Configuration

Transformer (DeepProtein benchmark)

Configuration of Transformer: sequence model; default DeepProtein configuration.

Overview

An explanatory profile has not yet been reviewed for this record.

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

Evaluations and results

34 evaluations · 34 results. Different protocols are not a single leaderboard.

Sorted by Macro F1 (averaged macro F1 (Figure 3 caption: 'averaged macro F1'), printed on a 0 to 100 scale) (higher is better). The best value in each column is highlighted. Decimals are rounded for display; each value links to the printed value and its source.

Tested configuration	Protocol and dataset	Macro F1 (averaged macro F1 (Figure 3 caption: 'averaged macro F1'), printed on a 0 to 100 scale)	MAE (mean absolute error)	AUPRC (area under the precision-recall curve, printed on a 0 to 100 scale)	R² (coefficient of determination)	Accuracy (accuracy, printed on a 0 to 100 scale)	AUROC (area under the ROC curve, printed on a 0 to 100 scale)	Spearman (Spearman rank correlation, as defined in the article's Evaluation metrics section; supervised split)
Transformer (DeepProtein benchmark)Evaluation	DeepProtein Binary localization (PEER): Averaged F1 ↑, Binary localization (PEER)	72.20 ± 2.21% (best in column)	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
Transformer (DeepProtein benchmark)Evaluation	DeepProtein Human PPI (PEER): Averaged F1 ↑, Human PPI (PEER)	68.64 ± 1.06%	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
Transformer (DeepProtein benchmark)Evaluation	DeepProtein Solubility (PEER): Averaged F1 ↑, Solubility (PEER)	61.28 ± 1.42%	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
Transformer (DeepProtein benchmark)Evaluation	DeepProtein Yeast PPI (PEER): Averaged F1 ↑, Yeast PPI (PEER)	51.93 ± 0.40%	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
Transformer (DeepProtein benchmark)Evaluation	DeepProtein Secondary structure prediction (TAPE): Averaged F1 ↑, Secondary structure prediction (TAPE)	49.66 ± 0.00%	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
Transformer (DeepProtein benchmark)Evaluation	DeepProtein PDB-Jespersen epitope prediction: Averaged F1 ↑, PDB-Jespersen epitope prediction	27.31 ± 0.56%	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
Transformer (DeepProtein benchmark)Evaluation	DeepProtein SAbDab-Liberis paratope prediction: Averaged F1 ↑, SAbDab-Liberis paratope prediction	26.73 ± 0.15%	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
Transformer (DeepProtein benchmark)Evaluation	DeepProtein Subcellular localization (PEER): Averaged F1 ↑, Subcellular localization (PEER)	25.46 ± 0.01%	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
Transformer (DeepProtein benchmark)Evaluation	DeepProtein IEDB epitope prediction: Averaged F1 ↑, IEDB epitope prediction	16.79 ± 0.07%	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
Transformer (DeepProtein benchmark)Evaluation	DeepProtein Fold classification (TAPE): Averaged F1 ↑, Fold classification (TAPE)	0.20 ± 0.02%	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
Transformer (DeepProtein benchmark)Evaluation	DeepProtein beta-lactamase (PEER): MAE ↓, beta-lactamase (PEER)	Not reported	0.232 ± 0.007	Not reported	Not reported	Not reported	Not reported	Not reported
Transformer (DeepProtein benchmark)Evaluation	DeepProtein beta-lactamase (PEER): ρ ↑, beta-lactamase (PEER)	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	0.310±0.041
Transformer (DeepProtein benchmark)Evaluation	DeepProtein Binary localization (PEER): PR-AUC ↑, Binary localization (PEER)	Not reported	Not reported	78.38±0.25%	Not reported	Not reported	Not reported	Not reported
Transformer (DeepProtein benchmark)Evaluation	DeepProtein CRISPR-Leenay repair outcome: MAE ↓, CRISPR-Leenay repair outcome	Not reported	0.1216±0.0020 (best in column)	Not reported	Not reported	Not reported	Not reported	Not reported
Transformer (DeepProtein benchmark)Evaluation	DeepProtein CRISPR-Leenay repair outcome: R2 ↑, CRISPR-Leenay repair outcome	Not reported	Not reported	Not reported	0.200 ± 0.054	Not reported	Not reported	Not reported
