Protocol

OGBl-ppa PPI link prediction, Accuracy (Table 6)

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 OGBl-ppa with protein embeddings as GNN node features; Accuracy as printed in Table 6.

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: OGBl-ppa PPI link prediction, Accuracy (Table 6) · Dataset: OGBl-ppa PPI graph (embedding study)

Sorted by Accuracy (OGBl-ppa 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	Accuracy (OGBl-ppa PPI link prediction)
NGNN with GraphSAGE combined with SEAL with RDF2Vec protein embeddings (function (knowledge-graph embedding)) (PPI embeddings study)Evaluation	0.988 (best in column)
NGNN with GraphSAGE combined with SEAL with randomly initialised node features (baseline) (PPI embeddings study)Evaluation	0.987
GCN with ComplEx protein embeddings (function (knowledge-graph embedding)) (PPI embeddings study)Evaluation	0.984
GCN with RDF2Vec protein embeddings (function (knowledge-graph embedding)) (PPI embeddings study)Evaluation	0.982
GCN with ESM-IF1 protein embeddings (structure) (PPI embeddings study)Evaluation	0.981
NGNN with GraphSAGE combined with SEAL with ComplEx protein embeddings (function (knowledge-graph embedding)) (PPI embeddings study)Evaluation	0.981
NGNN with GCN combined with SEAL with ProtTrans protein embeddings (sequence) (PPI embeddings study)Evaluation	0.981
NGNN with GraphSAGE combined with SEAL with ProtTrans protein embeddings (sequence) (PPI embeddings study)Evaluation	0.98
GraphSAGE with RDF2Vec protein embeddings (function (knowledge-graph embedding)) (PPI embeddings study)Evaluation	0.98
NGNN with GraphSAGE with ESM-IF1 protein embeddings (structure) (PPI embeddings study)Evaluation	0.975
GraphSAGE with ComplEx protein embeddings (function (knowledge-graph embedding)) (PPI embeddings study)Evaluation	0.974
NGNN with GraphSAGE combined with SEAL with ESM-2 protein embeddings (sequence) (PPI embeddings study)Evaluation	0.969
GraphSAGE with TransE protein embeddings (function (knowledge-graph embedding)) (PPI embeddings study)Evaluation	0.967
NGNN with GCN combined with SEAL with ESM-2 protein embeddings (sequence) (PPI embeddings study)Evaluation	0.967
GCN with majority vote across the representations (PPI embeddings study)Evaluation	0.942
NGNN with GCN combined with SEAL with ESM-IF1 protein embeddings (structure) (PPI embeddings study)Evaluation	0.941
NGNN with GCN combined with SEAL with ProGen2 protein embeddings (sequence) (PPI embeddings study)Evaluation	0.941
NGNN with GraphSAGE with randomly initialised node features (baseline) (PPI embeddings study)Evaluation	0.939
NGNN with GraphSAGE combined with SEAL with ProGen2 protein embeddings (sequence) (PPI embeddings study)Evaluation	0.935
NGNN with GraphSAGE combined with SEAL with majority vote across the representations (PPI embeddings study)Evaluation	0.934
NGNN with GCN with ESM-2 protein embeddings (sequence) (PPI embeddings study)Evaluation	0.927
NGNN with GraphSAGE combined with SEAL with ESM-IF1 protein embeddings (structure) (PPI embeddings study)Evaluation	0.92
NGNN with GCN with RDF2Vec protein embeddings (function (knowledge-graph embedding)) (PPI embeddings study)Evaluation	0.917
GCN with ProGen2 protein embeddings (sequence) (PPI embeddings study)Evaluation	0.913
NGNN with GCN with ESM-IF1 protein embeddings (structure) (PPI embeddings study)Evaluation	0.911
GraphSAGE with ESM-IF1 protein embeddings (structure) (PPI embeddings study)Evaluation	0.911
NGNN with GCN combined with SEAL with majority vote across the representations (PPI embeddings study)Evaluation	0.911
NGNN with GraphSAGE with ComplEx protein embeddings (function (knowledge-graph embedding)) (PPI embeddings study)Evaluation	0.903
NGNN with GraphSAGE with RDF2Vec protein embeddings (function (knowledge-graph embedding)) (PPI embeddings study)Evaluation	0.902
