Task

protein-protein interaction prediction

Protein-interaction classification contrasts ordinary pair-level validation with a more stringent protein-partitioned benchmark.

Sources

ESM2_AMP: an interpretable framework for protein–protein interactions prediction and biological mechanism discovery · Methods: Protein–protein interaction datasets; Results: strictly constructed dataset; cached text lines 10–12, 58–59, 67–68

7 evaluations · 34 results

Overview

Datasets

Pan_dataset and an independent real_test collection; Bernett data provide an additional evaluation.

Metrics

AUC and accuracy are among the reported metrics.

Allowed inputs

Pairs of protein sequences represented using ESM2.

Sources

Evaluation procedure diagram

How it worksComputational evaluation flow

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

Sources

Source reviewed · Automated source review, 2026-09-16. All specifications and missing details

Results

Each comparison retains its reviewed evaluation scope, dataset and metric. Results are shown without a pooled ranking.

Evaluation scope and datasetMetric and reported setup

Pan_dataset five-fold PPI cross-validation · Table 2

Accuracy (fraction) · Higher values are better.

Pan_dataset five-fold PPI cross-validation (protein-protein interaction prediction) · Pan_dataset five-fold PPI cross-validation

Evidence origin: Author-reported evaluation.

ESM2_AMP: an interpretable framework for protein–protein interactions prediction and biological mechanism discovery · Table 2: Accuracy, Pan_dataset five-fold PPI cross-validation

Do not combine with real_test or Bernett splits.

Comparison details and limitations

ESM 2_AMPS, ESM 2_AMP_CSE and ESM 2_DPM evaluated as complete PPI pipelines. Pan_dataset; Table 2 five-fold cross-validation.

No interval assigned unless printed in source cell.

Automated source review: 2026-09-17. Numerical source review does not establish independent reproduction.

Dots show point estimates. Whiskers show only explicitly defined uncertainty (standard deviation, standard error or a labelled interval); their definitions remain in Table. Unresolved uncertainty is not plotted. Differences do not establish statistical significance.

Find a tested model or method

Showing 3 of 3 matching rows.

Zoom to observed range

Tested configuration

00.250.50.751

Reported score

Methods and evaluation design

Procedure, tasks and evaluated configurations

How it works

Evaluation methodology

Pan_dataset and an independent real_test collection; Bernett data provide an additional evaluation. Five-fold cross-validation on Pan_dataset; separate Bernett training/validation/test partitions. AUC and accuracy are among the reported metrics. The Bernett comparison includes performance values supplied by previous studies. The real_test set filters high-similarity proteins; Bernett uses graph partitioning and within-partition redundancy filtering.

Sources

Evaluation design

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

Protocols

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

Recorded evaluations

Each evaluation records what was tested and under which conditions.

ESM2_AMPS: protein-protein interaction prediction

Run this benchmark

Choose a concrete protocol before running an evaluation. Its inputs, split and scoring rules determine which results can be compared.

Run instructions

No runnable recipe has been reviewed for this task. Dataset access, model requirements, licences and compute requirements must be checked against its sources before execution.

A task describes a biological question. Choose a linked protocol to obtain concrete split and scoring instructions.

Strengths, limitations and unresolved questions

Strengths and limitations

Strengths supported by sources

No source-reviewed explanatory claims are recorded here yet.

Limitations and conditions

Pair-level cross-validation and protein-disjoint partitioning answer different generalization questions. Literature comparator scores retain their original execution provenance.
Sources
ESM2_AMP: an interpretable framework for protein–protein interactions prediction and biological mechanism discovery · Methods: Protein–protein interaction datasets; Results: strictly constructed dataset; cached text lines 10–12, 58–59, 67–68

