List your company
ResearchFormerly WizWand

Molecular Property Prediction on MoleculeNet Tox21 (scaffold)

85.4ROC-AUCGraphConv + dummy super node
61.79267.92174.0580.179Mar 20, 2022Aug 20, 2022Jan 20, 2023Jun 22, 2023Nov 22, 2023Apr 23, 2024Sep 23, 2024
Updated 8mo ago

Evaluation results

MethodLinks
GraphConv + dummy super nodeGraph construction=dummy super node2024.0985.4
KPGT2023.0484.8
DumplingGNN2024.0982.3
SVM2023.0881.8
MolXPT2024.0979.6
Hu et al.2023.0878.7
Hu et al.2023.0478.7
MolCLR2023.0478.7
L2_SPBackbone=GIN (supervised_contextpred), Strategy=Fine-tuning strategy2022.0378.7
GTOT-TuningBackbone=GIN (supervised_contextpred), Strategy=GTOT-Tuning2022.0378.6
StochNormBackbone=GIN (supervised_contextpred), Strategy=Fine-tuning strategy2022.0378.4
BSSBackbone=GIN (supervised_contextpred), Strategy=Fine-tuning strategy2022.0378.3
GEM2023.0478.1
GROVER_largeModel scale=large2024.0978.1
Uni-Mol2024.0978.1
Fine-TuningBackbone=GIN (supervised_contextpred), Strategy=Baseline2022.0378.1
DELTABackbone=GIN (supervised_contextpred), Strategy=Fine-tuning strategy2022.0377.9
Feature (DELTA w/o ATT)Backbone=GIN (supervised_contextpred), Strategy=Fine-tuning strategy2022.0377.9
SchNet2023.0477.2
N-Gram XGBClassifier=XGBoost2024.0977.2
ChemBFN2024.0977.1
RF2023.0876.9
Attentive FP2024.0976.3
D-MPNN2023.0475.9
D-MPNN2024.0975.9
MolCLR2024.0975.9
PretrainGNN2024.0975.8
SYN-FUSIONfusion_source=MolCLR2023.0875.1
GEM2024.0975
GraphMVP-C2023.0474.4
N-Gram RFClassifier=Random Forest2024.0974.3
GIN2023.0874
GIN2023.0474
SYN-FUSIONfusion_source=Hu et. al2023.0873.8
GraphMVP2024.0973.5
MolCLRbackbone=GIN2023.0872
GCN2023.0870.9
GCN2023.0470.9
MGCN2023.0470.7
JOAOEvaluation Protocol=Linear Probing, Pre-training Dataset=ZINC15, Backbone=5-layer GIN2024.0570.6
AttrMaskEvaluation Protocol=Linear Probing, Pre-training Dataset=ZINC15, Backbone=5-layer GIN2024.0569.1
D-MPNN2023.0868.9
ContextPredEvaluation Protocol=Linear Probing, Pre-training Dataset=ZINC15, Backbone=5-layer GIN2024.0568.4
NID_CLEvaluation Protocol=Linear Probing, Pre-training Dataset=ZINC15, Backbone=5-layer GIN2024.0566.3
SELFormer2023.0465.3
SimGRACEEvaluation Protocol=Linear Probing, Pre-training Dataset=ZINC15, Backbone=5-layer GIN2024.0564.6
GraphCLEvaluation Protocol=Linear Probing, Pre-training Dataset=ZINC15, Backbone=5-layer GIN2024.0564.4
EdgePredEvaluation Protocol=Linear Probing, Pre-training Dataset=ZINC15, Backbone=5-layer GIN2024.0562.7