Model type
Gradient-boosted-tree pipeline; this record is the paper-specific evaluated configuration.
Configuration
FUJISAN
FUJISAN predicts whether two proteins catalyse the same enzymatic reaction using sequence, domain and pocket similarities.
Sources
Enhanced prediction of protein functional identity through the integration of sequence and structural features · Abstract (paragraph 1); Results and discussion/Limitations and perspectives (paragraph 1)How it worksEvaluated procedure (conceptual)
Conceptual input–method–output guide. Check the procedure text and linked evaluation for fitted components, additional inputs and exact settings.
Sources
Enhanced prediction of protein functional identity through the integration of sequence and structural features · Materials and methods/Feature engineering/Pocket similarity features (paragraph 1); Conclusions (paragraph 1)At a glance
Biological inputs
Pairs of protein sequences and predicted structures with domain and pocket decomposition
Sources
Enhanced prediction of protein functional identity through the integration of sequence and structural features · Materials and methods/Dataset construction (paragraph 1); Results and discussion/Limitations and perspectives (paragraph 1)Outputs
Same-reaction versus different-reaction classification
Sources
Enhanced prediction of protein functional identity through the integration of sequence and structural features · Materials and methods/Model training and hyperparameter optimization (paragraph 1); Materials and methods/Feature importance/Gini importance (paragraph 1)limited source coverage · Automated source review, 2026-09-16. All specifications and missing details
Evaluations and results
Release 2026-09-17-d277315f7d76 · 1 evaluation · 8 metric rows. Different protocols are not a single leaderboard.
| Metric and finding | Coverage and uncertainty | Evidence |
|---|---|---|
| FUJISAN: Enzyme functional identity prediction Configuration: FUJISANProtocol: Enzyme-pair functional identity: original held-out test (Enzyme functional identity prediction)Dataset: FUJISAN test sub-dataset LightGBM FUJISAN and comparison methods; predictions thresholded to maximizeF 1. Protein-pair splitting is not evidence of disjoint proteins or families. 41,600 protein pairs; balanced functional-identity classes; random 56.25/18.75/25% training/validation/test split. Author-reported evaluation · Evaluation metadata: needs review | ||
| 0.9427 AUROC Unit: unitless · Direction: higher | Uncertainty: not reported in legacy extract Scored: Not reported · Eligible: Not reported | source checkedEnhanced prediction of protein functional identity through the integration of sequence and structural features; Enhanced prediction of protein functional identity through the integration of sequence and structural features · Table 1, FUJISAN row, AUROC column Source checking is not independent reproduction. |
| 87.05% REC (%) Unit: percent · Direction: higher | Uncertainty: unreported Scored: Not reported · Eligible: Not reported | source checkedEnhanced prediction of protein functional identity through the integration of sequence and structural features · Table 1, row FUJISAN, column REC (%); XML row2 column4 Source checking is not independent reproduction. |
| 0.7421 MCC Unit: dimensionless · Direction: higher | Uncertainty: unreported Scored: Not reported · Eligible: Not reported | source checkedEnhanced prediction of protein functional identity through the integration of sequence and structural features · Table 1, row FUJISAN, column MCC; XML row2 column7 Source checking is not independent reproduction. |
| 87.24% PRE (%) Unit: percent · Direction: higher | Uncertainty: unreported Scored: Not reported · Eligible: Not reported | source checkedEnhanced prediction of protein functional identity through the integration of sequence and structural features · Table 1, row FUJISAN, column PRE (%); XML row2 column3 Source checking is not independent reproduction. |
| 0.9413 AUPR Unit: dimensionless · Direction: higher | Uncertainty: unreported Scored: Not reported · Eligible: Not reported | source checkedEnhanced prediction of protein functional identity through the integration of sequence and structural features · Table 1, row FUJISAN, column AUPR; XML row2 column9 Source checking is not independent reproduction. |
| 87.05% ACC (%) Unit: percent · Direction: higher | Uncertainty: unreported Scored: Not reported · Eligible: Not reported | source checkedEnhanced prediction of protein functional identity through the integration of sequence and structural features · Table 1, row FUJISAN, column ACC (%); XML row2 column2 Source checking is not independent reproduction. |
| 0.8728 F1 Unit: dimensionless · Direction: higher | Uncertainty: unreported Scored: Not reported · Eligible: Not reported | source checkedEnhanced prediction of protein functional identity through the integration of sequence and structural features · Table 1, row FUJISAN, column F1; XML row2 column6 Source checking is not independent reproduction. |
| 13.35% FPR (%) Unit: percent · Direction: lower | Uncertainty: unreported Scored: Not reported · Eligible: Not reported | source checkedEnhanced prediction of protein functional identity through the integration of sequence and structural features · Table 1, row FUJISAN, column FPR (%); XML row2 column5 Source checking is not independent reproduction. |
How it works
How the evaluated method works
Features include full-sequence similarity, domain structural similarity and pocket similarity from AlphaFold2 structural models. A LightGBM classifier combines these comparisons.
