Protocol

KIBA drug-target affinity, DeepDTA holdout fold

Affinity regression on the KIBA DeepDTA holdout fold; CI and MSE as printed.

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.

16 recorded evaluations, 32 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

16 evaluations · 32 results. Different protocols are not a single leaderboard.

Protocol: KIBA drug-target affinity, DeepDTA holdout fold · Dataset: KIBA holdout test fold (DeepDTA split)

Sorted by Concordance index (KIBA DeepDTA holdout fold) (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	Concordance index (KIBA DeepDTA holdout fold)	MSE (KIBA DeepDTA holdout fold)
PLM-GraphDTA with ProstT5 protein and GAT-GCN drug representationEvaluation	0.904 (best in column)	0.124 (best in column)
DeepGraphDTA with 1D conv. (32) protein and GAT-GCN drug representationEvaluation	0.903	0.125
PLM-GraphDTA with ProstT5 protein and GCN drug representationEvaluation	0.902	0.124 (best in column)
DeepGraphDTA with 1D conv. (8) protein and GCN drug representationEvaluation	0.901	0.128
GraphDTA with 1D conv. protein and GCN drug representationEvaluation	0.892	0.144
GraphDTA with 1D conv. protein and GAT-GCN drug representationEvaluation	0.89	0.145
DeepGraphDTA with 1D conv. (16) protein and GIN drug representationEvaluation	0.888	0.145
PLM-GraphDTA with ESMC 600M protein and GIN drug representationEvaluation	0.888	0.143
GraphDTA with 1D conv. protein and GIN drug representationEvaluation	0.884	0.149
DeepGraphDTA with 1D conv. (24) protein and GAT drug representationEvaluation	0.872	0.173
PGraphDTA with ESM2 650M protein and GAT drug representationEvaluation	0.872	0.16
PLM-GraphDTA with ProstT5 protein and GAT drug representationEvaluation	0.871	0.17
GraphDTA with 1D conv. protein and GAT drug representationEvaluation	0.866	0.178
DeepDTA with 1D conv. protein and 1D conv. drug representationEvaluation	0.863	0.194
SimBoost with Similarity features protein and Similarity features drug representationEvaluation	0.836	0.222
KronRLS with Similarity vector protein and Similarity vector drug representationEvaluation	0.782	0.411

