Protocol

HuRI PPI link prediction, Hits@100 (Table 5)

Evidence concern: excluded from comparisons

The text's summary does not match the tables: it lists ProtT5 among structure embeddings while the tables print ProstT5; it reports a GraphSAGE with DistMult result (+38% Hits@100 on HuRI) although DistMult is not a column; and the stated gains (for example ESM-2 with GraphSAGE +6% Hits@100 on OGBl-ppa) cannot be reproduced from the printed table values (GS random 0.0104, ESM-2 0.2421). Values are kept as printed; comparisons should rely on the tables only after a reviewer has judged this. Random-feature baselines on OGBl-ppa (GCN 0.0588, GS 0.0104 Hits@100) look far below the public OGB leaderboard values the authors say they reproduced (Supplementary Table S2, not retrieved; reviewer did not verify the leaderboard values).The role of protein embeddings for protein-protein interaction prediction with graph neural networks · Results and discussion, first paragraph; Tables 5 and 6

PPI link prediction on HuRI with protein embeddings as GNN node features; Hits@100 as printed in Table 5.

77 evaluations · 77 results

Overview

An explanatory profile has not yet been reviewed for this record.

Consult the linked sources for architecture or protocol details. Missing evidence is not evidence of a missing capability.

77 recorded evaluations, 77 metric rows. A comparison chart has not yet been validated for these results. The table retains the individual findings and their sources.

View coverage and remaining gaps across all benchmarks

Results

Results are available, but no reviewed comparison panel is linked in this release.

All evaluations

77 evaluations · 77 results. Different protocols are not a single leaderboard.

Protocol: HuRI PPI link prediction, Hits@100 (Table 5) · Dataset: HuRI PPI graph (embedding study)

Sorted by Hits at 100 (HuRI PPI link prediction) (higher is better). The best value in each column is highlighted. Decimals are rounded for display; each value links to the printed value and its source.

Tested configuration	Hits at 100 (HuRI PPI link prediction)
GCN with RDF2Vec protein embeddings (function (knowledge-graph embedding)) (PPI embeddings study)Evaluation	0.651 (best in column)
NGNN with GCN combined with SEAL with majority vote across the representations (PPI embeddings study)Evaluation	0.65
NGNN with GCN with RDF2Vec protein embeddings (function (knowledge-graph embedding)) (PPI embeddings study)Evaluation	0.648
NGNN with GCN combined with SEAL with randomly initialised node features (baseline) (PPI embeddings study)Evaluation	0.646
NGNN with GCN combined with SEAL with ESM-2 protein embeddings (sequence) (PPI embeddings study)Evaluation	0.642
NGNN with GCN combined with SEAL with ComplEx protein embeddings (function (knowledge-graph embedding)) (PPI embeddings study)Evaluation	0.641
NGNN with GCN combined with SEAL with ProGen2 protein embeddings (sequence) (PPI embeddings study)Evaluation	0.638
NGNN with GraphSAGE combined with SEAL with PiFold protein embeddings (structure) (PPI embeddings study)Evaluation	0.637
NGNN with GCN combined with SEAL with ESM-IF1 protein embeddings (structure) (PPI embeddings study)Evaluation	0.637
NGNN with GCN combined with SEAL with ProtTrans protein embeddings (sequence) (PPI embeddings study)Evaluation	0.633
NGNN with GraphSAGE combined with SEAL with ESM-IF1 protein embeddings (structure) (PPI embeddings study)Evaluation	0.633
NGNN with GCN combined with SEAL with ProstT5 protein embeddings (structure) (PPI embeddings study)Evaluation	0.633
NGNN with GraphSAGE combined with SEAL with ComplEx protein embeddings (function (knowledge-graph embedding)) (PPI embeddings study)Evaluation	0.631
NGNN with GraphSAGE combined with SEAL with ESM-2 protein embeddings (sequence) (PPI embeddings study)Evaluation	0.63
NGNN with GraphSAGE combined with SEAL with ProtTrans protein embeddings (sequence) (PPI embeddings study)Evaluation	0.63
NGNN with GraphSAGE combined with SEAL with ProstT5 protein embeddings (structure) (PPI embeddings study)Evaluation	0.63
NGNN with GraphSAGE combined with SEAL with majority vote across the representations (PPI embeddings study)Evaluation	0.629
NGNN with GCN combined with SEAL with PiFold protein embeddings (structure) (PPI embeddings study)Evaluation	0.629
NGNN with GraphSAGE combined with SEAL with randomly initialised node features (baseline) (PPI embeddings study)Evaluation	0.629
NGNN with GraphSAGE combined with SEAL with ProGen2 protein embeddings (sequence) (PPI embeddings study)Evaluation	0.628
NGNN with GraphSAGE combined with SEAL with RDF2Vec protein embeddings (function (knowledge-graph embedding)) (PPI embeddings study)Evaluation	0.628
NGNN with GCN combined with SEAL with TransE protein embeddings (function (knowledge-graph embedding)) (PPI embeddings study)Evaluation	0.624
NGNN with GCN combined with SEAL with RDF2Vec protein embeddings (function (knowledge-graph embedding)) (PPI embeddings study)Evaluation	0.617
NGNN with GraphSAGE combined with SEAL with TransE protein embeddings (function (knowledge-graph embedding)) (PPI embeddings study)Evaluation	0.616
NGNN with GraphSAGE with PiFold protein embeddings (structure) (PPI embeddings study)Evaluation	0.612
GCN with ComplEx protein embeddings (function (knowledge-graph embedding)) (PPI embeddings study)Evaluation	0.606
NGNN with GCN with ComplEx protein embeddings (function (knowledge-graph embedding)) (PPI embeddings study)Evaluation	0.594
NGNN with GraphSAGE with RDF2Vec protein embeddings (function (knowledge-graph embedding)) (PPI embeddings study)Evaluation	0.589
GraphSAGE with RDF2Vec protein embeddings (function (knowledge-graph embedding)) (PPI embeddings study)Evaluation	0.582
NGNN with GCN with ESM-IF1 protein embeddings (structure) (PPI embeddings study)Evaluation	0.564
GraphSAGE with ComplEx protein embeddings (function (knowledge-graph embedding)) (PPI embeddings study)Evaluation	0.562
NGNN with GCN with PiFold protein embeddings (structure) (PPI embeddings study)Evaluation	0.561
NGNN with GraphSAGE with ESM-IF1 protein embeddings (structure) (PPI embeddings study)Evaluation	0.556
NGNN with GCN with majority vote across the representations (PPI embeddings study)Evaluation	0.551
NGNN with GCN with randomly initialised node features (baseline) (PPI embeddings study)Evaluation	0.545
NGNN with GraphSAGE with ComplEx protein embeddings (function (knowledge-graph embedding)) (PPI embeddings study)Evaluation	0.529
GCN with majority vote across the representations (PPI embeddings study)Evaluation	0.529
GCN with ESM-IF1 protein embeddings (structure) (PPI embeddings study)Evaluation	0.497
GCN with PiFold protein embeddings (structure) (PPI embeddings study)Evaluation	0.457
GCN with ProGen2 protein embeddings (sequence) (PPI embeddings study)Evaluation	0.454
GCN with ProtTrans protein embeddings (sequence) (PPI embeddings study)Evaluation	0.45
GCN with ProstT5 protein embeddings (structure) (PPI embeddings study)Evaluation	0.447
GCN with ESM-2 protein embeddings (sequence) (PPI embeddings study)Evaluation	0.444
NGNN with GCN with ESM-2 protein embeddings (sequence) (PPI embeddings study)Evaluation	0.442
NGNN with GCN with ProtTrans protein embeddings (sequence) (PPI embeddings study)Evaluation	0.439
NGNN with GCN with ProstT5 protein embeddings (structure) (PPI embeddings study)Evaluation	0.438
GCN with randomly initialised node features (baseline) (PPI embeddings study)Evaluation	0.435
NGNN with GCN with ProGen2 protein embeddings (sequence) (PPI embeddings study)Evaluation	0.433
GCN with TransE protein embeddings (function (knowledge-graph embedding)) (PPI embeddings study)Evaluation	0.432
NGNN with GCN with TransE protein embeddings (function (knowledge-graph embedding)) (PPI embeddings study)Evaluation	0.423
NGNN with GraphSAGE with randomly initialised node features (baseline) (PPI embeddings study)Evaluation	0.418
GraphSAGE with PiFold protein embeddings (structure) (PPI embeddings study)Evaluation	0.412
GraphSAGE with ESM-IF1 protein embeddings (structure) (PPI embeddings study)Evaluation	0.381
MLP on concatenated protein embeddings (protein-only baseline, no network) with RDF2Vec protein embeddings (function (knowledge-graph embedding)) (PPI embeddings study)Evaluation	0.347
GraphSAGE with majority vote across the representations (PPI embeddings study)Evaluation	0.312
NGNN with GraphSAGE with majority vote across the representations (PPI embeddings study)Evaluation	0.289
MLP on concatenated protein embeddings (protein-only baseline, no network) with ComplEx protein embeddings (function (knowledge-graph embedding)) (PPI embeddings study)Evaluation	0.257
MLP on concatenated protein embeddings (protein-only baseline, no network) with TransE protein embeddings (function (knowledge-graph embedding)) (PPI embeddings study)Evaluation	0.209
GraphSAGE with randomly initialised node features (baseline) (PPI embeddings study)Evaluation	0.208
GraphSAGE with ProtTrans protein embeddings (sequence) (PPI embeddings study)Evaluation	0.192
GraphSAGE with ProGen2 protein embeddings (sequence) (PPI embeddings study)Evaluation	0.174
GraphSAGE with ProstT5 protein embeddings (structure) (PPI embeddings study)Evaluation	0.172
MLP on concatenated protein embeddings (protein-only baseline, no network) with ProstT5 protein embeddings (structure) (PPI embeddings study)Evaluation	0.172
MLP on concatenated protein embeddings (protein-only baseline, no network) with ESM-IF1 protein embeddings (structure) (PPI embeddings study)Evaluation	0.171
NGNN with GraphSAGE with ProstT5 protein embeddings (structure) (PPI embeddings study)Evaluation	0.163
MLP on concatenated protein embeddings (protein-only baseline, no network) with PiFold protein embeddings (structure) (PPI embeddings study)Evaluation	0.16
MLP on concatenated protein embeddings (protein-only baseline, no network) with ProtTrans protein embeddings (sequence) (PPI embeddings study)Evaluation	0.141
MLP on concatenated protein embeddings (protein-only baseline, no network) with majority vote across the representations (PPI embeddings study)Evaluation	0.132
NGNN with GraphSAGE with ProGen2 protein embeddings (sequence) (PPI embeddings study)Evaluation	0.126
NGNN with GraphSAGE with ESM-2 protein embeddings (sequence) (PPI embeddings study)Evaluation	0.114
MLP on concatenated protein embeddings (protein-only baseline, no network) with ProGen2 protein embeddings (sequence) (PPI embeddings study)Evaluation	0.111
GraphSAGE with ESM-2 protein embeddings (sequence) (PPI embeddings study)Evaluation	0.108
MLP on concatenated protein embeddings (protein-only baseline, no network) with randomly initialised node features (baseline) (PPI embeddings study)Evaluation	0.105
GraphSAGE with TransE protein embeddings (function (knowledge-graph embedding)) (PPI embeddings study)Evaluation	0.0852
MLP on concatenated protein embeddings (protein-only baseline, no network) with ESM-2 protein embeddings (sequence) (PPI embeddings study)Evaluation	0.0808
NGNN with GraphSAGE with TransE protein embeddings (function (knowledge-graph embedding)) (PPI embeddings study)Evaluation	0.0664
NGNN with GraphSAGE with ProtTrans protein embeddings (sequence) (PPI embeddings study)Evaluation	0.0591