Transformer (DeepProtein benchmark)Evaluation	DeepProtein Fluorescence (TAPE): MAE ↓, Fluorescence (TAPE)	Not reported	0.371 ± 0.005	Not reported	Not reported	Not reported	Not reported	Not reported
Transformer (DeepProtein benchmark)Evaluation	DeepProtein Fluorescence (TAPE): ρ ↑, Fluorescence (TAPE)	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	0.648±0.001 (best in column)
Transformer (DeepProtein benchmark)Evaluation	DeepProtein Fold classification (TAPE): Acc ↑, Fold classification (TAPE)	Not reported	Not reported	Not reported	Not reported	5.34 ± 0.24%	Not reported	Not reported
Transformer (DeepProtein benchmark)Evaluation	DeepProtein Human PPI (PEER): PR-AUC ↑, Human PPI (PEER)	Not reported	Not reported	59.36±4.00%	Not reported	Not reported	Not reported	Not reported
Transformer (DeepProtein benchmark)Evaluation	DeepProtein IEDB epitope prediction: ROC-AUC ↑, IEDB epitope prediction	Not reported	Not reported	Not reported	Not reported	Not reported	59.79 ± 0.06**%	Not reported
Transformer (DeepProtein benchmark)Evaluation	DeepProtein PDB-Jespersen epitope prediction: ROC-AUC ↑, PDB-Jespersen epitope prediction	Not reported	Not reported	Not reported	Not reported	Not reported	60.10±0.32%	Not reported
Transformer (DeepProtein benchmark)Evaluation	DeepProtein PPI affinity (PEER): MAE ↓, PPI affinity (PEER)	Not reported	2.081 ± 0.133	Not reported	Not reported	Not reported	Not reported	Not reported
Transformer (DeepProtein benchmark)Evaluation	DeepProtein PPI affinity (PEER): R2 ↑, PPI affinity (PEER)	Not reported	Not reported	Not reported	0.425±0.021	Not reported	Not reported	Not reported
Transformer (DeepProtein benchmark)Evaluation	DeepProtein SAbDab-Chen antibody developability: MAE ↓, SAbDab-Chen antibody developability	Not reported	0.238±0.012	Not reported	Not reported	Not reported	Not reported	Not reported
Transformer (DeepProtein benchmark)Evaluation	DeepProtein SAbDab-Chen antibody developability: R2 ↑, SAbDab-Chen antibody developability	Not reported	Not reported	Not reported	0.452 ± 0.011 (best in column)	Not reported	Not reported	Not reported
Transformer (DeepProtein benchmark)Evaluation	DeepProtein SAbDab-Liberis paratope prediction: ROC-AUC ↑, SAbDab-Liberis paratope prediction	Not reported	Not reported	Not reported	Not reported	Not reported	64.77±0.11% (best in column)	Not reported
Transformer (DeepProtein benchmark)Evaluation	DeepProtein Secondary structure prediction (TAPE): Acc ↑, Secondary structure prediction (TAPE)	Not reported	Not reported	Not reported	Not reported	98.64 ± 0.00% (best in column)	Not reported	Not reported
Transformer (DeepProtein benchmark)Evaluation	DeepProtein Solubility (PEER): PR-AUC ↑, Solubility (PEER)	Not reported	Not reported	78.86 ± 0.46% (best in column)	Not reported	Not reported	Not reported	Not reported
Transformer (DeepProtein benchmark)Evaluation	DeepProtein Stability (TAPE): MAE ↓, Stability (TAPE)	Not reported	0.411 ± 0.026	Not reported	Not reported	Not reported	Not reported	Not reported
Transformer (DeepProtein benchmark)Evaluation	DeepProtein Stability (TAPE): ρ ↑, Stability (TAPE)	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	0.375±0.052
Transformer (DeepProtein benchmark)Evaluation	DeepProtein Subcellular localization (PEER): Acc ↑, Subcellular localization (PEER)	Not reported	Not reported	Not reported	Not reported	42.63±0.68%	Not reported	Not reported
Transformer (DeepProtein benchmark)Evaluation	DeepProtein TAP antibody developability: MAE ↓, TAP antibody developability	Not reported	3.476±0.004	Not reported	Not reported	Not reported	Not reported	Not reported
Transformer (DeepProtein benchmark)Evaluation	DeepProtein TAP antibody developability: R2 ↑, TAP antibody developability	Not reported	Not reported	Not reported	0.030 ± 0.011	Not reported	Not reported	Not reported
Transformer (DeepProtein benchmark)Evaluation	DeepProtein Yeast PPI (PEER): PR-AUC ↑, Yeast PPI (PEER)	Not reported	Not reported	53.79±1.07%	Not reported	Not reported	Not reported	Not reported

