Task

Enzyme functional identity prediction

Enzyme functional-identity classification predicts whether a protein pair shares its annotated reaction function.

Sources

Enhanced prediction of protein functional identity through the integration of sequence and structural features · Methods: Dataset construction; classification and metrics; Results: model comparison; cached text lines 10–11, 25, 28, 52, 55; uncertainty/repeat-run/statistical-comparison passages

5 evaluations · 40 metric rows

At a glance

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.

Data, procedure and scoring
Property	Description and evidence
Datasets	Swiss-Prot reaction annotations and AlphaFold Database structures; balanced same-function and different-function pairs. Sources Enhanced prediction of protein functional identity through the integration of sequence and structural features · Methods: Dataset construction; classification and metrics; Results: model comparison; cached text lines 10–11, 25, 28, 52, 55; uncertainty/repeat-run/statistical-comparison passages
Splits	Random pair partitions provide training, validation and test subsets; model hyperparameters are tuned using cross-validation. Sources Enhanced prediction of protein functional identity through the integration of sequence and structural features · Methods: Dataset construction; classification and metrics; Results: model comparison; cached text lines 10–11, 25, 28, 52, 55; uncertainty/repeat-run/statistical-comparison passages
Metrics	Accuracy, false-positive rate, MCC, precision, recall, F1, AUROC and AUPR. Sources Enhanced prediction of protein functional identity through the integration of sequence and structural features · Methods: Dataset construction; classification and metrics; Results: model comparison; cached text lines 10–11, 25, 28, 52, 55; uncertainty/repeat-run/statistical-comparison passages
Baselines	LightGBM and multiple conventional classifiers. Sources Enhanced prediction of protein functional identity through the integration of sequence and structural features · Methods: Dataset construction; classification and metrics; Results: model comparison; cached text lines 10–11, 25, 28, 52, 55; uncertainty/repeat-run/statistical-comparison passages
Leakage controls	The low-sequence-similarity evaluation excludes pairs from the original dataset; random splitting of the main pair dataset does not establish protein-identity holdout. Sources Enhanced prediction of protein functional identity through the integration of sequence and structural features · Methods: Dataset construction; classification and metrics; Results: model comparison; cached text lines 10–11, 25, 28, 52, 55; uncertainty/repeat-run/statistical-comparison passages
Uncertainty	The paper assesses stability using repeated bootstrap iterations; its sampling unit must remain attached to the reported interval. Sources Enhanced prediction of protein functional identity through the integration of sequence and structural features · Methods: Dataset construction; classification and metrics; Results: model comparison; cached text lines 10–11, 25, 28, 52, 55; uncertainty/repeat-run/statistical-comparison passages
Entity type	Paper-specific computational evaluation protocol. Sources Enhanced prediction of protein functional identity through the integration of sequence and structural features · Methods: Dataset construction; classification and metrics; Results: model comparison; cached text lines 10–11, 25, 28, 52, 55; uncertainty/repeat-run/statistical-comparison passages
Organisms	Proteins were selected through Swiss-Prot release 2022_04 entries with Rhea reaction annotations and AlphaFold DB v4 structures. Dataset construction does not enumerate organism frequencies for the sampled 100,000 protein pairs, so a species-restricted population cannot be assigned. · Not reported in inspected sources Sources Enhanced prediction of protein functional identity through the integration of sequence and structural features · Materials and methods: Dataset construction
Assays	Swiss-Prot reaction/function annotations with AlphaFold structures. Sources Enhanced prediction of protein functional identity through the integration of sequence and structural features · Methods: Dataset construction; classification and metrics; Results: model comparison; cached text lines 10–11, 25, 28, 52, 55; uncertainty/repeat-run/statistical-comparison passages
Allowed inputs	Pairs of enzyme representations. Sources Enhanced prediction of protein functional identity through the integration of sequence and structural features · Methods: Dataset construction; classification and metrics; Results: model comparison; cached text lines 10–11, 25, 28, 52, 55; uncertainty/repeat-run/statistical-comparison passages
Adaptation	Supervised same-function classification; hyperparameters use cross-validation, with algorithm choice additionally compared on test data. Sources Enhanced prediction of protein functional identity through the integration of sequence and structural features · Methods: Dataset construction; classification and metrics; Results: model comparison; cached text lines 10–11, 25, 28, 52, 55; uncertainty/repeat-run/statistical-comparison passages

How it works

How it worksComputational evaluation flow

Conceptual summary of the cited evaluation; exact task configuration and source version remain part of the protocol.

