Protocol

Ssym direct and inverse ddG prediction (Dieckhaus et al. 2024 Table 3)

RMSE and correlation of predicted against experimental ddG on the Ssym direct and inverse.

Overview

RMSE and correlation of predicted against experimental ddG on the Ssym direct and inverse.

Consult the linked sources for architecture or protocol details. Missing evidence is not evidence of a missing capability.

13 recorded evaluations, 50 metric rows. A comparison chart has not yet been validated for these results. The table retains the individual findings and their sources.

View coverage and remaining gaps across all benchmarks

Results

Results are available, but no reviewed comparison panel is linked in this release.

All evaluations

13 evaluations · 50 results. Different protocols are not a single leaderboard.

Filter evaluations

Tested model or methodProtocolDatasetEvaluation setupMetricEvidence origin

Applied filters: All linked evaluations

Exact evaluated configurations and original reported results
Tested configuration	Protocol and dataset	Finding	Evidence and details
Configuration: ABYSSAL (Dieckhaus et al. 2024)	Protocol: Ssym direct and inverse ddG prediction (Dieckhaus et al. 2024 Table 3) Dataset: Ssym (342 direct and 342 inverse variants with experimental structures)	0.46 pearson-correlation unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Result quoted from another source · Source checked Methods, coverage and source ABYSSAL on Ssym direct and inverse (Dieckhaus et al. 2024) protein-stability-20261009-protocol-dieckhaus2024-ssym Aggregation: Not reported Transfer learning to leverage larger datasets for improved prediction of protein stability changes · Table 3, row 'ABYSSAL ( 16 )', column 'Ssym (direct) PCC'
Configuration: ABYSSAL (Dieckhaus et al. 2024)	Protocol: Ssym direct and inverse ddG prediction (Dieckhaus et al. 2024 Table 3) Dataset: Ssym (342 direct and 342 inverse variants with experimental structures)	0.44 pearson-correlation unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Result quoted from another source · Source checked Methods, coverage and source ABYSSAL on Ssym direct and inverse (Dieckhaus et al. 2024) protein-stability-20261009-protocol-dieckhaus2024-ssym Aggregation: Not reported Transfer learning to leverage larger datasets for improved prediction of protein stability changes · Table 3, row 'ABYSSAL ( 16 )', column 'Ssym (inverse) PCC'
Configuration: ACDC-NN (Dieckhaus et al. 2024)	Protocol: Ssym direct and inverse ddG prediction (Dieckhaus et al. 2024 Table 3) Dataset: Ssym (342 direct and 342 inverse variants with experimental structures)	0.58 pearson-correlation unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Result quoted from another source · Source checked Methods, coverage and source ACDC-NN on Ssym direct and inverse (Dieckhaus et al. 2024) protein-stability-20261009-protocol-dieckhaus2024-ssym Aggregation: Not reported Transfer learning to leverage larger datasets for improved prediction of protein stability changes · Table 3, row 'ACDC-NN ( 30 , 36 )', column 'Ssym (direct) PCC'
Configuration: ACDC-NN (Dieckhaus et al. 2024)	Protocol: Ssym direct and inverse ddG prediction (Dieckhaus et al. 2024 Table 3) Dataset: Ssym (342 direct and 342 inverse variants with experimental structures)	1.42 root-mean-squared-error kilocalorie-per-mole · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Result quoted from another source · Source checked Methods, coverage and source ACDC-NN on Ssym direct and inverse (Dieckhaus et al. 2024) protein-stability-20261009-protocol-dieckhaus2024-ssym Aggregation: Not reported Transfer learning to leverage larger datasets for improved prediction of protein stability changes · Table 3, row 'ACDC-NN ( 30 , 36 )', column 'Ssym (direct) RMSE (kcal/mol)'
Configuration: ACDC-NN (Dieckhaus et al. 2024)	Protocol: Ssym direct and inverse ddG prediction (Dieckhaus et al. 2024 Table 3) Dataset: Ssym (342 direct and 342 inverse variants with experimental structures)	0.55 pearson-correlation unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Result quoted from another source · Source checked Methods, coverage and source ACDC-NN on Ssym direct and inverse (Dieckhaus et al. 2024) protein-stability-20261009-protocol-dieckhaus2024-ssym Aggregation: Not reported Transfer learning to leverage larger datasets for improved prediction of protein stability changes · Table 3, row 'ACDC-NN ( 30 , 36 )', column 'Ssym (inverse) PCC'