All 34 result rows with coverage, uncertainty and sources

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: Transformer (DeepProtein benchmark)	Protocol: DeepProtein beta-lactamase (PEER): MAE ↓ Dataset: beta-lactamase (PEER)	0.232 ± 0.007 MAE (mean absolute error) unit-unreported · lower Uncertainty: SD 0.007 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Figure 3's caption calls the regression metric 'Spearman (Pearson) Coefficient' while the Evaluation metrics section defines rho as Spearman rank correlation and R2 separately. The section's definition is taken as authoritative and the rho columns are recorded as Spearman; the caption wording is noted so a reader of the figure is not surprised.DeepProtein: deep learning library and benchmark for protein sequence learning · Tables 2, 4 and 6 column headings 'rho' and 'R2'; Figure 3 caption Methods, coverage and source Transformer on DeepProtein beta-lactamase (PEER) (MAE ↓) lit-protein-20261011-deepprotein-protocol-beta-lactamase-mae Aggregation: Not reported DeepProtein: deep learning library and benchmark for protein sequence learning · Table 2. row 'Transformer', column group 'β-lactamase', column 'MAE ↓'
Configuration: Transformer (DeepProtein benchmark)	Protocol: DeepProtein beta-lactamase (PEER): ρ ↑ Dataset: beta-lactamase (PEER)	0.310±0.041 Spearman (Spearman rank correlation, as defined in the article's Evaluation metrics section; supervised split) unitless · higher Uncertainty: SD 0.041 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Figure 3's caption calls the regression metric 'Spearman (Pearson) Coefficient' while the Evaluation metrics section defines rho as Spearman rank correlation and R2 separately. The section's definition is taken as authoritative and the rho columns are recorded as Spearman; the caption wording is noted so a reader of the figure is not surprised.DeepProtein: deep learning library and benchmark for protein sequence learning · Tables 2, 4 and 6 column headings 'rho' and 'R2'; Figure 3 caption Methods, coverage and source Transformer on DeepProtein beta-lactamase (PEER) (ρ ↑) lit-protein-20261011-deepprotein-protocol-beta-lactamase-rho Aggregation: Not reported DeepProtein: deep learning library and benchmark for protein sequence learning · Table 2. row 'Transformer', column group 'β-lactamase', column 'ρ ↑'
Configuration: Transformer (DeepProtein benchmark)	Protocol: DeepProtein Binary localization (PEER): Averaged F1 ↑ Dataset: Binary localization (PEER)	72.20 ± 2.21% Macro F1 (averaged macro F1 (Figure 3 caption: 'averaged macro F1'), printed on a 0 to 100 scale) percent · higher Uncertainty: SD 2.21 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Figure 3's caption calls the regression metric 'Spearman (Pearson) Coefficient' while the Evaluation metrics section defines rho as Spearman rank correlation and R2 separately. The section's definition is taken as authoritative and the rho columns are recorded as Spearman; the caption wording is noted so a reader of the figure is not surprised.DeepProtein: deep learning library and benchmark for protein sequence learning · Tables 2, 4 and 6 column headings 'rho' and 'R2'; Figure 3 caption Methods, coverage and source Transformer on DeepProtein Binary localization (PEER) (Averaged F1 ↑) lit-protein-20261011-deepprotein-protocol-binary-avg-f1 Aggregation: Not reported DeepProtein: deep learning library and benchmark for protein sequence learning · Table 3. row 'Transformer', column group 'Binary', column 'Averaged F1 ↑'
Configuration: Transformer (DeepProtein benchmark)	Protocol: DeepProtein Binary localization (PEER): PR-AUC ↑ Dataset: Binary localization (PEER)	78.38±0.25% AUPRC (area under the precision-recall curve, printed on a 0 to 100 scale) percent · higher Uncertainty: SD 0.25 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Figure 3's caption calls the regression metric 'Spearman (Pearson) Coefficient' while the Evaluation metrics section defines rho as Spearman rank correlation and R2 separately. The section's definition is taken as authoritative and the rho columns are recorded as Spearman; the caption wording is noted so a reader of the figure is not surprised.DeepProtein: deep learning library and benchmark for protein sequence learning · Tables 2, 4 and 6 column headings 'rho' and 'R2'; Figure 3 caption Methods, coverage and source Transformer on DeepProtein Binary localization (PEER) (PR-AUC ↑) lit-protein-20261011-deepprotein-protocol-binary-pr-auc Aggregation: Not reported DeepProtein: deep learning library and benchmark for protein sequence learning · Table 3. row 'Transformer', column group 'Binary', column 'PR-AUC ↑'