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-09c3100b77dcc5

Specifications

Inputs, training, access and other details

Explanatory profile: source reviewed · 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	Pan_dataset and an independent real_test collection; Bernett data provide an additional evaluation. Sources ESM2_AMP: an interpretable framework for protein–protein interactions prediction and biological mechanism discovery · Methods: Protein–protein interaction datasets; Results: strictly constructed dataset; cached text lines 10–12, 58–59, 67–68
Splits	Five-fold cross-validation on Pan_dataset; separate Bernett training/validation/test partitions. Sources ESM2_AMP: an interpretable framework for protein–protein interactions prediction and biological mechanism discovery · Methods: Protein–protein interaction datasets; Results: strictly constructed dataset; cached text lines 10–12, 58–59, 67–68
Metrics	AUC and accuracy are among the reported metrics. Sources ESM2_AMP: an interpretable framework for protein–protein interactions prediction and biological mechanism discovery · Methods: Protein–protein interaction datasets; Results: strictly constructed dataset; cached text lines 10–12, 58–59, 67–68
Baselines	The Bernett comparison includes performance values supplied by previous studies. Sources ESM2_AMP: an interpretable framework for protein–protein interactions prediction and biological mechanism discovery · Methods: Protein–protein interaction datasets; Results: strictly constructed dataset; cached text lines 10–12, 58–59, 67–68
Leakage controls	The real_test set filters high-similarity proteins; Bernett uses graph partitioning and within-partition redundancy filtering. Sources ESM2_AMP: an interpretable framework for protein–protein interactions prediction and biological mechanism discovery · Methods: Protein–protein interaction datasets; Results: strictly constructed dataset; cached text lines 10–12, 58–59, 67–68
Uncertainty	The Pan_dataset experiment averages five cross-validation folds. Tables 2 and 4 present point metrics without score confidence intervals; quoted Bernett comparator values are not additional independent repetitions. Sources ESM2_AMP: an interpretable framework for protein–protein interactions prediction and biological mechanism discovery · Methods: Protein–protein interaction datasets; Results and Tables 2, 4
Entity type	Paper-specific computational evaluation protocol. Sources ESM2_AMP: an interpretable framework for protein–protein interactions prediction and biological mechanism discovery · Methods: Protein–protein interaction datasets; Results: strictly constructed dataset; cached text lines 10–12, 58–59, 67–68
Organisms	Pan_dataset, real_test and Bernett are human interaction datasets. The separate Multi_species collection contains C. elegans, D. melanogaster and E. coli; performance on this collection must retain its multi-species context. Sources ESM2_AMP: an interpretable framework for protein–protein interactions prediction and biological mechanism discovery · Methods: Protein–protein interaction datasets; Table 1
Assays	Protein-pair interaction labels. Sources ESM2_AMP: an interpretable framework for protein–protein interactions prediction and biological mechanism discovery · Methods: Protein–protein interaction datasets; Results: strictly constructed dataset; cached text lines 10–12, 58–59, 67–68
Allowed inputs	Pairs of protein sequences represented using ESM2. Sources ESM2_AMP: an interpretable framework for protein–protein interactions prediction and biological mechanism discovery · Methods: Protein–protein interaction datasets; Results: strictly constructed dataset; cached text lines 10–12, 58–59, 67–68
Adaptation	Supervised pair classification with cross-validation and separate independent tests. Sources ESM2_AMP: an interpretable framework for protein–protein interactions prediction and biological mechanism discovery · Methods: Protein–protein interaction datasets; Results: strictly constructed dataset; cached text lines 10–12, 58–59, 67–68

Evidence

Source checking verifies the cited claim or transcription. It does not establish 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
ESM2_AMP: an interpretable framework for protein–protein interactions prediction and biological mechanism discovery	version of record	Read source DOI: 10.1093/bib/bbaf434

Historical gaps recorded on 2026-09-17

The catalogue now holds 34 result rows for this benchmark. A note below about pending extraction describes the state on 2026-09-17 and may since have been answered by a later batch. The result rows and their sources are the current record.

Independent batch review before import; preserve existing observation identities.

