MoleculeNet
ToxCast
Structure
8,597Graphs
19Nodes
19Edges
617Classes
9Node Feature Dim
3Edge Feature Dim
Coverage
271Results
1Variants
45Papers
- A Generalist Cross-Domain Molecular Learning Framework for Structure-Based Drug Discovery A Generalist Cross-Domain Molecular Learning Framework for Structure-Based Drug Discovery
- ICML 2025: Graph Generative Pre-trained Transformer Graph Generative Pre-trained Transformer ICML 2025
- ICML 2024: Towards Graph Foundation Models: Learning Generalities Across Graphs via Task-Trees Towards Graph Foundation Models: Learning Generalities Across Graphs via Task-Trees ICML 2024
- AAAI 2024: Pre-training Graph Neural Networks on Molecules by Using Subgraph-Conditioned Graph Information Bottleneck Pre-training Graph Neural Networks on Molecules by Using Subgraph-Conditioned Graph Information Bottleneck AAAI 2024
- TMLR 2024: Towards Graph Foundation Models: A Study on the Generalization of Positional and Structural Encodings Towards Graph Foundation Models: A Study on the Generalization of Positional and Structural Encodings TMLR 2024
- NeurIPS 2024: GDeR: Safeguarding Efficiency, Balancing, and Robustness via Prototypical Graph Pruning GDeR: Safeguarding Efficiency, Balancing, and Robustness via Prototypical Graph Pruning NeurIPS 2024
- SpeGCL: Self-supervised Graph Spectrum Contrastive Learning without Positive Samples SpeGCL: Self-supervised Graph Spectrum Contrastive Learning without Positive Samples
- Molecular Topological Profile (MOLTOP) - Simple and Strong Baseline for Molecular Graph Classification Molecular Topological Profile (MOLTOP) - Simple and Strong Baseline for Molecular Graph Classification
- NeurIPS 2024: Text-space Graph Foundation Models: Comprehensive Benchmarks and New Insights Text-space Graph Foundation Models: Comprehensive Benchmarks and New Insights NeurIPS 2024
- ICML 2024: UniCorn: A Unified Contrastive Learning Approach for Multi-view Molecular Representation Learning UniCorn: A Unified Contrastive Learning Approach for Multi-view Molecular Representation Learning ICML 2024
- NeurIPS 2024: SubGDiff: A Subgraph Diffusion Model to Improve Molecular Representation Learning SubGDiff: A Subgraph Diffusion Model to Improve Molecular Representation Learning NeurIPS 2024
- ICML 2024: Community-Invariant Graph Contrastive Learning Community-Invariant Graph Contrastive Learning ICML 2024
- ICLR 2024: Decoupling Weighing and Selecting for Integrating Multiple Graph Pre-training Tasks Decoupling Weighing and Selecting for Integrating Multiple Graph Pre-training Tasks ICLR 2024
- Subgraph-level Universal Prompt Tuning Subgraph-level Universal Prompt Tuning
- UGMAE: A Unified Framework for Graph Masked Autoencoders UGMAE: A Unified Framework for Graph Masked Autoencoders
- Impact of Domain Knowledge and Multi-Modality on Intelligent Molecular Property Prediction: A Systematic Survey Impact of Domain Knowledge and Multi-Modality on Intelligent Molecular Property Prediction: A Systematic Survey
- AAAI 2023: Fine-tuning Graph Neural Networks by Preserving Graph Generative Patterns Fine-tuning Graph Neural Networks by Preserving Graph Generative Patterns AAAI 2023
- NeurIPS 2023: Better with Less: A Data-Active Perspective on Pre-Training Graph Neural Networks Better with Less: A Data-Active Perspective on Pre-Training Graph Neural Networks NeurIPS 2023
- NeurIPS 2023: Rethinking Tokenizer and Decoder in Masked Graph Modeling for Molecules Rethinking Tokenizer and Decoder in Masked Graph Modeling for Molecules NeurIPS 2023
- UniMAP: Universal SMILES-Graph Representation Learning UniMAP: Universal SMILES-Graph Representation Learning
- Atom-Motif Contrastive Transformer for Molecular Property Prediction Atom-Motif Contrastive Transformer for Molecular Property Prediction
- Deep Prompt Tuning for Graph Transformers Deep Prompt Tuning for Graph Transformers
- AAAI 2023: 3D Denoisers are Good 2D Teachers: Molecular Pretraining via Denoising and Cross-Modal Distillation 3D Denoisers are Good 2D Teachers: Molecular Pretraining via Denoising and Cross-Modal Distillation AAAI 2023
- Motif-aware Attribute Masking for Molecular Graph Pre-training Motif-aware Attribute Masking for Molecular Graph Pre-training
- Graph Self-Contrast Representation Learning Graph Self-Contrast Representation Learning
