Configuration

Prot-T5 (DeepProtein benchmark)

Configuration of Prot-T5: protein language 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

26 evaluations · 26 results. Different protocols are not a single leaderboard.

Sorted by Peak memory (peak GPU memory) (lower 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	Peak memory (peak GPU memory)	Runtime (training wall-clock time)
Prot-T5 (DeepProtein benchmark)Evaluation	DeepProtein CRISPR-Leenay repair outcome: GPU Memory (GB), CRISPR-Leenay repair outcome	5.16 (best in column)	Not reported
Prot-T5 (DeepProtein benchmark)Evaluation	DeepProtein SAbDab-Chen antibody developability: GPU Memory (GB), SAbDab-Chen antibody developability	5.16 (best in column)	Not reported
Prot-T5 (DeepProtein benchmark)Evaluation	DeepProtein TAP antibody developability: GPU Memory (GB), TAP antibody developability	5.16 (best in column)	Not reported
Prot-T5 (DeepProtein benchmark)Evaluation	DeepProtein PPI affinity (PEER): GPU Memory (GB), PPI affinity (PEER)	5.16	Not reported
Prot-T5 (DeepProtein benchmark)Evaluation	DeepProtein beta-lactamase (PEER): GPU Memory (GB), beta-lactamase (PEER)	5.2	Not reported
Prot-T5 (DeepProtein benchmark)Evaluation	DeepProtein Fluorescence (TAPE): GPU Memory (GB), Fluorescence (TAPE)	5.2	Not reported
Prot-T5 (DeepProtein benchmark)Evaluation	DeepProtein Fold classification (TAPE): GPU Memory (GB), Fold classification (TAPE)	5.22	Not reported
Prot-T5 (DeepProtein benchmark)Evaluation	DeepProtein Binary localization (PEER): GPU Memory (GB), Binary localization (PEER)	5.62	Not reported
Prot-T5 (DeepProtein benchmark)Evaluation	DeepProtein Subcellular localization (PEER): GPU Memory (GB), Subcellular localization (PEER)	5.71	Not reported
Prot-T5 (DeepProtein benchmark)Evaluation	DeepProtein Solubility (PEER): GPU Memory (GB), Solubility (PEER)	7.33	Not reported
Prot-T5 (DeepProtein benchmark)Evaluation	DeepProtein Yeast PPI (PEER): GPU Memory (GB), Yeast PPI (PEER)	9.04	Not reported
Prot-T5 (DeepProtein benchmark)Evaluation	DeepProtein Human PPI (PEER): GPU Memory (GB), Human PPI (PEER)	9.38	Not reported
Prot-T5 (DeepProtein benchmark)Evaluation	DeepProtein Stability (TAPE): GPU Memory (GB), Stability (TAPE)	10.2	Not reported
Prot-T5 (DeepProtein benchmark)Evaluation	DeepProtein beta-lactamase (PEER): Time (hour), beta-lactamase (PEER)	Not reported	0.0006
Prot-T5 (DeepProtein benchmark)Evaluation	DeepProtein Binary localization (PEER): Time (hour), Binary localization (PEER)	Not reported	0.0003
Prot-T5 (DeepProtein benchmark)Evaluation	DeepProtein CRISPR-Leenay repair outcome: Time (hour), CRISPR-Leenay repair outcome	Not reported	0.0005
Prot-T5 (DeepProtein benchmark)Evaluation	DeepProtein Fluorescence (TAPE): Time (hour), Fluorescence (TAPE)	Not reported	0.0016
Prot-T5 (DeepProtein benchmark)Evaluation	DeepProtein Fold classification (TAPE): Time (hour), Fold classification (TAPE)	Not reported	0.0002 (best in column)
Prot-T5 (DeepProtein benchmark)Evaluation	DeepProtein Human PPI (PEER): Time (hour), Human PPI (PEER)	Not reported	0.0032
Prot-T5 (DeepProtein benchmark)Evaluation	DeepProtein PPI affinity (PEER): Time (hour), PPI affinity (PEER)	Not reported	0.0005
Prot-T5 (DeepProtein benchmark)Evaluation	DeepProtein SAbDab-Chen antibody developability: Time (hour), SAbDab-Chen antibody developability	Not reported	0.0006
Prot-T5 (DeepProtein benchmark)Evaluation	DeepProtein Solubility (PEER): Time (hour), Solubility (PEER)	Not reported	0.04
Prot-T5 (DeepProtein benchmark)Evaluation	DeepProtein Stability (TAPE): Time (hour), Stability (TAPE)	Not reported	0.00472
Prot-T5 (DeepProtein benchmark)Evaluation	DeepProtein Subcellular localization (PEER): Time (hour), Subcellular localization (PEER)	Not reported	0.0006
Prot-T5 (DeepProtein benchmark)Evaluation	DeepProtein TAP antibody developability: Time (hour), TAP antibody developability	Not reported	0.0003
Prot-T5 (DeepProtein benchmark)Evaluation	DeepProtein Yeast PPI (PEER): Time (hour), Yeast PPI (PEER)	Not reported	0.0002 (best in column)