Sources

Evaluation methodology

Swiss-Prot reaction annotations and AlphaFold Database structures; balanced same-function and different-function pairs. Random pair partitions provide training, validation and test subsets; model hyperparameters are tuned using cross-validation. Accuracy, false-positive rate, MCC, precision, recall, F1, AUROC and AUPR. LightGBM and multiple conventional classifiers. The low-sequence-similarity evaluation excludes pairs from the original dataset; random splitting of the main pair dataset does not establish protein-identity holdout.

Sources

Evaluation design

Benchmarks bring together tasks and protocols. A task describes the biological question; a protocol defines a particular test.

Protocols

Enzyme-pair functional identity: original held-out test (Enzyme functional identity prediction)

These source-backed links do not make different protocols or scores interchangeable.

Published comparisons

Explore the results reported under one evaluation protocol. Each figure keeps its source, dataset and metric together; it is not a ranking across studies.

Comparison and metric

Enzyme-pair functional identity: original held-out test · Table 1

ACC (%) (percent) · Higher values are better for this metric.

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.

Evaluation protocol · FUJISAN test sub-dataset

FUJISAN · Configuration · Author-reported evaluation87.05
E-value · Configuration · Author-reported evaluation81.91
DeepFRI · Configuration · Author-reported evaluation80.88
ESM2 · Configuration · Independent external evaluation71.33
Pfam · Configuration · Author-reported evaluation61.99

Source order is preserved. Plotted marks show point estimates; uncertainty, where reported, is retained in the printed values and table. Differences do not establish statistical significance.

Enhanced prediction of protein functional identity through the integration of sequence and structural features · Table 1: ACC (%), Enzyme-pair functional identity: original held-out test

Values, uncertainty and evidence

ACC (%): original source values
Tested entity	Printed value	Uncertainty	Evidence
FUJISAN · Configuration	87.05 percent	Not reported	Author-reported evaluation · source checkedEnhanced prediction of protein functional identity through the integration of sequence and structural features · Table 1, row FUJISAN, column ACC (%); XML row2 column2
E-value · Configuration	81.91 percent	Not reported	Author-reported evaluation · source checkedEnhanced prediction of protein functional identity through the integration of sequence and structural features · Table 1, row E-value, column ACC (%); XML row3 column2
DeepFRI · Configuration	80.88 percent	Not reported	Author-reported evaluation · source checkedEnhanced prediction of protein functional identity through the integration of sequence and structural features · Table 1, row DeepFRI, column ACC (%); XML row4 column2
ESM2 · Configuration	71.33 percent	Not reported	Independent external evaluation · source checkedEnhanced prediction of protein functional identity through the integration of sequence and structural features · Table 1, row ESM2, column ACC (%); XML row5 column2
Pfam · Configuration	61.99 percent	Not reported	Author-reported evaluation · source checkedEnhanced prediction of protein functional identity through the integration of sequence and structural features · Table 1, row Pfam, column ACC (%); XML row6 column2

Scope and limitations

Input information differs: sequence similarity, protein embeddings, structure-aware descriptors and domain annotations.
Table1 reports point values;50bootstrap iterations described elsewhere do not establish a Table1 interval.
No interval assigned unless printed in source cell.

Source transcription and grouping reviewed by automated source review on 2026-09-17. These experiments were not independently reproduced by rewire.

Tested entities and results

Release 2026-09-17-d277315f7d76 · 5 evaluations · 40 metric rows. Different protocols are not a single leaderboard.