NGNN with GCN with ComplEx protein embeddings (function (knowledge-graph embedding)) (PPI embeddings study)Evaluation	0.902
GCN with TransE protein embeddings (function (knowledge-graph embedding)) (PPI embeddings study)Evaluation	0.901
NGNN with GraphSAGE combined with SEAL with ProstT5 protein embeddings (structure) (PPI embeddings study)Evaluation	0.899
GCN with PiFold protein embeddings (structure) (PPI embeddings study)Evaluation	0.899
NGNN with GCN combined with SEAL with randomly initialised node features (baseline) (PPI embeddings study)Evaluation	0.896
NGNN with GCN combined with SEAL with PiFold protein embeddings (structure) (PPI embeddings study)Evaluation	0.895
NGNN with GraphSAGE combined with SEAL with PiFold protein embeddings (structure) (PPI embeddings study)Evaluation	0.893
NGNN with GCN with TransE protein embeddings (function (knowledge-graph embedding)) (PPI embeddings study)Evaluation	0.892
NGNN with GCN combined with SEAL with RDF2Vec protein embeddings (function (knowledge-graph embedding)) (PPI embeddings study)Evaluation	0.891
NGNN with GCN combined with SEAL with ComplEx protein embeddings (function (knowledge-graph embedding)) (PPI embeddings study)Evaluation	0.891
NGNN with GraphSAGE with TransE protein embeddings (function (knowledge-graph embedding)) (PPI embeddings study)Evaluation	0.891
NGNN with GraphSAGE combined with SEAL with TransE protein embeddings (function (knowledge-graph embedding)) (PPI embeddings study)Evaluation	0.89
GraphSAGE with majority vote across the representations (PPI embeddings study)Evaluation	0.882
NGNN with GCN with randomly initialised node features (baseline) (PPI embeddings study)Evaluation	0.881
NGNN with GCN with majority vote across the representations (PPI embeddings study)Evaluation	0.874
GCN with ESM-2 protein embeddings (sequence) (PPI embeddings study)Evaluation	0.873
GCN with ProtTrans protein embeddings (sequence) (PPI embeddings study)Evaluation	0.871
NGNN with GCN with PiFold protein embeddings (structure) (PPI embeddings study)Evaluation	0.868
GCN with randomly initialised node features (baseline) (PPI embeddings study)Evaluation	0.867
NGNN with GraphSAGE with PiFold protein embeddings (structure) (PPI embeddings study)Evaluation	0.861
NGNN with GCN combined with SEAL with ProstT5 protein embeddings (structure) (PPI embeddings study)Evaluation	0.861
NGNN with GraphSAGE with majority vote across the representations (PPI embeddings study)Evaluation	0.848
NGNN with GCN combined with SEAL with TransE protein embeddings (function (knowledge-graph embedding)) (PPI embeddings study)Evaluation	0.846
GraphSAGE with PiFold protein embeddings (structure) (PPI embeddings study)Evaluation	0.842
MLP on concatenated protein embeddings (protein-only baseline, no network) with RDF2Vec protein embeddings (function (knowledge-graph embedding)) (PPI embeddings study)Evaluation	0.832
MLP on concatenated protein embeddings (protein-only baseline, no network) with ComplEx protein embeddings (function (knowledge-graph embedding)) (PPI embeddings study)Evaluation	0.815
GCN with ProstT5 protein embeddings (structure) (PPI embeddings study)Evaluation	0.808
NGNN with GCN with ProtTrans protein embeddings (sequence) (PPI embeddings study)Evaluation	0.795
MLP on concatenated protein embeddings (protein-only baseline, no network) with TransE protein embeddings (function (knowledge-graph embedding)) (PPI embeddings study)Evaluation	0.76
NGNN with GCN with ProGen2 protein embeddings (sequence) (PPI embeddings study)Evaluation	0.76
MLP on concatenated protein embeddings (protein-only baseline, no network) with ProtTrans protein embeddings (sequence) (PPI embeddings study)Evaluation	0.748
NGNN with GCN with ProstT5 protein embeddings (structure) (PPI embeddings study)Evaluation	0.734
NGNN with GraphSAGE with ESM-2 protein embeddings (sequence) (PPI embeddings study)Evaluation	0.731
