rewire.it
Dataset

UniProtSMB test split

Dataset and cohort used in the cited comparison. Dataset population counts do not establish successful prediction coverage.

Dataset and evaluation context

A dataset supplies biological observations. The evaluation protocol defines how those observations are split, used and scored.

Evaluation results

Release 2026-09-17-d277315f7d76 · 4 evaluations · 16 metric rows. Different protocols are not a single leaderboard.

Results grouped by the exact reported evaluation
Metric and findingCoverage and uncertaintyEvidence
DeepProSite: UniProtSMB test split

Residue-level small-molecule binding-site classification. 80/10/10 train/validation/test partition of nonredundant sequences.

Independent external evaluation · Evaluation metadata: needs review

0.490 ± 0.013 Recall

Unit: unitless · Direction: higher

Uncertainty: printed: 0.013; value: 0.013; type: not explicitly identified in inspected table or caption

Scored: Not reported · Eligible: Not reported

source checkedProtein-small molecule binding site prediction based on a pre-trained protein language model with contrastive learning · Table 4 (Tab4), row 4 DeepProSite, column 2: UniProtSMB test split Recall

Source checking is not independent reproduction.

0.756 ± 0.005 Precision

Unit: unitless · Direction: higher

Uncertainty: printed: 0.005; value: 0.005; type: not explicitly identified in inspected table or caption

Scored: Not reported · Eligible: Not reported

source checkedProtein-small molecule binding site prediction based on a pre-trained protein language model with contrastive learning · Table 4 (Tab4), row 4 DeepProSite, column 3: UniProtSMB test split Precision

Source checking is not independent reproduction.

0.598 ± 0.006 MCC

Unit: unitless · Direction: higher

Uncertainty: printed: 0.006; value: 0.006; type: not explicitly identified in inspected table or caption

Scored: Not reported · Eligible: Not reported

source checkedProtein-small molecule binding site prediction based on a pre-trained protein language model with contrastive learning · Table 4 (Tab4), row 4 DeepProSite, column 4: UniProtSMB test split MCC

Source checking is not independent reproduction.

0.965 ± 0.001 AUROC

Unit: unitless · Direction: higher

Uncertainty: printed: 0.001; value: 0.001; type: not explicitly identified in inspected table or caption

Scored: Not reported · Eligible: Not reported

source checkedProtein-small molecule binding site prediction based on a pre-trained protein language model with contrastive learning · Table 4 (Tab4), row 4 DeepProSite, column 5: UniProtSMB test split AUROC

Source checking is not independent reproduction.

CLAPE-SMB: UniProtSMB test split

Residue-level small-molecule binding-site classification. 80/10/10 train/validation/test partition of nonredundant sequences.

Author-reported evaluation · Evaluation metadata: needs review

0.743 ± 0.040 Precision

Unit: unitless · Direction: higher

Uncertainty: printed: 0.040; value: 0.04; type: not explicitly identified in inspected table or caption

Scored: Not reported · Eligible: Not reported

source checkedProtein-small molecule binding site prediction based on a pre-trained protein language model with contrastive learning · Table 4 (Tab4), row 5 CLAPE-SMB, column 3: UniProtSMB test split Precision

Source checking is not independent reproduction.

0.673 ± 0.031 Recall

Unit: unitless · Direction: higher

Uncertainty: printed: 0.031; value: 0.031; type: not explicitly identified in inspected table or caption

Scored: Not reported · Eligible: Not reported

source checkedProtein-small molecule binding site prediction based on a pre-trained protein language model with contrastive learning · Table 4 (Tab4), row 5 CLAPE-SMB, column 2: UniProtSMB test split Recall

Source checking is not independent reproduction.

0.699 ± 0.004 MCC

Unit: unitless · Direction: higher

Uncertainty: printed: 0.004; value: 0.004; type: not explicitly identified in inspected table or caption

Scored: Not reported · Eligible: Not reported

source checkedProtein-small molecule binding site prediction based on a pre-trained protein language model with contrastive learning · Table 4 (Tab4), row 5 CLAPE-SMB, column 4: UniProtSMB test split MCC

Source checking is not independent reproduction.

0.960 ± 0.001 AUROC

Unit: unitless · Direction: higher

Uncertainty: printed: 0.001; value: 0.001; type: not explicitly identified in inspected table or caption

Scored: Not reported · Eligible: Not reported

source checkedProtein-small molecule binding site prediction based on a pre-trained protein language model with contrastive learning · Table 4 (Tab4), row 5 CLAPE-SMB, column 5: UniProtSMB test split AUROC

Source checking is not independent reproduction.

