Physics-aware-Multiplex-GNN

KO | EN

gitlite — search

#javascript #python #hacktoberfest #react #ai #typescript #llm #go #golang #android #machine-learning #rust #deep-learning #linux

Physics-aware-Multiplex-GNN

★ 73 Open GitHub ↗

Source code for "A universal framework for accurate and efficient geometric deep learning of molecular systems" (Nature Scientific Reports)

다운로드

최종 버전 다운로드 (.zip)

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# PAMNet: A Universal Framework for Accurate and Efficient Geometric Deep Learning of Molecular Systems
[![PWC](https://img.shields.io/badge/State_of_the_Art-Drug_Discovery_on_QM9-22c1c3?logo=paperswithcode)](https://opencodepapers-b7572d.gitlab.io/benchmarks/drug-discovery-on-qm9.html)

Official implementation of **PAMNet (Physics-aware Multiplex Graph Neural Network)**, as presented in our paper **[A universal framework for accurate and efficient geometric deep learning of molecular systems](https://www.nature.com/articles/s41598-023-46382-8)** accepted by *Nature Scientific Reports*.

PAMNet builds upon our previous [MXMNet](https://github.com/zetayue/MXMNet) model, achieving higher accuracy and efficiency than state-of-the-art baselines in diverse tasks such as: 
- **Small molecule property prediction**
- **RNA 3D structure prediction**
- **Protein-ligand binding affinity prediction**
<br/><br/>

This implementation is also applicable to our following works:
1. [Efficient and Accurate Physics-aware Multiplex Graph Neural Networks for 3D Small Molecules and Macromolecule Complexes](https://arxiv.org/abs/2206.02789) (preprint).
2. [Physics-aware Graph Neural Network for Accurate RNA 3D Structure Prediction](https://arxiv.org/abs/2210.16392) ([Machine Learning for Structural Biology Workshop](https://www.mlsb.io/) at *NeurIPS 2022*).

If you have any questions, feel free to open an issue or reach out to: szhang4@gradcenter.cuny.edu.

## Overall Architecture

## Updates
- **`2024-10` We provide the saved checkpoint of PAMNet (`./save/pamnet_rna.pt`) and code (`inference_rna_puzzles.py`) that can be used for RNA 3D structure prediction or reproducing the related results in our paper.**
- **`2024-01` We provide the docker image for running PAMNet at https://hub.docker.com/r/zetayue/pamnet.**
- **`2023-10` PAMNet [paper](https://www.nature.com/articles/s41598-023-46382-8) was accepted by *Nature Scientific Reports*.**
- **`2023-07` We release the code for PAMNet.**

## Environment Setup
### Option 1: Base on Dependencies

- Python : 3.7.4 
 - CUDA : 10.1

Dependencies can be installed with:
```
pip install -r requirements.txt
```

**Optional**: Install Open Babel 3.1.1 for binding affinity prediction on PDBbind:

1. Download [source file](https://anaconda.org/conda-forge/openbabel/3.1.1/download/linux-64/openbabel-3.1.1-py37h200e996_1.tar.bz2)
 2. `conda install filename`

### Option 2: Docker Image
Docker image for running PAMNet is available at https://hub.docker.com/r/zetayue/pamnet.

Requires **[NVIDIA Container Toolkit](https://github.com/NVIDIA/nvidia-container-toolkit)** installed to run with GPU support.

Example command to run:
```
nvidia-docker run --name pamnet -it --network=host --shm-size=1g --rm -v LOCAL_PATH:MOUNTED_PATH zetayue/pamnet:latest
```

## Datasets

**QM9 for small molecule property prediction:**

The training script (`main_qm9.py`) will automatically download the QM9 dataset and preprocess it.

**PDBbind for protein-ligand binding affinity prediction:**

1. Download `PDBbind_dataset.tar.gz` from [dropbox](https://www.dropbox.com/sh/2uih3c6fq37qfli/AAD-LHXSWMLAuGWzcQLk5WI3a).
 2. Unzip the downloaded file under `./data/PDBbind`. There will be two subfolders (`core-set` and `refined-set`) after the unzip.
 3. Run `python preprocess_pdbbind.py` to preprocess the dataset to construct graphs.

**RNA-Puzzles for RNA 3D structure prediction:**

1. Download `classics_train_val.tar` from [Stanford Digital Repository](https://doi.org/10.25740/bn398fc4306).
 2. Unzip the downloaded file under `./data/RNA-Puzzles`. There will be one subfolder `classics_train_val` containing `example_train` and `example_val`after the unzip.
 3. Run `python preprocess_rna_puzzles.py` to preprocess the dataset to construct graphs.

## How to Run
### Arguments
```
  --gpu             GPU number
  --seed            random seed
  --dataset         dataset to be used
  --epochs          number of epochs to train
  --lr              initial learning rate
  --wd              weight decay value
  --n_layer         number of hidden layers
  --dim             size of input hidden units
  --batch_size      batch size
  --cutoff_l        distance cutoff used in the local layer
  --cutoff_g        distance cutoff used in the global layer
  --model           model to be used on QM9
  --target          index of target (0~11) for prediction on QM9
```
### Example commands
**Small molecule property prediction on QM9:**

python -u main_qm9.py --dataset 'QM9' --model 'PAMNet' --target=7 --epochs=900 --batch_size=32 --dim=128 --n_layer=6 --lr=1e-4

**Protein-ligand binding affinity prediction on PDBbind:**

python -u main_pdbbind.py --dataset 'PDBbind' --epochs=170 --batch_size=32 --dim=128 --n_layer=3 --lr=1e-3

**RNA 3D structure prediction on RNA-Puzzles:**

*Training and Validation on the datasets curated by [ARES](https://doi.org/10.1126/science.abe5650):*

python -u main_rna_puzzles.py --dataset 'RNA-Puzzles' --epochs=15 --batch_size=8  --dim=16 --n_layer=1 --lr=1e-4
    
*Inference on RNA-Puzzles (example below is to predict scores for the 21 native RNA structures in RNA-Puzzles between 2010 and 2017 using the saved checkpoint (`pamnet_rna.pt`) that can reproduce the results in our paper):*

python -u inference_rna_puzzles.py --batch_size=16 --dataset='rna_native' --saved_model='pamnet_rna.pt'
 
## Citation
If you find our model and code helpful in your work, please consider citing us:
```
@article{zhang2023universal,
  title={A Universal Framework for Accurate and Efficient Geometric Deep Learning of Molecular Systems},
  author={Zhang, Shuo and Liu, Yang and Xie, Lei},
  journal={Scientific Reports},
  volume={13},
  number={1},
  pages={19171},
  year={2023},
  publisher={Nature Publishing Group UK London}
}

@article{zhang2022physics,
  title={Physics-aware graph neural network for accurate RNA 3D structure prediction},
  author={Zhang, Shuo and Liu, Yang and Xie, Lei},
  journal={arXiv preprint arXiv:2210.16392},
  year={2022}
}
```

Physics-aware-Multiplex-GNN

다운로드

오늘의 추천 프로젝트

Was this content helpful?

Recent Feedback

Physics-aware-Multiplex-GNN

다운로드

오늘의 추천 프로젝트

Was this content helpful?

Recent Feedback

Download README