All 26 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: Prot-T5 (DeepProtein benchmark)	Protocol: DeepProtein beta-lactamase (PEER): GPU Memory (GB) Dataset: beta-lactamase (PEER)	5.2 Peak memory (peak GPU memory) gigabyte · lower Uncertainty: Not reported by the source 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 Prot-T5 resource usage on DeepProtein beta-lactamase (PEER) (GPU Memory (GB)) lit-protein-20261011-deepprotein-protocol-beta-lactamase-memory Aggregation: Not reported DeepProtein: deep learning library and benchmark for protein sequence learning · Table 8 row 'Beta' / 'Prot-T5', column 'GPU Memory (GB)'
Configuration: Prot-T5 (DeepProtein benchmark)	Protocol: DeepProtein beta-lactamase (PEER): Time (hour) Dataset: beta-lactamase (PEER)	0.0006 Runtime (training wall-clock time) hour · lower Uncertainty: Not reported by the source 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 Prot-T5 resource usage on DeepProtein beta-lactamase (PEER) (Time (hour)) lit-protein-20261011-deepprotein-protocol-beta-lactamase-time Aggregation: Not reported DeepProtein: deep learning library and benchmark for protein sequence learning · Table 8 row 'Beta' / 'Prot-T5', column 'Time (hour)'
Configuration: Prot-T5 (DeepProtein benchmark)	Protocol: DeepProtein Binary localization (PEER): GPU Memory (GB) Dataset: Binary localization (PEER)	5.62 Peak memory (peak GPU memory) gigabyte · lower Uncertainty: Not reported by the source 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 Prot-T5 resource usage on DeepProtein Binary localization (PEER) (GPU Memory (GB)) lit-protein-20261011-deepprotein-protocol-binary-memory Aggregation: Not reported DeepProtein: deep learning library and benchmark for protein sequence learning · Table 8 row 'SubCellular-Bin' / 'Prot-T5', column 'GPU Memory (GB)'
Configuration: Prot-T5 (DeepProtein benchmark)	Protocol: DeepProtein Binary localization (PEER): Time (hour) Dataset: Binary localization (PEER)	0.0003 Runtime (training wall-clock time) hour · lower Uncertainty: Not reported by the source 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 Prot-T5 resource usage on DeepProtein Binary localization (PEER) (Time (hour)) lit-protein-20261011-deepprotein-protocol-binary-time Aggregation: Not reported DeepProtein: deep learning library and benchmark for protein sequence learning · Table 8 row 'SubCellular-Bin' / 'Prot-T5', column 'Time (hour)'
Configuration: Prot-T5 (DeepProtein benchmark)	Protocol: DeepProtein CRISPR-Leenay repair outcome: GPU Memory (GB) Dataset: CRISPR-Leenay repair outcome	5.16 Peak memory (peak GPU memory) gigabyte · lower Uncertainty: Not reported by the source 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 Prot-T5 resource usage on DeepProtein CRISPR-Leenay repair outcome (GPU Memory (GB)) lit-protein-20261011-deepprotein-protocol-crispr-leenay-memory Aggregation: Not reported DeepProtein: deep learning library and benchmark for protein sequence learning · Table 8 row 'CRISPR' / 'Prot-T5', column 'GPU Memory (GB)'
Configuration: Prot-T5 (DeepProtein benchmark)	Protocol: DeepProtein CRISPR-Leenay repair outcome: Time (hour) Dataset: CRISPR-Leenay repair outcome	0.0005 Runtime (training wall-clock time) hour · lower Uncertainty: Not reported by the source 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 Prot-T5 resource usage on DeepProtein CRISPR-Leenay repair outcome (Time (hour)) lit-protein-20261011-deepprotein-protocol-crispr-leenay-time Aggregation: Not reported DeepProtein: deep learning library and benchmark for protein sequence learning · Table 8 row 'CRISPR' / 'Prot-T5', column 'Time (hour)'