Sources
Enhanced prediction of protein functional identity through the integration of sequence and structural features · Materials and methods/Feature engineering/Pocket similarity features (paragraph 1); Conclusions (paragraph 1)What was evaluated
The linked evaluation record identifies FUJISAN: Enzyme functional identity prediction. Its dataset, split, adaptation and evidence origin remain attached to the reported results.
Sources
Enhanced prediction of protein functional identity through the integration of sequence and structural features · The named evaluation’s methods and comparison table; exact preserved evaluation IDs: evaluation-lit-019Strengths and limitations
Strengths and considerations
- Combines sequence and structure information and exposes feature importance for the trained classifier.
Sources
Enhanced prediction of protein functional identity through the integration of sequence and structural features · Materials and methods/Feature importance/Gini importance (paragraph 1); Materials and methods/Feature importance/Shapley additive explanations (paragraph 1)
Limitations and conditions
- Pairs with uncomputable features are excluded, and the random-pair split must not be interpreted as a guaranteed unseen-protein split.
Sources
Enhanced prediction of protein functional identity through the integration of sequence and structural features · Materials and methods/Feature engineering/Full-length sequence similarity features (paragraph 1); Materials and methods/Model training and hyperparameter optimization (paragraph 1)
Profile review details
Primary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction.
Stable record: reported-model-9c10fbec02a365Specifications
Inputs, training, access and other details
Explanatory profile: limited source coverage · Automated source review, 2026-09-16. Review applies to the cited claims; unresolved fields are listed below. Numerical results retain their own review status.
| Property | Description and evidence |
|---|---|
| Model type | Gradient-boosted-tree pipeline; this record is the paper-specific evaluated configuration.SourcesEnhanced prediction of protein functional identity through the integration of sequence and structural features · Materials and methods/Feature engineering/Pocket similarity features (paragraph 1); Conclusions (paragraph 1) |
| Architecture / procedure | Features include full-sequence similarity, domain structural similarity and pocket similarity from AlphaFold2 structural models. A LightGBM classifier combines these comparisons.SourcesEnhanced prediction of protein functional identity through the integration of sequence and structural features · Materials and methods/Feature engineering/Pocket similarity features (paragraph 1); Conclusions (paragraph 1) |
| Biological inputs | Pairs of protein sequences and predicted structures with domain and pocket decompositionSourcesEnhanced prediction of protein functional identity through the integration of sequence and structural features · Materials and methods/Dataset construction (paragraph 1); Results and discussion/Limitations and perspectives (paragraph 1) |
| Outputs | Same-reaction versus different-reaction classificationSourcesEnhanced prediction of protein functional identity through the integration of sequence and structural features · Materials and methods/Model training and hyperparameter optimization (paragraph 1); Materials and methods/Feature importance/Gini importance (paragraph 1) |
| Parameters | An aggregate parameter total for this exact evaluated configuration is not established by the inspected sources. · Not reported in inspected sourcesSources (2)Enhanced prediction of protein functional identity through the integration of sequence and structural features; sfujita0601/FUJISAN README.md · Materials and methods/Dataset construction; Materials and methods/Feature engineering/Full-length sequence similarity features; Materials and methods/Feature engineering/Domain structural similarity features; Materials and methods/Feature engineering/Pocket similarity features; Materials and methods/Model training and hyperparameter optimization; Materials and methods/Performance assessment; Materials and methods/Prediction with DeepFRI; Materials and methods/Prediction with ESM-2; inspected for aggregate parameter count (component sizes are not added without an exact configuration); README.md at pinned repository revision |
| Known versions / configuration | FUJISAN is the comparison-table label; that label does not specify an immutable weight revision. · Not reported in inspected sourcesSourcesEnhanced prediction of protein functional identity through the integration of sequence and structural features · Model identification in the comparison table and corresponding Methods; immutable checkpoint revision is not supplied by the table label. |
| Training data / fitting | 20,800 same-function and 20,800 different-function pairs; train/validation/test proportions are 56.25%, 18.75% and 25%.SourcesEnhanced prediction of protein functional identity through the integration of sequence and structural features · Materials and methods/Model training and hyperparameter optimization (paragraph 1); Results and discussion/Performance on low sequence similarity dataset (paragraph 1) |