Evaluation setupMetricEvidence origin

Results grouped by the exact reported evaluation
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.
ESM2: Enzyme functional identity prediction Configuration: ESM2Protocol: 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. Independent external evaluation · Evaluation metadata: needs review
0.7991 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, ESM2 row, AUROC column Source checking is not independent reproduction.
79.33% 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 ESM2, column REC (%); XML row5 column4 Source checking is not independent reproduction.
0.8147 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 ESM2, column AUPR; XML row5 column9 Source checking is not independent reproduction.
0.4321 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 ESM2, column MCC; XML row5 column7 Source checking is not independent reproduction.
68.39% 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 ESM2, column PRE (%); XML row5 column3 Source checking is not independent reproduction.
E-value: Enzyme-pair functional identity: original held-out test Configuration: E-valueProtocol: 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
78.58% 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 E-value, column PRE (%); XML row3 column3 Source checking is not independent reproduction.
0.8291 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 E-value, column F1; XML row3 column6 Source checking is not independent reproduction.
0.6427 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 E-value, column MCC; XML row3 column7 Source checking is not independent reproduction.
23.92% 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 E-value, column FPR (%); XML row3 column5 Source checking is not independent reproduction.
87.75% 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 E-value, column REC (%); XML row3 column4 Source checking is not independent reproduction.
81.91% 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 E-value, column ACC (%); XML row3 column2 Source checking is not independent reproduction.
DeepFRI: Enzyme-pair functional identity: original held-out test Configuration: DeepFRIProtocol: 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
83.16% 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 DeepFRI, column REC (%); XML row4 column4 Source checking is not independent reproduction.
80.88% 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 DeepFRI, column ACC (%); XML row4 column2 Source checking is not independent reproduction.
0.6790 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 DeepFRI, column MCC; XML row4 column7 Source checking is not independent reproduction.
0.8143 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 DeepFRI, column F1; XML row4 column6 Source checking is not independent reproduction.
Pfam: Enzyme-pair functional identity: original held-out test Configuration: PfamProtocol: 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
61.99% 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 Pfam, column ACC (%); XML row6 column2 Source checking is not independent reproduction.
0.3520 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 Pfam, column MCC; XML row6 column7 Source checking is not independent reproduction.
56.92% 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 Pfam, column PRE (%); XML row6 column3 Source checking is not independent reproduction.
0.7217 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 Pfam, column F1; XML row6 column6 Source checking is not independent reproduction.
74.62% 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 Pfam, column FPR (%); XML row6 column5 Source checking is not independent reproduction.
98.60% 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 Pfam, column REC (%); XML row6 column4 Source checking is not independent reproduction.

Papers and result coverage

Last literature check: 2026-09-17. Primary-source discovery and table/protocol screening; source checked is not independently reproduced. Raw acquisitions not automatically numerical publication approval.

Paper or primary resource	Version	Reference
Enhanced prediction of protein functional identity through the integration of sequence and structural features	PMC11609699.1	Read source DOI: 10.1016/j.csbj.2024.11.028

What is still missing

Independent batch review before import; preserve existing observation identities.

Search and extraction details

complete comparison tables extracted pending publication review

Searches

Enhanced prediction of protein functional identity through the integration of sequence and structural features primary paper benchmark results

Evidence locations

Table1; Model training and hyperparameter optimization; Performance assessment

Strengths and limitations

Strengths and considerations

No source-reviewed explanatory claims are recorded here yet.

Limitations and conditions

The source reports selecting the best algorithm after test-set comparison, which limits interpretation as a final untouched test. Pair-level splitting does not establish protein-disjoint generalization.
Sources
Enhanced prediction of protein functional identity through the integration of sequence and structural features · Methods: Dataset construction; classification and metrics; Results: model comparison; cached text lines 10–11, 25, 28, 52, 55; uncertainty/repeat-run/statistical-comparison passages

Profile review details

Targeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change.

Stable record: reported-task-1ebf9b408517f9

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.

