Molecular Property Prediction On Bbbp 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
GROVER (large)	69.5	Self-Supervised Graph Transformer on Large-Scale Molecular Data
Uni-Mol	72.9	Uni-Mol: A Universal 3D Molecular Representation Learning Framework
GAL 6.7B	53.5	Galactica: A Large Language Model for Science
XGBoost	90.5	Accurate ADMET Prediction with XGBoost
Cano-BERT	89.2	Pushing the boundaries of molecular property prediction for drug discovery with multitask learning BERT enhanced by SMILES enumeration
Deep-CBN	75.8	Integrating convolutional layers and biformer network with forward-forward and backpropagation training
AttentiveFP	85.5	Therapeutics Data Commons: Machine Learning Datasets and Tasks for Drug Discovery and Development
GAL 125M	39.3	Galactica: A Large Language Model for Science
N-GramXGB	69.1	N-Gram Graph: Simple Unsupervised Representation for Graphs, with Applications to Molecules
ChemBERTa-2 (MTR-77M)	72.8	ChemBERTa-2: Towards Chemical Foundation Models
GAL 120B	66.1	Galactica: A Large Language Model for Science
ChemRL-GEM	72.4	ChemRL-GEM: Geometry Enhanced Molecular Representation Learning for Property Prediction	-
SPMM	73.3	Bidirectional Generation of Structure and Properties Through a Single Molecular Foundation Model
PretrainGNN	68.7	Strategies for Pre-training Graph Neural Networks	-
SMA	75.0	Self-Guided Masked Autoencoders for Domain-Agnostic Self-Supervised Learning
N-GramRF	69.7	N-Gram Graph: Simple Unsupervised Representation for Graphs, with Applications to Molecules
AttrMasking	89.2	Therapeutics Data Commons: Machine Learning Datasets and Tasks for Drug Discovery and Development
GROVER (base)	70.0	Self-Supervised Graph Transformer on Large-Scale Molecular Data
SELFormer	90.2	SELFormer: Molecular Representation Learning via SELFIES Language Models
S-CGIB	88.75±0.49	Pre-training Graph Neural Networks on Molecules by Using Subgraph-Conditioned Graph Information Bottleneck

0 of 29 row(s) selected.