Molecular Property Prediction On Tox21 1

評価指標

ROC-AUC

評価結果

このベンチマークにおける各モデルのパフォーマンス結果

モデル名	ROC-AUC	Paper Title	Repository
Autogluon	77.84	AutoGluon-Tabular: Robust and Accurate AutoML for Structured Data
N-GramRF	74.3	N-Gram Graph: Simple Unsupervised Representation for Graphs, with Applications to Molecules
Uni-Mol	79.6	Uni-Mol: A Universal 3D Molecular Representation Learning Framework
GAL 125M	54.3	Galactica: A Large Language Model for Science
GROVER (base)	74.3	Self-Supervised Graph Transformer on Large-Scale Molecular Data
PretrainGNN	78.1	Strategies for Pre-training Graph Neural Networks	-
GAL 120B	68.9	Galactica: A Large Language Model for Science
IterRefLSTM	83.00	Low Data Drug Discovery with One-shot Learning	-
Uni-Mol	79.6	Galactica: A Large Language Model for Science
GROVER (large)	73.5	Self-Supervised Graph Transformer on Large-Scale Molecular Data
GAL 6.7B	63.9	Galactica: A Large Language Model for Science
MolXPT	77.1	MolXPT: Wrapping Molecules with Text for Generative Pre-training	-
ChemRL-GEM	78.1	ChemRL-GEM: Geometry Enhanced Molecular Representation Learning for Property Prediction	-
BioAct-Het	89.80	BioAct-Het: A Heterogeneous Siamese Neural Network for Bioactivity Prediction Using Novel Bioactivity Representatio
N-GramXGB	75.8	N-Gram Graph: Simple Unsupervised Representation for Graphs, with Applications to Molecules
GAL 30B	68.5	Galactica: A Large Language Model for Science
S-CGIB	80.94±0.17	Pre-training Graph Neural Networks on Molecules by Using Subgraph-Conditioned Graph Information Bottleneck
D-MPNN	75.9	Analyzing Learned Molecular Representations for Property Prediction
Deep-CBN	92.4	Integrating convolutional layers and biformer network with forward-forward and backpropagation training
GAL 1.3B	60.6	Galactica: A Large Language Model for Science

0 of 20 row(s) selected.