Molecular Property Prediction on MoleculeNet ClinTox (scaffold)
0.983ROC-AUCChem-GMNet
Evaluation Results
| Method | Links | |
|---|---|---|
| Chem-GMNetPre-trained=true, Pre-training Corpus=10M SMILES, Pre-training Task=MLM-10M2026.05 | 0.983 | |
| DumplingGNN2024.09 | 0.959 | |
| SYN-FUSIONfusion_source=MolCLR2023.08 | 0.947 | |
| SYN-FUSIONfusion_source=Hu et. al2023.08 | 0.946 | |
| MolXPT2024.09 | 0.919 | |
| GEM2024.09 | 0.912 | |
| D-MPNN2024.09 | 0.906 | |
| D-MPNN2023.08 | 0.905 | |
| Uni-Mol2024.09 | 0.901 | |
| MolCLRbackbone=GIN2023.08 | 0.886 | |
| N-Gram XGBClassifier=XGBoost2024.09 | 0.875 | |
| PretrainGNN2024.09 | 0.875 | |
| Attentive FP2024.09 | 0.832 | |
| MolCLR2024.09 | 0.791 | |
| Hu et al.2023.08 | 0.789 | |
| GTOT-TuningBackbone=GIN (supervised_contextpred), Strategy=GTOT-Tuning2022.03 | 0.779 | |
| N-Gram RFClassifier=Random Forest2024.09 | 0.775 | |
| GraphMVP2024.09 | 0.762 | |
| GINGraph-level pre-training=Supervised, Node-level pre-training=Attribute Masking2019.05 | 0.737 | |
| BSSBackbone=GIN (supervised_contextpred), Strategy=Fine-tuning strategy2022.03 | 0.737 | |
| StochNormBackbone=GIN (supervised_contextpred), Strategy=Fine-tuning strategy2022.03 | 0.732 | |
| DELTABackbone=GIN (supervised_contextpred), Strategy=Fine-tuning strategy2022.03 | 0.727 | |
| Feature (DELTA w/o ATT)Backbone=GIN (supervised_contextpred), Strategy=Fine-tuning strategy2022.03 | 0.727 | |
| GROVER_largeModel scale=large2024.09 | 0.726 | |
| GINGraph-level pre-training=Supervised, Node-level pre-training=Context Prediction2019.05 | 0.726 | |
| Fine-TuningBackbone=GIN (supervised_contextpred), Strategy=Baseline2022.03 | 0.726 | |
| GINGraph-level pre-training=None, Node-level pre-training=Attribute Masking2019.05 | 0.718 | |
| L2_SPBackbone=GIN (supervised_contextpred), Strategy=Fine-tuning strategy2022.03 | 0.718 | |
| RF2023.08 | 0.713 | |
| GINGraph-level pre-training=Supervised, Node-level pre-training=Infomax2019.05 | 0.712 | |
| GINGraph-level pre-training=Supervised, Node-level pre-training=EdgePred2019.05 | 0.709 | |
| GINGraph-level pre-training=None, Node-level pre-training=Infomax2019.05 | 0.699 | |
| SVM2023.08 | 0.669 | |
| GINGraph-level pre-training=None, Node-level pre-training=Context Prediction2019.05 | 0.659 | |
| NID_CLEvaluation Protocol=Linear Probing, Pre-training Dataset=ZINC15, Backbone=5-layer GIN2024.05 | 0.653 | |
| GINGraph-level pre-training=None, Node-level pre-training=EdgePred2019.05 | 0.641 | |
| SimGRACEEvaluation Protocol=Linear Probing, Pre-training Dataset=ZINC15, Backbone=5-layer GIN2024.05 | 0.634 | |
| GCN2023.08 | 0.625 | |
| GraphCLEvaluation Protocol=Linear Probing, Pre-training Dataset=ZINC15, Backbone=5-layer GIN2024.05 | 0.598 | |
| GIN2023.08 | 0.58 | |
| GINGraph-level pre-training=None, Node-level pre-training=None2019.05 | 0.58 | |
| GINGraph-level pre-training=Supervised, Node-level pre-training=None2019.05 | 0.572 | |
| JOAOEvaluation Protocol=Linear Probing, Pre-training Dataset=ZINC15, Backbone=5-layer GIN2024.05 | 0.541 | |
| AttrMaskEvaluation Protocol=Linear Probing, Pre-training Dataset=ZINC15, Backbone=5-layer GIN2024.05 | 0.516 | |
| EdgePredEvaluation Protocol=Linear Probing, Pre-training Dataset=ZINC15, Backbone=5-layer GIN2024.05 | 0.489 | |
| ContextPredEvaluation Protocol=Linear Probing, Pre-training Dataset=ZINC15, Backbone=5-layer GIN2024.05 | 0.432 | |
| ChemBERTa-2Pre-trained=true, Pre-training Corpus=10M SMILES, Pre-training Task=MLM-10M2026.05 | 0.349 |