Configuration: Prot-T5 (DeepProtein benchmark)	Protocol: DeepProtein Fluorescence (TAPE): GPU Memory (GB) Dataset: Fluorescence (TAPE)	5.2 Peak memory (peak GPU memory) gigabyte · lower Uncertainty: Not reported by the source 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 Prot-T5 resource usage on DeepProtein Fluorescence (TAPE) (GPU Memory (GB)) lit-protein-20261011-deepprotein-protocol-fluorescence-memory Aggregation: Not reported DeepProtein: deep learning library and benchmark for protein sequence learning · Table 8 row 'Fluorescence' / 'Prot-T5', column 'GPU Memory (GB)'
Configuration: Prot-T5 (DeepProtein benchmark)	Protocol: DeepProtein Fluorescence (TAPE): Time (hour) Dataset: Fluorescence (TAPE)	0.0016 Runtime (training wall-clock time) hour · lower Uncertainty: Not reported by the source 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 Prot-T5 resource usage on DeepProtein Fluorescence (TAPE) (Time (hour)) lit-protein-20261011-deepprotein-protocol-fluorescence-time Aggregation: Not reported DeepProtein: deep learning library and benchmark for protein sequence learning · Table 8 row 'Fluorescence' / 'Prot-T5', column 'Time (hour)'
Configuration: Prot-T5 (DeepProtein benchmark)	Protocol: DeepProtein Fold classification (TAPE): GPU Memory (GB) Dataset: Fold classification (TAPE)	5.22 Peak memory (peak GPU memory) gigabyte · lower Uncertainty: Not reported by the source 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 Prot-T5 resource usage on DeepProtein Fold classification (TAPE) (GPU Memory (GB)) lit-protein-20261011-deepprotein-protocol-fold-memory Aggregation: Not reported DeepProtein: deep learning library and benchmark for protein sequence learning · Table 8 row 'Fold' / 'Prot-T5', column 'GPU Memory (GB)'
Configuration: Prot-T5 (DeepProtein benchmark)	Protocol: DeepProtein Fold classification (TAPE): Time (hour) Dataset: Fold classification (TAPE)	0.0002 Runtime (training wall-clock time) hour · lower Uncertainty: Not reported by the source 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 Prot-T5 resource usage on DeepProtein Fold classification (TAPE) (Time (hour)) lit-protein-20261011-deepprotein-protocol-fold-time Aggregation: Not reported DeepProtein: deep learning library and benchmark for protein sequence learning · Table 8 row 'Fold' / 'Prot-T5', column 'Time (hour)'
Configuration: Prot-T5 (DeepProtein benchmark)	Protocol: DeepProtein Human PPI (PEER): GPU Memory (GB) Dataset: Human PPI (PEER)	9.38 Peak memory (peak GPU memory) gigabyte · lower Uncertainty: Not reported by the source 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 Prot-T5 resource usage on DeepProtein Human PPI (PEER) (GPU Memory (GB)) lit-protein-20261011-deepprotein-protocol-human-ppi-memory Aggregation: Not reported DeepProtein: deep learning library and benchmark for protein sequence learning · Table 8 row 'Human-PPI' / 'Prot-T5', column 'GPU Memory (GB)'
Configuration: Prot-T5 (DeepProtein benchmark)	Protocol: DeepProtein Human PPI (PEER): Time (hour) Dataset: Human PPI (PEER)	0.0032 Runtime (training wall-clock time) hour · lower Uncertainty: Not reported by the source 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 Prot-T5 resource usage on DeepProtein Human PPI (PEER) (Time (hour)) lit-protein-20261011-deepprotein-protocol-human-ppi-time Aggregation: Not reported DeepProtein: deep learning library and benchmark for protein sequence learning · Table 8 row 'Human-PPI' / 'Prot-T5', column 'Time (hour)'
Configuration: Prot-T5 (DeepProtein benchmark)	Protocol: DeepProtein PPI affinity (PEER): GPU Memory (GB) Dataset: PPI affinity (PEER)	5.16 Peak memory (peak GPU memory) gigabyte · lower Uncertainty: Not reported by the source 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 Prot-T5 resource usage on DeepProtein PPI affinity (PEER) (GPU Memory (GB)) lit-protein-20261011-deepprotein-protocol-ppi-affinity-memory Aggregation: Not reported DeepProtein: deep learning library and benchmark for protein sequence learning · Table 8 row 'PPI_Affinity' / 'Prot-T5', column 'GPU Memory (GB)'