NGNN with GraphSAGE with ProGen2 protein embeddings (sequence) (PPI embeddings study)Evaluation	0.723
GraphSAGE with ProtTrans protein embeddings (sequence) (PPI embeddings study)Evaluation	0.719
GraphSAGE with ProGen2 protein embeddings (sequence) (PPI embeddings study)Evaluation	0.713
MLP on concatenated protein embeddings (protein-only baseline, no network) with majority vote across the representations (PPI embeddings study)Evaluation	0.712
NGNN with GraphSAGE with ProtTrans protein embeddings (sequence) (PPI embeddings study)Evaluation	0.706
MLP on concatenated protein embeddings (protein-only baseline, no network) with randomly initialised node features (baseline) (PPI embeddings study)Evaluation	0.702
MLP on concatenated protein embeddings (protein-only baseline, no network) with ESM-2 protein embeddings (sequence) (PPI embeddings study)Evaluation	0.7
MLP on concatenated protein embeddings (protein-only baseline, no network) with ProGen2 protein embeddings (sequence) (PPI embeddings study)Evaluation	0.7
NGNN with GraphSAGE with ProstT5 protein embeddings (structure) (PPI embeddings study)Evaluation	0.689
GraphSAGE with ESM-2 protein embeddings (sequence) (PPI embeddings study)Evaluation	0.676
GraphSAGE with ProstT5 protein embeddings (structure) (PPI embeddings study)Evaluation	0.659
MLP on concatenated protein embeddings (protein-only baseline, no network) with ESM-IF1 protein embeddings (structure) (PPI embeddings study)Evaluation	0.634
MLP on concatenated protein embeddings (protein-only baseline, no network) with ProstT5 protein embeddings (structure) (PPI embeddings study)Evaluation	0.626
MLP on concatenated protein embeddings (protein-only baseline, no network) with PiFold protein embeddings (structure) (PPI embeddings study)Evaluation	0.619
GraphSAGE with randomly initialised node features (baseline) (PPI embeddings study)Evaluation	0.503

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: OGBl-ppa PPI link prediction, Accuracy (Table 6) Dataset: OGBl-ppa PPI graph (embedding study)	0.984 Accuracy (OGBl-ppa 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 OGBl-ppa (Accuracy) lit-interactions-20261011-ppiemb-protocol-ogbl-ppa-accuracy Aggregation: Not reported The role of protein embeddings for protein-protein interaction prediction with graph neural networks · Table 6, block 'OGBl-ppa', row 'GCN', column 'ComplEx'
Configuration: GCN with majority vote across the representations (PPI embeddings study)	Protocol: OGBl-ppa PPI link prediction, Accuracy (Table 6) Dataset: OGBl-ppa PPI graph (embedding study)	0.942 Accuracy (OGBl-ppa 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 OGBl-ppa (Accuracy) lit-interactions-20261011-ppiemb-protocol-ogbl-ppa-accuracy Aggregation: Not reported The role of protein embeddings for protein-protein interaction prediction with graph neural networks · Table 6, block 'OGBl-ppa', row 'GCN', column 'Ensemble'
Configuration: GCN with ESM-2 protein embeddings (sequence) (PPI embeddings study)	Protocol: OGBl-ppa PPI link prediction, Accuracy (Table 6) Dataset: OGBl-ppa PPI graph (embedding study)	0.873 Accuracy (OGBl-ppa 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 OGBl-ppa (Accuracy) lit-interactions-20261011-ppiemb-protocol-ogbl-ppa-accuracy Aggregation: Not reported The role of protein embeddings for protein-protein interaction prediction with graph neural networks · Table 6, block 'OGBl-ppa', row 'GCN', column 'ESM-2'
Configuration: GCN with ESM-IF1 protein embeddings (structure) (PPI embeddings study)	Protocol: OGBl-ppa PPI link prediction, Accuracy (Table 6) Dataset: OGBl-ppa PPI graph (embedding study)	0.981 Accuracy (OGBl-ppa 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 OGBl-ppa (Accuracy) lit-interactions-20261011-ppiemb-protocol-ogbl-ppa-accuracy Aggregation: Not reported The role of protein embeddings for protein-protein interaction prediction with graph neural networks · Table 6, block 'OGBl-ppa', row 'GCN', column 'ESM-IF1'