Configuration: Transformer (DeepProtein benchmark)	Protocol: DeepProtein CRISPR-Leenay repair outcome: MAE ↓ Dataset: CRISPR-Leenay repair outcome	0.1216±0.0020 MAE (mean absolute error) unit-unreported · lower Uncertainty: SD 0.0020 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Figure 3's caption calls the regression metric 'Spearman (Pearson) Coefficient' while the Evaluation metrics section defines rho as Spearman rank correlation and R2 separately. The section's definition is taken as authoritative and the rho columns are recorded as Spearman; the caption wording is noted so a reader of the figure is not surprised.DeepProtein: deep learning library and benchmark for protein sequence learning · Tables 2, 4 and 6 column headings 'rho' and 'R2'; Figure 3 caption Methods, coverage and source Transformer on DeepProtein CRISPR-Leenay repair outcome (MAE ↓) lit-protein-20261011-deepprotein-protocol-crispr-leenay-mae Aggregation: Not reported DeepProtein: deep learning library and benchmark for protein sequence learning · Table 6. row 'Transformer', column group 'CRISPR-Leenay', column 'MAE ↓'
Configuration: Transformer (DeepProtein benchmark)	Protocol: DeepProtein CRISPR-Leenay repair outcome: R2 ↑ Dataset: CRISPR-Leenay repair outcome	0.200 ± 0.054 R² (coefficient of determination) unitless · higher Uncertainty: SD 0.054 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Figure 3's caption calls the regression metric 'Spearman (Pearson) Coefficient' while the Evaluation metrics section defines rho as Spearman rank correlation and R2 separately. The section's definition is taken as authoritative and the rho columns are recorded as Spearman; the caption wording is noted so a reader of the figure is not surprised.DeepProtein: deep learning library and benchmark for protein sequence learning · Tables 2, 4 and 6 column headings 'rho' and 'R2'; Figure 3 caption Methods, coverage and source Transformer on DeepProtein CRISPR-Leenay repair outcome (R2 ↑) lit-protein-20261011-deepprotein-protocol-crispr-leenay-r2 Aggregation: Not reported DeepProtein: deep learning library and benchmark for protein sequence learning · Table 6. row 'Transformer', column group 'CRISPR-Leenay', column 'R2 ↑'
Configuration: Transformer (DeepProtein benchmark)	Protocol: DeepProtein Fluorescence (TAPE): MAE ↓ Dataset: Fluorescence (TAPE)	0.371 ± 0.005 MAE (mean absolute error) unit-unreported · lower Uncertainty: SD 0.005 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Figure 3's caption calls the regression metric 'Spearman (Pearson) Coefficient' while the Evaluation metrics section defines rho as Spearman rank correlation and R2 separately. The section's definition is taken as authoritative and the rho columns are recorded as Spearman; the caption wording is noted so a reader of the figure is not surprised.DeepProtein: deep learning library and benchmark for protein sequence learning · Tables 2, 4 and 6 column headings 'rho' and 'R2'; Figure 3 caption Methods, coverage and source Transformer on DeepProtein Fluorescence (TAPE) (MAE ↓) lit-protein-20261011-deepprotein-protocol-fluorescence-mae Aggregation: Not reported DeepProtein: deep learning library and benchmark for protein sequence learning · Table 2. row 'Transformer', column group 'Fluorescence', column 'MAE ↓'
Configuration: Transformer (DeepProtein benchmark)	Protocol: DeepProtein Fluorescence (TAPE): ρ ↑ Dataset: Fluorescence (TAPE)	0.648±0.001 Spearman (Spearman rank correlation, as defined in the article's Evaluation metrics section; supervised split) unitless · higher Uncertainty: SD 0.001 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Figure 3's caption calls the regression metric 'Spearman (Pearson) Coefficient' while the Evaluation metrics section defines rho as Spearman rank correlation and R2 separately. The section's definition is taken as authoritative and the rho columns are recorded as Spearman; the caption wording is noted so a reader of the figure is not surprised.DeepProtein: deep learning library and benchmark for protein sequence learning · Tables 2, 4 and 6 column headings 'rho' and 'R2'; Figure 3 caption Methods, coverage and source Transformer on DeepProtein Fluorescence (TAPE) (ρ ↑) lit-protein-20261011-deepprotein-protocol-fluorescence-rho Aggregation: Not reported DeepProtein: deep learning library and benchmark for protein sequence learning · Table 2. row 'Transformer', column group 'Fluorescence', column 'ρ ↑'
Configuration: Transformer (DeepProtein benchmark)	Protocol: DeepProtein Fold classification (TAPE): Acc ↑ Dataset: Fold classification (TAPE)	5.34 ± 0.24% Accuracy (accuracy, printed on a 0 to 100 scale) percent · higher Uncertainty: SD 0.24 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Figure 3's caption calls the regression metric 'Spearman (Pearson) Coefficient' while the Evaluation metrics section defines rho as Spearman rank correlation and R2 separately. The section's definition is taken as authoritative and the rho columns are recorded as Spearman; the caption wording is noted so a reader of the figure is not surprised.DeepProtein: deep learning library and benchmark for protein sequence learning · Tables 2, 4 and 6 column headings 'rho' and 'R2'; Figure 3 caption Methods, coverage and source Transformer on DeepProtein Fold classification (TAPE) (Acc ↑) lit-protein-20261011-deepprotein-protocol-fold-acc Aggregation: Not reported DeepProtein: deep learning library and benchmark for protein sequence learning · Table 7. row 'Transformer', column group 'Fold', column 'Acc ↑'