Configuration: Prot-T5 (DeepProtein benchmark)	Protocol: DeepProtein PPI affinity (PEER): Time (hour) Dataset: PPI affinity (PEER)	0.0005 Runtime (training wall-clock time) hour · lower Uncertainty: Not reported by the source 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 Prot-T5 resource usage on DeepProtein PPI affinity (PEER) (Time (hour)) lit-protein-20261011-deepprotein-protocol-ppi-affinity-time Aggregation: Not reported DeepProtein: deep learning library and benchmark for protein sequence learning · Table 8 row 'PPI_Affinity' / 'Prot-T5', column 'Time (hour)'
Configuration: Prot-T5 (DeepProtein benchmark)	Protocol: DeepProtein SAbDab-Chen antibody developability: GPU Memory (GB) Dataset: SAbDab-Chen antibody developability	5.16 Peak memory (peak GPU memory) gigabyte · lower Uncertainty: Not reported by the source 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 Prot-T5 resource usage on DeepProtein SAbDab-Chen antibody developability (GPU Memory (GB)) lit-protein-20261011-deepprotein-protocol-sabdab-chen-memory Aggregation: Not reported DeepProtein: deep learning library and benchmark for protein sequence learning · Table 8 row 'SAbDab-Chen' / 'Prot-T5', column 'GPU Memory (GB)'
Configuration: Prot-T5 (DeepProtein benchmark)	Protocol: DeepProtein SAbDab-Chen antibody developability: Time (hour) Dataset: SAbDab-Chen antibody developability	0.0006 Runtime (training wall-clock time) hour · lower Uncertainty: Not reported by the source 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 Prot-T5 resource usage on DeepProtein SAbDab-Chen antibody developability (Time (hour)) lit-protein-20261011-deepprotein-protocol-sabdab-chen-time Aggregation: Not reported DeepProtein: deep learning library and benchmark for protein sequence learning · Table 8 row 'SAbDab-Chen' / 'Prot-T5', column 'Time (hour)'
Configuration: Prot-T5 (DeepProtein benchmark)	Protocol: DeepProtein Solubility (PEER): GPU Memory (GB) Dataset: Solubility (PEER)	7.33 Peak memory (peak GPU memory) gigabyte · lower Uncertainty: Not reported by the source 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 Prot-T5 resource usage on DeepProtein Solubility (PEER) (GPU Memory (GB)) lit-protein-20261011-deepprotein-protocol-solubility-memory Aggregation: Not reported DeepProtein: deep learning library and benchmark for protein sequence learning · Table 8 row 'Solubility' / 'Prot-T5', column 'GPU Memory (GB)'
Configuration: Prot-T5 (DeepProtein benchmark)	Protocol: DeepProtein Solubility (PEER): Time (hour) Dataset: Solubility (PEER)	0.04 Runtime (training wall-clock time) hour · lower Uncertainty: Not reported by the source 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 Prot-T5 resource usage on DeepProtein Solubility (PEER) (Time (hour)) lit-protein-20261011-deepprotein-protocol-solubility-time Aggregation: Not reported DeepProtein: deep learning library and benchmark for protein sequence learning · Table 8 row 'Solubility' / 'Prot-T5', column 'Time (hour)'
Configuration: Prot-T5 (DeepProtein benchmark)	Protocol: DeepProtein Stability (TAPE): GPU Memory (GB) Dataset: Stability (TAPE)	10.2 Peak memory (peak GPU memory) gigabyte · lower Uncertainty: Not reported by the source 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 Prot-T5 resource usage on DeepProtein Stability (TAPE) (GPU Memory (GB)) lit-protein-20261011-deepprotein-protocol-stability-memory Aggregation: Not reported DeepProtein: deep learning library and benchmark for protein sequence learning · Table 8 row 'Stability' / 'Prot-T5', column 'GPU Memory (GB)'
Configuration: Prot-T5 (DeepProtein benchmark)	Protocol: DeepProtein Stability (TAPE): Time (hour) Dataset: Stability (TAPE)	0.00472 Runtime (training wall-clock time) hour · lower Uncertainty: Not reported by the source 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 Prot-T5 resource usage on DeepProtein Stability (TAPE) (Time (hour)) lit-protein-20261011-deepprotein-protocol-stability-time Aggregation: Not reported DeepProtein: deep learning library and benchmark for protein sequence learning · Table 8 row 'Stability' / 'Prot-T5', column 'Time (hour)'
