Transfer learning to leverage larger datasets for improved prediction of protein stability changes
PNAS 121(6):e2314853121, published 2024-01-29; PMC10861915 full-text XML · Peer-reviewed
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.
Claims
Statements this source supports, each with where in the source it was checked.
- Baseline: Assess methods for protein stability experiments: Baseline FoldX and Rosetta (protein-stability-20261009-source-pancotti2022: Methods (FoldX empirical force field, Rosetta energy difference); protein-stability-20261009-source-dieckhaus2024: Introduction (empirical energy functions historically) and Discussion (FoldX and Rosetta))
- Evidence summary: protein variant stability prediction: Summary Three published comparisons add evidence beyond the AMFR assay. Each uses its own dataset, split and metric, so values cannot be pooled. Pancotti et al. 2022 ran 21 predictors on S669, 669 experimental ddG variants in proteins dissimilar to the main training sets, plus their reverse variants; several of the tools, including ACDC-NN, DDGun, INPS and I-Mutant, were developed by the paper's own authors. The highest Pearson correlation on direct variants was 0.5 (MAESTRO), but MAESTRO fell to 0.2 on reverse variants with a bias of -0.57, while tools built to be antisymmetric, such as INPS-Seq, kept 0.43 in both directions with a bias of 0. On all 1,338 variants the highest correlations were 0.62 (PremPS) and 0.61 (ACDC-NN and INPS-Seq). Dieckhaus et al. 2024, the ThermoMPNN developers, held out proteins clustered at 25% identity in the mega-scale proteolysis set: ThermoMPNN reached Pearson 0.75 and RMSE 0.71 kcal/mol, retrained RaSP 0.71 and Rosetta 0.53 with RMSE 5.18. On a homologue-free FireProtDB split ThermoMPNN reached 0.65 against 0.59 for retrained PROSTATA and 0.47 for retrained RaSP. Chu et al. 2024, the ESM therm developers, show the limit of transfer: on held-out mega-scale domains of 40 to 72 residues RaSP and ELASPIC-2 reached Spearman 0.64 and Rosetta 0.61, but on six single proteins of 177 to 501 residues their fine-tuned model scored between -0.11 and 0.06, while ELASPIC-2 scored 0.47 to 0.58 on five of them and Rosetta 0.33 to 0.49. Before choosing a method, a user still needs to validate transfer to proteins larger than the small domains these models were trained on, and to check antisymmetry on reverse variants, which only one of these comparisons tests across many tools. None of the comparisons covers the AMFR construct, and none establishes whole-protein function, fitness or pathogenicity. (protein-stability-20261009-source-pancotti2022: Section 2, Table 1; protein-stability-20261009-source-dieckhaus2024: Table 2; protein-stability-20261009-source-chu2024: Tables 1 and 2)
- Relevance of Fireprot homologue-free split ddG prediction (Dieckhaus et al. 2024) to "Assess methods for protein stability experiments": Assessed by Fireprot homologue-free split ddG prediction (Dieckhaus et al. 2024 Table 2) (protein-stability-20261009-source-dieckhaus2024: Table 2 and footnotes; Methods 'Datasets')
- Relevance of Megascale held-out test split ddG prediction (Dieckhaus et al. 2024) to "Assess methods for protein stability experiments": Assessed by Megascale held-out test split ddG prediction (Dieckhaus et al. 2024 Table 2) (protein-stability-20261009-source-dieckhaus2024: Table 2 and footnotes; Methods 'Datasets')
- Relevance of S669 direct ddG prediction (Dieckhaus et al. 2024) to "Assess methods for protein stability experiments": Assessed by S669 direct ddG prediction (Dieckhaus et al. 2024 Table 3) (protein-stability-20261009-source-dieckhaus2024: Table 3 and footnotes; Methods 'Datasets')
- Relevance of Ssym direct and inverse ddG prediction (Dieckhaus et al. 2024) to "Assess methods for protein stability experiments": Assessed by Ssym direct and inverse ddG prediction (Dieckhaus et al. 2024 Table 3) (protein-stability-20261009-source-dieckhaus2024: Table 3 and footnotes; Methods 'Datasets')
- ThermoMPNN: description: Description Deep neural network that predicts the stability change of a point mutation from an input structure, by transfer learning on features extracted from ProteinMPNN. (Abstract)
Models, benchmarks and other records
Methods (12)
Configurations (14)
- ABYSSAL (Dieckhaus et al. 2024)
- ACDC-NN (Dieckhaus et al. 2024)
- ACDC-NN-Seq (Dieckhaus et al. 2024)
- FoldX (Dieckhaus et al. 2024)
- MAESTRO (Dieckhaus et al. 2024)
- mCSM (Dieckhaus et al. 2024)
- MUPRO (Dieckhaus et al. 2024)
- PROSTATA (Dieckhaus et al. 2024)
- ProteinMPNN (Dieckhaus et al. 2024)
- RaSP (Dieckhaus et al. 2024)
- Rosetta (Dieckhaus et al. 2024)
- Stability Oracle (Dieckhaus et al. 2024)
- ThermoMPNN (Dieckhaus et al. 2024)
- ThermoNet (Dieckhaus et al. 2024)
Protocols (4)
Datasets (4)
Evaluations (50)
- ABYSSAL on S669 direct (Dieckhaus et al. 2024)
- ABYSSAL on Ssym direct and inverse (Dieckhaus et al. 2024)
- ACDC-NN on Fireprot homologue-free split (Dieckhaus et al. 2024)
- ACDC-NN on Megascale held-out test split (Dieckhaus et al. 2024)
- ACDC-NN on S669 direct (Dieckhaus et al. 2024)
- ACDC-NN on Ssym direct and inverse (Dieckhaus et al. 2024)
- ACDC-NN-Seq on Fireprot homologue-free split (Dieckhaus et al. 2024)
- ACDC-NN-Seq on Megascale held-out test split (Dieckhaus et al. 2024)
- FoldX on Fireprot homologue-free split (Dieckhaus et al. 2024)
- FoldX on Megascale held-out test split (Dieckhaus et al. 2024)