Configuration: ACDC-NN (Dieckhaus et al. 2024)	Protocol: Ssym direct and inverse ddG prediction (Dieckhaus et al. 2024 Table 3) Dataset: Ssym (342 direct and 342 inverse variants with experimental structures)	1.47 root-mean-squared-error kilocalorie-per-mole · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Result quoted from another source · Source checked Methods, coverage and source ACDC-NN on Ssym direct and inverse (Dieckhaus et al. 2024) protein-stability-20261009-protocol-dieckhaus2024-ssym Aggregation: Not reported Transfer learning to leverage larger datasets for improved prediction of protein stability changes · Table 3, row 'ACDC-NN ( 30 , 36 )', column 'Ssym (inverse) RMSE (kcal/mol)'
Configuration: FoldX (Dieckhaus et al. 2024)	Protocol: Ssym direct and inverse ddG prediction (Dieckhaus et al. 2024 Table 3) Dataset: Ssym (342 direct and 342 inverse variants with experimental structures)	0.63 pearson-correlation unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Result quoted from another source · Source checked Methods, coverage and source FoldX on Ssym direct and inverse (Dieckhaus et al. 2024) protein-stability-20261009-protocol-dieckhaus2024-ssym Aggregation: Not reported Transfer learning to leverage larger datasets for improved prediction of protein stability changes · Table 3, row 'FoldX ( 29 , 30 )', column 'Ssym (direct) PCC'
Configuration: FoldX (Dieckhaus et al. 2024)	Protocol: Ssym direct and inverse ddG prediction (Dieckhaus et al. 2024 Table 3) Dataset: Ssym (342 direct and 342 inverse variants with experimental structures)	1.56 root-mean-squared-error kilocalorie-per-mole · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Result quoted from another source · Source checked Methods, coverage and source FoldX on Ssym direct and inverse (Dieckhaus et al. 2024) protein-stability-20261009-protocol-dieckhaus2024-ssym Aggregation: Not reported Transfer learning to leverage larger datasets for improved prediction of protein stability changes · Table 3, row 'FoldX ( 29 , 30 )', column 'Ssym (direct) RMSE (kcal/mol)'
Configuration: FoldX (Dieckhaus et al. 2024)	Protocol: Ssym direct and inverse ddG prediction (Dieckhaus et al. 2024 Table 3) Dataset: Ssym (342 direct and 342 inverse variants with experimental structures)	0.39 pearson-correlation unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Result quoted from another source · Source checked Methods, coverage and source FoldX on Ssym direct and inverse (Dieckhaus et al. 2024) protein-stability-20261009-protocol-dieckhaus2024-ssym Aggregation: Not reported Transfer learning to leverage larger datasets for improved prediction of protein stability changes · Table 3, row 'FoldX ( 29 , 30 )', column 'Ssym (inverse) PCC'
Configuration: FoldX (Dieckhaus et al. 2024)	Protocol: Ssym direct and inverse ddG prediction (Dieckhaus et al. 2024 Table 3) Dataset: Ssym (342 direct and 342 inverse variants with experimental structures)	2.13 root-mean-squared-error kilocalorie-per-mole · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Result quoted from another source · Source checked Methods, coverage and source FoldX on Ssym direct and inverse (Dieckhaus et al. 2024) protein-stability-20261009-protocol-dieckhaus2024-ssym Aggregation: Not reported Transfer learning to leverage larger datasets for improved prediction of protein stability changes · Table 3, row 'FoldX ( 29 , 30 )', column 'Ssym (inverse) RMSE (kcal/mol)'
Configuration: MAESTRO (Dieckhaus et al. 2024)	Protocol: Ssym direct and inverse ddG prediction (Dieckhaus et al. 2024 Table 3) Dataset: Ssym (342 direct and 342 inverse variants with experimental structures)	0.52 pearson-correlation unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Result quoted from another source · Source checked Methods, coverage and source MAESTRO on Ssym direct and inverse (Dieckhaus et al. 2024) protein-stability-20261009-protocol-dieckhaus2024-ssym Aggregation: Not reported Transfer learning to leverage larger datasets for improved prediction of protein stability changes · Table 3, row 'MAESTRO ( 29 , 30 )', column 'Ssym (direct) PCC'
Configuration: MAESTRO (Dieckhaus et al. 2024)	Protocol: Ssym direct and inverse ddG prediction (Dieckhaus et al. 2024 Table 3) Dataset: Ssym (342 direct and 342 inverse variants with experimental structures)	1.36 root-mean-squared-error kilocalorie-per-mole · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Result quoted from another source · Source checked Methods, coverage and source MAESTRO on Ssym direct and inverse (Dieckhaus et al. 2024) protein-stability-20261009-protocol-dieckhaus2024-ssym Aggregation: Not reported Transfer learning to leverage larger datasets for improved prediction of protein stability changes · Table 3, row 'MAESTRO ( 29 , 30 )', column 'Ssym (direct) RMSE (kcal/mol)'