Configuration: Prot-T5 (DeepProtein benchmark)	Protocol: DeepProtein Subcellular localization (PEER): GPU Memory (GB) Dataset: Subcellular localization (PEER)	5.71 Peak memory (peak GPU memory) gigabyte · lower Uncertainty: Not reported by the source 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 Prot-T5 resource usage on DeepProtein Subcellular localization (PEER) (GPU Memory (GB)) lit-protein-20261011-deepprotein-protocol-subcellular-memory Aggregation: Not reported DeepProtein: deep learning library and benchmark for protein sequence learning · Table 8 row 'SubCellular' / 'Prot-T5', column 'GPU Memory (GB)'
Configuration: Prot-T5 (DeepProtein benchmark)	Protocol: DeepProtein Subcellular localization (PEER): Time (hour) Dataset: Subcellular localization (PEER)	0.0006 Runtime (training wall-clock time) hour · lower Uncertainty: Not reported by the source 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 Prot-T5 resource usage on DeepProtein Subcellular localization (PEER) (Time (hour)) lit-protein-20261011-deepprotein-protocol-subcellular-time Aggregation: Not reported DeepProtein: deep learning library and benchmark for protein sequence learning · Table 8 row 'SubCellular' / 'Prot-T5', column 'Time (hour)'
Configuration: Prot-T5 (DeepProtein benchmark)	Protocol: DeepProtein TAP antibody developability: GPU Memory (GB) Dataset: TAP antibody developability	5.16 Peak memory (peak GPU memory) gigabyte · lower Uncertainty: Not reported by the source 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 Prot-T5 resource usage on DeepProtein TAP antibody developability (GPU Memory (GB)) lit-protein-20261011-deepprotein-protocol-tap-memory Aggregation: Not reported DeepProtein: deep learning library and benchmark for protein sequence learning · Table 8 row 'TAP' / 'Prot-T5', column 'GPU Memory (GB)'
Configuration: Prot-T5 (DeepProtein benchmark)	Protocol: DeepProtein TAP antibody developability: Time (hour) Dataset: TAP antibody developability	0.0003 Runtime (training wall-clock time) hour · lower Uncertainty: Not reported by the source 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 Prot-T5 resource usage on DeepProtein TAP antibody developability (Time (hour)) lit-protein-20261011-deepprotein-protocol-tap-time Aggregation: Not reported DeepProtein: deep learning library and benchmark for protein sequence learning · Table 8 row 'TAP' / 'Prot-T5', column 'Time (hour)'
Configuration: Prot-T5 (DeepProtein benchmark)	Protocol: DeepProtein Yeast PPI (PEER): GPU Memory (GB) Dataset: Yeast PPI (PEER)	9.04 Peak memory (peak GPU memory) gigabyte · lower Uncertainty: Not reported by the source 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 Prot-T5 resource usage on DeepProtein Yeast PPI (PEER) (GPU Memory (GB)) lit-protein-20261011-deepprotein-protocol-yeast-ppi-memory Aggregation: Not reported DeepProtein: deep learning library and benchmark for protein sequence learning · Table 8 row 'Yeast-PPI' / 'Prot-T5', column 'GPU Memory (GB)'

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-prot-t5

areas: protein-function
contexts: research
method types: foundation_model
reported name: Prot-T5
reported configuration: protein language model; default DeepProtein configuration (Table 9)
model identity note: Table 8 prints 'Prot-T5' and Tables 2 to 7 print 'Prot-T5-XL'. They are kept as separate configurations because the article does not state that they are the same checkpoint; their values must not be pooled.
foundation model eligible: true
source locator: Tables 2 to 8, row 'Prot-T5'; Table 9 for the default configuration
missing metadata: version: reason: unreported; note: The tables name the model without a release version
provenance note: Prot-T5 as trained and evaluated in the DeepProtein benchmark (protein language model).

Related records

Suggest a correction