All 32 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: DeepDTA with 1D conv. protein and 1D conv. drug representation	Protocol: KIBA drug-target affinity, DeepDTA holdout fold Dataset: KIBA holdout test fold (DeepDTA split)	0.863 Concordance index (KIBA DeepDTA holdout fold) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Evidence concern: excluded from comparisons Table 3 KIBA rows KronRLS, SimBoost and DeepDTA equal the values printed in Ozturk et al. 2018, while the proposed models are 5-seed means; the rows may not share a training run or protocol. Do not compare these three rows against the proposed models automatically.Comprehensive Evaluation of Protein Language Model Embeddings for Drug-Target Affinity Prediction · Table 3, rows KronRLS, SimBoost, DeepDTA Methods, coverage and source DeepDTA (1D conv.; 1D conv.) on KIBA lit-interactions-20261011-plmdta-protocol-kiba-deepdta-holdout Aggregation: Not reported Comprehensive Evaluation of Protein Language Model Embeddings for Drug-Target Affinity Prediction · Table 3, row 'DeepDTA' with protein '1D conv.' and drug '1D conv.', column 'CI' (text-layer line 585)
Configuration: DeepDTA with 1D conv. protein and 1D conv. drug representation	Protocol: KIBA drug-target affinity, DeepDTA holdout fold Dataset: KIBA holdout test fold (DeepDTA split)	0.194 MSE (KIBA DeepDTA holdout fold) unit-unreported · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Evidence concern: excluded from comparisons Table 3 KIBA rows KronRLS, SimBoost and DeepDTA equal the values printed in Ozturk et al. 2018, while the proposed models are 5-seed means; the rows may not share a training run or protocol. Do not compare these three rows against the proposed models automatically.Comprehensive Evaluation of Protein Language Model Embeddings for Drug-Target Affinity Prediction · Table 3, rows KronRLS, SimBoost, DeepDTA Methods, coverage and source DeepDTA (1D conv.; 1D conv.) on KIBA lit-interactions-20261011-plmdta-protocol-kiba-deepdta-holdout Aggregation: Not reported Comprehensive Evaluation of Protein Language Model Embeddings for Drug-Target Affinity Prediction · Table 3, row 'DeepDTA' with protein '1D conv.' and drug '1D conv.', column 'MSE' (text-layer line 585)
Configuration: DeepGraphDTA with 1D conv. (16) protein and GIN drug representation	Protocol: KIBA drug-target affinity, DeepDTA holdout fold Dataset: KIBA holdout test fold (DeepDTA split)	0.888 Concordance index (KIBA DeepDTA holdout fold) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Table 3 KIBA rows KronRLS, SimBoost and DeepDTA equal the values printed in Ozturk et al. 2018, while the proposed models are 5-seed means; the rows may not share a training run or protocol. Do not compare these three rows against the proposed models automatically.Comprehensive Evaluation of Protein Language Model Embeddings for Drug-Target Affinity Prediction · Table 3, rows KronRLS, SimBoost, DeepDTA Methods, coverage and source DeepGraphDTA (1D conv. (16); GIN) on KIBA lit-interactions-20261011-plmdta-protocol-kiba-deepdta-holdout Aggregation: Not reported Comprehensive Evaluation of Protein Language Model Embeddings for Drug-Target Affinity Prediction · Table 3, row 'DeepGraphDTA' with protein '1D conv. (16)' and drug 'GIN', column 'CI' (text-layer line 594)
Configuration: DeepGraphDTA with 1D conv. (16) protein and GIN drug representation	Protocol: KIBA drug-target affinity, DeepDTA holdout fold Dataset: KIBA holdout test fold (DeepDTA split)	0.145 MSE (KIBA DeepDTA holdout fold) unit-unreported · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Table 3 KIBA rows KronRLS, SimBoost and DeepDTA equal the values printed in Ozturk et al. 2018, while the proposed models are 5-seed means; the rows may not share a training run or protocol. Do not compare these three rows against the proposed models automatically.Comprehensive Evaluation of Protein Language Model Embeddings for Drug-Target Affinity Prediction · Table 3, rows KronRLS, SimBoost, DeepDTA Methods, coverage and source DeepGraphDTA (1D conv. (16); GIN) on KIBA lit-interactions-20261011-plmdta-protocol-kiba-deepdta-holdout Aggregation: Not reported Comprehensive Evaluation of Protein Language Model Embeddings for Drug-Target Affinity Prediction · Table 3, row 'DeepGraphDTA' with protein '1D conv. (16)' and drug 'GIN', column 'MSE' (text-layer line 594)
