List your company
ResearchFormerly WizWand

Molecular Property Prediction on MoleculeNet MUV (scaffold)

0.903ROC-AUCSYN-FUSION
0.662760.725130.78750.84987May 29, 2019Aug 1, 2020Oct 6, 2021Dec 10, 2022Feb 14, 2024Apr 19, 2025Jun 24, 2026
Updated 4mo ago

Evaluation results

MethodLinks
SYN-FUSIONfusion_source=MolCLR2023.080.903
SYN-FUSIONfusion_source=Hu et. al2023.080.889
DELTABackbone=GIN (supervised_contextpred), Strategy=Fine-tuning strategy2022.030.859
Feature (DELTA w/o ATT)Backbone=GIN (supervised_contextpred), Strategy=Fine-tuning strategy2022.030.856
L2_SPBackbone=GIN (supervised_contextpred), Strategy=Fine-tuning strategy2022.030.85
GTOT-TuningBackbone=GIN (supervised_contextpred), Strategy=GTOT-Tuning2022.030.85
MolCLRbackbone=GIN2023.080.838
StochNormBackbone=GIN (supervised_contextpred), Strategy=Fine-tuning strategy2022.030.825
Hu et al.2023.080.814
GINGraph-level pre-training=Supervised, Node-level pre-training=Infomax2019.050.813
GINGraph-level pre-training=Supervised, Node-level pre-training=Context Prediction2019.050.813
Fine-TuningBackbone=GIN (supervised_contextpred), Strategy=Baseline2022.030.813
GINGraph-level pre-training=Supervised, Node-level pre-training=Attribute Masking2019.050.812
GINGraph-level pre-training=Supervised, Node-level pre-training=None2019.050.794
SimSGT2026.020.79
BSSBackbone=GIN (supervised_contextpred), Strategy=Fine-tuning strategy2022.030.786
Mole-BERT2023.110.786
Mole-BERTPre-training status=Pre-trained, Pre-training dataset=ZINC15, Evaluation protocol=Fine-tuning, Split type=Scaffold-split2024.050.786
AttentiveFP2026.060.786
GINGraph-level pre-training=Supervised, Node-level pre-training=EdgePred2019.050.785
GraphMAE22026.020.785
GraSPNet2026.020.785
GraphMAE2Pre-training status=Pre-trained, Pre-training dataset=ZINC15, Evaluation protocol=Fine-tuning, Split type=Scaffold-split2024.050.785
GraphMVP2023.110.777
GraphMVPPre-training status=Pre-trained, Pre-training dataset=ZINC15, Evaluation protocol=Fine-tuning, Split type=Scaffold-split2024.050.777
MGSSL2023.110.776
Hi-GMAE-FPre-training status=Pre-trained, Pre-training dataset=ZINC15, Evaluation protocol=Fine-tuning, Split type=Scaffold-split2024.050.775
MAM2023.110.774
TMCL2023.110.772
Mole-BERT2026.020.772
Hi-GMAE-GPre-training status=Pre-trained, Pre-training dataset=ZINC15, Evaluation protocol=Fine-tuning, Split type=Scaffold-split2024.050.771
UnifiedMolPre-training status=Pre-trained, Pre-training dataset=ZINC15, Evaluation protocol=Fine-tuning, Split type=Scaffold-split2024.050.769
BGRL2026.020.767
JOAO2023.110.766
GPSEaugmented2026.060.766
MAMEncoder=vanilla VQ-VAE2023.110.765
GraphCL2023.110.764
GraphMAE2023.110.764
AD-GCL2023.110.763
GraphMAE2026.020.763
MGSSL2026.020.763
GraphMAEPre-training status=Pre-trained, Pre-training dataset=ZINC15, Evaluation protocol=Fine-tuning, Split type=Scaffold-split2024.050.763
GraphMAE2026.060.763
D-MPNN2023.080.762
3D InfoMax2023.110.762
GraphLogPre-training status=Pre-trained, Pre-training dataset=ZINC15, Evaluation protocol=Fine-tuning, Split type=Scaffold-split2024.050.76
GraphLoG2026.060.76
GPT-GNN2023.110.759
APTBase Model=Mole-BERT2023.110.759