Configuration: Transformer (DeepProtein benchmark)	Protocol: DeepProtein Fold classification (TAPE): Averaged F1 ↑ Dataset: Fold classification (TAPE)	0.20 ± 0.02% Macro F1 (averaged macro F1 (Figure 3 caption: 'averaged macro F1'), printed on a 0 to 100 scale) percent · higher Uncertainty: SD 0.02 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Figure 3's caption calls the regression metric 'Spearman (Pearson) Coefficient' while the Evaluation metrics section defines rho as Spearman rank correlation and R2 separately. The section's definition is taken as authoritative and the rho columns are recorded as Spearman; the caption wording is noted so a reader of the figure is not surprised.DeepProtein: deep learning library and benchmark for protein sequence learning · Tables 2, 4 and 6 column headings 'rho' and 'R2'; Figure 3 caption Methods, coverage and source Transformer on DeepProtein Fold classification (TAPE) (Averaged F1 ↑) lit-protein-20261011-deepprotein-protocol-fold-avg-f1 Aggregation: Not reported DeepProtein: deep learning library and benchmark for protein sequence learning · Table 7. row 'Transformer', column group 'Fold', column 'Averaged F1 ↑'
Configuration: Transformer (DeepProtein benchmark)	Protocol: DeepProtein Human PPI (PEER): Averaged F1 ↑ Dataset: Human PPI (PEER)	68.64 ± 1.06% Macro F1 (averaged macro F1 (Figure 3 caption: 'averaged macro F1'), printed on a 0 to 100 scale) percent · higher Uncertainty: SD 1.06 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Figure 3's caption calls the regression metric 'Spearman (Pearson) Coefficient' while the Evaluation metrics section defines rho as Spearman rank correlation and R2 separately. The section's definition is taken as authoritative and the rho columns are recorded as Spearman; the caption wording is noted so a reader of the figure is not surprised.DeepProtein: deep learning library and benchmark for protein sequence learning · Tables 2, 4 and 6 column headings 'rho' and 'R2'; Figure 3 caption Methods, coverage and source Transformer on DeepProtein Human PPI (PEER) (Averaged F1 ↑) lit-protein-20261011-deepprotein-protocol-human-ppi-avg-f1 Aggregation: Not reported DeepProtein: deep learning library and benchmark for protein sequence learning · Table 4. row 'Transformer', column group 'Human PPI', column 'Averaged F1 ↑'
Configuration: Transformer (DeepProtein benchmark)	Protocol: DeepProtein Human PPI (PEER): PR-AUC ↑ Dataset: Human PPI (PEER)	59.36±4.00% AUPRC (area under the precision-recall curve, printed on a 0 to 100 scale) percent · higher Uncertainty: SD 4.00 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Figure 3's caption calls the regression metric 'Spearman (Pearson) Coefficient' while the Evaluation metrics section defines rho as Spearman rank correlation and R2 separately. The section's definition is taken as authoritative and the rho columns are recorded as Spearman; the caption wording is noted so a reader of the figure is not surprised.DeepProtein: deep learning library and benchmark for protein sequence learning · Tables 2, 4 and 6 column headings 'rho' and 'R2'; Figure 3 caption Methods, coverage and source Transformer on DeepProtein Human PPI (PEER) (PR-AUC ↑) lit-protein-20261011-deepprotein-protocol-human-ppi-pr-auc Aggregation: Not reported DeepProtein: deep learning library and benchmark for protein sequence learning · Table 4. row 'Transformer', column group 'Human PPI', column 'PR-AUC ↑'
Configuration: Transformer (DeepProtein benchmark)	Protocol: DeepProtein IEDB epitope prediction: Averaged F1 ↑ Dataset: IEDB epitope prediction	16.79 ± 0.07% Macro F1 (averaged macro F1 (Figure 3 caption: 'averaged macro F1'), printed on a 0 to 100 scale) percent · higher Uncertainty: SD 0.07 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Figure 3's caption calls the regression metric 'Spearman (Pearson) Coefficient' while the Evaluation metrics section defines rho as Spearman rank correlation and R2 separately. The section's definition is taken as authoritative and the rho columns are recorded as Spearman; the caption wording is noted so a reader of the figure is not surprised.DeepProtein: deep learning library and benchmark for protein sequence learning · Tables 2, 4 and 6 column headings 'rho' and 'R2'; Figure 3 caption Methods, coverage and source Transformer on DeepProtein IEDB epitope prediction (Averaged F1 ↑) lit-protein-20261011-deepprotein-protocol-iedb-avg-f1 Aggregation: Not reported DeepProtein: deep learning library and benchmark for protein sequence learning · Table 5. row 'Transformer', column group 'IEDB', column 'Averaged F1 ↑'