Configuration: DeepGraphDTA with 1D conv. (24) protein and GAT drug representation	Protocol: KIBA drug-target affinity, DeepDTA holdout fold Dataset: KIBA holdout test fold (DeepDTA split)	0.872 Concordance index (KIBA DeepDTA holdout fold) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Table 3 KIBA rows KronRLS, SimBoost and DeepDTA equal the values printed in Ozturk et al. 2018, while the proposed models are 5-seed means; the rows may not share a training run or protocol. Do not compare these three rows against the proposed models automatically.Comprehensive Evaluation of Protein Language Model Embeddings for Drug-Target Affinity Prediction · Table 3, rows KronRLS, SimBoost, DeepDTA Methods, coverage and source DeepGraphDTA (1D conv. (24); GAT) on KIBA lit-interactions-20261011-plmdta-protocol-kiba-deepdta-holdout Aggregation: Not reported Comprehensive Evaluation of Protein Language Model Embeddings for Drug-Target Affinity Prediction · Table 3, row 'DeepGraphDTA' with protein '1D conv. (24)' and drug 'GAT', column 'CI' (text-layer line 593)
Configuration: DeepGraphDTA with 1D conv. (24) protein and GAT drug representation	Protocol: KIBA drug-target affinity, DeepDTA holdout fold Dataset: KIBA holdout test fold (DeepDTA split)	0.173 MSE (KIBA DeepDTA holdout fold) unit-unreported · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Table 3 KIBA rows KronRLS, SimBoost and DeepDTA equal the values printed in Ozturk et al. 2018, while the proposed models are 5-seed means; the rows may not share a training run or protocol. Do not compare these three rows against the proposed models automatically.Comprehensive Evaluation of Protein Language Model Embeddings for Drug-Target Affinity Prediction · Table 3, rows KronRLS, SimBoost, DeepDTA Methods, coverage and source DeepGraphDTA (1D conv. (24); GAT) on KIBA lit-interactions-20261011-plmdta-protocol-kiba-deepdta-holdout Aggregation: Not reported Comprehensive Evaluation of Protein Language Model Embeddings for Drug-Target Affinity Prediction · Table 3, row 'DeepGraphDTA' with protein '1D conv. (24)' and drug 'GAT', column 'MSE' (text-layer line 593)
Configuration: DeepGraphDTA with 1D conv. (32) protein and GAT-GCN drug representation	Protocol: KIBA drug-target affinity, DeepDTA holdout fold Dataset: KIBA holdout test fold (DeepDTA split)	0.903 Concordance index (KIBA DeepDTA holdout fold) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Table 3 KIBA rows KronRLS, SimBoost and DeepDTA equal the values printed in Ozturk et al. 2018, while the proposed models are 5-seed means; the rows may not share a training run or protocol. Do not compare these three rows against the proposed models automatically.Comprehensive Evaluation of Protein Language Model Embeddings for Drug-Target Affinity Prediction · Table 3, rows KronRLS, SimBoost, DeepDTA Methods, coverage and source DeepGraphDTA (1D conv. (32); GAT-GCN) on KIBA lit-interactions-20261011-plmdta-protocol-kiba-deepdta-holdout Aggregation: Not reported Comprehensive Evaluation of Protein Language Model Embeddings for Drug-Target Affinity Prediction · Table 3, row 'DeepGraphDTA' with protein '1D conv. (32)' and drug 'GAT-GCN', column 'CI' (text-layer line 598)
Configuration: DeepGraphDTA with 1D conv. (32) protein and GAT-GCN drug representation	Protocol: KIBA drug-target affinity, DeepDTA holdout fold Dataset: KIBA holdout test fold (DeepDTA split)	0.125 MSE (KIBA DeepDTA holdout fold) unit-unreported · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Table 3 KIBA rows KronRLS, SimBoost and DeepDTA equal the values printed in Ozturk et al. 2018, while the proposed models are 5-seed means; the rows may not share a training run or protocol. Do not compare these three rows against the proposed models automatically.Comprehensive Evaluation of Protein Language Model Embeddings for Drug-Target Affinity Prediction · Table 3, rows KronRLS, SimBoost, DeepDTA Methods, coverage and source DeepGraphDTA (1D conv. (32); GAT-GCN) on KIBA lit-interactions-20261011-plmdta-protocol-kiba-deepdta-holdout Aggregation: Not reported Comprehensive Evaluation of Protein Language Model Embeddings for Drug-Target Affinity Prediction · Table 3, row 'DeepGraphDTA' with protein '1D conv. (32)' and drug 'GAT-GCN', column 'MSE' (text-layer line 598)
