qualifier; attributes.printed_value; attributes.numeric_value; sha256: 8845c52c86fb441a39039a17a7edb15ae7d494e2f4519e77433887a7bf3e0fac; record id: protein-stability-20261009-source-dieckhaus2024; fields: status; attributes.artifact_sha256; sha256: e4c02837eab159fbef7943f8346e38196625d3a62702c961e9e1e54d1d61464e; record id: use-case-protein-stability; fields: status; name; description; facets; attributes.question; attributes.decision; attributes.inputs; attributes.output; attributes.exclusions; attributes.setting; attributes.clinical_scope; attributes.intended_users; sha256: 2dd1d0e139a17e51ae72cc5945196ffbb366fe4daa4c20c4efd950346a30a54f
Related records

Suggest a correction