- FoldX on S669 direct (Dieckhaus et al. 2024)
- FoldX on Ssym direct and inverse (Dieckhaus et al. 2024)
- MAESTRO on Fireprot homologue-free split (Dieckhaus et al. 2024)
- MAESTRO on Megascale held-out test split (Dieckhaus et al. 2024)
- MAESTRO on S669 direct (Dieckhaus et al. 2024)
- MAESTRO on Ssym direct and inverse (Dieckhaus et al. 2024)
- mCSM on Fireprot homologue-free split (Dieckhaus et al. 2024)
- mCSM on Megascale held-out test split (Dieckhaus et al. 2024)
- mCSM on S669 direct (Dieckhaus et al. 2024)
- mCSM on Ssym direct and inverse (Dieckhaus et al. 2024)
- MUPRO on Fireprot homologue-free split (Dieckhaus et al. 2024)
- MUPRO on Megascale held-out test split (Dieckhaus et al. 2024)
- MUPRO on S669 direct (Dieckhaus et al. 2024)
- MUPRO on Ssym direct and inverse (Dieckhaus et al. 2024)
- PROSTATA on Fireprot homologue-free split (Dieckhaus et al. 2024)
Use cases (1)
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.
17 evidence rows matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| Artifact SHA-256 ba9a763c388eeea47d70fd0d8e2fbf497f61fc8a88dc93d5dac261572daa8010 Source metadata | Transfer learning to leverage larger datasets for improved prediction of protein stability changes No field-specific location recorded Version: PNAS 121(6):e2314853121, published 2024-01-29; PMC10861915 full-text XML | catalogued No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Artifact url https://www.ebi.ac.uk/europepmc/webservices/rest/PMC10861915/fullTextXML Source metadata | Transfer learning to leverage larger datasets for improved prediction of protein stability changes No field-specific location recorded Version: PNAS 121(6):e2314853121, published 2024-01-29; PMC10861915 full-text XML | catalogued No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Doi 10.1073/pnas.2314853121 Source metadata | Transfer learning to leverage larger datasets for improved prediction of protein stability changes No field-specific location recorded Version: PNAS 121(6):e2314853121, published 2024-01-29; PMC10861915 full-text XML | catalogued No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Licence CC-BY-NC-ND-4.0 Source metadata | Transfer learning to leverage larger datasets for improved prediction of protein stability changes No field-specific location recorded Version: PNAS 121(6):e2314853121, published 2024-01-29; PMC10861915 full-text XML | catalogued No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Media type application/xml Source metadata | Transfer learning to leverage larger datasets for improved prediction of protein stability changes No field-specific location recorded Version: PNAS 121(6):e2314853121, published 2024-01-29; PMC10861915 full-text XML | catalogued No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Publication status peer_reviewed Source metadata | Transfer learning to leverage larger datasets for improved prediction of protein stability changes No field-specific location recorded Version: PNAS 121(6):e2314853121, published 2024-01-29; PMC10861915 full-text XML | catalogued No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Retrieved at 2026-10-09T21:01:06Z Source metadata | Transfer learning to leverage larger datasets for improved prediction of protein stability changes No field-specific location recorded Version: PNAS 121(6):e2314853121, published 2024-01-29; PMC10861915 full-text XML | catalogued No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Url https://doi.org/10.1073/pnas.2314853121 Source metadata | Transfer learning to leverage larger datasets for improved prediction of protein stability changes No field-specific location recorded Version: PNAS 121(6):e2314853121, published 2024-01-29; PMC10861915 full-text XML | catalogued No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Version PNAS 121(6):e2314853121, published 2024-01-29; PMC10861915 full-text XML Source metadata | Transfer learning to leverage larger datasets for improved prediction of protein stability changes No field-specific location recorded Version: PNAS 121(6):e2314853121, published 2024-01-29; PMC10861915 full-text XML | catalogued No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Description Primary source retrieved and hashed for the protein stability use-case pass. Source metadata | Transfer learning to leverage larger datasets for improved prediction of protein stability changes No field-specific location recorded Version: PNAS 121(6):e2314853121, published 2024-01-29; PMC10861915 full-text XML | catalogued No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
Sources and history
Release 2026-11-21-adc15377fab2 · Record review: source checked
Primary source retrieved and hashed for the protein stability use-case pass.
Technical metadata and extraction receipts
Stable ID: protein-stability-20261009-source-dieckhaus2024
- areas
- proteins-complexes
- contexts
- research
- url
- https://doi.org/10.1073/pnas.2314853121
- artifact url
- https://www.ebi.ac.uk/europepmc/webservices/rest/PMC10861915/fullTextXML
- version
- PNAS 121(6):e2314853121, published 2024-01-29; PMC10861915 full-text XML
- retrieved at
- 2026-10-09T21:01:06Z
- artifact sha256
- ba9a763c388eeea47d70fd0d8e2fbf497f61fc8a88dc93d5dac261572daa8010
- doi
- 10.1073/pnas.2314853121
- publication status
- peer_reviewed
- licence
- CC-BY-NC-ND-4.0
- media type
- application/xml