Configuration: DeepGraphDTA with 1D conv. (8) protein and GCN drug representation	Protocol: KIBA drug-target affinity, DeepDTA holdout fold Dataset: KIBA holdout test fold (DeepDTA split)	0.901 Concordance index (KIBA DeepDTA holdout fold) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Table 3 KIBA rows KronRLS, SimBoost and DeepDTA equal the values printed in Ozturk et al. 2018, while the proposed models are 5-seed means; the rows may not share a training run or protocol. Do not compare these three rows against the proposed models automatically.Comprehensive Evaluation of Protein Language Model Embeddings for Drug-Target Affinity Prediction · Table 3, rows KronRLS, SimBoost, DeepDTA Methods, coverage and source DeepGraphDTA (1D conv. (8); GCN) on KIBA lit-interactions-20261011-plmdta-protocol-kiba-deepdta-holdout Aggregation: Not reported Comprehensive Evaluation of Protein Language Model Embeddings for Drug-Target Affinity Prediction · Table 3, row 'DeepGraphDTA' with protein '1D conv. (8)' and drug 'GCN', column 'CI' (text-layer line 596)
Configuration: DeepGraphDTA with 1D conv. (8) protein and GCN drug representation	Protocol: KIBA drug-target affinity, DeepDTA holdout fold Dataset: KIBA holdout test fold (DeepDTA split)	0.128 MSE (KIBA DeepDTA holdout fold) unit-unreported · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Table 3 KIBA rows KronRLS, SimBoost and DeepDTA equal the values printed in Ozturk et al. 2018, while the proposed models are 5-seed means; the rows may not share a training run or protocol. Do not compare these three rows against the proposed models automatically.Comprehensive Evaluation of Protein Language Model Embeddings for Drug-Target Affinity Prediction · Table 3, rows KronRLS, SimBoost, DeepDTA Methods, coverage and source DeepGraphDTA (1D conv. (8); GCN) on KIBA lit-interactions-20261011-plmdta-protocol-kiba-deepdta-holdout Aggregation: Not reported Comprehensive Evaluation of Protein Language Model Embeddings for Drug-Target Affinity Prediction · Table 3, row 'DeepGraphDTA' with protein '1D conv. (8)' and drug 'GCN', column 'MSE' (text-layer line 596)
Configuration: GraphDTA with 1D conv. protein and GAT-GCN drug representation	Protocol: KIBA drug-target affinity, DeepDTA holdout fold Dataset: KIBA holdout test fold (DeepDTA split)	0.89 Concordance index (KIBA DeepDTA holdout fold) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Evidence concern: excluded from comparisons Table 3 KIBA rows KronRLS, SimBoost and DeepDTA equal the values printed in Ozturk et al. 2018, while the proposed models are 5-seed means; the rows may not share a training run or protocol. Do not compare these three rows against the proposed models automatically.Comprehensive Evaluation of Protein Language Model Embeddings for Drug-Target Affinity Prediction · Table 3, rows KronRLS, SimBoost, DeepDTA Methods, coverage and source GraphDTA (1D conv.; GAT-GCN) on KIBA lit-interactions-20261011-plmdta-protocol-kiba-deepdta-holdout Aggregation: Not reported Comprehensive Evaluation of Protein Language Model Embeddings for Drug-Target Affinity Prediction · Table 3, row 'GraphDTA' with protein '1D conv.' and drug 'GAT-GCN', column 'CI' (text-layer line 589)
Configuration: GraphDTA with 1D conv. protein and GAT-GCN drug representation	Protocol: KIBA drug-target affinity, DeepDTA holdout fold Dataset: KIBA holdout test fold (DeepDTA split)	0.145 MSE (KIBA DeepDTA holdout fold) unit-unreported · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Evidence concern: excluded from comparisons Table 3 KIBA rows KronRLS, SimBoost and DeepDTA equal the values printed in Ozturk et al. 2018, while the proposed models are 5-seed means; the rows may not share a training run or protocol. Do not compare these three rows against the proposed models automatically.Comprehensive Evaluation of Protein Language Model Embeddings for Drug-Target Affinity Prediction · Table 3, rows KronRLS, SimBoost, DeepDTA Methods, coverage and source GraphDTA (1D conv.; GAT-GCN) on KIBA lit-interactions-20261011-plmdta-protocol-kiba-deepdta-holdout Aggregation: Not reported Comprehensive Evaluation of Protein Language Model Embeddings for Drug-Target Affinity Prediction · Table 3, row 'GraphDTA' with protein '1D conv.' and drug 'GAT-GCN', column 'MSE' (text-layer line 589)
Configuration: GraphDTA with 1D conv. protein and GAT drug representation	Protocol: KIBA drug-target affinity, DeepDTA holdout fold Dataset: KIBA holdout test fold (DeepDTA split)	0.866 Concordance index (KIBA DeepDTA holdout fold) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Evidence concern: excluded from comparisons Table 3 KIBA rows KronRLS, SimBoost and DeepDTA equal the values printed in Ozturk et al. 2018, while the proposed models are 5-seed means; the rows may not share a training run or protocol. Do not compare these three rows against the proposed models automatically.Comprehensive Evaluation of Protein Language Model Embeddings for Drug-Target Affinity Prediction · Table 3, rows KronRLS, SimBoost, DeepDTA Methods, coverage and source GraphDTA (1D conv.; GAT) on KIBA lit-interactions-20261011-plmdta-protocol-kiba-deepdta-holdout Aggregation: Not reported Comprehensive Evaluation of Protein Language Model Embeddings for Drug-Target Affinity Prediction · Table 3, row 'GraphDTA' with protein '1D conv.' and drug 'GAT', column 'CI' (text-layer line 586)
