- 📢 News
- 🧪 1. Summary
- 🧬 2. EDBench Database
- 🧪 3. Benchmark Tasks
- 🚀 4. Running Benchmarks
- 📬 Contact
- 📘 License
-
[2025/05/13] Uploaded code of prediction tasks with X-3D and PointVector.
-
[2025/05/10] Repository initialized!
Most existing molecular machine learning force fields (MLFFs) focus on atom- or molecule-level properties like energy and forces, while overlooking the foundational role of electron density (ED), denoted as
EDBench 🐋 addresses this gap by providing a large-scale, high-quality dataset of electron densities for over 3.3 million molecules, based on the PCQM4Mv2 standard. To benchmark electronic-scale learning, we introduce a suite of ED-centric tasks covering:
- Prediction of quantum chemical properties
- Retrieval across structure and ED modalities
- Generation of ED from molecular structures
We demonstrate that ML models can learn from ED with high accuracy and also generate high-quality ED, dramatically reducing DFT costs. All data and benchmarks will be made publicly available to support ED-driven research in drug discovery and materials science.
📄 Citation
@misc{xiang2025edbenchlargescaleelectrondensity, title = {EDBench: Large-Scale Electron Density Data for Molecular Modeling}, author = {Hongxin Xiang and Ke Li and Mingquan Liu and Zhixiang Cheng and Bin Yao and Wenjie Du and Jun Xia and Li Zeng and Xin Jin and Xiangxiang Zeng}, year = {2025}, eprint = {2505.09262}, archivePrefix= {arXiv}, primaryClass = {physics.chem-ph}, url = {https://arxiv.org/abs/2505.09262}
Built on PCQM4Mv2, the EDBench dataset contains accurate DFT-computed EDs for 3.3M+ molecules, enabling deep learning at the electronic scale.
We design a suite of benchmark tasks centered on electron density (ED):
Predict quantum chemical properties from ED representations.
📂 Click to expand the directory structure
{benchmark_root}
{benchmark root}
├── ed_energy_5w
│ ├── raw
│ │ ├── ed_energy_5w.csv
│ │ ├── readme.md
│ │ └── psi4_grid0.4_cubes
│ │ └── {mol_index}
│ │ ├── Mol1_Dt.cube
│ │ ├── timer.dat
│ │ ├── Mol1.sdf
│ │ ├── Mol1_ESP.cube
│ │ └── {mol_index}_Psi4.out
│ └── processed
│ └── mol_EDthresh{thresh}_data.pkl
├── ed_homo_lumo_5w
│ ├── raw
│ │ ├── ed_homo_lumo_5w.csv
│ │ ├── readme.md
│ │ └── psi4_grid0.4_cubes
│ └── processed
│ └── mol_EDthresh{thresh}_data.pkl
├── ed_multipole_moments_5w
│ ├── raw
│ │ ├── ed_multipole_moments_5w.csv
│ │ ├── readme.md
│ │ └── psi4_grid0.4_cubes
│ └── processed
│ └── mol_EDthresh{thresh}_data.pkl
└── ed_open_shell_5w
├── raw
│ ├── ed_open_shell_5w.csv
│ ├── readme.md
│ └── psi4_grid0.4_cubes
└── processed
└── mol_EDthresh{thresh}_data.pkl| Dataset | Dir Name | Link | Description |
|---|---|---|---|
| ED5-EC | ed_energy_5w |
Dataverse | 6 energy components (DF-RKS Final Energy, Nuclear Repulsion Energy, One-Electron Energy, Two-Electron Energy, DFT Exchange-Correlation Energy, Total Energy) |
| ED5-OE | ed_homo_lumo_5w |
Dataverse | 7 orbital energies (HOMO-2, HOMO-1, HOMO-0, LUMO+0, LUMO+1, LUMO+2, LUMO+3) |
| ED5-MM | ed_multipole_moments_5w |
Dataverse | 4 multipole moment (Dipole X, Dipole Y, Dipole Z, Magnitude) |
| ED5-OCS | ed_open_shell_5w |
Dataverse | Binary classification of open-/closed-shell systems |
Cross-modal retrieval between molecular structures (MS) and electron densities (ED).
📂 Click to expand the directory structure
{benchmark_root}
├── ed_retrieval_5w/
│ ├── raw/
│ │ ├── ed_retrieval_5w.csv
│ │ ├── readme.md
│ │ └── psi4_grid0.4_cubes/
│ └── processed/
│ └── mol_EDthresh{thresh}_data.pkl| Dataset | Dir Name | Link | Description |
|---|---|---|---|
| ED5-MER | ed_retrieval_5w |
Dataverse | Cross-modal retrieval: MS ↔ ED |
Generate ED representations from molecular structures.
📂 Click to expand the directory structure
{benchmark_root}
├── ed_prediction_5w/
│ ├── raw/
│ │ ├── ed_prediction_5w.csv
│ │ ├── readme.md
│ │ └── psi4_grid0.4_cubes/
│ └── processed/
│ └── mol_EDthresh{thresh}_data.pkl| Dataset | Dir Name | Link | Description |
|---|---|---|---|
| ED5-EDP | ed_prediction_5w |
Dataverse | Predict ED from molecular structures |
Each raw/ directory includes a .csv summary file describing each molecule.
index: Molecule indexsmiles: Original SMILEScanonical_smiles: Canonicalized SMILESscaffold_split: Scaffold-based split (80% train / 10% valid / 10% test)random_split: Random split (80% train / 10% valid / 10% test)
- Prediction:
label: Ground-truth values (space-separated if multi-task)
- Retrieval:
negative_index: Space-separated indices of 10 negative samples
The code and detailed instructions for running prediction tasks can be found in this 📂directory.
Feel free to open an issue or pull request for questions or contributions. For academic inquiries, contact the authors upon paper publication.
Released for research use under an open-source MIT license.