- Subgraph Networks Based Contrastive Learning Subgraph Networks Based Contrastive Learning
- ICML 2023: A Group Symmetric Stochastic Differential Equation Model for Molecule Multi-modal Pretraining A Group Symmetric Stochastic Differential Equation Model for Molecule Multi-modal Pretraining ICML 2023
- gimlet: A Unified Graph-Text Model for Instruction-Based Molecule Zero-Shot Learning gimlet: A Unified Graph-Text Model for Instruction-Based Molecule Zero-Shot Learning
- Robust Ante-hoc Graph Explainer using Bilevel Optimization Robust Ante-hoc Graph Explainer using Bilevel Optimization
- NeurIPS 2022: Universal Prompt Tuning for Graph Neural Networks Universal Prompt Tuning for Graph Neural Networks NeurIPS 2022
- Improving Molecular Pretraining with Complementary Featurizations Improving Molecular Pretraining with Complementary Featurizations
- NeurIPS 2022: Does GNN Pretraining Help Molecular Representation? Does GNN Pretraining Help Molecular Representation? NeurIPS 2022
- ICML 2022: Let Invariant Rationale Discovery Inspire Graph Contrastive Learning Let Invariant Rationale Discovery Inspire Graph Contrastive Learning ICML 2022
- KDD 2022: KPGT: Knowledge-Guided Pre-training of Graph Transformer for Molecular Property Prediction KPGT: Knowledge-Guided Pre-training of Graph Transformer for Molecular Property Prediction KDD 2022
- ICML 2022: Omni-Granular Ego-Semantic Propagation for Self-Supervised Graph Representation Learning Omni-Granular Ego-Semantic Propagation for Self-Supervised Graph Representation Learning ICML 2022
- KDD 2022: GraphMAE: Self-Supervised Masked Graph Autoencoders GraphMAE: Self-Supervised Masked Graph Autoencoders KDD 2022
- NeurIPS 2022: Graph Self-supervised Learning with Accurate Discrepancy Learning Graph Self-supervised Learning with Accurate Discrepancy Learning NeurIPS 2022
- OOD-GNN: Out-of-Distribution Generalized Graph Neural Network OOD-GNN: Out-of-Distribution Generalized Graph Neural Network
- ICLR 2021: 16 Pre-training Molecular Graph Representation with 3D Geometry 16 Pre-training Molecular Graph Representation with 3D Geometry ICLR 2021
- NeurIPS 2021: Motif-based Graph Self-Supervised Learning for Molecular Property Prediction Motif-based Graph Self-Supervised Learning for Molecular Property Prediction NeurIPS 2021
- AAAI 2021: GeomGCL: Geometric Graph Contrastive Learning for Molecular Property Prediction GeomGCL: Geometric Graph Contrastive Learning for Molecular Property Prediction AAAI 2021
- ChemRL-GEM: Geometry Enhanced Molecular Representation Learning for Property Prediction ChemRL-GEM: Geometry Enhanced Molecular Representation Learning for Property Prediction
- Graph convolutions that can finally model local structure Graph convolutions that can finally model local structure
- ICLR 2019: Strategies for Pre-training Graph Neural Networks Strategies for Pre-training Graph Neural Networks ICLR 2019
- AAAI 2018: Adaptive Graph Convolutional Neural Networks Adaptive Graph Convolutional Neural Networks AAAI 2018
617-task multi-label graph classification Multi-task toxicological profile prediction (617 tasks) from the EPA ToxCast program. SMILES and labels are fixed; molecular graph featurization is implementation-defined. Evaluated by ROC-AUC.
Dataset details
Task
Multi-task toxicological profile prediction (617 tasks) from the EPA ToxCast program. The primary catalog metric is ROC-AUC.
Data
Multi-task toxicological profile prediction (617 tasks) from the EPA ToxCast program.
Features
MoleculeNet distributes SMILES and targets, not one mandatory graph featurization. A graph implementation normally derives atom and bond fields with RDKit or DeepChem; results depend on featurizer, salt handling, stereochemistry, and invalid-molecule policy.
Splits and evaluation
The catalog records these protocols or variants: Scaffold split. Evaluation uses ROC-AUC (higher is better). Exact masks or folds must come from the cited release.
Quirks and pitfalls
Small samples, imbalance, missing assay labels, duplicate compounds, and scaffold leakage are common. Missing labels are not negatives. Always report split algorithm, featurizer, metric aggregation, and dataset version; random and scaffold results are not comparable.