Configuration: GraphDTA with 1D conv. protein and GAT drug representation	Protocol: KIBA drug-target affinity, DeepDTA holdout fold Dataset: KIBA holdout test fold (DeepDTA split)	0.178 MSE (KIBA DeepDTA holdout fold) unit-unreported · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Evidence concern: excluded from comparisons Table 3 KIBA rows KronRLS, SimBoost and DeepDTA equal the values printed in Ozturk et al. 2018, while the proposed models are 5-seed means; the rows may not share a training run or protocol. Do not compare these three rows against the proposed models automatically.Comprehensive Evaluation of Protein Language Model Embeddings for Drug-Target Affinity Prediction · Table 3, rows KronRLS, SimBoost, DeepDTA Methods, coverage and source GraphDTA (1D conv.; GAT) on KIBA lit-interactions-20261011-plmdta-protocol-kiba-deepdta-holdout Aggregation: Not reported Comprehensive Evaluation of Protein Language Model Embeddings for Drug-Target Affinity Prediction · Table 3, row 'GraphDTA' with protein '1D conv.' and drug 'GAT', column 'MSE' (text-layer line 586)
Configuration: GraphDTA with 1D conv. protein and GCN drug representation	Protocol: KIBA drug-target affinity, DeepDTA holdout fold Dataset: KIBA holdout test fold (DeepDTA split)	0.892 Concordance index (KIBA DeepDTA holdout fold) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Evidence concern: excluded from comparisons Table 3 KIBA rows KronRLS, SimBoost and DeepDTA equal the values printed in Ozturk et al. 2018, while the proposed models are 5-seed means; the rows may not share a training run or protocol. Do not compare these three rows against the proposed models automatically.Comprehensive Evaluation of Protein Language Model Embeddings for Drug-Target Affinity Prediction · Table 3, rows KronRLS, SimBoost, DeepDTA Methods, coverage and source GraphDTA (1D conv.; GCN) on KIBA lit-interactions-20261011-plmdta-protocol-kiba-deepdta-holdout Aggregation: Not reported Comprehensive Evaluation of Protein Language Model Embeddings for Drug-Target Affinity Prediction · Table 3, row 'GraphDTA' with protein '1D conv.' and drug 'GCN', column 'CI' (text-layer line 590)
Configuration: GraphDTA with 1D conv. protein and GCN drug representation	Protocol: KIBA drug-target affinity, DeepDTA holdout fold Dataset: KIBA holdout test fold (DeepDTA split)	0.144 MSE (KIBA DeepDTA holdout fold) unit-unreported · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Evidence concern: excluded from comparisons Table 3 KIBA rows KronRLS, SimBoost and DeepDTA equal the values printed in Ozturk et al. 2018, while the proposed models are 5-seed means; the rows may not share a training run or protocol. Do not compare these three rows against the proposed models automatically.Comprehensive Evaluation of Protein Language Model Embeddings for Drug-Target Affinity Prediction · Table 3, rows KronRLS, SimBoost, DeepDTA Methods, coverage and source GraphDTA (1D conv.; GCN) on KIBA lit-interactions-20261011-plmdta-protocol-kiba-deepdta-holdout Aggregation: Not reported Comprehensive Evaluation of Protein Language Model Embeddings for Drug-Target Affinity Prediction · Table 3, row 'GraphDTA' with protein '1D conv.' and drug 'GCN', column 'MSE' (text-layer line 590)
Configuration: GraphDTA with 1D conv. protein and GIN drug representation	Protocol: KIBA drug-target affinity, DeepDTA holdout fold Dataset: KIBA holdout test fold (DeepDTA split)	0.884 Concordance index (KIBA DeepDTA holdout fold) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Evidence concern: excluded from comparisons Table 3 KIBA rows KronRLS, SimBoost and DeepDTA equal the values printed in Ozturk et al. 2018, while the proposed models are 5-seed means; the rows may not share a training run or protocol. Do not compare these three rows against the proposed models automatically.Comprehensive Evaluation of Protein Language Model Embeddings for Drug-Target Affinity Prediction · Table 3, rows KronRLS, SimBoost, DeepDTA Methods, coverage and source GraphDTA (1D conv.; GIN) on KIBA lit-interactions-20261011-plmdta-protocol-kiba-deepdta-holdout Aggregation: Not reported Comprehensive Evaluation of Protein Language Model Embeddings for Drug-Target Affinity Prediction · Table 3, row 'GraphDTA' with protein '1D conv.' and drug 'GIN', column 'CI' (text-layer line 588)