| Context limits | A maximum input/context length for this exact evaluated configuration is not established by the inspected sources. · Not reported in inspected sourcesSources (2)Enhanced prediction of protein functional identity through the integration of sequence and structural features; sfujita0601/FUJISAN README.md · Materials and methods/Dataset construction; Materials and methods/Feature engineering/Full-length sequence similarity features; Materials and methods/Feature engineering/Domain structural similarity features; Materials and methods/Feature engineering/Pocket similarity features; Materials and methods/Model training and hyperparameter optimization; Materials and methods/Performance assessment; Materials and methods/Prediction with DeepFRI; Materials and methods/Prediction with ESM-2; inspected for explicit maximum input length (dataset lengths and family-wide limits are not substituted); README.md at pinned repository revision |
| Access | Official study implementation and usage documentation: https://github.com/sfujita0601/FUJISAN/blob/588daf65810c49b021af9e47b11ec752986dcb94/README.md. This pinned documentation revision is not automatically the evaluated weight revision.Sourcessfujita0601/FUJISAN README.md · README.md; installation, model download and usage instructions |
| Code licence | No explicit code licence was established from the paper’s availability statement and inspected repository-root documentation. · Not reported in inspected sourcesSourcessfujita0601/FUJISAN README.md · README.md and repository-root licence-file search |
| Weights licence | The inspected model-access documentation does not explicitly identify terms for this exact evaluated checkpoint or fitted head; repository code terms are shown separately. · Not reported in inspected sourcesSourcessfujita0601/FUJISAN README.md · README.md; checkpoint/access documentation and licence scope |
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.
21 evidence rows matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| Diagram caption Conceptual input–method–output guide. Check the procedure text and linked evaluation for fitted components, additional inputs and exact settings. Individual claims | Enhanced prediction of protein functional identity through the integration of sequence and structural features Materials and methods/Feature engineering/Pocket similarity features (paragraph 1); Conclusions (paragraph 1) Version: PMC11609699.1 | source checked automated source review · 2026-09-16 Audit detailsPrimary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Diagram steps ["Pairs of protein sequences and predicted structures with domain and pocket decomposition","FUJISAN","Same-reaction versus different-reaction classification"] Individual claims | Enhanced prediction of protein functional identity through the integration of sequence and structural features Materials and methods/Feature engineering/Pocket similarity features (paragraph 1); Conclusions (paragraph 1) Version: PMC11609699.1 | source checked automated source review · 2026-09-16 Audit detailsPrimary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Diagram title Evaluated procedure (conceptual) Individual claims | Enhanced prediction of protein functional identity through the integration of sequence and structural features Materials and methods/Feature engineering/Pocket similarity features (paragraph 1); Conclusions (paragraph 1) Version: PMC11609699.1 | source checked automated source review · 2026-09-16 Audit detailsPrimary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Model type Gradient-boosted-tree pipeline; this record is the paper-specific evaluated configuration. Individual claims | Enhanced prediction of protein functional identity through the integration of sequence and structural features Materials and methods/Feature engineering/Pocket similarity features (paragraph 1); Conclusions (paragraph 1) Version: PMC11609699.1 | source checked automated source review · 2026-09-16 Audit detailsPrimary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Architecture / procedure Features include full-sequence similarity, domain structural similarity and pocket similarity from AlphaFold2 structural models. A LightGBM classifier combines these comparisons. Individual claims | Enhanced prediction of protein functional identity through the integration of sequence and structural features Materials and methods/Feature engineering/Pocket similarity features (paragraph 1); Conclusions (paragraph 1) Version: PMC11609699.1 | source checked automated source review · 2026-09-16 Audit detailsPrimary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Weights licence The inspected model-access documentation does not explicitly identify terms for this exact evaluated checkpoint or fitted head; repository code terms are shown separately. Individual