Search and extraction details

complete comparison tables extracted pending publication review

Searches

ESM2_AMP: an interpretable framework for protein–protein interactions prediction and biological mechanism discovery primary paper benchmark results

Evidence locations

Tables2–4; Pan_dataset/real_test/Bernett evaluation

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 2026-09-29-06401fd5b220
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	ESM2_AMP: an interpretable framework for protein–protein interactions prediction and biological mechanism discovery Original source ↗ Methods: Protein–protein interaction datasets; Results: strictly constructed dataset; cached text lines 10–12, 58–59, 67–68 Version: version of record Retrieved: 2026-09-16T10:33:58.625Z	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: `8e7ad6efb72ca28d73037cdf465b0e62f99cd6d0ee4ca9eaf96a4c48da22fd6c` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Diagram steps Input: Pairs of protein sequences represented using ESM2. Evaluation: Five-fold cross-validation on Pan_dataset; separate Bernett training/validation/test partitions. Readout: AUC and accuracy are among the reported metrics. Individual claims	ESM2_AMP: an interpretable framework for protein–protein interactions prediction and biological mechanism discovery Original source ↗ Methods: Protein–protein interaction datasets; Results: strictly constructed dataset; cached text lines 10–12, 58–59, 67–68 Version: version of record Retrieved: 2026-09-16T10:33:58.625Z	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: `8e7ad6efb72ca28d73037cdf465b0e62f99cd6d0ee4ca9eaf96a4c48da22fd6c` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Diagram title Computational evaluation flow Individual claims	ESM2_AMP: an interpretable framework for protein–protein interactions prediction and biological mechanism discovery Original source ↗ Methods: Protein–protein interaction datasets; Results: strictly constructed dataset; cached text lines 10–12, 58–59, 67–68 Version: version of record Retrieved: 2026-09-16T10:33:58.625Z	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: `8e7ad6efb72ca28d73037cdf465b0e62f99cd6d0ee4ca9eaf96a4c48da22fd6c` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Datasets Pan_dataset and an independent real_test collection; Bernett data provide an additional evaluation. Individual claims	ESM2_AMP: an interpretable framework for protein–protein interactions prediction and biological mechanism discovery Original source ↗ Methods: Protein–protein interaction datasets; Results: strictly constructed dataset; cached text lines 10–12, 58–59, 67–68 Version: version of record Retrieved: 2026-09-16T10:33:58.625Z	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: `8e7ad6efb72ca28d73037cdf465b0e62f99cd6d0ee4ca9eaf96a4c48da22fd6c` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Splits Five-fold cross-validation on Pan_dataset; separate Bernett training/validation/test partitions. Individual claims	ESM2_AMP: an interpretable framework for protein–protein interactions prediction and biological mechanism discovery Original source ↗ Methods: Protein–protein interaction datasets; Results: strictly constructed dataset; cached text lines 10–12, 58–59, 67–68 Version: version of record Retrieved: 2026-09-16T10:33:58.625Z	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: `8e7ad6efb72ca28d73037cdf465b0e62f99cd6d0ee4ca9eaf96a4c48da22fd6c` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Adaptation Supervised pair classification with cross-validation and separate independent tests. Individual claims	ESM2_AMP: an interpretable framework for protein–protein interactions prediction and biological mechanism discovery Original source ↗ Methods: Protein–protein interaction datasets; Results: strictly constructed dataset; cached text lines 10–12, 58–59, 67–68 Version: version of record Retrieved: 2026-09-16T10:33:58.625Z	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: `8e7ad6efb72ca28d73037cdf465b0e62f99cd6d0ee4ca9eaf96a4c48da22fd6c` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Metrics AUC and accuracy are among the reported metrics. Individual claims	ESM2_AMP: an interpretable framework for protein–protein interactions prediction and biological mechanism discovery Original source ↗ Methods: Protein–protein interaction datasets; Results: strictly constructed dataset; cached text lines 10–12, 58–59, 67–68 Version: version of record Retrieved: 2026-09-16T10:33:58.625Z	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: `8e7ad6efb72ca28d73037cdf465b0e62f99cd6d0ee4ca9eaf96a4c48da22fd6c` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Baselines The Bernett comparison includes performance values supplied by previous studies. Individual claims	ESM2_AMP: an interpretable framework for protein–protein interactions prediction and biological mechanism discovery Original source ↗ Methods: Protein–protein interaction datasets; Results: strictly constructed dataset; cached text lines 10–12, 58–59, 67–68 Version: version of record Retrieved: 2026-09-16T10:33:58.625Z	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: `8e7ad6efb72ca28d73037cdf465b0e62f99cd6d0ee4ca9eaf96a4c48da22fd6c` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Leakage controls The real_test set filters high-similarity proteins; Bernett uses graph partitioning and within-partition redundancy filtering. Individual claims	ESM2_AMP: an interpretable framework for protein–protein interactions prediction and biological mechanism discovery Original source ↗ Methods: Protein–protein interaction datasets; Results: strictly constructed dataset; cached text lines 10–12, 58–59, 67–68 Version: version of record Retrieved: 2026-09-16T10:33:58.625Z	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: `8e7ad6efb72ca28d73037cdf465b0e62f99cd6d0ee4ca9eaf96a4c48da22fd6c` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Uncertainty The Pan_dataset experiment averages five cross-validation folds. Tables 2 and 4 present point metrics without score confidence intervals; quoted Bernett comparator values are not additional independent repetitions. Individual claims	ESM2_AMP: an interpretable framework for protein–protein interactions prediction and biological mechanism discovery Original source ↗ Methods: Protein–protein interaction datasets; Results and Tables 2, 4 Version: version of record Retrieved: 2026-09-16T10:33:58.625Z	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: `8e7ad6efb72ca28d73037cdf465b0e62f99cd6d0ee4ca9eaf96a4c48da22fd6c` 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