All 77 result rows with coverage, uncertainty and sources

Filter evaluations

Tested model or methodProtocolDatasetEvaluation setupMetricEvidence origin

Applied filters: All linked evaluations

Exact evaluated configurations and original reported results
Tested configuration	Protocol and dataset	Finding	Evidence and details
Configuration: GCN with ComplEx protein embeddings (function (knowledge-graph embedding)) (PPI embeddings study)	Protocol: HuRI PPI link prediction, Hits@100 (Table 5) Dataset: HuRI PPI graph (embedding study)	0.606 Hits at 100 (HuRI PPI link prediction) fraction · higher Uncertainty: Not reported by the source: Only a table-wide maximum SD is printed (Table 5/6 footnote) Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons The text's summary does not match the tables: it lists ProtT5 among structure embeddings while the tables print ProstT5; it reports a GraphSAGE with DistMult result (+38% Hits@100 on HuRI) although DistMult is not a column; and the stated gains (for example ESM-2 with GraphSAGE +6% Hits@100 on OGBl-ppa) cannot be reproduced from the printed table values (GS random 0.0104, ESM-2 0.2421). Values are kept as printed; comparisons should rely on the tables only after a reviewer has judged this. Random-feature baselines on OGBl-ppa (GCN 0.0588, GS 0.0104 Hits@100) look far below the public OGB leaderboard values the authors say they reproduced (Supplementary Table S2, not retrieved; reviewer did not verify the leaderboard values).The role of protein embeddings for protein-protein interaction prediction with graph neural networks · Results and discussion, first paragraph; Tables 5 and 6 Methods, coverage and source GCN / ComplEx on HuRI (Hits@100) lit-interactions-20261011-ppiemb-protocol-huri-hits-100 Aggregation: Not reported The role of protein embeddings for protein-protein interaction prediction with graph neural networks · Table 5, block 'HuRI', row 'GCN', column 'ComplEx'
Configuration: GCN with majority vote across the representations (PPI embeddings study)	Protocol: HuRI PPI link prediction, Hits@100 (Table 5) Dataset: HuRI PPI graph (embedding study)	0.529 Hits at 100 (HuRI PPI link prediction) fraction · higher Uncertainty: Not reported by the source: Only a table-wide maximum SD is printed (Table 5/6 footnote) Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Evidence concern: excluded from comparisons The text's summary does not match the tables: it lists ProtT5 among structure embeddings while the tables print ProstT5; it reports a GraphSAGE with DistMult result (+38% Hits@100 on HuRI) although DistMult is not a column; and the stated gains (for example ESM-2 with GraphSAGE +6% Hits@100 on OGBl-ppa) cannot be reproduced from the printed table values (GS random 0.0104, ESM-2 0.2421). Values are kept as printed; comparisons should rely on the tables only after a reviewer has judged this. Random-feature baselines on OGBl-ppa (GCN 0.0588, GS 0.0104 Hits@100) look far below the public OGB leaderboard values the authors say they reproduced (Supplementary Table S2, not retrieved; reviewer did not verify the leaderboard values).The role of protein embeddings for protein-protein interaction prediction with graph neural networks · Results and discussion, first paragraph; Tables 5 and 6 Methods, coverage and source GCN / Ensemble on HuRI (Hits@100) lit-interactions-20261011-ppiemb-protocol-huri-hits-100 Aggregation: Not reported The role of protein embeddings for protein-protein interaction prediction with graph neural networks · Table 5, block 'HuRI', row 'GCN', column 'Ensemble'
Configuration: GCN with ESM-2 protein embeddings (sequence) (PPI embeddings study)	Protocol: HuRI PPI link prediction, Hits@100 (Table 5) Dataset: HuRI PPI graph (embedding study)	0.444 Hits at 100 (HuRI PPI link prediction) fraction · higher Uncertainty: Not reported by the source: Only a table-wide maximum SD is printed (Table 5/6 footnote) Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons The text's summary does not match the tables: it lists ProtT5 among structure embeddings while the tables print ProstT5; it reports a GraphSAGE with DistMult result (+38% Hits@100 on HuRI) although DistMult is not a column; and the stated gains (for example ESM-2 with GraphSAGE +6% Hits@100 on OGBl-ppa) cannot be reproduced from the printed table values (GS random 0.0104, ESM-2 0.2421). Values are kept as printed; comparisons should rely on the tables only after a reviewer has judged this. Random-feature baselines on OGBl-ppa (GCN 0.0588, GS 0.0104 Hits@100) look far below the public OGB leaderboard values the authors say they reproduced (Supplementary Table S2, not retrieved; reviewer did not verify the leaderboard values).The role of protein embeddings for protein-protein interaction prediction with graph neural networks · Results and discussion, first paragraph; Tables 5 and 6 Methods, coverage and source GCN / ESM-2 on HuRI (Hits@100) lit-interactions-20261011-ppiemb-protocol-huri-hits-100 Aggregation: Not reported The role of protein embeddings for protein-protein interaction prediction with graph neural networks · Table 5, block 'HuRI', row 'GCN', column 'ESM-2'
Configuration: GCN with ESM-IF1 protein embeddings (structure) (PPI embeddings study)	Protocol: HuRI PPI link prediction, Hits@100 (Table 5) Dataset: HuRI PPI graph (embedding study)	0.497 Hits at 100 (HuRI PPI link prediction) fraction · higher Uncertainty: Not reported by the source: Only a table-wide maximum SD is printed (Table 5/6 footnote) Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons The text's summary does not match the tables: it lists ProtT5 among structure embeddings while the tables print ProstT5; it reports a GraphSAGE with DistMult result (+38% Hits@100 on HuRI) although DistMult is not a column; and the stated gains (for example ESM-2 with GraphSAGE +6% Hits@100 on OGBl-ppa) cannot be reproduced from the printed table values (GS random 0.0104, ESM-2 0.2421). Values are kept as printed; comparisons should rely on the tables only after a reviewer has judged this. Random-feature baselines on OGBl-ppa (GCN 0.0588, GS 0.0104 Hits@100) look far below the public OGB leaderboard values the authors say they reproduced (Supplementary Table S2, not retrieved; reviewer did not verify the leaderboard values).The role of protein embeddings for protein-protein interaction prediction with graph neural networks · Results and discussion, first paragraph; Tables 5 and 6 Methods, coverage and source GCN / ESM-IF1 on HuRI (Hits@100) lit-interactions-20261011-ppiemb-protocol-huri-hits-100 Aggregation: Not reported The role of protein embeddings for protein-protein interaction prediction with graph neural networks · Table 5, block 'HuRI', row 'GCN', column 'ESM-IF1'
Configuration: GCN with PiFold protein embeddings (structure) (PPI embeddings study)	Protocol: HuRI PPI link prediction, Hits@100 (Table 5) Dataset: HuRI PPI graph (embedding study)	0.457 Hits at 100 (HuRI PPI link prediction) fraction · higher Uncertainty: Not reported by the source: Only a table-wide maximum SD is printed (Table 5/6 footnote) Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons The text's summary does not match the tables: it lists ProtT5 among structure embeddings while the tables print ProstT5; it reports a GraphSAGE with DistMult result (+38% Hits@100 on HuRI) although DistMult is not a column; and the stated gains (for example ESM-2 with GraphSAGE +6% Hits@100 on OGBl-ppa) cannot be reproduced from the printed table values (GS random 0.0104, ESM-2 0.2421). Values are kept as printed; comparisons should rely on the tables only after a reviewer has judged this. Random-feature baselines on OGBl-ppa (GCN 0.0588, GS 0.0104 Hits@100) look far below the public OGB leaderboard values the authors say they reproduced (Supplementary Table S2, not retrieved; reviewer did not verify the leaderboard values).The role of protein embeddings for protein-protein interaction prediction with graph neural networks · Results and discussion, first paragraph; Tables 5 and 6 Methods, coverage and source GCN / PiFold on HuRI (Hits@100) lit-interactions-20261011-ppiemb-protocol-huri-hits-100 Aggregation: Not reported The role of protein embeddings for protein-protein interaction prediction with graph neural networks · Table 5, block 'HuRI', row 'GCN', column 'PiFold'