GraphBind: UniProtSMB test split

Residue-level small-molecule binding-site classification. 80/10/10 train/validation/test partition of nonredundant sequences.

Independent external evaluation · Evaluation metadata: needs review

0.932 ± 0.003 AUROC

Unit: unitless · Direction: higher

Uncertainty: printed: 0.003; value: 0.003; type: not explicitly identified in inspected table or caption

Scored: Not reported · Eligible: Not reported

source checkedProtein-small molecule binding site prediction based on a pre-trained protein language model with contrastive learning · Table 4 (Tab4), row 3 GraphBind, column 5: UniProtSMB test split AUROC

Source checking is not independent reproduction.

0.565 ± 0.020 Recall

Unit: unitless · Direction: higher

Uncertainty: printed: 0.020; value: 0.02; type: not explicitly identified in inspected table or caption

Scored: Not reported · Eligible: Not reported

source checkedProtein-small molecule binding site prediction based on a pre-trained protein language model with contrastive learning · Table 4 (Tab4), row 3 GraphBind, column 2: UniProtSMB test split Recall

Source checking is not independent reproduction.

0.430 ± 0.007 Precision

Unit: unitless · Direction: higher

Uncertainty: printed: 0.007; value: 0.007; type: not explicitly identified in inspected table or caption

Scored: Not reported · Eligible: Not reported

source checkedProtein-small molecule binding site prediction based on a pre-trained protein language model with contrastive learning · Table 4 (Tab4), row 3 GraphBind, column 3: UniProtSMB test split Precision

Source checking is not independent reproduction.

0.473 ± 0.007 MCC

Unit: unitless · Direction: higher

Uncertainty: printed: 0.007; value: 0.007; type: not explicitly identified in inspected table or caption

Scored: Not reported · Eligible: Not reported

source checkedProtein-small molecule binding site prediction based on a pre-trained protein language model with contrastive learning · Table 4 (Tab4), row 3 GraphBind, column 4: UniProtSMB test split MCC

Source checking is not independent reproduction.

P2Rank: UniProtSMB test split

Residue-level small-molecule binding-site classification. 80/10/10 train/validation/test partition of nonredundant sequences.

Independent external evaluation · Evaluation metadata: needs review

N/A AUROC

Unit: unitless · Direction: higher

Uncertainty: unreported

Scored: Not reported · Eligible: Not reported

source checkedProtein-small molecule binding site prediction based on a pre-trained protein language model with contrastive learning · Table 4 (Tab4), row 2 P2Rank, column 5: UniProtSMB test split AUROC

Source checking is not independent reproduction.

0.236 MCC

Unit: unitless · Direction: higher

Uncertainty: unreported

Scored: Not reported · Eligible: Not reported

source checkedProtein-small molecule binding site prediction based on a pre-trained protein language model with contrastive learning · Table 4 (Tab4), row 2 P2Rank, column 4: UniProtSMB test split MCC

Source checking is not independent reproduction.

0.124 Precision

Unit: unitless · Direction: higher

Uncertainty: unreported

Scored: Not reported · Eligible: Not reported

source checkedProtein-small molecule binding site prediction based on a pre-trained protein language model with contrastive learning · Table 4 (Tab4), row 2 P2Rank, column 3: UniProtSMB test split Precision

Source checking is not independent reproduction.

0.632 Recall

Unit: unitless · Direction: higher

Uncertainty: unreported

Scored: Not reported · Eligible: Not reported

source checkedProtein-small molecule binding site prediction based on a pre-trained protein language model with contrastive learning · Table 4 (Tab4), row 2 P2Rank, column 2: UniProtSMB test split Recall

Source checking is not independent reproduction.

Evidence table

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.