17 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-09-17-d277315f7d76
Property and statement	Original source and location	Review and provenance
Diagram caption Conceptual summary of the cited evaluation; exact task configuration and source version remain part of the protocol. Individual claims	Enhanced prediction of protein functional identity through the integration of sequence and structural features Original source ↗ Methods: Dataset construction; classification and metrics; Results: model comparison; cached text lines 10–11, 25, 28, 52, 55; uncertainty/repeat-run/statistical-comparison passages Version: PMC11609699.1 Retrieved: 2026-09-16T10:33:35.728Z	source checked automated source review · 2026-09-16 Audit details Targeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: `attributes.profile.diagram.caption` Source artifact SHA-256: `db33e0542005ffae00cd644dfe697185b94c8823d5aee2768620a6db0c48e56f` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Diagram steps ["Input: Pairs of enzyme representations.","Evaluation: Random pair partitions provide training, validation and test subsets; model hyperparameters are tuned using cross-validation.","Readout: Accuracy, false-positive rate, MCC, precision, recall, F1, AUROC and AUPR."] Individual claims	Enhanced prediction of protein functional identity through the integration of sequence and structural features Original source ↗ Methods: Dataset construction; classification and metrics; Results: model comparison; cached text lines 10–11, 25, 28, 52, 55; uncertainty/repeat-run/statistical-comparison passages Version: PMC11609699.1 Retrieved: 2026-09-16T10:33:35.728Z	source checked automated source review · 2026-09-16 Audit details Targeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: `attributes.profile.diagram.steps` Source artifact SHA-256: `db33e0542005ffae00cd644dfe697185b94c8823d5aee2768620a6db0c48e56f` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Diagram title Computational evaluation flow Individual claims	Enhanced prediction of protein functional identity through the integration of sequence and structural features Original source ↗ Methods: Dataset construction; classification and metrics; Results: model comparison; cached text lines 10–11, 25, 28, 52, 55; uncertainty/repeat-run/statistical-comparison passages Version: PMC11609699.1 Retrieved: 2026-09-16T10:33:35.728Z	source checked automated source review · 2026-09-16 Audit details Targeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: `attributes.profile.diagram.title` Source artifact SHA-256: `db33e0542005ffae00cd644dfe697185b94c8823d5aee2768620a6db0c48e56f` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Datasets Swiss-Prot reaction annotations and AlphaFold Database structures; balanced same-function and different-function pairs. Individual claims	Enhanced prediction of protein functional identity through the integration of sequence and structural features Original source ↗ Methods: Dataset construction; classification and metrics; Results: model comparison; cached text lines 10–11, 25, 28, 52, 55; uncertainty/repeat-run/statistical-comparison passages Version: PMC11609699.1 Retrieved: 2026-09-16T10:33:35.728Z	source checked automated source review · 2026-09-16 Audit details Targeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: `attributes.profile.facts.0.value` Source artifact SHA-256: `db33e0542005ffae00cd644dfe697185b94c8823d5aee2768620a6db0c48e56f` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Splits Random pair partitions provide training, validation and test subsets; model hyperparameters are tuned using cross-validation. Individual claims	Enhanced prediction of protein functional identity through the integration of sequence and structural features Original source ↗ Methods: Dataset construction; classification and metrics; Results: model comparison; cached text lines 10–11, 25, 28, 52, 55; uncertainty/repeat-run/statistical-comparison passages Version: PMC11609699.1 Retrieved: 2026-09-16T10:33:35.728Z	source checked automated source review · 2026-09-16 Audit details Targeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: `attributes.profile.facts.1.value` Source artifact