Configuration: GCN with ProGen2 protein embeddings (sequence) (PPI embeddings study)	Protocol: HuRI PPI link prediction, Hits@100 (Table 5) Dataset: HuRI PPI graph (embedding study)	0.454 Hits at 100 (HuRI PPI link prediction) fraction · higher Uncertainty: Not reported by the source: Only a table-wide maximum SD is printed (Table 5/6 footnote) Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons The text's summary does not match the tables: it lists ProtT5 among structure embeddings while the tables print ProstT5; it reports a GraphSAGE with DistMult result (+38% Hits@100 on HuRI) although DistMult is not a column; and the stated gains (for example ESM-2 with GraphSAGE +6% Hits@100 on OGBl-ppa) cannot be reproduced from the printed table values (GS random 0.0104, ESM-2 0.2421). Values are kept as printed; comparisons should rely on the tables only after a reviewer has judged this. Random-feature baselines on OGBl-ppa (GCN 0.0588, GS 0.0104 Hits@100) look far below the public OGB leaderboard values the authors say they reproduced (Supplementary Table S2, not retrieved; reviewer did not verify the leaderboard values).The role of protein embeddings for protein-protein interaction prediction with graph neural networks · Results and discussion, first paragraph; Tables 5 and 6 Methods, coverage and source GCN / ProGen2 on HuRI (Hits@100) lit-interactions-20261011-ppiemb-protocol-huri-hits-100 Aggregation: Not reported The role of protein embeddings for protein-protein interaction prediction with graph neural networks · Table 5, block 'HuRI', row 'GCN', column 'ProGen2'
Configuration: GCN with ProstT5 protein embeddings (structure) (PPI embeddings study)	Protocol: HuRI PPI link prediction, Hits@100 (Table 5) Dataset: HuRI PPI graph (embedding study)	0.447 Hits at 100 (HuRI PPI link prediction) fraction · higher Uncertainty: Not reported by the source: Only a table-wide maximum SD is printed (Table 5/6 footnote) Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons The text's summary does not match the tables: it lists ProtT5 among structure embeddings while the tables print ProstT5; it reports a GraphSAGE with DistMult result (+38% Hits@100 on HuRI) although DistMult is not a column; and the stated gains (for example ESM-2 with GraphSAGE +6% Hits@100 on OGBl-ppa) cannot be reproduced from the printed table values (GS random 0.0104, ESM-2 0.2421). Values are kept as printed; comparisons should rely on the tables only after a reviewer has judged this. Random-feature baselines on OGBl-ppa (GCN 0.0588, GS 0.0104 Hits@100) look far below the public OGB leaderboard values the authors say they reproduced (Supplementary Table S2, not retrieved; reviewer did not verify the leaderboard values).The role of protein embeddings for protein-protein interaction prediction with graph neural networks · Results and discussion, first paragraph; Tables 5 and 6 Methods, coverage and source GCN / ProstT5 on HuRI (Hits@100) lit-interactions-20261011-ppiemb-protocol-huri-hits-100 Aggregation: Not reported The role of protein embeddings for protein-protein interaction prediction with graph neural networks · Table 5, block 'HuRI', row 'GCN', column 'ProstT5'
Configuration: GCN with ProtTrans protein embeddings (sequence) (PPI embeddings study)	Protocol: HuRI PPI link prediction, Hits@100 (Table 5) Dataset: HuRI PPI graph (embedding study)	0.45 Hits at 100 (HuRI PPI link prediction) fraction · higher Uncertainty: Not reported by the source: Only a table-wide maximum SD is printed (Table 5/6 footnote) Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons The text's summary does not match the tables: it lists ProtT5 among structure embeddings while the tables print ProstT5; it reports a GraphSAGE with DistMult result (+38% Hits@100 on HuRI) although DistMult is not a column; and the stated gains (for example ESM-2 with GraphSAGE +6% Hits@100 on OGBl-ppa) cannot be reproduced from the printed table values (GS random 0.0104, ESM-2 0.2421). Values are kept as printed; comparisons should rely on the tables only after a reviewer has judged this. Random-feature baselines on OGBl-ppa (GCN 0.0588, GS 0.0104 Hits@100) look far below the public OGB leaderboard values the authors say they reproduced (Supplementary Table S2, not retrieved; reviewer did not verify the leaderboard values).The role of protein embeddings for protein-protein interaction prediction with graph neural networks · Results and discussion, first paragraph; Tables 5 and 6 Methods, coverage and source GCN / ProtTrans on HuRI (Hits@100) lit-interactions-20261011-ppiemb-protocol-huri-hits-100 Aggregation: Not reported The role of protein embeddings for protein-protein interaction prediction with graph neural networks · Table 5, block 'HuRI', row 'GCN', column 'ProtTrans'
Configuration: GCN with randomly initialised node features (baseline) (PPI embeddings study)	Protocol: HuRI PPI link prediction, Hits@100 (Table 5) Dataset: HuRI PPI graph (embedding study)	0.435 Hits at 100 (HuRI PPI link prediction) fraction · higher Uncertainty: Not reported by the source: Only a table-wide maximum SD is printed (Table 5/6 footnote) Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons The text's summary does not match the tables: it lists ProtT5 among structure embeddings while the tables print ProstT5; it reports a GraphSAGE with DistMult result (+38% Hits@100 on HuRI) although DistMult is not a column; and the stated gains (for example ESM-2 with GraphSAGE +6% Hits@100 on OGBl-ppa) cannot be reproduced from the printed table values (GS random 0.0104, ESM-2 0.2421). Values are kept as printed; comparisons should rely on the tables only after a reviewer has judged this. Random-feature baselines on OGBl-ppa (GCN 0.0588, GS 0.0104 Hits@100) look far below the public OGB leaderboard values the authors say they reproduced (Supplementary Table S2, not retrieved; reviewer did not verify the leaderboard values).The role of protein embeddings for protein-protein interaction prediction with graph neural networks · Results and discussion, first paragraph; Tables 5 and 6 Methods, coverage and source GCN / Random on HuRI (Hits@100) lit-interactions-20261011-ppiemb-protocol-huri-hits-100 Aggregation: Not reported The role of protein embeddings for protein-protein interaction prediction with graph neural networks · Table 5, block 'HuRI', row 'GCN', column 'Random'
Configuration: GCN with RDF2Vec protein embeddings (function (knowledge-graph embedding)) (PPI embeddings study)	Protocol: HuRI PPI link prediction, Hits@100 (Table 5) Dataset: HuRI PPI graph (embedding study)	0.651 Hits at 100 (HuRI PPI link prediction) fraction · higher Uncertainty: Not reported by the source: Only a table-wide maximum SD is printed (Table 5/6 footnote) Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons The text's summary does not match the tables: it lists ProtT5 among structure embeddings while the tables print ProstT5; it reports a GraphSAGE with DistMult result (+38% Hits@100 on HuRI) although DistMult is not a column; and the stated gains (for example ESM-2 with GraphSAGE +6% Hits@100 on OGBl-ppa) cannot be reproduced from the printed table values (GS random 0.0104, ESM-2 0.2421). Values are kept as printed; comparisons should rely on the tables only after a reviewer has judged this. Random-feature baselines on OGBl-ppa (GCN 0.0588, GS 0.0104 Hits@100) look far below the public OGB leaderboard values the authors say they reproduced (Supplementary Table S2, not retrieved; reviewer did not verify the leaderboard values).The role of protein embeddings for protein-protein interaction prediction with graph neural networks · Results and discussion, first paragraph; Tables 5 and 6 Methods, coverage and source GCN / RDF2Vec on HuRI (Hits@100) lit-interactions-20261011-ppiemb-protocol-huri-hits-100 Aggregation: Not reported The role of protein embeddings for protein-protein interaction prediction with graph neural networks · Table 5, block 'HuRI', row 'GCN', column 'RDF2Vec'