7 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-09-17-d277315f7d76
Property and statementOriginal source and locationReview and provenance
attributes.reported_population.count

205848

Context-only references
Protein-small molecule binding site prediction based on a pre-trained protein language model with contrastive learning

Original source ↗

Comparison of CLAPE-SMB with other models on the UniProtSMB; Table 4 (Tab4), row 2 P2Rank, column 2: UniProtSMB test split Recall; Table 4 (Tab4), row 3 GraphBind, column 2: UniProtSMB test split Recall; Table 4 (Tab4), row 4 DeepProSite, column 2: UniProtSMB test split Recall; Table 4 (Tab4), row 5 CLAPE-SMB, column 2: UniProtSMB test split Recall

Version: version of record
Retrieved: 2026-09-16T10:41:06Z

not individually reviewed

No individual claim review recorded

Audit details

Field: attributes.reported_population.count

Source artifact SHA-256: 215919244c3dd2dfb0b55fce91c211430fd8d4aee4bb28bd03eab9f4feb73e62

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

Inspected artifact

attributes.reported_population.unit

labelled residues in 496 test proteins

Context-only references
Protein-small molecule binding site prediction based on a pre-trained protein language model with contrastive learning

Original source ↗

Comparison of CLAPE-SMB with other models on the UniProtSMB; Table 4 (Tab4), row 2 P2Rank, column 2: UniProtSMB test split Recall; Table 4 (Tab4), row 3 GraphBind, column 2: UniProtSMB test split Recall; Table 4 (Tab4), row 4 DeepProSite, column 2: UniProtSMB test split Recall; Table 4 (Tab4), row 5 CLAPE-SMB, column 2: UniProtSMB test split Recall

Version: version of record
Retrieved: 2026-09-16T10:41:06Z

not individually reviewed

No individual claim review recorded

Audit details

Field: attributes.reported_population.unit

Source artifact SHA-256: 215919244c3dd2dfb0b55fce91c211430fd8d4aee4bb28bd03eab9f4feb73e62

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

Inspected artifact

attributes.source_locator

Comparison of CLAPE-SMB with other models on the UniProtSMB; Table 4 (Tab4), row 2 P2Rank, column 2: UniProtSMB test split Recall; Table 4 (Tab4), row 3 GraphBind, column 2: UniProtSMB test split Recall; Table 4 (Tab4), row 4 DeepProSite, column 2: UniProtSMB test split Recall; Table 4 (Tab4), row 5 CLAPE-SMB, column 2: UniProtSMB test split Recall

Context-only references
Protein-small molecule binding site prediction based on a pre-trained protein language model with contrastive learning

Original source ↗

Comparison of CLAPE-SMB with other models on the UniProtSMB; Table 4 (Tab4), row 2 P2Rank, column 2: UniProtSMB test split Recall; Table 4 (Tab4), row 3 GraphBind, column 2: UniProtSMB test split Recall; Table 4 (Tab4), row 4 DeepProSite, column 2: UniProtSMB test split Recall; Table 4 (Tab4), row 5 CLAPE-SMB, column 2: UniProtSMB test split Recall

Version: version of record
Retrieved: 2026-09-16T10:41:06Z

not individually reviewed

No individual claim review recorded

Audit details

Field: attributes.source_locator

Source artifact SHA-256: 215919244c3dd2dfb0b55fce91c211430fd8d4aee4bb28bd03eab9f4feb73e62

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

Inspected artifact

attributes.split

Residue-level small-molecule binding-site classification. 80/10/10 train/validation/test partition of nonredundant sequences.

Context-only references
Protein-small molecule binding site prediction based on a pre-trained protein language model with contrastive learning

Original source ↗

Comparison of CLAPE-SMB with other models on the UniProtSMB; Table 4 (Tab4), row 2 P2Rank, column 2: UniProtSMB test split Recall; Table 4 (Tab4), row 3 GraphBind, column 2: UniProtSMB test split Recall; Table 4 (Tab4), row 4 DeepProSite, column 2: UniProtSMB test split Recall; Table 4 (Tab4), row 5 CLAPE-SMB, column 2: UniProtSMB test split Recall

Version: version of record
Retrieved: 2026-09-16T10:41:06Z

not individually reviewed

No individual claim review recorded

Audit details

Field: attributes.split

Source artifact SHA-256: 215919244c3dd2dfb0b55fce91c211430fd8d4aee4bb28bd03eab9f4feb73e62

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

Inspected artifact

attributes.subset

No value recorded

Context-only references
Protein-small molecule binding site prediction based on a pre-trained protein language model with contrastive learning

Original source ↗

Comparison of CLAPE-SMB with other models on the UniProtSMB; Table 4 (Tab4), row 2 P2Rank, column 2: UniProtSMB test split Recall; Table 4 (Tab4), row 3 GraphBind, column 2: UniProtSMB test split Recall; Table 4 (Tab4), row 4 DeepProSite, column 2: UniProtSMB test split Recall; Table 4 (Tab4), row 5 CLAPE-SMB, column 2: UniProtSMB test split Recall

Version: version of record
Retrieved: 2026-09-16T10:41:06Z

missing or unspecified

No individual claim review recorded

Audit details

Field: attributes.subset

Source artifact SHA-256: 215919244c3dd2dfb0b55fce91c211430fd8d4aee4bb28bd03eab9f4feb73e62

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

Inspected artifact

description

Dataset and cohort used in the cited comparison. Dataset population counts do not establish successful prediction coverage.

