List your company
ResearchFormerly WizWand

Molecular Property Prediction on MoleculeNet SIDER (scaffold)

0.849ROC-AUCMPTr+CIPE
0.585880.654190.72250.79081May 29, 2019Aug 1, 2020Oct 6, 2021Dec 10, 2022Feb 14, 2024Apr 19, 2025Jun 24, 2026
Updated 4mo ago

Evaluation results

MethodLinks
MPTr+CIPEBackbone=MPTr, Positional encoding=CIPE2026.060.849
MPTr+HKSEBackbone=MPTr, Positional encoding=HKSE2026.060.843
MPTr+CycleSEBackbone=MPTr, Positional encoding=CycleSE2026.060.842
MPTr+RWSEBackbone=MPTr, Positional encoding=RWSE2026.060.839
MPTr+LapPEBackbone=MPTr, Positional encoding=LapPE2026.060.838
MPTrBackbone=MPTr2026.060.835
SELFormer2023.040.745
DumplingGNN2024.090.74
GraphConv + dummy super nodeGraph construction=dummy super node2024.090.735
SYN-FUSIONfusion_source=Hu et. al2023.080.699
RF2023.080.684
SVM2023.080.682
GEM2023.040.672
GROVER_largeModel scale=large2024.090.672
MolXPT2024.090.672
N-Gram RFClassifier=Random Forest2024.090.668
GraphMVP2024.090.659
Uni-Mol2024.090.659
N-Gram XGBClassifier=XGBoost2024.090.655
PretrainGNN2024.090.654
Hu et al.2023.080.652
Hu et al.2023.040.652
MolCLR2023.040.652
SYN-FUSIONfusion_source=MolCLR2023.080.65
MolCLRbackbone=GIN2023.080.649
KPGT2023.040.649
GraphMVP-C2023.040.639
GINGraph-level pre-training=Supervised, Node-level pre-training=Attribute Masking2019.050.639
L2_SPBackbone=GIN (supervised_contextpred), Strategy=Fine-tuning strategy2022.030.638
GINGraph-level pre-training=Supervised, Node-level pre-training=EdgePred2019.050.633
GTOT-TuningBackbone=GIN (supervised_contextpred), Strategy=GTOT-Tuning2022.030.633
D-MPNN2023.080.632
Feature (DELTA w/o ATT)Backbone=GIN (supervised_contextpred), Strategy=Fine-tuning strategy2022.030.63
DELTABackbone=GIN (supervised_contextpred), Strategy=Fine-tuning strategy2022.030.629
BSSBackbone=GIN (supervised_contextpred), Strategy=Fine-tuning strategy2022.030.628
Mole-BERT2023.110.628
Mole-BERTPre-training status=Pre-trained, Pre-training dataset=ZINC15, Evaluation protocol=Fine-tuning, Split type=Scaffold-split2024.050.628
GINGraph-level pre-training=Supervised, Node-level pre-training=Context Prediction2019.050.627
Fine-TuningBackbone=GIN (supervised_contextpred), Strategy=Baseline2022.030.627
GraSPNet2026.020.625
StochNormBackbone=GIN (supervised_contextpred), Strategy=Fine-tuning strategy2022.030.622
UnifiedMolPre-training status=Pre-trained, Pre-training dataset=ZINC15, Evaluation protocol=Fine-tuning, Split type=Scaffold-split2024.050.622
GINGraph-level pre-training=Supervised, Node-level pre-training=None2019.050.621
Hi-GMAE-FPre-training status=Pre-trained, Pre-training dataset=ZINC15, Evaluation protocol=Fine-tuning, Split type=Scaffold-split2024.050.62
G2PT2026.060.619
MGSSL2023.110.616
AD-GCL2023.110.615
MGSSL2026.020.615
AD-GCLPre-training status=Pre-trained, Pre-training dataset=ZINC15, Evaluation protocol=Fine-tuning, Split type=Scaffold-split2024.050.615
MAM2023.110.614
APTBase Model=EdgePred2023.110.614
GraphLogPre-training status=Pre-trained, Pre-training dataset=ZINC15, Evaluation protocol=Fine-tuning, Split type=Scaffold-split2024.050.612