Configuration: GCN with TransE protein embeddings (function (knowledge-graph embedding)) (PPI embeddings study)	Protocol: HuRI PPI link prediction, Hits@100 (Table 5) Dataset: HuRI PPI graph (embedding study)	0.432 Hits at 100 (HuRI PPI link prediction) fraction · higher Uncertainty: Not reported by the source: Only a table-wide maximum SD is printed (Table 5/6 footnote) Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons The text's summary does not match the tables: it lists ProtT5 among structure embeddings while the tables print ProstT5; it reports a GraphSAGE with DistMult result (+38% Hits@100 on HuRI) although DistMult is not a column; and the stated gains (for example ESM-2 with GraphSAGE +6% Hits@100 on OGBl-ppa) cannot be reproduced from the printed table values (GS random 0.0104, ESM-2 0.2421). Values are kept as printed; comparisons should rely on the tables only after a reviewer has judged this. Random-feature baselines on OGBl-ppa (GCN 0.0588, GS 0.0104 Hits@100) look far below the public OGB leaderboard values the authors say they reproduced (Supplementary Table S2, not retrieved; reviewer did not verify the leaderboard values).The role of protein embeddings for protein-protein interaction prediction with graph neural networks · Results and discussion, first paragraph; Tables 5 and 6 Methods, coverage and source GCN / TransE on HuRI (Hits@100) lit-interactions-20261011-ppiemb-protocol-huri-hits-100 Aggregation: Not reported The role of protein embeddings for protein-protein interaction prediction with graph neural networks · Table 5, block 'HuRI', row 'GCN', column 'TransE'
Configuration: GraphSAGE with ComplEx protein embeddings (function (knowledge-graph embedding)) (PPI embeddings study)	Protocol: HuRI PPI link prediction, Hits@100 (Table 5) Dataset: HuRI PPI graph (embedding study)	0.562 Hits at 100 (HuRI PPI link prediction) fraction · higher Uncertainty: Not reported by the source: Only a table-wide maximum SD is printed (Table 5/6 footnote) Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons The text's summary does not match the tables: it lists ProtT5 among structure embeddings while the tables print ProstT5; it reports a GraphSAGE with DistMult result (+38% Hits@100 on HuRI) although DistMult is not a column; and the stated gains (for example ESM-2 with GraphSAGE +6% Hits@100 on OGBl-ppa) cannot be reproduced from the printed table values (GS random 0.0104, ESM-2 0.2421). Values are kept as printed; comparisons should rely on the tables only after a reviewer has judged this. Random-feature baselines on OGBl-ppa (GCN 0.0588, GS 0.0104 Hits@100) look far below the public OGB leaderboard values the authors say they reproduced (Supplementary Table S2, not retrieved; reviewer did not verify the leaderboard values).The role of protein embeddings for protein-protein interaction prediction with graph neural networks · Results and discussion, first paragraph; Tables 5 and 6 Methods, coverage and source GraphSAGE / ComplEx on HuRI (Hits@100) lit-interactions-20261011-ppiemb-protocol-huri-hits-100 Aggregation: Not reported The role of protein embeddings for protein-protein interaction prediction with graph neural networks · Table 5, block 'HuRI', row 'GS', column 'ComplEx'
Configuration: GraphSAGE with majority vote across the representations (PPI embeddings study)	Protocol: HuRI PPI link prediction, Hits@100 (Table 5) Dataset: HuRI PPI graph (embedding study)	0.312 Hits at 100 (HuRI PPI link prediction) fraction · higher Uncertainty: Not reported by the source: Only a table-wide maximum SD is printed (Table 5/6 footnote) Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Evidence concern: excluded from comparisons The text's summary does not match the tables: it lists ProtT5 among structure embeddings while the tables print ProstT5; it reports a GraphSAGE with DistMult result (+38% Hits@100 on HuRI) although DistMult is not a column; and the stated gains (for example ESM-2 with GraphSAGE +6% Hits@100 on OGBl-ppa) cannot be reproduced from the printed table values (GS random 0.0104, ESM-2 0.2421). Values are kept as printed; comparisons should rely on the tables only after a reviewer has judged this. Random-feature baselines on OGBl-ppa (GCN 0.0588, GS 0.0104 Hits@100) look far below the public OGB leaderboard values the authors say they reproduced (Supplementary Table S2, not retrieved; reviewer did not verify the leaderboard values).The role of protein embeddings for protein-protein interaction prediction with graph neural networks · Results and discussion, first paragraph; Tables 5 and 6 Methods, coverage and source GraphSAGE / Ensemble on HuRI (Hits@100) lit-interactions-20261011-ppiemb-protocol-huri-hits-100 Aggregation: Not reported The role of protein embeddings for protein-protein interaction prediction with graph neural networks · Table 5, block 'HuRI', row 'GS', column 'Ensemble'
Configuration: GraphSAGE with ESM-2 protein embeddings (sequence) (PPI embeddings study)	Protocol: HuRI PPI link prediction, Hits@100 (Table 5) Dataset: HuRI PPI graph (embedding study)	0.108 Hits at 100 (HuRI PPI link prediction) fraction · higher Uncertainty: Not reported by the source: Only a table-wide maximum SD is printed (Table 5/6 footnote) Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons The text's summary does not match the tables: it lists ProtT5 among structure embeddings while the tables print ProstT5; it reports a GraphSAGE with DistMult result (+38% Hits@100 on HuRI) although DistMult is not a column; and the stated gains (for example ESM-2 with GraphSAGE +6% Hits@100 on OGBl-ppa) cannot be reproduced from the printed table values (GS random 0.0104, ESM-2 0.2421). Values are kept as printed; comparisons should rely on the tables only after a reviewer has judged this. Random-feature baselines on OGBl-ppa (GCN 0.0588, GS 0.0104 Hits@100) look far below the public OGB leaderboard values the authors say they reproduced (Supplementary Table S2, not retrieved; reviewer did not verify the leaderboard values).The role of protein embeddings for protein-protein interaction prediction with graph neural networks · Results and discussion, first paragraph; Tables 5 and 6 Methods, coverage and source GraphSAGE / ESM-2 on HuRI (Hits@100) lit-interactions-20261011-ppiemb-protocol-huri-hits-100 Aggregation: Not reported The role of protein embeddings for protein-protein interaction prediction with graph neural networks · Table 5, block 'HuRI', row 'GS', column 'ESM-2'
Configuration: GraphSAGE with ESM-IF1 protein embeddings (structure) (PPI embeddings study)	Protocol: HuRI PPI link prediction, Hits@100 (Table 5) Dataset: HuRI PPI graph (embedding study)	0.381 Hits at 100 (HuRI PPI link prediction) fraction · higher Uncertainty: Not reported by the source: Only a table-wide maximum SD is printed (Table 5/6 footnote) Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons The text's summary does not match the tables: it lists ProtT5 among structure embeddings while the tables print ProstT5; it reports a GraphSAGE with DistMult result (+38% Hits@100 on HuRI) although DistMult is not a column; and the stated gains (for example ESM-2 with GraphSAGE +6% Hits@100 on OGBl-ppa) cannot be reproduced from the printed table values (GS random 0.0104, ESM-2 0.2421). Values are kept as printed; comparisons should rely on the tables only after a reviewer has judged this. Random-feature baselines on OGBl-ppa (GCN 0.0588, GS 0.0104 Hits@100) look far below the public OGB leaderboard values the authors say they reproduced (Supplementary Table S2, not retrieved; reviewer did not verify the leaderboard values).The role of protein embeddings for protein-protein interaction prediction with graph neural networks · Results and discussion, first paragraph; Tables 5 and 6 Methods, coverage and source GraphSAGE / ESM-IF1 on HuRI (Hits@100) lit-interactions-20261011-ppiemb-protocol-huri-hits-100 Aggregation: Not reported The role of protein embeddings for protein-protein interaction prediction with graph neural networks · Table 5, block 'HuRI', row 'GS', column 'ESM-IF1'