Configuration: GCN with PiFold protein embeddings (structure) (PPI embeddings study)	Protocol: OGBl-ppa PPI link prediction, Accuracy (Table 6) Dataset: OGBl-ppa PPI graph (embedding study)	0.899 Accuracy (OGBl-ppa 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 OGBl-ppa (Accuracy) lit-interactions-20261011-ppiemb-protocol-ogbl-ppa-accuracy Aggregation: Not reported The role of protein embeddings for protein-protein interaction prediction with graph neural networks · Table 6, block 'OGBl-ppa', row 'GCN', column 'PiFold'
Configuration: GCN with ProGen2 protein embeddings (sequence) (PPI embeddings study)	Protocol: OGBl-ppa PPI link prediction, Accuracy (Table 6) Dataset: OGBl-ppa PPI graph (embedding study)	0.913 Accuracy (OGBl-ppa 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 OGBl-ppa (Accuracy) lit-interactions-20261011-ppiemb-protocol-ogbl-ppa-accuracy Aggregation: Not reported The role of protein embeddings for protein-protein interaction prediction with graph neural networks · Table 6, block 'OGBl-ppa', row 'GCN', column 'ProGen2'
Configuration: GCN with ProstT5 protein embeddings (structure) (PPI embeddings study)	Protocol: OGBl-ppa PPI link prediction, Accuracy (Table 6) Dataset: OGBl-ppa PPI graph (embedding study)	0.808 Accuracy (OGBl-ppa 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 OGBl-ppa (Accuracy) lit-interactions-20261011-ppiemb-protocol-ogbl-ppa-accuracy Aggregation: Not reported The role of protein embeddings for protein-protein interaction prediction with graph neural networks · Table 6, block 'OGBl-ppa', row 'GCN', column 'ProstT5'
Configuration: GCN with ProtTrans protein embeddings (sequence) (PPI embeddings study)	Protocol: OGBl-ppa PPI link prediction, Accuracy (Table 6) Dataset: OGBl-ppa PPI graph (embedding study)	0.871 Accuracy (OGBl-ppa 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 OGBl-ppa (Accuracy) lit-interactions-20261011-ppiemb-protocol-ogbl-ppa-accuracy Aggregation: Not reported The role of protein embeddings for protein-protein interaction prediction with graph neural networks · Table 6, block 'OGBl-ppa', row 'GCN', column 'ProtTrans'
Configuration: GCN with randomly initialised node features (baseline) (PPI embeddings study)	Protocol: OGBl-ppa PPI link prediction, Accuracy (Table 6) Dataset: OGBl-ppa PPI graph (embedding study)	0.867 Accuracy (OGBl-ppa 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 OGBl-ppa (Accuracy) lit-interactions-20261011-ppiemb-protocol-ogbl-ppa-accuracy Aggregation: Not reported The role of protein embeddings for protein-protein interaction prediction with graph neural networks · Table 6, block 'OGBl-ppa', row 'GCN', column 'Random'
Configuration: GCN with RDF2Vec protein embeddings (function (knowledge-graph embedding)) (PPI embeddings study)	Protocol: OGBl-ppa PPI link prediction, Accuracy (Table 6) Dataset: OGBl-ppa PPI graph (embedding study)	0.982 Accuracy (OGBl-ppa 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 OGBl-ppa (Accuracy) lit-interactions-20261011-ppiemb-protocol-ogbl-ppa-accuracy Aggregation: Not reported The role of protein embeddings for protein-protein interaction prediction with graph neural networks · Table 6, block 'OGBl-ppa', row 'GCN', column 'RDF2Vec'
Configuration: GCN with TransE protein embeddings (function (knowledge-graph embedding)) (PPI embeddings study)	Protocol: OGBl-ppa PPI link prediction, Accuracy (Table 6) Dataset: OGBl-ppa PPI graph (embedding study)	0.901 Accuracy (OGBl-ppa 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 OGBl-ppa (Accuracy) lit-interactions-20261011-ppiemb-protocol-ogbl-ppa-accuracy Aggregation: Not reported The role of protein embeddings for protein-protein interaction prediction with graph neural networks · Table 6, block 'OGBl-ppa', row 'GCN', column 'TransE'