RGCLPre-training status=Pre-trained, Pre-training dataset=ZINC15, Evaluation protocol=Fine-tuning, Split type=Scaffold-split2024.050.612
GraphLoG2026.060.612
GPSEaugmented2026.060.611
GINGraph-level pre-training=None, Node-level pre-training=Attribute Masking2019.050.61
G-Motif2023.110.61
AttrMaskingPre-training status=Pre-trained, Pre-training dataset=ZINC15, Evaluation protocol=Fine-tuning, Split type=Scaffold-split2024.050.61
SSL pre-trainingPre-training strategy=SSL2026.060.61
GINGraph-level pre-training=None, Node-level pre-training=Context Prediction2019.050.609
GINGraph-level pre-training=Supervised, Node-level pre-training=Infomax2019.050.609
GATPre-training status=None, Pre-training dataset=N/A, Evaluation protocol=Supervised Learning, Split type=Scaffold-split2024.050.609
ContextPredPre-training status=Pre-trained, Pre-training dataset=ZINC15, Evaluation protocol=Fine-tuning, Split type=Scaffold-split2024.050.609
APTBase Model=Mole-BERT2023.110.608
JOAO2026.020.608
MAMEncoder=vanilla VQ-VAE2023.110.607
Attentive FP2024.090.606
SimSGT2026.020.606
AttentiveFP2026.060.606
GraphMAE2023.110.605
AttrMask2023.110.605
SAGPoolPre-training status=None, Pre-training dataset=N/A, Evaluation protocol=Supervised Learning, Split type=Scaffold-split2024.050.605
GraphCLPre-training status=Pre-trained, Pre-training dataset=ZINC15, Evaluation protocol=Fine-tuning, Split type=Scaffold-split2024.050.605
Hi-GMAE-GPre-training status=Pre-trained, Pre-training dataset=ZINC15, Evaluation protocol=Fine-tuning, Split type=Scaffold-split2024.050.605
GraphCLPre-training strategy=GraphCL2026.060.605
GINGraph-level pre-training=None, Node-level pre-training=EdgePred2019.050.604
JOAO2023.110.604
EdgePred2023.110.604
BGRL2026.020.604
GraphMAEPre-training status=Pre-trained, Pre-training dataset=ZINC15, Evaluation protocol=Fine-tuning, Split type=Scaffold-split2024.050.603
GraphMAE2026.060.603
SimGRACE2023.110.602
GraphMVP2023.110.602
CP2026.020.602
SimGRACEPre-training status=Pre-trained, Pre-training dataset=ZINC15, Evaluation protocol=Fine-tuning, Split type=Scaffold-split2024.050.602
GraphMVPPre-training status=Pre-trained, Pre-training dataset=ZINC15, Evaluation protocol=Fine-tuning, Split type=Scaffold-split2024.050.602
GraphGPS2026.060.602
NID_CLEvaluation Protocol=Linear Probing, Pre-training Dataset=ZINC15, Backbone=5-layer GIN2024.050.601
Infomax2026.020.601
GraphMAE2026.020.6
GCNPre-training status=None, Pre-training dataset=N/A, Evaluation protocol=Supervised Learning, Split type=Scaffold-split2024.050.6
JOAOPre-training status=Pre-trained, Pre-training dataset=ZINC15, Evaluation protocol=Fine-tuning, Split type=Scaffold-split2024.050.6
GraphCL2023.110.598
GraphLOG2026.020.598
ContextPred2023.110.597
GraphLoG2023.110.596
TMCL2023.110.596
Attr mask2026.020.596
GraphMAE22026.020.596
GraphMAE2Pre-training status=Pre-trained, Pre-training dataset=ZINC15, Evaluation protocol=Fine-tuning, Split type=Scaffold-split2024.050.596