Configuration: GraphSAGE with PiFold protein embeddings (structure) (PPI embeddings study)	Protocol: HuRI PPI link prediction, Hits@100 (Table 5) Dataset: HuRI PPI graph (embedding study)	0.412 Hits at 100 (HuRI PPI link prediction) fraction · higher Uncertainty: Not reported by the source: Only a table-wide maximum SD is printed (Table 5/6 footnote) Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons The text's summary does not match the tables: it lists ProtT5 among structure embeddings while the tables print ProstT5; it reports a GraphSAGE with DistMult result (+38% Hits@100 on HuRI) although DistMult is not a column; and the stated gains (for example ESM-2 with GraphSAGE +6% Hits@100 on OGBl-ppa) cannot be reproduced from the printed table values (GS random 0.0104, ESM-2 0.2421). Values are kept as printed; comparisons should rely on the tables only after a reviewer has judged this. Random-feature baselines on OGBl-ppa (GCN 0.0588, GS 0.0104 Hits@100) look far below the public OGB leaderboard values the authors say they reproduced (Supplementary Table S2, not retrieved; reviewer did not verify the leaderboard values).The role of protein embeddings for protein-protein interaction prediction with graph neural networks · Results and discussion, first paragraph; Tables 5 and 6 Methods, coverage and source GraphSAGE / PiFold on HuRI (Hits@100) lit-interactions-20261011-ppiemb-protocol-huri-hits-100 Aggregation: Not reported The role of protein embeddings for protein-protein interaction prediction with graph neural networks · Table 5, block 'HuRI', row 'GS', column 'PiFold'
Configuration: GraphSAGE with ProGen2 protein embeddings (sequence) (PPI embeddings study)	Protocol: HuRI PPI link prediction, Hits@100 (Table 5) Dataset: HuRI PPI graph (embedding study)	0.174 Hits at 100 (HuRI PPI link prediction) fraction · higher Uncertainty: Not reported by the source: Only a table-wide maximum SD is printed (Table 5/6 footnote) Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons The text's summary does not match the tables: it lists ProtT5 among structure embeddings while the tables print ProstT5; it reports a GraphSAGE with DistMult result (+38% Hits@100 on HuRI) although DistMult is not a column; and the stated gains (for example ESM-2 with GraphSAGE +6% Hits@100 on OGBl-ppa) cannot be reproduced from the printed table values (GS random 0.0104, ESM-2 0.2421). Values are kept as printed; comparisons should rely on the tables only after a reviewer has judged this. Random-feature baselines on OGBl-ppa (GCN 0.0588, GS 0.0104 Hits@100) look far below the public OGB leaderboard values the authors say they reproduced (Supplementary Table S2, not retrieved; reviewer did not verify the leaderboard values).The role of protein embeddings for protein-protein interaction prediction with graph neural networks · Results and discussion, first paragraph; Tables 5 and 6 Methods, coverage and source GraphSAGE / ProGen2 on HuRI (Hits@100) lit-interactions-20261011-ppiemb-protocol-huri-hits-100 Aggregation: Not reported The role of protein embeddings for protein-protein interaction prediction with graph neural networks · Table 5, block 'HuRI', row 'GS', column 'ProGen2'
Configuration: GraphSAGE with ProstT5 protein embeddings (structure) (PPI embeddings study)	Protocol: HuRI PPI link prediction, Hits@100 (Table 5) Dataset: HuRI PPI graph (embedding study)	0.172 Hits at 100 (HuRI PPI link prediction) fraction · higher Uncertainty: Not reported by the source: Only a table-wide maximum SD is printed (Table 5/6 footnote) Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons The text's summary does not match the tables: it lists ProtT5 among structure embeddings while the tables print ProstT5; it reports a GraphSAGE with DistMult result (+38% Hits@100 on HuRI) although DistMult is not a column; and the stated gains (for example ESM-2 with GraphSAGE +6% Hits@100 on OGBl-ppa) cannot be reproduced from the printed table values (GS random 0.0104, ESM-2 0.2421). Values are kept as printed; comparisons should rely on the tables only after a reviewer has judged this. Random-feature baselines on OGBl-ppa (GCN 0.0588, GS 0.0104 Hits@100) look far below the public OGB leaderboard values the authors say they reproduced (Supplementary Table S2, not retrieved; reviewer did not verify the leaderboard values).The role of protein embeddings for protein-protein interaction prediction with graph neural networks · Results and discussion, first paragraph; Tables 5 and 6 Methods, coverage and source GraphSAGE / ProstT5 on HuRI (Hits@100) lit-interactions-20261011-ppiemb-protocol-huri-hits-100 Aggregation: Not reported The role of protein embeddings for protein-protein interaction prediction with graph neural networks · Table 5, block 'HuRI', row 'GS', column 'ProstT5'
Configuration: GraphSAGE with ProtTrans protein embeddings (sequence) (PPI embeddings study)	Protocol: HuRI PPI link prediction, Hits@100 (Table 5) Dataset: HuRI PPI graph (embedding study)	0.192 Hits at 100 (HuRI PPI link prediction) fraction · higher Uncertainty: Not reported by the source: Only a table-wide maximum SD is printed (Table 5/6 footnote) Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons The text's summary does not match the tables: it lists ProtT5 among structure embeddings while the tables print ProstT5; it reports a GraphSAGE with DistMult result (+38% Hits@100 on HuRI) although DistMult is not a column; and the stated gains (for example ESM-2 with GraphSAGE +6% Hits@100 on OGBl-ppa) cannot be reproduced from the printed table values (GS random 0.0104, ESM-2 0.2421). Values are kept as printed; comparisons should rely on the tables only after a reviewer has judged this. Random-feature baselines on OGBl-ppa (GCN 0.0588, GS 0.0104 Hits@100) look far below the public OGB leaderboard values the authors say they reproduced (Supplementary Table S2, not retrieved; reviewer did not verify the leaderboard values).The role of protein embeddings for protein-protein interaction prediction with graph neural networks · Results and discussion, first paragraph; Tables 5 and 6 Methods, coverage and source GraphSAGE / ProtTrans on HuRI (Hits@100) lit-interactions-20261011-ppiemb-protocol-huri-hits-100 Aggregation: Not reported The role of protein embeddings for protein-protein interaction prediction with graph neural networks · Table 5, block 'HuRI', row 'GS', column 'ProtTrans'
Configuration: GraphSAGE with randomly initialised node features (baseline) (PPI embeddings study)	Protocol: HuRI PPI link prediction, Hits@100 (Table 5) Dataset: HuRI PPI graph (embedding study)	0.208 Hits at 100 (HuRI PPI link prediction) fraction · higher Uncertainty: Not reported by the source: Only a table-wide maximum SD is printed (Table 5/6 footnote) Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons The text's summary does not match the tables: it lists ProtT5 among structure embeddings while the tables print ProstT5; it reports a GraphSAGE with DistMult result (+38% Hits@100 on HuRI) although DistMult is not a column; and the stated gains (for example ESM-2 with GraphSAGE +6% Hits@100 on OGBl-ppa) cannot be reproduced from the printed table values (GS random 0.0104, ESM-2 0.2421). Values are kept as printed; comparisons should rely on the tables only after a reviewer has judged this. Random-feature baselines on OGBl-ppa (GCN 0.0588, GS 0.0104 Hits@100) look far below the public OGB leaderboard values the authors say they reproduced (Supplementary Table S2, not retrieved; reviewer did not verify the leaderboard values).The role of protein embeddings for protein-protein interaction prediction with graph neural networks · Results and discussion, first paragraph; Tables 5 and 6 Methods, coverage and source GraphSAGE / Random on HuRI (Hits@100) lit-interactions-20261011-ppiemb-protocol-huri-hits-100 Aggregation: Not reported The role of protein embeddings for protein-protein interaction prediction with graph neural networks · Table 5, block 'HuRI', row 'GS', column 'Random'