claims | sfujita0601/FUJISAN README.md README.md; checkpoint/access documentation and licence scope Version: 588daf65810c49b021af9e47b11ec752986dcb94 | unreported automated source review · 2026-09-16 Audit detailsPrimary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Biological inputs Pairs of protein sequences and predicted structures with domain and pocket decomposition Individual claims | Enhanced prediction of protein functional identity through the integration of sequence and structural features Materials and methods/Dataset construction (paragraph 1); Results and discussion/Limitations and perspectives (paragraph 1) Version: PMC11609699.1 | source checked automated source review · 2026-09-16 Audit detailsPrimary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Outputs Same-reaction versus different-reaction classification Individual claims | Enhanced prediction of protein functional identity through the integration of sequence and structural features Materials and methods/Model training and hyperparameter optimization (paragraph 1); Materials and methods/Feature importance/Gini importance (paragraph 1) Version: PMC11609699.1 | source checked automated source review · 2026-09-16 Audit detailsPrimary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Parameters An aggregate parameter total for this exact evaluated configuration is not established by the inspected sources. Individual claims | sfujita0601/FUJISAN README.md Materials and methods/Dataset construction; Materials and methods/Feature engineering/Full-length sequence similarity features; Materials and methods/Feature engineering/Domain structural similarity features; Materials and methods/Feature engineering/Pocket similarity features; Materials and methods/Model training and hyperparameter optimization; Materials and methods/Performance assessment; Materials and methods/Prediction with DeepFRI; Materials and methods/Prediction with ESM-2; inspected for aggregate parameter count (component sizes are not added without an exact configuration); README.md at pinned repository revision Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 588daf65810c49b021af9e47b11ec752986dcb94 | unreported automated source review · 2026-09-16 Audit detailsPrimary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Parameters An aggregate parameter total for this exact evaluated configuration is not established by the inspected sources. Individual claims | Enhanced prediction of protein functional identity through the integration of sequence and structural features Materials and methods/Dataset construction; Materials and methods/Feature engineering/Full-length sequence similarity features; Materials and methods/Feature engineering/Domain structural similarity features; Materials and methods/Feature engineering/Pocket similarity features; Materials and methods/Model training and hyperparameter optimization; Materials and methods/Performance assessment; Materials and methods/Prediction with DeepFRI; Materials and methods/Prediction with ESM-2; inspected for aggregate parameter count (component sizes are not added without an exact configuration); README.md at pinned repository revision Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: PMC11609699.1 | unreported automated source review · 2026-09-16 Audit detailsPrimary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: 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
2 source records and release history
- Enhanced prediction of protein functional identity through the integration of sequence and structural features · Original source · PMC11609699.1
- sfujita0601/FUJISAN README.md · Original source · 588daf65810c49b021af9e47b11ec752986dcb94
Technical metadata and extraction receipts
Stable ID: reported-model-9c10fbec02a365
- areas
- proteins-complexes
- entity level
- method
- version
- Not reported
- reported name
- FUJISAN
- historical missing metadata
- version: not_reported_in_legacy_extract; checkpoint revision: not_reported_in_legacy_extract; training data: not_reported_in_legacy_extract; licence: not_reported_in_legacy_extract
- metadata review scope
- historical_missing_metadata preserves the original discovery state. Current descriptive evidence and missingness are recorded in profile.facts; numerical-result review is separate.
- legacy kinds
- model
- entity classification
- review date: 2026-09-17; rationale: This source-scoped entry preserves the method/configuration actually named in an evaluation. It is neither a global family identity nor proof of an immutable checkpoint; the linked evaluation retains adaptation, fitting and scoring details.; source ids: fujisan-2024; source locator: Materials and methods/Feature engineering/Pocket similarity features (paragraph 1); Conclusions (paragraph 1) | Abstract (paragraph 1); Results and discussion/Limitations and perspectives (paragraph 1); ambiguities: Configuration means the source-labelled evaluated identity. It does not establish missing checkpoint hashes, default settings or equivalence to same-named records in other papers.