Configuration: MAESTRO (Dieckhaus et al. 2024)	Protocol: Ssym direct and inverse ddG prediction (Dieckhaus et al. 2024 Table 3) Dataset: Ssym (342 direct and 342 inverse variants with experimental structures)	0.32 pearson-correlation unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Result quoted from another source · Source checked Methods, coverage and source MAESTRO on Ssym direct and inverse (Dieckhaus et al. 2024) protein-stability-20261009-protocol-dieckhaus2024-ssym Aggregation: Not reported Transfer learning to leverage larger datasets for improved prediction of protein stability changes · Table 3, row 'MAESTRO ( 29 , 30 )', column 'Ssym (inverse) PCC'
Configuration: MAESTRO (Dieckhaus et al. 2024)	Protocol: Ssym direct and inverse ddG prediction (Dieckhaus et al. 2024 Table 3) Dataset: Ssym (342 direct and 342 inverse variants with experimental structures)	2.09 root-mean-squared-error kilocalorie-per-mole · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Result quoted from another source · Source checked Methods, coverage and source MAESTRO on Ssym direct and inverse (Dieckhaus et al. 2024) protein-stability-20261009-protocol-dieckhaus2024-ssym Aggregation: Not reported Transfer learning to leverage larger datasets for improved prediction of protein stability changes · Table 3, row 'MAESTRO ( 29 , 30 )', column 'Ssym (inverse) RMSE (kcal/mol)'
Configuration: mCSM (Dieckhaus et al. 2024)	Protocol: Ssym direct and inverse ddG prediction (Dieckhaus et al. 2024 Table 3) Dataset: Ssym (342 direct and 342 inverse variants with experimental structures)	0.61 pearson-correlation unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Result quoted from another source · Source checked Methods, coverage and source mCSM on Ssym direct and inverse (Dieckhaus et al. 2024) protein-stability-20261009-protocol-dieckhaus2024-ssym Aggregation: Not reported Transfer learning to leverage larger datasets for improved prediction of protein stability changes · Table 3, row 'mCSM ( 29 , 30 )', column 'Ssym (direct) PCC'
Configuration: mCSM (Dieckhaus et al. 2024)	Protocol: Ssym direct and inverse ddG prediction (Dieckhaus et al. 2024 Table 3) Dataset: Ssym (342 direct and 342 inverse variants with experimental structures)	1.23 root-mean-squared-error kilocalorie-per-mole · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Result quoted from another source · Source checked Methods, coverage and source mCSM on Ssym direct and inverse (Dieckhaus et al. 2024) protein-stability-20261009-protocol-dieckhaus2024-ssym Aggregation: Not reported Transfer learning to leverage larger datasets for improved prediction of protein stability changes · Table 3, row 'mCSM ( 29 , 30 )', column 'Ssym (direct) RMSE (kcal/mol)'
Configuration: mCSM (Dieckhaus et al. 2024)	Protocol: Ssym direct and inverse ddG prediction (Dieckhaus et al. 2024 Table 3) Dataset: Ssym (342 direct and 342 inverse variants with experimental structures)	0.14 pearson-correlation unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Result quoted from another source · Source checked Methods, coverage and source mCSM on Ssym direct and inverse (Dieckhaus et al. 2024) protein-stability-20261009-protocol-dieckhaus2024-ssym Aggregation: Not reported Transfer learning to leverage larger datasets for improved prediction of protein stability changes · Table 3, row 'mCSM ( 29 , 30 )', column 'Ssym (inverse) PCC'
Configuration: mCSM (Dieckhaus et al. 2024)	Protocol: Ssym direct and inverse ddG prediction (Dieckhaus et al. 2024 Table 3) Dataset: Ssym (342 direct and 342 inverse variants with experimental structures)	2.43 root-mean-squared-error kilocalorie-per-mole · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Result quoted from another source · Source checked Methods, coverage and source mCSM on Ssym direct and inverse (Dieckhaus et al. 2024) protein-stability-20261009-protocol-dieckhaus2024-ssym Aggregation: Not reported Transfer learning to leverage larger datasets for improved prediction of protein stability changes · Table 3, row 'mCSM ( 29 , 30 )', column 'Ssym (inverse) RMSE (kcal/mol)'