Configuration: GraphSAGE with RDF2Vec protein embeddings (function (knowledge-graph embedding)) (PPI embeddings study)	Protocol: HuRI PPI link prediction, Hits@100 (Table 5) Dataset: HuRI PPI graph (embedding study)	0.582 Hits at 100 (HuRI PPI link prediction) fraction · higher Uncertainty: Not reported by the source: Only a table-wide maximum SD is printed (Table 5/6 footnote) Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons The text's summary does not match the tables: it lists ProtT5 among structure embeddings while the tables print ProstT5; it reports a GraphSAGE with DistMult result (+38% Hits@100 on HuRI) although DistMult is not a column; and the stated gains (for example ESM-2 with GraphSAGE +6% Hits@100 on OGBl-ppa) cannot be reproduced from the printed table values (GS random 0.0104, ESM-2 0.2421). Values are kept as printed; comparisons should rely on the tables only after a reviewer has judged this. Random-feature baselines on OGBl-ppa (GCN 0.0588, GS 0.0104 Hits@100) look far below the public OGB leaderboard values the authors say they reproduced (Supplementary Table S2, not retrieved; reviewer did not verify the leaderboard values).The role of protein embeddings for protein-protein interaction prediction with graph neural networks · Results and discussion, first paragraph; Tables 5 and 6 Methods, coverage and source GraphSAGE / RDF2Vec on HuRI (Hits@100) lit-interactions-20261011-ppiemb-protocol-huri-hits-100 Aggregation: Not reported The role of protein embeddings for protein-protein interaction prediction with graph neural networks · Table 5, block 'HuRI', row 'GS', column 'RDF2Vec'
Configuration: GraphSAGE with TransE protein embeddings (function (knowledge-graph embedding)) (PPI embeddings study)	Protocol: HuRI PPI link prediction, Hits@100 (Table 5) Dataset: HuRI PPI graph (embedding study)	0.0852 Hits at 100 (HuRI PPI link prediction) fraction · higher Uncertainty: Not reported by the source: Only a table-wide maximum SD is printed (Table 5/6 footnote) Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons The text's summary does not match the tables: it lists ProtT5 among structure embeddings while the tables print ProstT5; it reports a GraphSAGE with DistMult result (+38% Hits@100 on HuRI) although DistMult is not a column; and the stated gains (for example ESM-2 with GraphSAGE +6% Hits@100 on OGBl-ppa) cannot be reproduced from the printed table values (GS random 0.0104, ESM-2 0.2421). Values are kept as printed; comparisons should rely on the tables only after a reviewer has judged this. Random-feature baselines on OGBl-ppa (GCN 0.0588, GS 0.0104 Hits@100) look far below the public OGB leaderboard values the authors say they reproduced (Supplementary Table S2, not retrieved; reviewer did not verify the leaderboard values).The role of protein embeddings for protein-protein interaction prediction with graph neural networks · Results and discussion, first paragraph; Tables 5 and 6 Methods, coverage and source GraphSAGE / TransE on HuRI (Hits@100) lit-interactions-20261011-ppiemb-protocol-huri-hits-100 Aggregation: Not reported The role of protein embeddings for protein-protein interaction prediction with graph neural networks · Table 5, block 'HuRI', row 'GS', column 'TransE'
Configuration: MLP on concatenated protein embeddings (protein-only baseline, no network) with ComplEx protein embeddings (function (knowledge-graph embedding)) (PPI embeddings study)	Protocol: HuRI PPI link prediction, Hits@100 (Table 5) Dataset: HuRI PPI graph (embedding study)	0.257 Hits at 100 (HuRI PPI link prediction) fraction · higher Uncertainty: Not reported by the source: Only a table-wide maximum SD is printed (Table 5/6 footnote) Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons The text's summary does not match the tables: it lists ProtT5 among structure embeddings while the tables print ProstT5; it reports a GraphSAGE with DistMult result (+38% Hits@100 on HuRI) although DistMult is not a column; and the stated gains (for example ESM-2 with GraphSAGE +6% Hits@100 on OGBl-ppa) cannot be reproduced from the printed table values (GS random 0.0104, ESM-2 0.2421). Values are kept as printed; comparisons should rely on the tables only after a reviewer has judged this. Random-feature baselines on OGBl-ppa (GCN 0.0588, GS 0.0104 Hits@100) look far below the public OGB leaderboard values the authors say they reproduced (Supplementary Table S2, not retrieved; reviewer did not verify the leaderboard values).The role of protein embeddings for protein-protein interaction prediction with graph neural networks · Results and discussion, first paragraph; Tables 5 and 6 Methods, coverage and source MLP on concatenated protein embeddings (protein-only baseline, no network) / ComplEx on HuRI (Hits@100) lit-interactions-20261011-ppiemb-protocol-huri-hits-100 Aggregation: Not reported The role of protein embeddings for protein-protein interaction prediction with graph neural networks · Table 5, block 'HuRI', row 'MLP', column 'ComplEx'
Configuration: MLP on concatenated protein embeddings (protein-only baseline, no network) with majority vote across the representations (PPI embeddings study)	Protocol: HuRI PPI link prediction, Hits@100 (Table 5) Dataset: HuRI PPI graph (embedding study)	0.132 Hits at 100 (HuRI PPI link prediction) fraction · higher Uncertainty: Not reported by the source: Only a table-wide maximum SD is printed (Table 5/6 footnote) Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Evidence concern: excluded from comparisons The text's summary does not match the tables: it lists ProtT5 among structure embeddings while the tables print ProstT5; it reports a GraphSAGE with DistMult result (+38% Hits@100 on HuRI) although DistMult is not a column; and the stated gains (for example ESM-2 with GraphSAGE +6% Hits@100 on OGBl-ppa) cannot be reproduced from the printed table values (GS random 0.0104, ESM-2 0.2421). Values are kept as printed; comparisons should rely on the tables only after a reviewer has judged this. Random-feature baselines on OGBl-ppa (GCN 0.0588, GS 0.0104 Hits@100) look far below the public OGB leaderboard values the authors say they reproduced (Supplementary Table S2, not retrieved; reviewer did not verify the leaderboard values).The role of protein embeddings for protein-protein interaction prediction with graph neural networks · Results and discussion, first paragraph; Tables 5 and 6 Methods, coverage and source MLP on concatenated protein embeddings (protein-only baseline, no network) / Ensemble on HuRI (Hits@100) lit-interactions-20261011-ppiemb-protocol-huri-hits-100 Aggregation: Not reported The role of protein embeddings for protein-protein interaction prediction with graph neural networks · Table 5, block 'HuRI', row 'MLP', column 'Ensemble'
Configuration: MLP on concatenated protein embeddings (protein-only baseline, no network) with ESM-2 protein embeddings (sequence) (PPI embeddings study)	Protocol: HuRI PPI link prediction, Hits@100 (Table 5) Dataset: HuRI PPI graph (embedding study)	0.0808 Hits at 100 (HuRI PPI link prediction) fraction · higher Uncertainty: Not reported by the source: Only a table-wide maximum SD is printed (Table 5/6 footnote) Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons The text's summary does not match the tables: it lists ProtT5 among structure embeddings while the tables print ProstT5; it reports a GraphSAGE with DistMult result (+38% Hits@100 on HuRI) although DistMult is not a column; and the stated gains (for example ESM-2 with GraphSAGE +6% Hits@100 on OGBl-ppa) cannot be reproduced from the printed table values (GS random 0.0104, ESM-2 0.2421). Values are kept as printed; comparisons should rely on the tables only after a reviewer has judged this. Random-feature baselines on OGBl-ppa (GCN 0.0588, GS 0.0104 Hits@100) look far below the public OGB leaderboard values the authors say they reproduced (Supplementary Table S2, not retrieved; reviewer did not verify the leaderboard values).The role of protein embeddings for protein-protein interaction prediction with graph neural networks · Results and discussion, first paragraph; Tables 5 and 6 Methods, coverage and source MLP on concatenated protein embeddings (protein-only baseline, no network) / ESM-2 on HuRI (Hits@100) lit-interactions-20261011-ppiemb-protocol-huri-hits-100 Aggregation: Not reported The role of protein embeddings for protein-protein interaction prediction with graph neural networks · Table 5, block 'HuRI', row 'MLP', column 'ESM-2'

