SJC 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.
| Metric and finding | Coverage and uncertainty | Evidence |
|---|---|---|
| CLAPE-SMB: SJC test split Configuration: CLAPE-SMBProtocol: SJC test split (protein-small molecule binding-site prediction)Dataset: SJC 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 | ||
| 0.651 ± 0.016 Precision Unit: unitless · Direction: higher | Uncertainty: printed: 0.016; value: 0.016; 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 3 (Tab3), row 5 CLAPE-SMB, column 3: SJC test split Precision Source checking is not independent reproduction. |
| 0.529 ± 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 3 (Tab3), row 5 CLAPE-SMB, column 4: SJC test split MCC Source checking is not independent reproduction. |
| 0.915 ± 0.002 AUROC Unit: unitless · Direction: higher | Uncertainty: printed: 0.002; value: 0.002; 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 3 (Tab3), row 5 CLAPE-SMB, column 5: SJC test split AUROC Source checking is not independent reproduction. |
| 0.456 ± 0.006 Recall 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 3 (Tab3), row 5 CLAPE-SMB, column 2: SJC test split Recall Source checking is not independent reproduction. |
| P2Rank: SJC test split Configuration: P2RankProtocol: SJC test split (protein-small molecule binding-site prediction)Dataset: SJC 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 | ||
| 0.660 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 3 (Tab3), row 2 P2Rank, column 2: SJC test split Recall Source checking is not independent reproduction. |
| 0.293 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 3 (Tab3), row 2 P2Rank, column 4: SJC test split MCC Source checking is not independent reproduction. |
| 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 3 (Tab3), row 2 P2Rank, column 5: SJC test split AUROC Source checking is not independent reproduction. |
| 0.180 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 3 (Tab3), row 2 P2Rank, column 3: SJC test split Precision Source checking is not independent reproduction. |
| GraphBind: SJC test split Configuration: GraphBindProtocol: SJC test split (protein-small molecule binding-site prediction)Dataset: SJC 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 | ||
| 0.486 ± 0.005 MCC 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 3 (Tab3), row 3 GraphBind, column 4: SJC test split MCC Source checking is not independent reproduction. |
| 0.906 ± 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 3 (Tab3), row 3 GraphBind, column 5: SJC test split AUROC Source checking is not independent reproduction. |
| 0.568 ± 0.024 Recall Unit: unitless · Direction: higher | Uncertainty: printed: 0.024; value: 0.024; 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 3 (Tab3), row 3 GraphBind, column 2: SJC test split Recall Source checking is not independent reproduction. |
| 0.462 ± 0.011 Precision Unit: unitless · Direction: higher | Uncertainty: printed: 0.011; value: 0.011; 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 3 (Tab3), row 3 GraphBind, column 3: SJC test split Precision Source checking is not independent reproduction. |
| DeepProSite: SJC test split Configuration: DeepProSiteProtocol: SJC test split (protein-small molecule binding-site prediction)Dataset: SJC 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 | ||
| 0.458 ± 0.022 Recall Unit: unitless · Direction: higher | Uncertainty: printed: 0.022; value: 0.022; 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 3 (Tab3), row 4 DeepProSite, column 2: SJC test split Recall Source checking is not independent reproduction. |
| 0.926 ± 0.002 AUROC Unit: unitless · Direction: higher | Uncertainty: printed: 0.002; value: 0.002; 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 3 (Tab3), row 4 DeepProSite, column 5: SJC test split AUROC Source checking is not independent reproduction. |
| 0.524 ± 0.015 MCC Unit: unitless · Direction: higher | Uncertainty: printed: 0.015; value: 0.015; 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 3 (Tab3), row 4 DeepProSite, column 4: SJC test split MCC Source checking is not independent reproduction. |
| 0.644 ± 0.011 Precision Unit: unitless · Direction: higher | Uncertainty: printed: 0.011; value: 0.011; 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 3 (Tab3), row 4 DeepProSite, column 3: SJC test split Precision 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.