Context-only references
Protein-small molecule binding site prediction based on a pre-trained protein language model with contrastive learning

Original source ↗

Comparison of CLAPE-SMB with other models on the UniProtSMB; Table 4 (Tab4), row 2 P2Rank, column 2: UniProtSMB test split Recall; Table 4 (Tab4), row 3 GraphBind, column 2: UniProtSMB test split Recall; Table 4 (Tab4), row 4 DeepProSite, column 2: UniProtSMB test split Recall; Table 4 (Tab4), row 5 CLAPE-SMB, column 2: UniProtSMB test split Recall

Version: version of record
Retrieved: 2026-09-16T10:41:06Z

not individually reviewed

No individual claim review recorded

Audit details

Field: description

Source artifact SHA-256: 215919244c3dd2dfb0b55fce91c211430fd8d4aee4bb28bd03eab9f4feb73e62

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

Inspected artifact

name

UniProtSMB test split

Context-only references
Protein-small molecule binding site prediction based on a pre-trained protein language model with contrastive learning

Original source ↗

Comparison of CLAPE-SMB with other models on the UniProtSMB; Table 4 (Tab4), row 2 P2Rank, column 2: UniProtSMB test split Recall; Table 4 (Tab4), row 3 GraphBind, column 2: UniProtSMB test split Recall; Table 4 (Tab4), row 4 DeepProSite, column 2: UniProtSMB test split Recall; Table 4 (Tab4), row 5 CLAPE-SMB, column 2: UniProtSMB test split Recall

Version: version of record
Retrieved: 2026-09-16T10:41:06Z

not individually reviewed

No individual claim review recorded

Audit details

Field: name

Source artifact SHA-256: 215919244c3dd2dfb0b55fce91c211430fd8d4aee4bb28bd03eab9f4feb73e62

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

Inspected artifact

Sources and history

Release 2026-09-17-d277315f7d76 · Record review: needs review

Download this release
Technical metadata and extraction receipts

Stable ID: paper-dataset-7ed13bec749f1e245b

areas
proteins-complexes
tasks
protein-small molecule binding-site prediction
split
Residue-level small-molecule binding-site classification. 80/10/10 train/validation/test partition of nonredundant sequences.
subset
Not reported
reported population
count: 205848; unit: labelled residues in 496 test proteins
source locator
Comparison of CLAPE-SMB with other models on the UniProtSMB; Table 4 (Tab4), row 2 P2Rank, column 2: UniProtSMB test split Recall; Table 4 (Tab4), row 3 GraphBind, column 2: UniProtSMB test split Recall; Table 4 (Tab4), row 4 DeepProSite, column 2: UniProtSMB test split Recall; Table 4 (Tab4), row 5 CLAPE-SMB, column 2: UniProtSMB test split Recall
missing metadata
manifest: unextracted; scored count: unreported
entity classification
review date: 2026-09-17; rationale: This record identifies a biological data collection or source-labelled evaluation cohort. Keep its dataset identity; split, assay, taxonomic level, candidate restrictions and comparison context remain attributes rather than automatically becoming new entity kinds.; source ids: clape-smb-2024; source locator: Comparison of CLAPE-SMB with other models on the UniProtSMB; Table 4 (Tab4), row 2 P2Rank, column 2: UniProtSMB test split Recall; Table 4 (Tab4), row 3 GraphBind, column 2: UniProtSMB test split Recall; Table 4 (Tab4), row 4 DeepProSite, column 2: UniProtSMB test split Recall; Table 4 (Tab4), row 5 CLAPE-SMB, column 2: UniProtSMB test split Recall; ambiguities: The name suggests a selected cohort, but this record has no verified parent-dataset relationship or independently pinned membership manifest. Retain dataset rather than infer a new parent/subset identity from its name alone.
Related records

Suggest a correction