Molecular Property Prediction On Clintox 1

评估指标

ROC-AUC

评测结果

各个模型在此基准测试上的表现结果

模型名称	ROC-AUC	Paper Title	Repository
SPMM	91.0	Bidirectional Generation of Structure and Properties Through a Single Molecular Foundation Model	-
GAL 1.3B	58.9	Galactica: A Large Language Model for Science	-
GAL 125M	51.8	Galactica: A Large Language Model for Science	-
N-GramRF	77.5	N-Gram Graph: Simple Unsupervised Representation for Graphs, with Applications to Molecules	-
GAL 120B	82.6	Galactica: A Large Language Model for Science	-
Deep-CBN	99.2	Integrating convolutional layers and biformer network with forward-forward and backpropagation training
ChemBFN	99.18	A Bayesian Flow Network Framework for Chemistry Tasks	-
ChemBERTa-2 (MTR-77M)	56.3	ChemBERTa-2: Towards Chemical Foundation Models	-
GROVER (base)	81.2	Self-Supervised Graph Transformer on Large-Scale Molecular Data	-
Uni-Mol	91.9	Uni-Mol: A Universal 3D Molecular Representation Learning Framework
GAL 6.7B	78.4	Galactica: A Large Language Model for Science	-
S-CGIB	78.58±2.01	Pre-training Graph Neural Networks on Molecules by Using Subgraph-Conditioned Graph Information Bottleneck
D-MPNN	90.6	Analyzing Learned Molecular Representations for Property Prediction	-
MolXPT	95.3±0.2	MolXPT: Wrapping Molecules with Text for Generative Pre-training	-
GAL 30B	82.2	Galactica: A Large Language Model for Science	-
ChemRL-GEM	90.1	ChemRL-GEM: Geometry Enhanced Molecular Representation Learning for Property Prediction	-
N-GramXGB	87.5	N-Gram Graph: Simple Unsupervised Representation for Graphs, with Applications to Molecules	-
GROVER (large)	76.2	Self-Supervised Graph Transformer on Large-Scale Molecular Data	-
SYN-FUSION	94.7±0.2	Synergistic Fusion of Graph and Transformer Features for Enhanced Molecular Property Prediction	-
PretrainGNN	72.6	Strategies for Pre-training Graph Neural Networks	-

0 of 20 row(s) selected.