Configuration: GraphSAGE with ComplEx protein embeddings (function (knowledge-graph embedding)) (PPI embeddings study)	Protocol: OGBl-ppa PPI link prediction, Accuracy (Table 6) Dataset: OGBl-ppa PPI graph (embedding study)	0.974 Accuracy (OGBl-ppa 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 OGBl-ppa (Accuracy) lit-interactions-20261011-ppiemb-protocol-ogbl-ppa-accuracy Aggregation: Not reported The role of protein embeddings for protein-protein interaction prediction with graph neural networks · Table 6, block 'OGBl-ppa', row 'GS', column 'ComplEx'
Configuration: GraphSAGE with majority vote across the representations (PPI embeddings study)	Protocol: OGBl-ppa PPI link prediction, Accuracy (Table 6) Dataset: OGBl-ppa PPI graph (embedding study)	0.882 Accuracy (OGBl-ppa 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 OGBl-ppa (Accuracy) lit-interactions-20261011-ppiemb-protocol-ogbl-ppa-accuracy Aggregation: Not reported The role of protein embeddings for protein-protein interaction prediction with graph neural networks · Table 6, block 'OGBl-ppa', row 'GS', column 'Ensemble'
Configuration: GraphSAGE with ESM-2 protein embeddings (sequence) (PPI embeddings study)	Protocol: OGBl-ppa PPI link prediction, Accuracy (Table 6) Dataset: OGBl-ppa PPI graph (embedding study)	0.676 Accuracy (OGBl-ppa 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 OGBl-ppa (Accuracy) lit-interactions-20261011-ppiemb-protocol-ogbl-ppa-accuracy Aggregation: Not reported The role of protein embeddings for protein-protein interaction prediction with graph neural networks · Table 6, block 'OGBl-ppa', row 'GS', column 'ESM-2'
Configuration: GraphSAGE with ESM-IF1 protein embeddings (structure) (PPI embeddings study)	Protocol: OGBl-ppa PPI link prediction, Accuracy (Table 6) Dataset: OGBl-ppa PPI graph (embedding study)	0.911 Accuracy (OGBl-ppa 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 OGBl-ppa (Accuracy) lit-interactions-20261011-ppiemb-protocol-ogbl-ppa-accuracy Aggregation: Not reported The role of protein embeddings for protein-protein interaction prediction with graph neural networks · Table 6, block 'OGBl-ppa', row 'GS', column 'ESM-IF1'
Configuration: GraphSAGE with PiFold protein embeddings (structure) (PPI embeddings study)	Protocol: OGBl-ppa PPI link prediction, Accuracy (Table 6) Dataset: OGBl-ppa PPI graph (embedding study)	0.842 Accuracy (OGBl-ppa 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 OGBl-ppa (Accuracy) lit-interactions-20261011-ppiemb-protocol-ogbl-ppa-accuracy Aggregation: Not reported The role of protein embeddings for protein-protein interaction prediction with graph neural networks · Table 6, block 'OGBl-ppa', row 'GS', column 'PiFold'
Configuration: GraphSAGE with ProGen2 protein embeddings (sequence) (PPI embeddings study)	Protocol: OGBl-ppa PPI link prediction, Accuracy (Table 6) Dataset: OGBl-ppa PPI graph (embedding study)	0.713 Accuracy (OGBl-ppa 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 OGBl-ppa (Accuracy) lit-interactions-20261011-ppiemb-protocol-ogbl-ppa-accuracy Aggregation: Not reported The role of protein embeddings for protein-protein interaction prediction with graph neural networks · Table 6, block 'OGBl-ppa', row 'GS', column 'ProGen2'
Configuration: GraphSAGE with ProstT5 protein embeddings (structure) (PPI embeddings study)	Protocol: OGBl-ppa PPI link prediction, Accuracy (Table 6) Dataset: OGBl-ppa PPI graph (embedding study)	0.659 Accuracy (OGBl-ppa 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 OGBl-ppa (Accuracy) lit-interactions-20261011-ppiemb-protocol-ogbl-ppa-accuracy Aggregation: Not reported The role of protein embeddings for protein-protein interaction prediction with graph neural networks · Table 6, block 'OGBl-ppa', row 'GS', column 'ProstT5'
