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 metric rows

At a glance

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

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

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

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

Pan_dataset five-fold PPI cross-validation · Table 2

Accuracy (fraction) · Higher values are better for this metric.

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

Evaluation protocol · Pan_dataset five-fold PPI cross-validation

ESM2_AMPS · Configuration · Author-reported evaluation0.9776
ESM2_AMP_CSE · Configuration · Author-reported evaluation0.9787
ESM2_DPM · Configuration · Author-reported evaluation0.9802

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.

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

Values, uncertainty and evidence

Accuracy: original source values
Tested entity	Printed value	Uncertainty	Evidence
ESM2_AMPS · Configuration	0.9776 fraction	Not reported	Author-reported evaluation · source checkedESM2_AMP: an interpretable framework for protein–protein interactions prediction and biological mechanism discovery · Table 2, row ESM2_AMPS, column Accuracy; XML row2 column2
ESM2_AMP_CSE · Configuration	0.9787 fraction	Not reported	Author-reported evaluation · source checkedESM2_AMP: an interpretable framework for protein–protein interactions prediction and biological mechanism discovery · Table 2, row ESM2_AMP_CSE, column Accuracy; XML row3 column2
ESM2_DPM · Configuration	0.9802 fraction	Not reported	Author-reported evaluation · source checkedESM2_AMP: an interpretable framework for protein–protein interactions prediction and biological mechanism discovery · Table 2, row ESM2_DPM, column Accuracy; XML row4 column2