SHA-256: `db33e0542005ffae00cd644dfe697185b94c8823d5aee2768620a6db0c48e56f` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Adaptation Supervised same-function classification; hyperparameters use cross-validation, with algorithm choice additionally compared on test data. Individual claims	Enhanced prediction of protein functional identity through the integration of sequence and structural features Original source ↗ Methods: Dataset construction; classification and metrics; Results: model comparison; cached text lines 10–11, 25, 28, 52, 55; uncertainty/repeat-run/statistical-comparison passages Version: PMC11609699.1 Retrieved: 2026-09-16T10:33:35.728Z	source checked automated source review · 2026-09-16 Audit details Targeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: `attributes.profile.facts.10.value` Source artifact SHA-256: `db33e0542005ffae00cd644dfe697185b94c8823d5aee2768620a6db0c48e56f` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Metrics Accuracy, false-positive rate, MCC, precision, recall, F1, AUROC and AUPR. Individual claims	Enhanced prediction of protein functional identity through the integration of sequence and structural features Original source ↗ Methods: Dataset construction; classification and metrics; Results: model comparison; cached text lines 10–11, 25, 28, 52, 55; uncertainty/repeat-run/statistical-comparison passages Version: PMC11609699.1 Retrieved: 2026-09-16T10:33:35.728Z	source checked automated source review · 2026-09-16 Audit details Targeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: `attributes.profile.facts.2.value` Source artifact SHA-256: `db33e0542005ffae00cd644dfe697185b94c8823d5aee2768620a6db0c48e56f` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Baselines LightGBM and multiple conventional classifiers. Individual claims	Enhanced prediction of protein functional identity through the integration of sequence and structural features Original source ↗ Methods: Dataset construction; classification and metrics; Results: model comparison; cached text lines 10–11, 25, 28, 52, 55; uncertainty/repeat-run/statistical-comparison passages Version: PMC11609699.1 Retrieved: 2026-09-16T10:33:35.728Z	source checked automated source review · 2026-09-16 Audit details Targeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: `attributes.profile.facts.3.value` Source artifact SHA-256: `db33e0542005ffae00cd644dfe697185b94c8823d5aee2768620a6db0c48e56f` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Leakage controls The low-sequence-similarity evaluation excludes pairs from the original dataset; random splitting of the main pair dataset does not establish protein-identity holdout. Individual claims	Enhanced prediction of protein functional identity through the integration of sequence and structural features Original source ↗ Methods: Dataset construction; classification and metrics; Results: model comparison; cached text lines 10–11, 25, 28, 52, 55; uncertainty/repeat-run/statistical-comparison passages Version: PMC11609699.1 Retrieved: 2026-09-16T10:33:35.728Z	source checked automated source review · 2026-09-16 Audit details Targeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: `attributes.profile.facts.4.value` Source artifact SHA-256: `db33e0542005ffae00cd644dfe697185b94c8823d5aee2768620a6db0c48e56f` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Uncertainty The paper assesses stability using repeated bootstrap iterations; its sampling unit must remain attached to the reported interval. Individual claims	Enhanced prediction of protein functional identity through the integration of sequence and structural features Original source ↗ Methods: Dataset construction; classification and metrics; Results: model comparison; cached text lines 10–11, 25, 28, 52, 55; uncertainty/repeat-run/statistical-comparison passages Version: PMC11609699.1 Retrieved: 2026-09-16T10:33:35.728Z	source checked automated source review · 2026-09-16 Audit details Targeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: `attributes.profile.facts.5.value` Source artifact SHA-256: `db33e0542005ffae00cd644dfe697185b94c8823d5aee2768620a6db0c48e56f` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact

All evidence (CSV)All evidence (JSONL)How to read the evidence

Sources and history

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

2 source records and release history

Download this release

Technical metadata and extraction receipts

Stable ID: reported-task-1ebf9b408517f9

areas: proteins-complexes
tasks: Enzyme functional identity prediction
entity level: task
version: Not reported
task: Enzyme functional identity prediction
scope note: Paper-specific evaluation task; protocol completeness requires further extraction.
comparison panels: id: part2-fujisan-2024-tbl0005-bac8a6d22a; title: Enzyme-pair functional identity: original held-out test · Table 1; protocol id: paper-protocol-7088bcc2f0033b8a29; dataset id: reported-dataset-5197cca532f89d; metric: ACC (%); unit: percent; direction: higher; result ids: paper-result-eaf1d6c59a5f36f4ce; paper-result-7a33f77a25091433d2; paper-result-357d8f3b2935e06e3d; paper-result-b621ec294f38d3f19c; paper-result-23786f6a1a92179f21; source ids: part2-fujisan-2024; source locator: Table 1: ACC (%), Enzyme-pair functional identity: original held-out test; context: 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.; caveats: Input information differs: sequence similarity, protein embeddings, structure-aware descriptors and domain annotations.; Table1 reports point values;50bootstrap iterations described elsewhere do not establish a Table1 interval.; No interval assigned unless printed in source cell.; review: method: automated_source_review; date: 2026-09-17; id: part2-fujisan-2024-tbl0005-8cc77c9aa4; title: Enzyme-pair functional identity: original held-out test · Table 1; protocol id: paper-protocol-7088bcc2f0033b8a29; dataset id: reported-dataset-5197cca532f89d; metric: PRE (%); unit: percent; direction: higher; result ids: paper-result-989a4675188b8141c2; paper-result-003d7035891e68f095; paper-result-b6bde99a5fd8fcf312; paper-result-a18d074f2077ce82f8; paper-result-5c36a73bb7912f46bb; source ids: part2-fujisan-2024; source locator: Table 1: PRE (%), Enzyme-pair functional identity: original held-out test; context: 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.; caveats: Input information differs: sequence similarity, protein embeddings, structure-aware descriptors and domain annotations.; Table1 reports point values;50bootstrap iterations described elsewhere do not establish a Table1 interval.; No interval assigned unless printed in source cell.; review: method: automated_source_review; date: 2026-09-17; id: part2-fujisan-2024-tbl0005-3714094960; title: Enzyme-pair functional identity: original held-out test · Table 1; protocol id: paper-protocol-7088bcc2f0033b8a29; dataset id: reported-dataset-5197cca532f89d; metric: REC (%); unit: percent; direction: higher; result ids: paper-result-0081b12c9bb122c13a; paper-result-71abecaef7ab30d471; paper-result-21390f8f107e3d5169; paper-result-0d3498cab7dbd41b99; paper-result-9907ce062be9dbd488; source ids: part2-fujisan-2024; source locator: Table 1: REC (%), Enzyme-pair functional identity: original held-out test; context: 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.; caveats: Input information differs: sequence similarity, protein embeddings, structure-aware descriptors and domain annotations.; Table1 reports point values;50bootstrap iterations described elsewhere do not establish a Table1 interval.; No interval assigned unless printed in source cell.; review: method: automated_source_review; date: 2026-09-17; id: part2-fujisan-2024-tbl0005-a129b9c665; title: Enzyme-pair functional identity: original held-out test · Table 1; protocol id: paper-protocol-7088bcc2f0033b8a29; dataset id: reported-dataset-5197cca532f89d; metric: FPR (%); unit: percent; direction: lower; result ids: paper-result-ff3b35eac39b7fa2ed; paper-result-6e46bf4f05ccae3dff; paper-result-a36c2ff5211b482ac8; paper-result-c478bf21db79f9c0fa; paper-result-95850ea0b3b65d0a9f; source ids: part2-fujisan-2024; source locator: Table 1: FPR (%), Enzyme-pair functional identity: original held-out test; context: 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.; caveats: Input information differs: sequence similarity, protein embeddings, structure-aware descriptors and domain annotations.; Table1 reports point values;50bootstrap iterations described elsewhere do not establish a Table1 interval.; No interval assigned unless printed in source cell.; review: method: automated_source_review; date: 2026-09-17; id: part2-fujisan-2024-tbl0005-0b4696dd22; title: Enzyme-pair functional identity: original held-out test · Table 1; protocol id: paper-protocol-7088bcc2f0033b8a29; dataset id: reported-dataset-5197cca532f89d; metric: F1; unit: dimensionless; direction: higher; result ids: paper-result-ef58d0787535e7e9a5; paper-result-113e4214c6249dc3c8; paper-result-895a3e38bb00f10f4a; paper-result-b5897e7fb2d9f17e8c; paper-result-73d717fd51d9b2682a; source ids: part2-fujisan-2024; source locator: Table 1: F1, Enzyme-pair functional identity: original held-out test; context: 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.; caveats: Input information differs: sequence similarity, protein