Configuration: MUPRO (Dieckhaus et al. 2024)	Protocol: Ssym direct and inverse ddG prediction (Dieckhaus et al. 2024 Table 3) Dataset: Ssym (342 direct and 342 inverse variants with experimental structures)	0.79 pearson-correlation unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Result quoted from another source · Source checked Methods, coverage and source MUPRO on Ssym direct and inverse (Dieckhaus et al. 2024) protein-stability-20261009-protocol-dieckhaus2024-ssym Aggregation: Not reported Transfer learning to leverage larger datasets for improved prediction of protein stability changes · Table 3, row 'MUPRO ( 29 , 30 )', column 'Ssym (direct) PCC'
Configuration: MUPRO (Dieckhaus et al. 2024)	Protocol: Ssym direct and inverse ddG prediction (Dieckhaus et al. 2024 Table 3) Dataset: Ssym (342 direct and 342 inverse variants with experimental structures)	0.94 root-mean-squared-error kilocalorie-per-mole · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Result quoted from another source · Source checked Methods, coverage and source MUPRO on Ssym direct and inverse (Dieckhaus et al. 2024) protein-stability-20261009-protocol-dieckhaus2024-ssym Aggregation: Not reported Transfer learning to leverage larger datasets for improved prediction of protein stability changes · Table 3, row 'MUPRO ( 29 , 30 )', column 'Ssym (direct) RMSE (kcal/mol)'
Configuration: MUPRO (Dieckhaus et al. 2024)	Protocol: Ssym direct and inverse ddG prediction (Dieckhaus et al. 2024 Table 3) Dataset: Ssym (342 direct and 342 inverse variants with experimental structures)	0.07 pearson-correlation unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Result quoted from another source · Source checked Methods, coverage and source MUPRO on Ssym direct and inverse (Dieckhaus et al. 2024) protein-stability-20261009-protocol-dieckhaus2024-ssym Aggregation: Not reported Transfer learning to leverage larger datasets for improved prediction of protein stability changes · Table 3, row 'MUPRO ( 29 , 30 )', column 'Ssym (inverse) PCC'
Configuration: MUPRO (Dieckhaus et al. 2024)	Protocol: Ssym direct and inverse ddG prediction (Dieckhaus et al. 2024 Table 3) Dataset: Ssym (342 direct and 342 inverse variants with experimental structures)	2.51 root-mean-squared-error kilocalorie-per-mole · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Result quoted from another source · Source checked Methods, coverage and source MUPRO on Ssym direct and inverse (Dieckhaus et al. 2024) protein-stability-20261009-protocol-dieckhaus2024-ssym Aggregation: Not reported Transfer learning to leverage larger datasets for improved prediction of protein stability changes · Table 3, row 'MUPRO ( 29 , 30 )', column 'Ssym (inverse) RMSE (kcal/mol)'
Configuration: PROSTATA (Dieckhaus et al. 2024)	Protocol: Ssym direct and inverse ddG prediction (Dieckhaus et al. 2024 Table 3) Dataset: Ssym (342 direct and 342 inverse variants with experimental structures)	0.51 pearson-correlation unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Result quoted from another source · Source checked Methods, coverage and source PROSTATA on Ssym direct and inverse (Dieckhaus et al. 2024) protein-stability-20261009-protocol-dieckhaus2024-ssym Aggregation: Not reported Transfer learning to leverage larger datasets for improved prediction of protein stability changes · Table 3, row 'PROSTATA ( 17 )', column 'Ssym (direct) PCC'
Configuration: PROSTATA (Dieckhaus et al. 2024)	Protocol: Ssym direct and inverse ddG prediction (Dieckhaus et al. 2024 Table 3) Dataset: Ssym (342 direct and 342 inverse variants with experimental structures)	1.42 root-mean-squared-error kilocalorie-per-mole · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Result quoted from another source · Source checked Methods, coverage and source PROSTATA on Ssym direct and inverse (Dieckhaus et al. 2024) protein-stability-20261009-protocol-dieckhaus2024-ssym Aggregation: Not reported Transfer learning to leverage larger datasets for improved prediction of protein stability changes · Table 3, row 'PROSTATA ( 17 )', column 'Ssym (direct) RMSE (kcal/mol)'
Configuration: PROSTATA (Dieckhaus et al. 2024)	Protocol: Ssym direct and inverse ddG prediction (Dieckhaus et al. 2024 Table 3) Dataset: Ssym (342 direct and 342 inverse variants with experimental structures)	0.5 pearson-correlation unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Result quoted from another source · Source checked Methods, coverage and source PROSTATA on Ssym direct and inverse (Dieckhaus et al. 2024) protein-stability-20261009-protocol-dieckhaus2024-ssym Aggregation: Not reported Transfer learning to leverage larger datasets for improved prediction of protein stability changes · Table 3, row 'PROSTATA ( 17 )', column 'Ssym (inverse) PCC'

