alignn
Project description
Table of Contents
- Introduction
- Installation
- Examples
- Pre-trained models
- JARVIS-ALIGNN webapp
- ALIGNN-FF & ASE Calculator
- Peformances on a few datasets
- Useful notes
- References
- How to contribute
- Correspondence
- Funding support
ALIGNN & ALIGNN-FF (Introduction)
The Atomistic Line Graph Neural Network (https://www.nature.com/articles/s41524-021-00650-1) introduces a new graph convolution layer that explicitly models both two and three body interactions in atomistic systems. This is achieved by composing two edge-gated graph convolution layers, the first applied to the atomistic line graph L(g) (representing triplet interactions) and the second applied to the atomistic bond graph g (representing pair interactions).
A unified force-field model, ALIGNN-FF (https://pubs.rsc.org/en/content/articlehtml/2023/dd/d2dd00096b ) was developed that can model both structurally and chemically diverse solids with any combination of 89 elements from the periodic table.
Installation
First create a conda environment: Install miniconda environment from https://conda.io/miniconda.html Based on your system requirements, you'll get a file something like 'Miniconda3-latest-XYZ'.
Now,
bash Miniconda3-latest-Linux-x86_64.sh (for linux)
bash Miniconda3-latest-MacOSX-x86_64.sh (for Mac)
Download 32/64 bit python 3.10 miniconda exe and install (for windows)
Method 1 (conda based installation)
Now, let's make a conda environment, say "my_alignn", choose other name as you like::
conda create --name my_alignn python=3.10
conda activate my_alignn
conda install alignn -y
optional GPU dependencies notes
If you need CUDA support, it's best to install PyTorch and DGL before installing alignn to ensure that you get a CUDA-enabled version of DGL.
conda install dgl=2.1.0 pytorch torchvision torchaudio pytorch-cuda -c pytorch -c nvidia
Method 2 (edit/debug in-place install)
You can laso install a development version of alignn by cloning the repository and installing in place with pip:
git clone https://github.com/usnistgov/alignn
cd alignn
python -m pip install -e .
Method 3 (using pypi):
As an alternate method, ALIGNN can also be installed using pip
command as follows:
pip install alignn
pip install dgl -f https://data.dgl.ai/wheels/torch-2.1/cu121/repo.html
Examples
Notebooks | Google Colab | Descriptions |
---|---|---|
Regression model | Examples for developing single output regression model for exfoliation energies of 2D materials. | |
MLFF | Examples of training a machine learning force field for Silicon. | |
ALIGNN-FF Relaxer+EV_curve+Phonons+Interface gamma_surface+Interface separation | Examples of using pre-trained ALIGNN-FF force-field model. | |
Miscellaneous tasks | Examples for developing single output (such as formation energy, bandgaps) or multi-output (such as phonon DOS, electron DOS) Regression or Classification (such as metal vs non-metal), Using several pretrained models. |
Here, we provide examples for property prediction tasks, development of machine-learning force-fields (MLFF), usage of pre-trained property predictor, MLFFs, webapps etc.
Dataset preparation for property prediction tasks
The main script to train model is train_alignn.py
. A user needs at least the following info to train a model: 1) id_prop.csv
with name of the file and corresponding value, 2) config_example.json
a config file with training and hyperparameters.
Users can keep their structure files in POSCAR
, .cif
, .xyz
or .pdb
files in a directory. In the examples below we will use POSCAR format files. In the same directory, there should be an id_prop.csv
file.
In this directory, id_prop.csv
, the filenames, and correponding target values are kept in comma separated values (csv) format
.
Here is an example of training OptB88vdw bandgaps of 50 materials from JARVIS-DFT database. The example is created using the generate_sample_data_reg.py script. Users can modify the script for more than 50 data, or make their own dataset in this format. For list of available datasets see Databases.
The dataset in split in 80:10:10 as training-validation-test set (controlled by train_ratio, val_ratio, test_ratio
) . To change the split proportion and other parameters, change the config_example.json file. If, users want to train on certain sets and val/test on another dataset, set n_train
, n_val
, n_test
manually in the config_example.json
and also set keep_data_order
as True there so that random shuffle is disabled.
A brief help guide (-h
) can be obtained as follows.
train_alignn.py -h
Regression example
Now, the model is trained as follows. Please increase the batch_size
parameter to something like 32 or 64 in config_example.json
for general trainings.
train_alignn.py --root_dir "alignn/examples/sample_data" --config "alignn/examples/sample_data/config_example.json" --output_dir=temp
Classification example
While the above example is for regression, the follwoing example shows a classification task for metal/non-metal based on the above bandgap values. We transform the dataset
into 1 or 0 based on a threshold of 0.01 eV (controlled by the parameter, classification_threshold
) and train a similar classification model. Currently, the script allows binary classification tasks only.
train_alignn.py --root_dir "alignn/examples/sample_data" --classification_threshold 0.01 --config "alignn/examples/sample_data/config_example.json" --output_dir=temp
Multi-output model example
While the above example regression was for single-output values, we can train multi-output regression models as well. An example is given below for training formation energy per atom, bandgap and total energy per atom simulataneously. The script to generate the example data is provided in the script folder of the sample_data_multi_prop. Another example of training electron and phonon density of states is provided also.
train_alignn.py --root_dir "alignn/examples/sample_data_multi_prop" --config "alignn/examples/sample_data/config_example.json" --output_dir=temp
Automated model training
Users can try training using multiple example scripts to run multiple dataset (such as JARVIS-DFT, Materials project, QM9_JCTC etc.). Look into the alignn/scripts/train_*.py folder. This is done primarily to make the trainings more automated rather than making folder/ csv files etc. These scripts automatically download datasets from Databases in jarvis-tools and train several models. Make sure you specify your specific queuing system details in the scripts.
other examples
Additional example trainings for 2D-exfoliation energy, superconductor transition temperature.