View linked audit checks and correction history

Release 2026-09-29-06401fd5b220 · Record review: needs review

2 source records and release history

ESM2_AMP: an interpretable framework for protein–protein interactions prediction and biological mechanism discovery · Original source · version of record
ESM2_AMP: an interpretable framework for protein–protein interactions prediction and biological mechanism discovery · Original source · version of record

Download this release

Technical metadata and extraction receipts

Stable ID: reported-task-09c3100b77dcc5

areas: molecular-interactions
tasks: protein-protein interaction prediction
entity level: task
version: Not reported
task: protein-protein interaction prediction
scope note: Paper-specific evaluation task; protocol completeness requires further extraction.
comparison panels: id: part2-esm2-amp-2025-TB2-bcfa7fd935; title: Pan_dataset five-fold PPI cross-validation · Table 2; protocol id: paper-protocol-be1c9eab950fb814ec; dataset id: paper-dataset-1de23e14845ef72241; metric: Accuracy; unit: fraction; direction: higher; result ids: paper-result-849a689bb863da7b89; paper-result-ad1bca4f43523769b0; paper-result-95b8985c40d7060b18; source ids: part2-esm2-amp-2025; source locator: Table 2: Accuracy, Pan_dataset five-fold PPI cross-validation; context: ESM 2_AMPS, ESM 2_AMP_CSE and ESM 2_DPM evaluated as complete PPI pipelines. Pan_dataset; Table 2 five-fold cross-validation.; caveats: Do not combine with real_test or Bernett splits.; No interval assigned unless printed in source cell.; review: method: automated_source_review; date: 2026-09-17; id: part2-esm2-amp-2025-TB2-080c760521; title: Pan_dataset five-fold PPI cross-validation · Table 2; protocol id: paper-protocol-be1c9eab950fb814ec; dataset id: paper-dataset-1de23e14845ef72241; metric: Recall; unit: fraction; direction: higher; result ids: paper-result-d7ca453d8394415cf3; paper-result-6596ff3ab5a5186dd5; paper-result-d9f6f8b8dce18dabdc; source ids: part2-esm2-amp-2025; source locator: Table 2: Recall, Pan_dataset five-fold PPI cross-validation; context: ESM 2_AMPS, ESM 2_AMP_CSE and ESM 2_DPM evaluated as complete PPI pipelines. Pan_dataset; Table 2 five-fold cross-validation.; caveats: Do not combine with real_test or Bernett splits.; No interval assigned unless printed in source cell.; review: method: automated_source_review; date: 2026-09-17; id: part2-esm2-amp-2025-TB2-34516e10b1; title: Pan_dataset five-fold PPI cross-validation · Table 2; protocol id: paper-protocol-be1c9eab950fb814ec; dataset id: paper-dataset-1de23e14845ef72241; metric: F1 Score; unit: fraction; direction: higher; result ids: paper-result-b95e4f473396a4ec4a; paper-result-a7f701de866be03f45; paper-result-080bcca9522a063c76; source ids: part2-esm2-amp-2025; source locator: Table 2: F1 Score, Pan_dataset five-fold PPI cross-validation; context: ESM 2_AMPS, ESM 2_AMP_CSE and ESM 2_DPM evaluated as complete PPI pipelines. Pan_dataset; Table 2 five-fold cross-validation.; caveats: Do not combine with real_test or Bernett splits.; No interval assigned unless printed in source cell.; review: method: automated_source_review; date: 2026-09-17; id: part2-esm2-amp-2025-TB2-a76b0f5e92; title: Pan_dataset five-fold PPI cross-validation · Table 2; protocol id: paper-protocol-be1c9eab950fb814ec; dataset id: paper-dataset-1de23e14845ef72241; metric: AUC; unit: fraction; direction: higher; result ids: paper-result-65a00f3c782a024fa3; paper-result-29145ccafb7fa248fb; paper-result-4138022a44ce806e42; source ids: part2-esm2-amp-2025; source locator: Table 2: AUC, Pan_dataset five-fold PPI cross-validation; context: ESM 2_AMPS, ESM 2_AMP_CSE and ESM 2_DPM evaluated as complete PPI pipelines. Pan_dataset; Table 2 five-fold cross-validation.; caveats: Do not combine with real_test or Bernett splits.; No interval assigned unless printed in source cell.; review: method: automated_source_review; date: 2026-09-17; id: part2-esm2-amp-2025-TB2-c4db9319dd; title: Pan_dataset five-fold PPI cross-validation · Table 2; protocol id: paper-protocol-be1c9eab950fb814ec; dataset id: paper-dataset-1de23e14845ef72241; metric: MCC; unit: dimensionless; direction: higher; result ids: paper-result-7158b83512c200c2b8; paper-result-7317681be4f0a4ac94; paper-result-5695f2aceef2d88e83; source ids: part2-esm2-amp-2025; source locator: Table 2: MCC, Pan_dataset five-fold PPI cross-validation; context: ESM 2_AMPS, ESM 2_AMP_CSE and ESM 2_DPM evaluated as complete PPI pipelines. Pan_dataset; Table 2 five-fold cross-validation.; caveats: Do not combine with real_test or Bernett splits.; No interval assigned unless printed in source cell.; review: method: automated_source_review; date: 2026-09-17; id: part2-esm2-amp-2025-TB3-8efc06a1fc; title: real_test PPI held-out evaluation · Table 3; protocol id: paper-protocol-1edc32c80b0223fef1; dataset id: paper-dataset-a825ad55756b359150; metric: Accuracy; unit: fraction; direction: higher; result ids: paper-result-790e874858cc08f657; paper-result-99ad6e202a567da653; paper-result-6680db966a9d1e35b4; source ids: part2-esm2-amp-2025; source locator: Table 3: Accuracy, real_test PPI held-out evaluation; context: Complete trained PPI pipelines evaluated on real_test. Paper real_test dataset; Table 3.; caveats: Do not combine with Pan_dataset cross-validation.; No interval assigned unless printed in source cell.; review: method: automated_source_review; date: 2026-09-17; id: part2-esm2-amp-2025-TB3-43ece4a25b; title: real_test PPI held-out evaluation · Table 3; protocol id: paper-protocol-1edc32c80b0223fef1; dataset id: paper-dataset-a825ad55756b359150; metric: Recall; unit: fraction; direction: higher; result ids: paper-result-d6524b05023c42db9b; paper-result-f7a3d9ed37399b3a37; paper-result-ba3011fe28c284b86b; source ids: part2-esm2-amp-2025; source locator: Table 3: Recall, real_test PPI held-out evaluation; context: Complete trained PPI pipelines evaluated on real_test. Paper real_test dataset; Table 3.; caveats: Do not combine with Pan_dataset cross-validation.; No interval assigned unless printed in source cell.; review: method: automated_source_review; date: 2026-09-17; id: part2-esm2-amp-2025-TB3-639b23627b; title: real_test PPI held-out evaluation · Table 3; protocol id: paper-protocol-1edc32c80b0223fef1; dataset id: paper-dataset-a825ad55756b359150; metric: F1 Score; unit: fraction; direction: higher; result ids: paper-result-4f97fb035451eba1c6; paper-result-64ba0415593df539d7; paper-result-fa217cc5798f8af105; source