Sources
SOTA Progression
new SOTA
matches SOTA at that time
other proposed result
other baseline result
Leaderboard
| # | Model | ROC-AUC ↑ | Accuracy | Paper |
|---|---|---|---|---|
| 1 | GeomGCL | 0.7630 | — | |
| 2 | LiGhT DeepGPT | 0.7570
±
0.0110 | — | |
| 3 | CoMPT | 0.7550 | — | |
| 4 | GINE w/ VN | 0.7490
±
0.0020 Accuracy
0.7490
±
0.0020 | 0.7490
±
0.0020 | |
| 5 | GINe+ K=1 w/ VN | 0.7490
±
0.0080 Accuracy
0.7490
±
0.0080 | 0.7490
±
0.0080 | |
| 6 | KPGT | 0.7460
±
0.0020 | — | |
| 7 | LiGhT FT | 0.7450
±
0.0050 | — | |
| 8 | GCN w/ VN | 0.7430
±
0.0030 Accuracy
0.7430
±
0.0030 | 0.7430
±
0.0030 | |
| 9 | AttentiveFP | 0.7430 | — | |
| 10 | DMPNN | 0.7430 | — | |
| 11 | GeomMPNN | 0.7430 | — | |
| 12 | GINE | 0.7410
±
0.0040 Accuracy
0.7410
±
0.0040 | 0.7410
±
0.0040 | |
| 13 | NaiveGINe+ K=3 w/ VN | 0.7370
±
0.0070 Accuracy
0.7370
±
0.0070 | 0.7370
±
0.0070 | |
| 14 | GCN | 0.7350
±
0.0020 Accuracy
0.7350
±
0.0020 | 0.7350
±
0.0020 | |
| 15 | GraphGPS DeepGPT | 0.7350
±
0.0050 | — | |
| 16 | MAT | 0.7350 | — | |
| 17 | Graphormer DeepGPT | 0.7250
±
0.0110 | — | |
| 18 | Contextpred+Sup | 0.7240
±
0.0150 | — | |
| 19 | GraphGPS FT | 0.7220
±
0.0110 | — | |
| 20 | Context Prediction + Supervised | 0.7219
±
0.0079 | — | |
| 21 | HIMP | 0.7210
±
0.0040 Accuracy
0.7210
±
0.0040 | 0.7210
±
0.0040 | |
| 22 | MoCL | 0.7180 | — | |
| 23 | Masking Node + Supervised | 0.7166
±
0.0073 | — | |
| 24 | Supervised | 0.7164
±
0.0046 | — | |
| 25 | 3D Infomax | 0.7160
±
0.0130 | — | |
| 26 | Masking+Sup | 0.7150
±
0.0070 | — | |
| 27 | AMCT | 0.7150
±
0.0110 | — | |
| 28 | DeeperGCN | 0.7140
±
0.0050 Accuracy
0.7140
±
0.0050 | 0.7140
±
0.0050 | |
| 29 | ContextPred | 0.7140
±
0.0180 | — | |
| 30 | EdgePred | 0.7120
±
0.0110 | — | |
| 31 | JOAO | 0.7110
±
0.0140 | — | |
| 32 | S-CGIB | 0.7095
±
0.0027 | — | |
| 33 | GIN | 0.7095
±
0.0027 | — | |
| 34 | GROVER | 0.7080
±
0.0150 | — | |
| 35 | InfoGraph | 0.7050 | — | |
| 36 | AGCN | 0.7033 | — | |
| 37 | Graphormer | 0.7030
±
0.0100 | — | |
| 38 | HMGNN | 0.7020 | — | |
| 39 | Context Prediction | 0.7018
±
0.0044 | — | |
| 40 | GT | 0.6999
±
0.0037 | — | |
| 41 | Node Prediction | 0.6977
±
0.0013 | — | |
| 42 | GraphCL | 0.6960
±
0.0230 | — | |
| 43 | UniCorn | 0.6940
±
0.0110 | — | |
| 44 | GEM | 0.6920
±
0.0040 | — | |
| 45 | GraphFP | 0.6915
±
0.0192 | — | |
| 46 | No pretrain | 0.6913
±
0.0055 | — | |
| 47 | Molformer | 0.6910
±
0.0120 | — | |
| 48 | Motif Prediction | 0.6909
±
0.0007 | — | |
| 49 | Infomax | 0.6900
±
0.0120 | — | |
| 50 | GraphMVP | 0.6890
±
0.0100 | — |
SOTA performance
set a new SOTA at the time
matched the SOTA at the time