embeddings, structure-aware descriptors and domain annotations.; Table1 reports point values;50bootstrap iterations described elsewhere do not establish a Table1 interval.; No interval assigned unless printed in source cell.; review: method: automated_source_review; date: 2026-09-17; id: part2-fujisan-2024-tbl0005-d782fec4a4; title: Enzyme-pair functional identity: original held-out test · Table 1; protocol id: paper-protocol-7088bcc2f0033b8a29; dataset id: reported-dataset-5197cca532f89d; metric: MCC; unit: dimensionless; direction: higher; result ids: paper-result-1ebedcb0adb7517e54; paper-result-3559edcbf93633cc0d; paper-result-58038afdc07c1aada5; paper-result-46452dcfe78a4f3d04; paper-result-5ac77bcc4aed51f516; source ids: part2-fujisan-2024; source locator: Table 1: MCC, Enzyme-pair functional identity: original held-out test; context: 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.; caveats: Input information differs: sequence similarity, protein embeddings, structure-aware descriptors and domain annotations.; Table1 reports point values;50bootstrap iterations described elsewhere do not establish a Table1 interval.; No interval assigned unless printed in source cell.; review: method: automated_source_review; date: 2026-09-17; id: part2-fujisan-2024-tbl0005-d1fced1a9c; title: Enzyme-pair functional identity: original held-out test · Table 1; protocol id: paper-protocol-7088bcc2f0033b8a29; dataset id: reported-dataset-5197cca532f89d; metric: AUROC; unit: unitless; direction: higher; result ids: lit-019; paper-result-d2f325ea0c890b170d; paper-result-b0dd968f641a7e8f16; lit-020; paper-result-b29f561ff4e41c3215; source ids: part2-fujisan-2024; source locator: Table 1: AUROC, Enzyme-pair functional identity: original held-out test; context: 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.; caveats: Input information differs: sequence similarity, protein embeddings, structure-aware descriptors and domain annotations.; Table1 reports point values;50bootstrap iterations described elsewhere do not establish a Table1 interval.; No interval assigned unless printed in source cell.; review: method: automated_source_review; date: 2026-09-17; id: part2-fujisan-2024-tbl0005-f8b070cff8; title: Enzyme-pair functional identity: original held-out test · Table 1; protocol id: paper-protocol-7088bcc2f0033b8a29; dataset id: reported-dataset-5197cca532f89d; metric: AUPR; unit: dimensionless; direction: higher; result ids: paper-result-baae3f4bd4e7d2eb06; paper-result-c9d11b0a9461bd483c; paper-result-ddfb253a50cc5308a8; paper-result-1dc6f9c6ff21f4263a; paper-result-f9f63e4d253b1af323; source ids: part2-fujisan-2024; source locator: Table 1: AUPR, Enzyme-pair functional identity: original held-out test; context: 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.; caveats: Input information differs: sequence similarity, protein embeddings, structure-aware descriptors and domain annotations.; Table1 reports point values;50bootstrap iterations described elsewhere do not establish a Table1 interval.; No interval assigned unless printed in source cell.; review: method: automated_source_review; date: 2026-09-17
benchmark research: review date: 2026-09-17; status: complete_comparison_tables_extracted_pending_publication_review; primary sources: part2-fujisan-2024; inspected locators: Table1; Model training and hyperparameter optimization; Performance assessment; searched queries: Enhanced prediction of protein functional identity through the integration of sequence and structural features primary paper benchmark results; gaps: Independent batch review before import; preserve existing observation identities.; claim scope: Primary-source discovery and table/protocol screening; source checked is not independently reproduced. Raw acquisitions not automatically numerical publication approval.
historical missing metadata: protocol version: not_reported_in_legacy_extract; split: 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: benchmark
entity classification: review date: 2026-09-17; rationale: This source-scoped record identifies the biological prediction task and holds its paper context. Preserve the existing task identity; exact split, model adaptation and scoring remain in linked evaluations or separate protocol records.; source ids: fujisan-2024; source locator: Methods: Dataset construction; classification and metrics; Results: model comparison; cached text lines 10–11, 25, 28, 52, 55; uncertainty/repeat-run/statistical-comparison passages; ambiguities: A paper- or suite-specific task may constrain some inputs or metrics; that alone does not make it interchangeable with a complete versioned protocol. No protocol equivalence is inferred.; Some legacy profile Entity type facts use the generic phrase computational evaluation protocol. That boilerplate is not sufficient to establish a single fixed protocol identity or to merge this task with another protocol record.

Related records

dataset: FUJISAN test sub-dataset
evaluates task: Enzyme-pair functional identity: original held-out test (Enzyme functional identity prediction)

Suggest a correction