Configuration: GraphDTA with 1D conv. protein and GIN drug representation	Protocol: KIBA drug-target affinity, DeepDTA holdout fold Dataset: KIBA holdout test fold (DeepDTA split)	0.149 MSE (KIBA DeepDTA holdout fold) unit-unreported · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Evidence concern: excluded from comparisons Table 3 KIBA rows KronRLS, SimBoost and DeepDTA equal the values printed in Ozturk et al. 2018, while the proposed models are 5-seed means; the rows may not share a training run or protocol. Do not compare these three rows against the proposed models automatically.Comprehensive Evaluation of Protein Language Model Embeddings for Drug-Target Affinity Prediction · Table 3, rows KronRLS, SimBoost, DeepDTA Methods, coverage and source GraphDTA (1D conv.; GIN) on KIBA lit-interactions-20261011-plmdta-protocol-kiba-deepdta-holdout Aggregation: Not reported Comprehensive Evaluation of Protein Language Model Embeddings for Drug-Target Affinity Prediction · Table 3, row 'GraphDTA' with protein '1D conv.' and drug 'GIN', column 'MSE' (text-layer line 588)
Configuration: KronRLS with Similarity vector protein and Similarity vector drug representation	Protocol: KIBA drug-target affinity, DeepDTA holdout fold Dataset: KIBA holdout test fold (DeepDTA split)	0.782 Concordance index (KIBA DeepDTA holdout fold) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Evidence concern: excluded from comparisons Table 3 KIBA rows KronRLS, SimBoost and DeepDTA equal the values printed in Ozturk et al. 2018, while the proposed models are 5-seed means; the rows may not share a training run or protocol. Do not compare these three rows against the proposed models automatically.Comprehensive Evaluation of Protein Language Model Embeddings for Drug-Target Affinity Prediction · Table 3, rows KronRLS, SimBoost, DeepDTA Methods, coverage and source KronRLS (Similarity vector; Similarity vector) on KIBA lit-interactions-20261011-plmdta-protocol-kiba-deepdta-holdout Aggregation: Not reported Comprehensive Evaluation of Protein Language Model Embeddings for Drug-Target Affinity Prediction · Table 3, row 'KronRLS' with protein 'Similarity vector' and drug 'Similarity vector', column 'CI' (text-layer line 583)
Configuration: KronRLS with Similarity vector protein and Similarity vector drug representation	Protocol: KIBA drug-target affinity, DeepDTA holdout fold Dataset: KIBA holdout test fold (DeepDTA split)	0.411 MSE (KIBA DeepDTA holdout fold) unit-unreported · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Evidence concern: excluded from comparisons Table 3 KIBA rows KronRLS, SimBoost and DeepDTA equal the values printed in Ozturk et al. 2018, while the proposed models are 5-seed means; the rows may not share a training run or protocol. Do not compare these three rows against the proposed models automatically.Comprehensive Evaluation of Protein Language Model Embeddings for Drug-Target Affinity Prediction · Table 3, rows KronRLS, SimBoost, DeepDTA Methods, coverage and source KronRLS (Similarity vector; Similarity vector) on KIBA lit-interactions-20261011-plmdta-protocol-kiba-deepdta-holdout Aggregation: Not reported Comprehensive Evaluation of Protein Language Model Embeddings for Drug-Target Affinity Prediction · Table 3, row 'KronRLS' with protein 'Similarity vector' and drug 'Similarity vector', column 'MSE' (text-layer line 583)
Configuration: PGraphDTA with ESM2 650M protein and GAT drug representation	Protocol: KIBA drug-target affinity, DeepDTA holdout fold Dataset: KIBA holdout test fold (DeepDTA split)	0.872 Concordance index (KIBA DeepDTA holdout fold) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Evidence concern: excluded from comparisons Table 3 KIBA rows KronRLS, SimBoost and DeepDTA equal the values printed in Ozturk et al. 2018, while the proposed models are 5-seed means; the rows may not share a training run or protocol. Do not compare these three rows against the proposed models automatically.Comprehensive Evaluation of Protein Language Model Embeddings for Drug-Target Affinity Prediction · Table 3, rows KronRLS, SimBoost, DeepDTA Methods, coverage and source PGraphDTA (ESM2 650M; GAT) on KIBA lit-interactions-20261011-plmdta-protocol-kiba-deepdta-holdout Aggregation: Not reported Comprehensive Evaluation of Protein Language Model Embeddings for Drug-Target Affinity Prediction · Table 3, row 'PGraphDTA' with protein 'ESM2 650M' and drug 'GAT', column 'CI' (text-layer line 587)