Source checking is not independent reproduction. Release 2026-10-22-1b7cf027e4f6.

Methods and evaluation design

Procedure, tasks and evaluated configurations

Recorded evaluations

Each evaluation records what was tested and under which conditions.

Explore all linked results

Baseline coverage

Reference methods help show what a model adds beyond simple controls. We track a null control and a conventional method for each protocol.

0 of 2 active baseline roles have published Rewire measurements in this release. Measurements on a selected protocol do not establish coverage of an entire suite.

No execution recipe linked to this protocol. Recipe availability does not establish a completed evaluation.

Author-reported evaluations: 7
External evaluations: 70

Literature evidence is not a Rewire measurement. Executed but unpublished runs and private review status are not included.

Null control

Proposed control: requires review

Select a task-valid null control after reviewing inputs and metric

Protocol-specific applicability, permitted inputs, access, split, evaluator and execution requirements need review before implementation or execution.

This is a suggested selection rule, not a validated method or a measured score.

Conventional reference

Proposed control: requires review

Select an upstream conventional reference after reviewing the full protocol

Protocol-specific applicability, permitted inputs, access, split, evaluator and execution requirements need review before implementation or execution.

This is a suggested selection rule, not a validated method or a measured score.

Protocol coverage CSV (gzip) · Model evaluation matrix (gzip) · Source table (gzip) · Release and checksums (gzip)

Coverage is derived from release 2026-10-22-1b7cf027e4f6. Source citations describe the original records; they do not validate an unreviewed baseline proposal. No results have been generated by this audit.

Run instructions

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

Strengths, limitations and unresolved questions

Evidence

Source checking verifies the cited claim or transcription. It does not establish independent reproduction.

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.

0 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-10-22-1b7cf027e4f6
Property and statement	Original source and location	Review and provenance

No evidence rows match these filters. Choose another scope or clear the search.