GINGraph-level pre-training=None, Node-level pre-training=Context Prediction2019.050.758
AttrMask2023.110.758
ContextPredPre-training status=Pre-trained, Pre-training dataset=ZINC15, Evaluation protocol=Fine-tuning, Split type=Scaffold-split2024.050.758
SSL pre-trainingPre-training strategy=SSL2026.060.758
TMCLMode=w/o Ltri2023.110.757
GraphLoG2023.110.755
SimGRACE2023.110.754
SimGRACEPre-training status=Pre-trained, Pre-training dataset=ZINC15, Evaluation protocol=Fine-tuning, Split type=Scaffold-split2024.050.754
GINGraph-level pre-training=None, Node-level pre-training=Infomax2019.050.753
InfomaxPre-training status=Pre-trained, Pre-training dataset=ZINC15, Evaluation protocol=Fine-tuning, Split type=Scaffold-split2024.050.753
APTBase Model=EdgePred2023.110.752
EdgePred2023.110.751
Infomax2026.020.748
GINGraph-level pre-training=None, Node-level pre-training=Attribute Masking2019.050.747
Attr mask2026.020.747
AttrMaskingPre-training status=Pre-trained, Pre-training dataset=ZINC15, Evaluation protocol=Fine-tuning, Split type=Scaffold-split2024.050.747
G2PT2026.060.745
InfoGraph2023.110.744
JOAO2026.020.742
GINGraph-level pre-training=None, Node-level pre-training=EdgePred2019.050.741
GraphCL2026.020.738
No Pre-train2026.020.734
GCNPre-training status=None, Pre-training dataset=N/A, Evaluation protocol=Supervised Learning, Split type=Scaffold-split2024.050.732
RGCLPre-training status=Pre-trained, Pre-training dataset=ZINC15, Evaluation protocol=Fine-tuning, Split type=Scaffold-split2024.050.731
G-Motif2023.110.73
GraphLOG2026.020.728
ContextPred2023.110.725
AD-GCLPre-training status=Pre-trained, Pre-training dataset=ZINC15, Evaluation protocol=Fine-tuning, Split type=Scaffold-split2024.050.722
G-Contextual2023.110.721
GIN2023.080.718
GINGraph-level pre-training=None, Node-level pre-training=None2019.050.718
MPTr+CIPEBackbone=MPTr, Positional encoding=CIPE2026.060.718
JOAOPre-training status=Pre-trained, Pre-training dataset=ZINC15, Evaluation protocol=Fine-tuning, Split type=Scaffold-split2024.050.717
GCN2023.080.716
TMCLMode=w/o Lcon2023.110.716
ADGCL2026.020.715
GraphGPSPre-training status=None, Pre-training dataset=N/A, Evaluation protocol=Supervised Learning, Split type=Scaffold-split2024.050.712
Hi-GMAE-GPre-training status=None, Pre-training dataset=N/A, Evaluation protocol=Supervised Learning, Split type=Scaffold-split2024.050.712
MPTr+HKSEBackbone=MPTr, Positional encoding=HKSE2026.060.709
No pretrain2023.110.707
SAGPoolPre-training status=None, Pre-training dataset=N/A, Evaluation protocol=Supervised Learning, Split type=Scaffold-split2024.050.704
CP2026.020.702
MPTrBackbone=MPTr2026.060.701
MPTr+RWSEBackbone=MPTr, Positional encoding=RWSE2026.060.699
GraphCLPre-training status=Pre-trained, Pre-training dataset=ZINC15, Evaluation protocol=Fine-tuning, Split type=Scaffold-split2024.050.698
GraphCLPre-training strategy=GraphCL2026.060.698
MAE2026.020.697
MPTr+CycleSEBackbone=MPTr, Positional encoding=CycleSE2026.060.696
MPTr+LapPEBackbone=MPTr, Positional encoding=LapPE2026.060.695
SVM2023.080.673
GMTPre-training status=None, Pre-training dataset=N/A, Evaluation protocol=Supervised Learning, Split type=Scaffold-split2024.050.672