AGAT (Atomic Graph ATtention networks)

### The PyTorch backend AGAT is available now, try with pip install agat. For previous version, install with pip install agat==7.*.

Using AGAT

The documentation of AGAT API is available.

Installation

Install with conda environment

• Create a new environment
  console conda create -n agat python==3.10

• Activate the environment
  console conda activate agat

• Install PyTorch,
  Navigate to the installation page and choose you platform. For example (GPU): console conda install pytorch torchvision torchaudio pytorch-cuda=11.8 -c pytorch -c nvidia

• Install dgl.
  Please navigate to the Get Started page of dgl. For example (GPU):
  console conda install -c dglteam/label/cu118 dgl

• Install AGAT package
  console pip install agat

• Install CUDA and CUDNN [Optional].

  • For HPC, you may load CUDA by checking module av, or you can contact your administrator for help.
  • CUDA Toolkit
  • cuDNN

Quick start

Prepare VASP calculations

Run VASP calculations at this step.

Collect paths of VASP calculations

• We provided examples of VASP outputs at VASPcalculationsexample.
  
• Find all directories containing OUTCAR file:
  find . -name OUTCAR > paths.log
  
• Remove the string 'OUTCAR' in paths.log.
  sed -i 's/OUTCAR$//g' paths.log
  
• Specify the absolute paths in paths.log.
  sed -i "s#^.#${PWD}#g" paths.log

Build database

python from agat.data import BuildDatabase if __name__ == '__main__': database = BuildDatabase(mode_of_NN='ase_dist', num_of_cores=16) database.build()

Train AGAT model

python from agat.model import Fit f = Fit() f.fit()

Application (geometry optimization)

```python from ase.optimize import BFGS from agat.app import AgatCalculator from ase.io import read from ase import Atoms

modelsavedir = 'agatmodel' graphbuildschemedir = 'dataset'

atoms = read('POSCAR') calculator=AgatCalculator(modelsavedir, graphbuildscheme_dir) atoms = Atoms(atoms, calculator=calculator) dyn = BFGS(atoms, trajectory='test.traj') dyn.run(fmax=0.05) ```

Application (high-throughput prediction)

```python from agat.app.cata import HpAds

modelsavedir = 'agatmodel' graphbuildschemedir = 'dataset' formula='NiCoFePdPt'

ha = HpAds(modelsavedir=modelsavedir, graphbuildschemedir=graphbuildschemedir) ha.run(formula=formula) ```

For more custom manipulations, see our documentation page.

Some default parameters

agat/default_parameters.py; Explanations: docs/sphinx/source/Default parameters.md.

Change log

Please check Change_log.md