Using pre-trained models
All the trained models are distributed on [Figshare](https://figshare.com/projects/ALIGNN_models/126478.
The pretrained.py script can be applied to use them. These models can be used to directly make predictions.
A brief help section (-h
) is shown using:
pretrained.py -h
An example of prediction formation energy per atom using JARVIS-DFT dataset trained model is shown below:
pretrained.py --model_name jv_formation_energy_peratom_alignn --file_format poscar --file_path alignn/examples/sample_data/POSCAR-JVASP-10.vasp
Web-app
A basic web-app is for direct-prediction available at JARVIS-ALIGNN app. Given atomistic structure in POSCAR format it predict formation energy, total energy per atom and bandgap using data trained on JARVIS-DFT dataset.
ALIGNN-FF
Atomisitic line graph neural network-based FF (ALIGNN-FF) can be used to model both structurally and chemically diverse systems with any combination of 89 elements from the periodic table. To train the ALIGNN-FF model, we have used the JARVIS-DFT dataset which contains around 75000 materials and 4 million energy-force entries, out of which 307113 are used in the training. These models can be further finetuned, or new models can be developed from scratch on a new dataset.
ASE calculator provides interface to various codes. An example for ALIGNN-FF is give below. Note that there are multiple pretrained ALIGNN-FF models available, here we use the deafult_path model. As more accurate models are developed, they will be made available as well:
from alignn.ff.ff import (
AlignnAtomwiseCalculator,
default_path,
mptraj_path,
wt01_path,
)
import matplotlib.pyplot as plt
from ase import Atom, Atoms
import time
from ase.build import bulk
import numpy as np
import matplotlib.pyplot as plt
from ase.build import make_supercell
%matplotlib inline
model_path = default_path()
calc = AlignnAtomwiseCalculator(path=model_path)
t1 = time.time()
# a = 5.43
lattice_params = np.linspace(5.2, 5.6)
fcc_energies = []
ready = True
for a in lattice_params:
atoms = bulk("Si", "diamond", a=a)
atoms.set_tags(np.ones(len(atoms)))
atoms.calc = calc
e = atoms.get_potential_energy()
fcc_energies.append(e)
t2 = time.time()
print("Time", t2 - t1)
plt.plot(lattice_params, fcc_energies, "-o")
plt.title("Si")
plt.xlabel("Lattice constant ($\AA$)")
plt.ylabel("Total energy (eV)")
plt.show()
To train ALIGNN-FF use train_alignn.py
script which uses atomwise_alignn
model:
AtomWise prediction example which looks for similar setup as before but unstead of id_prop.csv
, it requires id_prop.json
file (see example in the sample_data_ff directory). An example to compile vasprun.xml files into a id_prop.json is kept here. Note ALIGNN-FF requires energy stored as energy per atom:
train_alignn.py --root_dir "alignn/examples/sample_data_ff" --config "alignn/examples/sample_data_ff/config_example_atomwise.json" --output_dir=temp
To finetune model, use --restart_model_path
tag as well in the above with the path of a pretrained ALIGNN-FF model with same model confurations.
An example for training MLFF for silicon is provided here. It is highly recommeded to get familiar with this example before developing a new model. Note: new model configs such as lg_on_fly
and add_reverse_forces
should be defaulted to True for newer versions. For MD runs, use_cutoff_function
is recommended.
A pretrained ALIGNN-FF (under active development right now) can be used for predicting several properties, such as:
run_alignn_ff.py --file_path alignn/examples/sample_data/POSCAR-JVASP-10.vasp --task="unrelaxed_energy"
run_alignn_ff.py --file_path alignn/examples/sample_data/POSCAR-JVASP-10.vasp --task="optimize"
run_alignn_ff.py --file_path alignn/examples/sample_data/POSCAR-JVASP-10.vasp --task="ev_curve"
To know about other tasks, type.
run_alignn_ff.py -h
Several supporting scripts for stucture optimization, equation of states, phonon and related calculations are provided in the repo as well. If you need further assistance for a particular task, feel free to raise an GitHus issue.
Performances
Please refer to JARVIS-Leaderboard to check the performance of ALIGNN models on several databases.