Configuration: GraphSAGE with ProtTrans protein embeddings (sequence) (PPI embeddings study)	Protocol: OGBl-ppa PPI link prediction, Accuracy (Table 6) Dataset: OGBl-ppa PPI graph (embedding study)	0.719 Accuracy (OGBl-ppa 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 OGBl-ppa (Accuracy) lit-interactions-20261011-ppiemb-protocol-ogbl-ppa-accuracy Aggregation: Not reported The role of protein embeddings for protein-protein interaction prediction with graph neural networks · Table 6, block 'OGBl-ppa', row 'GS', column 'ProtTrans'
Configuration: GraphSAGE with randomly initialised node features (baseline) (PPI embeddings study)	Protocol: OGBl-ppa PPI link prediction, Accuracy (Table 6) Dataset: OGBl-ppa PPI graph (embedding study)	0.503 Accuracy (OGBl-ppa 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 OGBl-ppa (Accuracy) lit-interactions-20261011-ppiemb-protocol-ogbl-ppa-accuracy Aggregation: Not reported The role of protein embeddings for protein-protein interaction prediction with graph neural networks · Table 6, block 'OGBl-ppa', row 'GS', column 'Random'
Configuration: GraphSAGE with RDF2Vec protein embeddings (function (knowledge-graph embedding)) (PPI embeddings study)	Protocol: OGBl-ppa PPI link prediction, Accuracy (Table 6) Dataset: OGBl-ppa PPI graph (embedding study)	0.98 Accuracy (OGBl-ppa 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 OGBl-ppa (Accuracy) lit-interactions-20261011-ppiemb-protocol-ogbl-ppa-accuracy Aggregation: Not reported The role of protein embeddings for protein-protein interaction prediction with graph neural networks · Table 6, block 'OGBl-ppa', row 'GS', column 'RDF2Vec'
Configuration: GraphSAGE with TransE protein embeddings (function (knowledge-graph embedding)) (PPI embeddings study)	Protocol: OGBl-ppa PPI link prediction, Accuracy (Table 6) Dataset: OGBl-ppa PPI graph (embedding study)	0.967 Accuracy (OGBl-ppa 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 OGBl-ppa (Accuracy) lit-interactions-20261011-ppiemb-protocol-ogbl-ppa-accuracy Aggregation: Not reported The role of protein embeddings for protein-protein interaction prediction with graph neural networks · Table 6, block 'OGBl-ppa', 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: OGBl-ppa PPI link prediction, Accuracy (Table 6) Dataset: OGBl-ppa PPI graph (embedding study)	0.815 Accuracy (OGBl-ppa 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 OGBl-ppa (Accuracy) lit-interactions-20261011-ppiemb-protocol-ogbl-ppa-accuracy Aggregation: Not reported The role of protein embeddings for protein-protein interaction prediction with graph neural networks · Table 6, block 'OGBl-ppa', 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: OGBl-ppa PPI link prediction, Accuracy (Table 6) Dataset: OGBl-ppa PPI graph (embedding study)	0.712 Accuracy (OGBl-ppa 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 OGBl-ppa (Accuracy) lit-interactions-20261011-ppiemb-protocol-ogbl-ppa-accuracy Aggregation: Not reported The role of protein embeddings for protein-protein interaction prediction with graph neural networks · Table 6, block 'OGBl-ppa', 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: OGBl-ppa PPI link prediction, Accuracy (Table 6) Dataset: OGBl-ppa PPI graph (embedding study)	0.7 Accuracy (OGBl-ppa 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 OGBl-ppa (Accuracy) lit-interactions-20261011-ppiemb-protocol-ogbl-ppa-accuracy Aggregation: Not reported The role of protein embeddings for protein-protein interaction prediction with graph neural networks · Table 6, block 'OGBl-ppa', 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-ogbl-ppa-accuracy

areas: molecular-interactions; proteins-complexes
contexts: research
protocol: OGBl-ppa PPI link prediction; Accuracy
version: bbag313
metric: accuracy
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 6, block 'OGBl-ppa'

Related records

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

Suggest a correction