Configuration: PGraphDTA with ESM2 650M protein and GAT drug representation	Protocol: KIBA drug-target affinity, DeepDTA holdout fold Dataset: KIBA holdout test fold (DeepDTA split)	0.16 MSE (KIBA DeepDTA holdout fold) unit-unreported · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Evidence concern: excluded from comparisons Table 3 KIBA rows KronRLS, SimBoost and DeepDTA equal the values printed in Ozturk et al. 2018, while the proposed models are 5-seed means; the rows may not share a training run or protocol. Do not compare these three rows against the proposed models automatically.Comprehensive Evaluation of Protein Language Model Embeddings for Drug-Target Affinity Prediction · Table 3, rows KronRLS, SimBoost, DeepDTA Methods, coverage and source PGraphDTA (ESM2 650M; GAT) on KIBA lit-interactions-20261011-plmdta-protocol-kiba-deepdta-holdout Aggregation: Not reported Comprehensive Evaluation of Protein Language Model Embeddings for Drug-Target Affinity Prediction · Table 3, row 'PGraphDTA' with protein 'ESM2 650M' and drug 'GAT', column 'MSE' (text-layer line 587)
Configuration: PLM-GraphDTA with ESMC 600M protein and GIN drug representation	Protocol: KIBA drug-target affinity, DeepDTA holdout fold Dataset: KIBA holdout test fold (DeepDTA split)	0.888 Concordance index (KIBA DeepDTA holdout fold) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Table 3 KIBA rows KronRLS, SimBoost and DeepDTA equal the values printed in Ozturk et al. 2018, while the proposed models are 5-seed means; the rows may not share a training run or protocol. Do not compare these three rows against the proposed models automatically.Comprehensive Evaluation of Protein Language Model Embeddings for Drug-Target Affinity Prediction · Table 3, rows KronRLS, SimBoost, DeepDTA Methods, coverage and source PLM-GraphDTA (ESMC 600M; GIN) on KIBA lit-interactions-20261011-plmdta-protocol-kiba-deepdta-holdout Aggregation: Not reported Comprehensive Evaluation of Protein Language Model Embeddings for Drug-Target Affinity Prediction · Table 3, row 'PLM-GraphDTA' with protein 'ESMC 600M' and drug 'GIN', column 'CI' (text-layer line 595)
Configuration: PLM-GraphDTA with ESMC 600M protein and GIN drug representation	Protocol: KIBA drug-target affinity, DeepDTA holdout fold Dataset: KIBA holdout test fold (DeepDTA split)	0.143 MSE (KIBA DeepDTA holdout fold) unit-unreported · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Table 3 KIBA rows KronRLS, SimBoost and DeepDTA equal the values printed in Ozturk et al. 2018, while the proposed models are 5-seed means; the rows may not share a training run or protocol. Do not compare these three rows against the proposed models automatically.Comprehensive Evaluation of Protein Language Model Embeddings for Drug-Target Affinity Prediction · Table 3, rows KronRLS, SimBoost, DeepDTA Methods, coverage and source PLM-GraphDTA (ESMC 600M; GIN) on KIBA lit-interactions-20261011-plmdta-protocol-kiba-deepdta-holdout Aggregation: Not reported Comprehensive Evaluation of Protein Language Model Embeddings for Drug-Target Affinity Prediction · Table 3, row 'PLM-GraphDTA' with protein 'ESMC 600M' and drug 'GIN', column 'MSE' (text-layer line 595)
Configuration: PLM-GraphDTA with ProstT5 protein and GAT-GCN drug representation	Protocol: KIBA drug-target affinity, DeepDTA holdout fold Dataset: KIBA holdout test fold (DeepDTA split)	0.904 Concordance index (KIBA DeepDTA holdout fold) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Evidence concern: excluded from comparisons Table 3 KIBA rows KronRLS, SimBoost and DeepDTA equal the values printed in Ozturk et al. 2018, while the proposed models are 5-seed means; the rows may not share a training run or protocol. Do not compare these three rows against the proposed models automatically.Comprehensive Evaluation of Protein Language Model Embeddings for Drug-Target Affinity Prediction · Table 3, rows KronRLS, SimBoost, DeepDTA Methods, coverage and source PLM-GraphDTA (ProstT5; GAT-GCN) on KIBA lit-interactions-20261011-plmdta-protocol-kiba-deepdta-holdout Aggregation: Not reported Comprehensive Evaluation of Protein Language Model Embeddings for Drug-Target Affinity Prediction · Table 3, row 'PLM-GraphDTA' with protein 'ProstT5' and drug 'GAT-GCN', column 'CI' (text-layer line 599)