Configuration: Transformer (DeepProtein benchmark)	Protocol: DeepProtein IEDB epitope prediction: ROC-AUC ↑ Dataset: IEDB epitope prediction	59.79 ± 0.06%** AUROC (area under the ROC curve, printed on a 0 to 100 scale) percent · higher Uncertainty: SD 0.06 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Figure 3's caption calls the regression metric 'Spearman (Pearson) Coefficient' while the Evaluation metrics section defines rho as Spearman rank correlation and R2 separately. The section's definition is taken as authoritative and the rho columns are recorded as Spearman; the caption wording is noted so a reader of the figure is not surprised.DeepProtein: deep learning library and benchmark for protein sequence learning · Tables 2, 4 and 6 column headings 'rho' and 'R2'; Figure 3 caption Methods, coverage and source Transformer on DeepProtein IEDB epitope prediction (ROC-AUC ↑) lit-protein-20261011-deepprotein-protocol-iedb-roc-auc Aggregation: Not reported DeepProtein: deep learning library and benchmark for protein sequence learning · Table 5. row 'Transformer', column group 'IEDB', column 'ROC-AUC ↑'
Configuration: Transformer (DeepProtein benchmark)	Protocol: DeepProtein PDB-Jespersen epitope prediction: Averaged F1 ↑ Dataset: PDB-Jespersen epitope prediction	27.31 ± 0.56% Macro F1 (averaged macro F1 (Figure 3 caption: 'averaged macro F1'), printed on a 0 to 100 scale) percent · higher Uncertainty: SD 0.56 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Figure 3's caption calls the regression metric 'Spearman (Pearson) Coefficient' while the Evaluation metrics section defines rho as Spearman rank correlation and R2 separately. The section's definition is taken as authoritative and the rho columns are recorded as Spearman; the caption wording is noted so a reader of the figure is not surprised.DeepProtein: deep learning library and benchmark for protein sequence learning · Tables 2, 4 and 6 column headings 'rho' and 'R2'; Figure 3 caption Methods, coverage and source Transformer on DeepProtein PDB-Jespersen epitope prediction (Averaged F1 ↑) lit-protein-20261011-deepprotein-protocol-pdb-jespersen-avg-f1 Aggregation: Not reported DeepProtein: deep learning library and benchmark for protein sequence learning · Table 5. row 'Transformer', column group 'PDB-Jespersen', column 'Averaged F1 ↑'
Configuration: Transformer (DeepProtein benchmark)	Protocol: DeepProtein PDB-Jespersen epitope prediction: ROC-AUC ↑ Dataset: PDB-Jespersen epitope prediction	60.10±0.32% AUROC (area under the ROC curve, printed on a 0 to 100 scale) percent · higher Uncertainty: SD 0.32 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Figure 3's caption calls the regression metric 'Spearman (Pearson) Coefficient' while the Evaluation metrics section defines rho as Spearman rank correlation and R2 separately. The section's definition is taken as authoritative and the rho columns are recorded as Spearman; the caption wording is noted so a reader of the figure is not surprised.DeepProtein: deep learning library and benchmark for protein sequence learning · Tables 2, 4 and 6 column headings 'rho' and 'R2'; Figure 3 caption Methods, coverage and source Transformer on DeepProtein PDB-Jespersen epitope prediction (ROC-AUC ↑) lit-protein-20261011-deepprotein-protocol-pdb-jespersen-roc-auc Aggregation: Not reported DeepProtein: deep learning library and benchmark for protein sequence learning · Table 5. row 'Transformer', column group 'PDB-Jespersen', column 'ROC-AUC ↑'
Configuration: Transformer (DeepProtein benchmark)	Protocol: DeepProtein PPI affinity (PEER): MAE ↓ Dataset: PPI affinity (PEER)	2.081 ± 0.133 MAE (mean absolute error) unit-unreported · lower Uncertainty: SD 0.133 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Figure 3's caption calls the regression metric 'Spearman (Pearson) Coefficient' while the Evaluation metrics section defines rho as Spearman rank correlation and R2 separately. The section's definition is taken as authoritative and the rho columns are recorded as Spearman; the caption wording is noted so a reader of the figure is not surprised.DeepProtein: deep learning library and benchmark for protein sequence learning · Tables 2, 4 and 6 column headings 'rho' and 'R2'; Figure 3 caption Methods, coverage and source Transformer on DeepProtein PPI affinity (PEER) (MAE ↓) lit-protein-20261011-deepprotein-protocol-ppi-affinity-mae Aggregation: Not reported DeepProtein: deep learning library and benchmark for protein sequence learning · Table 4. row 'Transformer', column group 'PPI Affinity', column 'MAE ↓'
Configuration: Transformer (DeepProtein benchmark)	Protocol: DeepProtein PPI affinity (PEER): R2 ↑ Dataset: PPI affinity (PEER)	0.425±0.021 R² (coefficient of determination) unitless · higher Uncertainty: SD 0.021 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Figure 3's caption calls the regression metric 'Spearman (Pearson) Coefficient' while the Evaluation metrics section defines rho as Spearman rank correlation and R2 separately. The section's definition is taken as authoritative and the rho columns are recorded as Spearman; the caption wording is noted so a reader of the figure is not surprised.DeepProtein: deep learning library and benchmark for protein sequence learning · Tables 2, 4 and 6 column headings 'rho' and 'R2'; Figure 3 caption Methods, coverage and source Transformer on DeepProtein PPI affinity (PEER) (R2 ↑) lit-protein-20261011-deepprotein-protocol-ppi-affinity-r2 Aggregation: Not reported DeepProtein: deep learning library and benchmark for protein sequence learning · Table 4. row 'Transformer', column group 'PPI Affinity', column 'R2 ↑'