Scope and limitations

Do not combine with real_test or Bernett splits.
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 · 7 evaluations · 34 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
ESM2_AMPS: protein-protein interaction prediction Pipeline: ESM2_AMPSTask: protein-protein interaction predictionDataset: Bernett PPI dataset ESM2-derived embeddings plus paper interaction predictor Author-reported evaluation · Evaluation metadata: needs review
0.68 AUROC Unit: fraction · Direction: unknown	Uncertainty: not reported in legacy extract Scored: Not reported · Eligible: Not reported	source checkedESM2_AMP: an interpretable framework for protein–protein interactions prediction and biological mechanism discovery · Table 4, ESM2_AMPS row, AUROC column Source checking is not independent reproduction.
ESM2_DPM: Pan_dataset five-fold PPI cross-validation Configuration: ESM2_DPMProtocol: Pan_dataset five-fold PPI cross-validation (protein-protein interaction prediction)Dataset: Pan_dataset five-fold PPI cross-validation ESM 2_AMPS, ESM 2_AMP_CSE and ESM 2_DPM evaluated as complete PPI pipelines. Pan_dataset; Table 2 five-fold cross-validation. Author-reported evaluation · Evaluation metadata: needs review
0.9801 F1 Score Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedESM2_AMP: an interpretable framework for protein–protein interactions prediction and biological mechanism discovery · Table 2, row ESM2_DPM, column F1 Score; XML row4 column4 Source checking is not independent reproduction.
0.9959 AUC Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedESM2_AMP: an interpretable framework for protein–protein interactions prediction and biological mechanism discovery · Table 2, row ESM2_DPM, column AUC; XML row4 column5 Source checking is not independent reproduction.
0.9605 MCC Unit: dimensionless · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedESM2_AMP: an interpretable framework for protein–protein interactions prediction and biological mechanism discovery · Table 2, row ESM2_DPM, column MCC; XML row4 column6 Source checking is not independent reproduction.
0.9802 Accuracy Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedESM2_AMP: an interpretable framework for protein–protein interactions prediction and biological mechanism discovery · Table 2, row ESM2_DPM, column Accuracy; XML row4 column2 Source checking is not independent reproduction.
ESM2_AMP_CSE: Pan_dataset five-fold PPI cross-validation Configuration: ESM2_AMP_CSEProtocol: Pan_dataset five-fold PPI cross-validation (protein-protein interaction prediction)Dataset: Pan_dataset five-fold PPI cross-validation ESM 2_AMPS, ESM 2_AMP_CSE and ESM 2_DPM evaluated as complete PPI pipelines. Pan_dataset; Table 2 five-fold cross-validation. Author-reported evaluation · Evaluation metadata: needs review
0.9937 AUC Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedESM2_AMP: an interpretable framework for protein–protein interactions prediction and biological mechanism discovery · Table 2, row ESM2_AMP_CSE, column AUC; XML row3 column5 Source checking is not independent reproduction.
0.974 Recall Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedESM2_AMP: an interpretable framework for protein–protein interactions prediction and biological mechanism discovery · Table 2, row ESM2_AMP_CSE, column Recall; XML row3 column3 Source checking is not independent reproduction.
0.9574 MCC Unit: dimensionless · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedESM2_AMP: an interpretable framework for protein–protein interactions prediction and biological mechanism discovery · Table 2, row ESM2_AMP_CSE, column MCC; XML row3 column6 Source checking is not independent reproduction.
0.9786 F1 Score Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedESM2_AMP: an interpretable framework for protein–protein interactions prediction and biological mechanism discovery · Table 2, row ESM2_AMP_CSE, column F1 Score; XML row3 column4 Source checking is not independent reproduction.
0.9787 Accuracy Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedESM2_AMP: an interpretable framework for protein–protein interactions prediction and biological mechanism discovery · Table 2, row ESM2_AMP_CSE, column Accuracy; XML row3 column2 Source checking is not independent reproduction.
ESM2_DPM: real_test PPI held-out evaluation Configuration: ESM2_DPMProtocol: real_test PPI held-out evaluation (protein-protein interaction prediction)Dataset: real_test PPI held-out evaluation Complete trained PPI pipelines evaluated on real_test. Paper real_test dataset; Table 3. Author-reported evaluation · Evaluation metadata: needs review
0.5733 MCC Unit: dimensionless · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedESM2_AMP: an interpretable framework for protein–protein interactions prediction and biological mechanism discovery · Table 3, row ESM2_DPM, column MCC; XML row4 column6 Source checking is not independent reproduction.
0.7703 Accuracy Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedESM2_AMP: an interpretable framework for protein–protein interactions prediction and biological mechanism discovery · Table 3, row ESM2_DPM, column Accuracy; XML row4 column2 Source checking is not independent reproduction.
0.7767 AUC Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedESM2_AMP: an interpretable framework for protein–protein interactions prediction and biological mechanism discovery · Table 3, row ESM2_DPM, column AUC; XML row4 column5 Source checking is not independent reproduction.
0.7023 Precision Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedESM2_AMP: an interpretable framework for protein–protein interactions prediction and biological mechanism discovery · Table 3, row ESM2_DPM, column Precision; XML row4 column7 Source checking is not independent reproduction.
ESM2_AMPS: real_test PPI held-out evaluation Configuration: ESM2_AMPSProtocol: real_test PPI held-out evaluation (protein-protein interaction prediction)Dataset: real_test PPI held-out evaluation Complete trained PPI pipelines evaluated on real_test. Paper real_test dataset; Table 3. Author-reported evaluation · Evaluation metadata: needs review
0.7932 AUC Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedESM2_AMP: an interpretable framework for protein–protein interactions prediction and biological mechanism discovery · Table 3, row ESM2_AMPS, column AUC; XML row2 column5 Source checking is not independent reproduction.
0.7123 Precision Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedESM2_AMP: an interpretable framework for protein–protein interactions prediction and biological mechanism discovery · Table 3, row ESM2_AMPS, column Precision; XML row2 column7 Source checking is not independent reproduction.
0.8045 F1 Score Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedESM2_AMP: an interpretable framework for protein–protein interactions prediction and biological mechanism discovery · Table 3, row ESM2_AMPS, column F1 Score; XML row2 column4 Source checking is not independent reproduction.
0.7761 Accuracy Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedESM2_AMP: an interpretable framework for protein–protein interactions prediction and biological mechanism discovery · Table 3, row ESM2_AMPS, column Accuracy; XML row2 column2 Source checking is not independent reproduction.
ESM2_AMP_CSE: real_test PPI held-out evaluation Configuration: ESM2_AMP_CSEProtocol: real_test PPI held-out evaluation (protein-protein interaction prediction)Dataset: real_test PPI held-out evaluation Complete trained PPI pipelines evaluated on real_test. Paper real_test dataset; Table 3. Author-reported evaluation · Evaluation metadata: needs review
0.5628 MCC Unit: dimensionless · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedESM2_AMP: an interpretable framework for protein–protein interactions prediction and biological mechanism discovery · Table 3, row ESM2_AMP_CSE, column MCC; XML row3 column6 Source checking is not independent reproduction.
0.7981 F1 Score Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedESM2_AMP: an interpretable framework for protein–protein interactions prediction and biological mechanism discovery · Table 3, row ESM2_AMP_CSE, column F1 Score; XML row3 column4 Source checking is not independent reproduction.
0.8064 AUC Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedESM2_AMP: an interpretable framework for protein–protein interactions prediction and biological mechanism discovery · Table 3, row ESM2_AMP_CSE, column AUC; XML row3 column5 Source checking is not independent reproduction.
0.7665 Accuracy Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedESM2_AMP: an interpretable framework for protein–protein interactions prediction and biological mechanism discovery · Table 3, row ESM2_AMP_CSE, column Accuracy; XML row3 column2 Source checking is not independent reproduction.
ESM2_AMPS: Pan_dataset five-fold PPI cross-validation Configuration: ESM2_AMPSProtocol: Pan_dataset five-fold PPI cross-validation (protein-protein interaction prediction)Dataset: Pan_dataset five-fold PPI cross-validation ESM 2_AMPS, ESM 2_AMP_CSE and ESM 2_DPM evaluated as complete PPI pipelines. Pan_dataset; Table 2 five-fold cross-validation. Author-reported evaluation · Evaluation metadata: needs review
0.9949 AUC Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedESM2_AMP: an interpretable framework for protein–protein interactions prediction and biological mechanism discovery · Table 2, row ESM2_AMPS, column AUC; XML row2 column5 Source checking is not independent reproduction.
0.9553 MCC Unit: dimensionless · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedESM2_AMP: an interpretable framework for protein–protein interactions prediction and biological mechanism discovery · Table 2, row ESM2_AMPS, column MCC; XML row2 column6 Source checking is not independent reproduction.
0.9776 Accuracy Unit: fraction · Direction: higher	Uncertainty: unreported Scored: Not reported · Eligible: Not reported	source checkedESM2_AMP: an interpretable framework for protein–protein interactions prediction and biological mechanism discovery · Table 2, row ESM2_AMPS, column Accuracy; XML row2 column2 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
ESM2_AMP: an interpretable framework for protein–protein interactions prediction and biological mechanism discovery	version of record	Read source DOI: 10.1093/bib/bbaf434

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

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

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

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	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

Release 2026-09-17-d277315f7d76 · 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