How to read the evidence

Sources and history

Release 2026-10-22-1b7cf027e4f6 · Record review: source checked

1 source record and release history

The role of protein embeddings for protein-protein interaction prediction with graph neural networks · Original source · Briefings in Bioinformatics 2026, bbag313; PMC13280947 full-text XML

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: lit-interactions-20261011-ppiemb-protocol-huri-hits-100

areas: molecular-interactions; proteins-complexes
contexts: research
protocol: HuRI PPI link prediction; Hits@100
version: bbag313
metric: hits-at-100
metric direction: higher
unit: fraction
limitations: The authors ran every configuration; none of the embedding models is theirs.; No per-cell uncertainty or run count is printed; the footnote of Tables 5 and 6 gives only the table-wide maximum standard deviation (0.0711 OGBl-ppa, 0.0928 HuRI).; The MLP row is a protein-only binary classifier on concatenated embeddings, not a GNN.; The text's summary of gains does not match the printed values; see the source's evidence concern.
source locator: Table 5, block 'HuRI'

Related records

part of: Protein embeddings for GNN PPI prediction (OGBl-ppa and HuRI)
uses data: HuRI PPI graph (embedding study)
assessment: GCN / ComplEx on HuRI (Hits@100)
assessment: GCN / Ensemble on HuRI (Hits@100)
assessment: GCN / ESM-2 on HuRI (Hits@100)
assessment: GCN / ESM-IF1 on HuRI (Hits@100)
assessment: GCN / PiFold on HuRI (Hits@100)
assessment: GCN / ProGen2 on HuRI (Hits@100)
assessment: GCN / ProstT5 on HuRI (Hits@100)
assessment: GCN / ProtTrans on HuRI (Hits@100)
assessment: GCN / Random on HuRI (Hits@100)
assessment: GCN / RDF2Vec on HuRI (Hits@100)
assessment: GCN / TransE on HuRI (Hits@100)
assessment: GraphSAGE / ComplEx on HuRI (Hits@100)
assessment: GraphSAGE / Ensemble on HuRI (Hits@100)
assessment: GraphSAGE / ESM-2 on HuRI (Hits@100)
assessment: GraphSAGE / ESM-IF1 on HuRI (Hits@100)
assessment: GraphSAGE / PiFold on HuRI (Hits@100)
assessment: GraphSAGE / ProGen2 on HuRI (Hits@100)
assessment: GraphSAGE / ProstT5 on HuRI (Hits@100)
assessment: GraphSAGE / ProtTrans on HuRI (Hits@100)
assessment: GraphSAGE / Random on HuRI (Hits@100)
assessment: GraphSAGE / RDF2Vec on HuRI (Hits@100)
assessment: GraphSAGE / TransE on HuRI (Hits@100)
assessment: MLP on concatenated protein embeddings (protein-only baseline, no network) / ComplEx on HuRI (Hits@100)
assessment: MLP on concatenated protein embeddings (protein-only baseline, no network) / Ensemble on HuRI (Hits@100)
assessment: MLP on concatenated protein embeddings (protein-only baseline, no network) / ESM-2 on HuRI (Hits@100)
assessment: MLP on concatenated protein embeddings (protein-only baseline, no network) / ESM-IF1 on HuRI (Hits@100)
assessment: MLP on concatenated protein embeddings (protein-only baseline, no network) / PiFold on HuRI (Hits@100)
assessment: MLP on concatenated protein embeddings (protein-only baseline, no network) / ProGen2 on HuRI (Hits@100)
assessment: MLP on concatenated protein embeddings (protein-only baseline, no network) / ProstT5 on HuRI (Hits@100)
assessment: MLP on concatenated protein embeddings (protein-only baseline, no network) / ProtTrans on HuRI (Hits@100)
assessment: MLP on concatenated protein embeddings (protein-only baseline, no network) / Random on HuRI (Hits@100)
assessment: MLP on concatenated protein embeddings (protein-only baseline, no network) / RDF2Vec on HuRI (Hits@100)
assessment: MLP on concatenated protein embeddings (protein-only baseline, no network) / TransE on HuRI (Hits@100)
assessment: NGNN with GCN / ComplEx on HuRI (Hits@100)
assessment: NGNN with GCN / Ensemble on HuRI (Hits@100)
assessment: NGNN with GCN / ESM-2 on HuRI (Hits@100)
assessment: NGNN with GCN / ESM-IF1 on HuRI (Hits@100)
assessment: NGNN with GCN / PiFold on HuRI (Hits@100)
assessment: NGNN with GCN combined with SEAL / ComplEx on HuRI (Hits@100)
assessment: NGNN with GCN combined with SEAL / Ensemble on HuRI (Hits@100)
assessment: NGNN with GCN combined with SEAL / ESM-2 on HuRI (Hits@100)
assessment: NGNN with GCN combined with SEAL / ESM-IF1 on HuRI (Hits@100)
assessment: NGNN with GCN combined with SEAL / PiFold on HuRI (Hits@100)
assessment: NGNN with GCN combined with SEAL / ProGen2 on HuRI (Hits@100)
assessment: NGNN with GCN combined with SEAL / ProstT5 on HuRI (Hits@100)
assessment: NGNN with GCN combined with SEAL / ProtTrans on HuRI (Hits@100)
assessment: NGNN with GCN combined with SEAL / Random on HuRI (Hits@100)
assessment: NGNN with GCN combined with SEAL / RDF2Vec on HuRI (Hits@100)
assessment: NGNN with GCN combined with SEAL / TransE on HuRI (Hits@100)
assessment: NGNN with GCN / ProGen2 on HuRI (Hits@100)
assessment: NGNN with GCN / ProstT5 on HuRI (Hits@100)
assessment: NGNN with GCN / ProtTrans on HuRI (Hits@100)
assessment: NGNN with GCN / Random on HuRI (Hits@100)
assessment: NGNN with GCN / RDF2Vec on HuRI (Hits@100)
assessment: NGNN with GCN / TransE on HuRI (Hits@100)
assessment: NGNN with GraphSAGE / ComplEx on HuRI (Hits@100)
assessment: NGNN with GraphSAGE / Ensemble on HuRI (Hits@100)
assessment: NGNN with GraphSAGE / ESM-2 on HuRI (Hits@100)
assessment: NGNN with GraphSAGE / ESM-IF1 on HuRI (Hits@100)
assessment: NGNN with GraphSAGE / PiFold on HuRI (Hits@100)
assessment: NGNN with GraphSAGE combined with SEAL / ComplEx on HuRI (Hits@100)
assessment: NGNN with GraphSAGE combined with SEAL / Ensemble on HuRI (Hits@100)
assessment: NGNN with GraphSAGE combined with SEAL / ESM-2 on HuRI (Hits@100)
assessment: NGNN with GraphSAGE combined with SEAL / ESM-IF1 on HuRI (Hits@100)
assessment: NGNN with GraphSAGE combined with SEAL / PiFold on HuRI (Hits@100)
assessment: NGNN with GraphSAGE combined with SEAL / ProGen2 on HuRI (Hits@100)
assessment: NGNN with GraphSAGE combined with SEAL / ProstT5 on HuRI (Hits@100)
assessment: NGNN with GraphSAGE combined with SEAL / ProtTrans on HuRI (Hits@100)
assessment: NGNN with GraphSAGE combined with SEAL / Random on HuRI (Hits@100)
assessment: NGNN with GraphSAGE combined with SEAL / RDF2Vec on HuRI (Hits@100)
assessment: NGNN with GraphSAGE combined with SEAL / TransE on HuRI (Hits@100)
assessment: NGNN with GraphSAGE / ProGen2 on HuRI (Hits@100)
assessment: NGNN with GraphSAGE / ProstT5 on HuRI (Hits@100)
assessment: NGNN with GraphSAGE / ProtTrans on HuRI (Hits@100)
assessment: NGNN with GraphSAGE / Random on HuRI (Hits@100)
assessment: NGNN with GraphSAGE / RDF2Vec on HuRI (Hits@100)
assessment: NGNN with GraphSAGE / TransE on HuRI (Hits@100)

Suggest a correction