6 evidence rows matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| attributes.reported_population No value recorded Context-only references | Protein-small molecule binding site prediction based on a pre-trained protein language model with contrastive learning Comparison of CLAPE-SMB with other models on the SJC; Table 3 (Tab3), row 2 P2Rank, column 2: SJC test split Recall; Table 3 (Tab3), row 3 GraphBind, column 2: SJC test split Recall; Table 3 (Tab3), row 4 DeepProSite, column 2: SJC test split Recall; Table 3 (Tab3), row 5 CLAPE-SMB, column 2: SJC test split Recall Version: version of record | missing or unspecified No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| attributes.source_locator Comparison of CLAPE-SMB with other models on the SJC; Table 3 (Tab3), row 2 P2Rank, column 2: SJC test split Recall; Table 3 (Tab3), row 3 GraphBind, column 2: SJC test split Recall; Table 3 (Tab3), row 4 DeepProSite, column 2: SJC test split Recall; Table 3 (Tab3), row 5 CLAPE-SMB, column 2: SJC test split Recall Context-only references | Protein-small molecule binding site prediction based on a pre-trained protein language model with contrastive learning Comparison of CLAPE-SMB with other models on the SJC; Table 3 (Tab3), row 2 P2Rank, column 2: SJC test split Recall; Table 3 (Tab3), row 3 GraphBind, column 2: SJC test split Recall; Table 3 (Tab3), row 4 DeepProSite, column 2: SJC test split Recall; Table 3 (Tab3), row 5 CLAPE-SMB, column 2: SJC test split Recall Version: version of record | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| 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 Comparison of CLAPE-SMB with other models on the SJC; Table 3 (Tab3), row 2 P2Rank, column 2: SJC test split Recall; Table 3 (Tab3), row 3 GraphBind, column 2: SJC test split Recall; Table 3 (Tab3), row 4 DeepProSite, column 2: SJC test split Recall; Table 3 (Tab3), row 5 CLAPE-SMB, column 2: SJC test split Recall Version: version of record | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| 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 Comparison of CLAPE-SMB with other models on the SJC; Table 3 (Tab3), row 2 P2Rank, column 2: SJC test split Recall; Table 3 (Tab3), row 3 GraphBind, column 2: SJC test split Recall; Table 3 (Tab3), row 4 DeepProSite, column 2: SJC test split Recall; Table 3 (Tab3), row 5 CLAPE-SMB, column 2: SJC test split Recall Version: version of record | missing or unspecified No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| 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 Comparison of CLAPE-SMB with other models on the SJC; Table 3 (Tab3), row 2 P2Rank, column 2: SJC test split Recall; Table 3 (Tab3), row 3 GraphBind, column 2: SJC test split Recall; Table 3 (Tab3), row 4 DeepProSite, column 2: SJC test split Recall; Table 3 (Tab3), row 5 CLAPE-SMB, column 2: SJC test split Recall Version: version of record | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| name SJC test split Context-only references | Protein-small molecule binding site prediction based on a pre-trained protein language model with contrastive learning Comparison of CLAPE-SMB with other models on the SJC; Table 3 (Tab3), row 2 P2Rank, column 2: SJC test split Recall; Table 3 (Tab3), row 3 GraphBind, column 2: SJC test split Recall; Table 3 (Tab3), row 4 DeepProSite, column 2: SJC test split Recall; Table 3 (Tab3), row 5 CLAPE-SMB, column 2: SJC test split Recall Version: version of record | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
Sources and history
Release 2026-09-17-d277315f7d76 · Record review: needs review
- Protein-small molecule binding site prediction based on a pre-trained protein language model with contrastive learning · Original source · version of record
Technical metadata and extraction receipts
Stable ID: paper-dataset-623c309e2fb4d39ef8
- 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
- Not reported
- source locator
- Comparison of CLAPE-SMB with other models on the SJC; Table 3 (Tab3), row 2 P2Rank, column 2: SJC test split Recall; Table 3 (Tab3), row 3 GraphBind, column 2: SJC test split Recall; Table 3 (Tab3), row 4 DeepProSite, column 2: SJC test split Recall; Table 3 (Tab3), row 5 CLAPE-SMB, column 2: SJC 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 SJC; Table 3 (Tab3), row 2 P2Rank, column 2: SJC test split Recall; Table 3 (Tab3), row 3 GraphBind, column 2: SJC test split Recall; Table 3 (Tab3), row 4 DeepProSite, column 2: SJC test split Recall; Table 3 (Tab3), row 5 CLAPE-SMB, column 2: SJC 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
- dataset: CLAPE-SMB: SJC test split
- dataset: GraphBind: SJC test split
- dataset: DeepProSite: SJC test split
- dataset: P2Rank: SJC test split