Configuration: Transformer (DeepProtein benchmark)	Protocol: DeepProtein SAbDab-Chen antibody developability: MAE ↓ Dataset: SAbDab-Chen antibody developability	0.238±0.012 MAE (mean absolute error) unit-unreported · lower Uncertainty: SD 0.012 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Figure 3's caption calls the regression metric 'Spearman (Pearson) Coefficient' while the Evaluation metrics section defines rho as Spearman rank correlation and R2 separately. The section's definition is taken as authoritative and the rho columns are recorded as Spearman; the caption wording is noted so a reader of the figure is not surprised.DeepProtein: deep learning library and benchmark for protein sequence learning · Tables 2, 4 and 6 column headings 'rho' and 'R2'; Figure 3 caption Methods, coverage and source Transformer on DeepProtein SAbDab-Chen antibody developability (MAE ↓) lit-protein-20261011-deepprotein-protocol-sabdab-chen-mae Aggregation: Not reported DeepProtein: deep learning library and benchmark for protein sequence learning · Table 6. row 'Transformer', column group 'SAbDab-Chen', column 'MAE ↓'
Configuration: Transformer (DeepProtein benchmark)	Protocol: DeepProtein SAbDab-Chen antibody developability: R2 ↑ Dataset: SAbDab-Chen antibody developability	0.452 ± 0.011 R² (coefficient of determination) unitless · higher Uncertainty: SD 0.011 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Figure 3's caption calls the regression metric 'Spearman (Pearson) Coefficient' while the Evaluation metrics section defines rho as Spearman rank correlation and R2 separately. The section's definition is taken as authoritative and the rho columns are recorded as Spearman; the caption wording is noted so a reader of the figure is not surprised.DeepProtein: deep learning library and benchmark for protein sequence learning · Tables 2, 4 and 6 column headings 'rho' and 'R2'; Figure 3 caption Methods, coverage and source Transformer on DeepProtein SAbDab-Chen antibody developability (R2 ↑) lit-protein-20261011-deepprotein-protocol-sabdab-chen-r2 Aggregation: Not reported DeepProtein: deep learning library and benchmark for protein sequence learning · Table 6. row 'Transformer', column group 'SAbDab-Chen', column 'R2 ↑'
Configuration: Transformer (DeepProtein benchmark)	Protocol: DeepProtein SAbDab-Liberis paratope prediction: Averaged F1 ↑ Dataset: SAbDab-Liberis paratope prediction	26.73 ± 0.15% Macro F1 (averaged macro F1 (Figure 3 caption: 'averaged macro F1'), printed on a 0 to 100 scale) percent · higher Uncertainty: SD 0.15 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Figure 3's caption calls the regression metric 'Spearman (Pearson) Coefficient' while the Evaluation metrics section defines rho as Spearman rank correlation and R2 separately. The section's definition is taken as authoritative and the rho columns are recorded as Spearman; the caption wording is noted so a reader of the figure is not surprised.DeepProtein: deep learning library and benchmark for protein sequence learning · Tables 2, 4 and 6 column headings 'rho' and 'R2'; Figure 3 caption Methods, coverage and source Transformer on DeepProtein SAbDab-Liberis paratope prediction (Averaged F1 ↑) lit-protein-20261011-deepprotein-protocol-sabdab-liberis-avg-f1 Aggregation: Not reported DeepProtein: deep learning library and benchmark for protein sequence learning · Table 5. row 'Transformer', column group 'SAbDab-Liberis', column 'Averaged F1 ↑'
Configuration: Transformer (DeepProtein benchmark)	Protocol: DeepProtein SAbDab-Liberis paratope prediction: ROC-AUC ↑ Dataset: SAbDab-Liberis paratope prediction	64.77±0.11% AUROC (area under the ROC curve, printed on a 0 to 100 scale) percent · higher Uncertainty: SD 0.11 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Figure 3's caption calls the regression metric 'Spearman (Pearson) Coefficient' while the Evaluation metrics section defines rho as Spearman rank correlation and R2 separately. The section's definition is taken as authoritative and the rho columns are recorded as Spearman; the caption wording is noted so a reader of the figure is not surprised.DeepProtein: deep learning library and benchmark for protein sequence learning · Tables 2, 4 and 6 column headings 'rho' and 'R2'; Figure 3 caption Methods, coverage and source Transformer on DeepProtein SAbDab-Liberis paratope prediction (ROC-AUC ↑) lit-protein-20261011-deepprotein-protocol-sabdab-liberis-roc-auc Aggregation: Not reported DeepProtein: deep learning library and benchmark for protein sequence learning · Table 5. row 'Transformer', column group 'SAbDab-Liberis', column 'ROC-AUC ↑'