Source checking is not independent reproduction. Release 2026-10-10-7fcc3e48a123.

Methods and evaluation design

Procedure, tasks and evaluated configurations

Recorded evaluations

Each evaluation records what was tested and under which conditions.

Explore all linked results

Baseline coverage

Reference methods help show what a model adds beyond simple controls. We track a null control and a conventional method for each protocol.

0 of 2 active baseline roles have published Rewire measurements in this release. Measurements on a selected protocol do not establish coverage of an entire suite.

No execution recipe linked to this protocol. Recipe availability does not establish a completed evaluation.

Author-reported evaluations: 1
External evaluations: 1
paper compilation: 11

Literature evidence is not a Rewire measurement. Executed but unpublished runs and private review status are not included.

Null control

Proposed control: requires review

Select a task-valid null control after reviewing inputs and metric

Protocol-specific applicability, permitted inputs, access, split, evaluator and execution requirements need review before implementation or execution.

This is a suggested selection rule, not a validated method or a measured score.

Conventional reference

Proposed control: requires review

Select an upstream conventional reference after reviewing the full protocol

Protocol-specific applicability, permitted inputs, access, split, evaluator and execution requirements need review before implementation or execution.

This is a suggested selection rule, not a validated method or a measured score.

Protocol coverage CSV (gzip) · Model evaluation matrix (gzip) · Source table (gzip) · Release and checksums (gzip)

Coverage is derived from release 2026-10-10-7fcc3e48a123. Source citations describe the original records; they do not validate an unreviewed baseline proposal. No results have been generated by this audit.

Run instructions

No runnable recipe has been reviewed for this protocol. Dataset access, model requirements, licences and compute requirements must be checked against its sources before execution.

Strengths, limitations and unresolved questions

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.

0 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-10-10-7fcc3e48a123
Property and statement	Original source and location	Review and provenance

No evidence rows match these filters. Choose another scope or clear the search.

All evidence (JSONL) (gzip)How to read the evidence

Sources and history

Release 2026-10-10-7fcc3e48a123 · Record review: source checked

1 source records and release history

Transfer learning to leverage larger datasets for improved prediction of protein stability changes · Original source · PNAS 121(6):e2314853121, published 2024-01-29; PMC10861915 full-text XML

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: protein-stability-20261009-protocol-dieckhaus2024-ssym

areas: proteins-complexes
contexts: research
protocol: Predicted ddG compared with experimental ddG in kcal/mol; PCC Pearson and SCC Spearman correlation.
version: Table 3
metric: pearson-correlation
limitations: Most rows are compiled from earlier publications (references 29 and 30 and the methods' own papers) rather than rerun by the authors.; Variant counts are not printed in Table 3.; No uncertainty is printed.; The Results text says homologues of both Ssym and S669 were removed from the Megascale training set before ThermoMPNN was retrained for Table 3, but only the S669 ThermoMPNN cells carry footnote *; whether the Ssym values use the filtered model is not stated.
source locator: Table 3; Methods 'Datasets'

Related records

uses data: Ssym (342 direct and 342 inverse variants with experimental structures)
assessment: ABYSSAL on Ssym direct and inverse (Dieckhaus et al. 2024)
assessment: ACDC-NN on Ssym direct and inverse (Dieckhaus et al. 2024)
assessment: FoldX on Ssym direct and inverse (Dieckhaus et al. 2024)
assessment: MAESTRO on Ssym direct and inverse (Dieckhaus et al. 2024)
assessment: mCSM on Ssym direct and inverse (Dieckhaus et al. 2024)
assessment: MUPRO on Ssym direct and inverse (Dieckhaus et al. 2024)
assessment: PROSTATA on Ssym direct and inverse (Dieckhaus et al. 2024)
assessment: ProteinMPNN on Ssym direct and inverse (Dieckhaus et al. 2024)
assessment: RaSP on Ssym direct and inverse (Dieckhaus et al. 2024)
assessment: Rosetta on Ssym direct and inverse (Dieckhaus et al. 2024)
assessment: Stability Oracle on Ssym direct and inverse (Dieckhaus et al. 2024)
assessment: ThermoMPNN on Ssym direct and inverse (Dieckhaus et al. 2024)
assessment: ThermoNet on Ssym direct and inverse (Dieckhaus et al. 2024)
assessed by: Assess methods for protein stability experiments

Suggest a correction