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: 8
unreported: 8

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

Null control

Proposed control: requires review

Training-set mean where supervised fitting is permitted

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

Simple features with train-only ridge regression

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

Comprehensive Evaluation of Protein Language Model Embeddings for Drug-Target Affinity Prediction · Original source · bioRxiv 10.64898/2026.08.31.748056v1 (posted 2026-09-03); 24-page PDF

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: lit-interactions-20261011-plmdta-protocol-kiba-deepdta-holdout

areas: molecular-interactions
contexts: research
protocol: KIBA DeepDTA holdout test fold; concordance index and MSE
version: DeepDTA split
limitations: For the proposed models, values are the mean over 5 random seeds (Section 3.4.3); the source does not say whether baseline values were rerun or taken from earlier papers.; Rows are sorted by CI and only the selected PLM per drug backbone is shown.; Table 3 KIBA rows KronRLS, SimBoost and DeepDTA equal the values printed in Ozturk et al. 2018, while the proposed models are 5-seed means; the rows may not share a training run or protocol.
source locator: Table 3

Related records

part of: Davis and KIBA drug-target affinity benchmark (DeepDTA split)
uses data: KIBA holdout test fold (DeepDTA split)
assessment: DeepDTA (1D conv.; 1D conv.) on KIBA
assessment: DeepGraphDTA (1D conv. (16); GIN) on KIBA
assessment: DeepGraphDTA (1D conv. (24); GAT) on KIBA
assessment: DeepGraphDTA (1D conv. (32); GAT-GCN) on KIBA
assessment: DeepGraphDTA (1D conv. (8); GCN) on KIBA
assessment: GraphDTA (1D conv.; GAT-GCN) on KIBA
assessment: GraphDTA (1D conv.; GAT) on KIBA
assessment: GraphDTA (1D conv.; GCN) on KIBA
assessment: GraphDTA (1D conv.; GIN) on KIBA
assessment: KronRLS (Similarity vector; Similarity vector) on KIBA
assessment: PGraphDTA (ESM2 650M; GAT) on KIBA
assessment: PLM-GraphDTA (ESMC 600M; GIN) on KIBA
assessment: PLM-GraphDTA (ProstT5; GAT-GCN) on KIBA
assessment: PLM-GraphDTA (ProstT5; GAT) on KIBA
assessment: PLM-GraphDTA (ProstT5; GCN) on KIBA
assessment: SimBoost (Similarity features; Similarity features) on KIBA

Suggest a correction