ids: part2-esm2-amp-2025; source locator: Table 3: F1 Score, real_test PPI held-out evaluation; context: Complete trained PPI pipelines evaluated on real_test. Paper real_test dataset; Table 3.; caveats: Do not combine with Pan_dataset cross-validation.; No interval assigned unless printed in source cell.; review: method: automated_source_review; date: 2026-09-17; id: part2-esm2-amp-2025-TB3-8425c57523; title: real_test PPI held-out evaluation · Table 3; protocol id: paper-protocol-1edc32c80b0223fef1; dataset id: paper-dataset-a825ad55756b359150; metric: AUC; unit: fraction; direction: higher; result ids: paper-result-3753a3981ea1aeabec; paper-result-888e32ae1ab2ab63d6; paper-result-71f635574e69fdb267; source ids: part2-esm2-amp-2025; source locator: Table 3: AUC, real_test PPI held-out evaluation; context: Complete trained PPI pipelines evaluated on real_test. Paper real_test dataset; Table 3.; caveats: Do not combine with Pan_dataset cross-validation.; No interval assigned unless printed in source cell.; review: method: automated_source_review; date: 2026-09-17; id: part2-esm2-amp-2025-TB3-52c0496256; title: real_test PPI held-out evaluation · Table 3; protocol id: paper-protocol-1edc32c80b0223fef1; dataset id: paper-dataset-a825ad55756b359150; metric: MCC; unit: dimensionless; direction: higher; result ids: paper-result-c79f5ab35255cb8020; paper-result-4819f0b5707a3da216; paper-result-337efc2e5382ae31b9; source ids: part2-esm2-amp-2025; source locator: Table 3: MCC, real_test PPI held-out evaluation; context: Complete trained PPI pipelines evaluated on real_test. Paper real_test dataset; Table 3.; caveats: Do not combine with Pan_dataset cross-validation.; No interval assigned unless printed in source cell.; review: method: automated_source_review; date: 2026-09-17; id: part2-esm2-amp-2025-TB3-52c4c639e8; title: real_test PPI held-out evaluation · Table 3; protocol id: paper-protocol-1edc32c80b0223fef1; dataset id: paper-dataset-a825ad55756b359150; metric: Precision; unit: fraction; direction: higher; result ids: paper-result-3fe2b44a09889f8fb9; paper-result-f8339dba99e6d18757; paper-result-7361fa18276a31b368; source ids: part2-esm2-amp-2025; source locator: Table 3: Precision, real_test PPI held-out evaluation; context: Complete trained PPI pipelines evaluated on real_test. Paper real_test dataset; Table 3.; caveats: Do not combine with Pan_dataset cross-validation.; 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-esm2-amp-2025; inspected locators: Tables2–4; Pan_dataset/real_test/Bernett evaluation; searched queries: ESM2_AMP: an interpretable framework for protein–protein interactions prediction and biological mechanism discovery 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: esm2-amp-2025; source locator: Methods: Protein–protein interaction datasets; Results: strictly constructed dataset; cached text lines 10–12, 58–59, 67–68; 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: Bernett PPI dataset
benchmark: ESM2_AMPS: protein-protein interaction prediction
evaluates task: real_test PPI held-out evaluation (protein-protein interaction prediction)
evaluates task: Pan_dataset five-fold PPI cross-validation (protein-protein interaction prediction)

Suggest a correction