Configuration: Transformer (DeepProtein benchmark)	Protocol: DeepProtein Secondary structure prediction (TAPE): Acc ↑ Dataset: Secondary structure prediction (TAPE)	98.64 ± 0.00% Accuracy (accuracy, printed on a 0 to 100 scale) percent · higher Uncertainty: SD 0.00 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Figure 3's caption calls the regression metric 'Spearman (Pearson) Coefficient' while the Evaluation metrics section defines rho as Spearman rank correlation and R2 separately. The section's definition is taken as authoritative and the rho columns are recorded as Spearman; the caption wording is noted so a reader of the figure is not surprised.DeepProtein: deep learning library and benchmark for protein sequence learning · Tables 2, 4 and 6 column headings 'rho' and 'R2'; Figure 3 caption Methods, coverage and source Transformer on DeepProtein Secondary structure prediction (TAPE) (Acc ↑) lit-protein-20261011-deepprotein-protocol-secondary-structure-acc Aggregation: Not reported DeepProtein: deep learning library and benchmark for protein sequence learning · Table 7. row 'Transformer', column group 'Secondary Structure', column 'Acc ↑'
Configuration: Transformer (DeepProtein benchmark)	Protocol: DeepProtein Secondary structure prediction (TAPE): Averaged F1 ↑ Dataset: Secondary structure prediction (TAPE)	49.66 ± 0.00% Macro F1 (averaged macro F1 (Figure 3 caption: 'averaged macro F1'), printed on a 0 to 100 scale) percent · higher Uncertainty: SD 0.00 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Figure 3's caption calls the regression metric 'Spearman (Pearson) Coefficient' while the Evaluation metrics section defines rho as Spearman rank correlation and R2 separately. The section's definition is taken as authoritative and the rho columns are recorded as Spearman; the caption wording is noted so a reader of the figure is not surprised.DeepProtein: deep learning library and benchmark for protein sequence learning · Tables 2, 4 and 6 column headings 'rho' and 'R2'; Figure 3 caption Methods, coverage and source Transformer on DeepProtein Secondary structure prediction (TAPE) (Averaged F1 ↑) lit-protein-20261011-deepprotein-protocol-secondary-structure-avg-f1 Aggregation: Not reported DeepProtein: deep learning library and benchmark for protein sequence learning · Table 7. row 'Transformer', column group 'Secondary Structure', column 'Averaged F1 ↑'
Configuration: Transformer (DeepProtein benchmark)	Protocol: DeepProtein Solubility (PEER): Averaged F1 ↑ Dataset: Solubility (PEER)	61.28 ± 1.42% Macro F1 (averaged macro F1 (Figure 3 caption: 'averaged macro F1'), printed on a 0 to 100 scale) percent · higher Uncertainty: SD 1.42 Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Figure 3's caption calls the regression metric 'Spearman (Pearson) Coefficient' while the Evaluation metrics section defines rho as Spearman rank correlation and R2 separately. The section's definition is taken as authoritative and the rho columns are recorded as Spearman; the caption wording is noted so a reader of the figure is not surprised.DeepProtein: deep learning library and benchmark for protein sequence learning · Tables 2, 4 and 6 column headings 'rho' and 'R2'; Figure 3 caption Methods, coverage and source Transformer on DeepProtein Solubility (PEER) (Averaged F1 ↑) lit-protein-20261011-deepprotein-protocol-solubility-avg-f1 Aggregation: Not reported DeepProtein: deep learning library and benchmark for protein sequence learning · Table 2. row 'Transformer', column group 'Solubility', column 'Averaged F1 ↑'

Source checking is not independent reproduction. Release 2026-10-22-1b7cf027e4f6.

Use this configuration

How it works, versions and access

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 2026-10-22-1b7cf027e4f6
Property and statement	Original source and location	Review and provenance

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

How to read the evidence

Sources and history

Release 2026-10-22-1b7cf027e4f6 · Record review: source checked

1 source record and release history

DeepProtein: deep learning library and benchmark for protein sequence learning · Original source · Version of record, Bioinformatics 2025 (PMC12553333 JATS full text)

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: lit-protein-20261011-deepprotein-config-transformer

areas: protein-function
contexts: research
method types: specialist
reported name: Transformer
reported configuration: sequence model; default DeepProtein configuration (Table 9)
foundation model eligible: false
source locator: Tables 2 to 8, row 'Transformer'; Table 9 for the default configuration
missing metadata: version: reason: unreported; note: The tables name the model without a release version
provenance note: Transformer as trained and evaluated in the DeepProtein benchmark (sequence model).

Related records

Suggest a correction