1) On JARVIS-DFT 2021 dataset (classification)
Model | Threshold | ALIGNN |
---|---|---|
Metal/non-metal classifier (OPT) | 0.01 eV | 0.92 |
Metal/non-metal classifier (MBJ) | 0.01 eV | 0.92 |
Magnetic/non-Magnetic classifier | 0.05 µB | 0.91 |
High/low SLME | 10 % | 0.83 |
High/low spillage | 0.1 | 0.80 |
Stable/unstable (ehull) | 0.1 eV | 0.94 |
High/low-n-Seebeck | -100 µVK-1 | 0.88 |
High/low-p-Seebeck | 100 µVK-1 | 0.92 |
High/low-n-powerfactor | 1000 µW(mK2)-1 | 0.74 |
High/low-p-powerfactor | 1000µW(mK2)-1 | 0.74 |
2) On JARVIS-DFT 2021 dataset (regression)
Property | Units | MAD | CFID | CGCNN | ALIGNN | MAD: MAE |
---|---|---|---|---|---|---|
Formation energy | eV(atom)-1 | 0.86 | 0.14 | 0.063 | 0.033 | 26.06 |
Bandgap (OPT) | eV | 0.99 | 0.30 | 0.20 | 0.14 | 7.07 |
Total energy | eV(atom)-1 | 1.78 | 0.24 | 0.078 | 0.037 | 48.11 |
Ehull | eV | 1.14 | 0.22 | 0.17 | 0.076 | 15.00 |
Bandgap (MBJ) | eV | 1.79 | 0.53 | 0.41 | 0.31 | 5.77 |
Kv | GPa | 52.80 | 14.12 | 14.47 | 10.40 | 5.08 |
Gv | GPa | 27.16 | 11.98 | 11.75 | 9.48 | 2.86 |
Mag. mom | µB | 1.27 | 0.45 | 0.37 | 0.26 | 4.88 |
SLME (%) | No unit | 10.93 | 6.22 | 5.66 | 4.52 | 2.42 |
Spillage | No unit | 0.52 | 0.39 | 0.40 | 0.35 | 1.49 |
Kpoint-length | Å | 17.88 | 9.68 | 10.60 | 9.51 | 1.88 |
Plane-wave cutoff | eV | 260.4 | 139.4 | 151.0 | 133.8 | 1.95 |
єx (OPT) | No unit | 57.40 | 24.83 | 27.17 | 20.40 | 2.81 |
єy (OPT) | No unit | 57.54 | 25.03 | 26.62 | 19.99 | 2.88 |
єz (OPT) | No unit | 56.03 | 24.77 | 25.69 | 19.57 | 2.86 |
єx (MBJ) | No unit | 64.43 | 30.96 | 29.82 | 24.05 | 2.68 |
єy (MBJ) | No unit | 64.55 | 29.89 | 30.11 | 23.65 | 2.73 |
єz (MBJ) | No unit | 60.88 | 29.18 | 30.53 | 23.73 | 2.57 |
є (DFPT:elec+ionic) | No unit | 45.81 | 43.71 | 38.78 | 28.15 | 1.63 |
Max. piezoelectric strain coeff (dij) | CN-1 | 24.57 | 36.41 | 34.71 | 20.57 | 1.19 |
Max. piezo. stress coeff (eij) | Cm-2 | 0.26 | 0.23 | 0.19 | 0.147 | 1.77 |
Exfoliation energy | meV(atom)-1 | 62.63 | 63.31 | 50.0 | 51.42 | 1.22 |
Max. EFG | 1021 Vm-2 | 43.90 | 24.54 | 24.7 | 19.12 | 2.30 |
avg. me | electron mass unit | 0.22 | 0.14 | 0.12 | 0.085 | 2.59 |
avg. mh | electron mass unit | 0.41 | 0.20 | 0.17 | 0.124 | 3.31 |
n-Seebeck | µVK-1 | 113.0 | 56.38 | 49.32 | 40.92 | 2.76 |
n-PF | µW(mK2)-1 | 697.80 | 521.54 | 552.6 | 442.30 | 1.58 |
p-Seebeck | µVK-1 | 166.33 | 62.74 | 52.68 | 42.42 | 3.92 |
p-PF | µW(mK2)-1 | 691.67 | 505.45 | 560.8 | 440.26 | 1.57 |
3) On Materials project 2018 dataset
The results from models other than ALIGNN are reported as given in corresponding papers, not necessarily reproduced by us.
Prop | Unit | MAD | CFID | CGCNN | MEGNet | SchNet | ALIGNN | MAD:MAE |
---|---|---|---|---|---|---|---|---|
Ef | eV(atom)-1 | 0.93 | 0.104 | 0.039 | 0.028 | 0.035 | 0.022 | 42.27 |
Eg | eV | 1.35 | 0.434 | 0.388 | 0.33 | - | 0.218 | 6.19 |
4) On QM9 dataset
Note the issue related to QM9 dataset. The results from models other than ALIGNN are reported as given in corresponding papers, not necessarily reproduced by us. These models were trained with same parameters as solid-state databases but for 1000 epochs.
Target | Units | SchNet | MEGNet | DimeNet++ | ALIGNN |
---|---|---|---|---|---|
HOMO | eV | 0.041 | 0.043 | 0.0246 | 0.0214 |
LUMO | eV | 0.034 | 0.044 | 0.0195 | 0.0195 |
Gap | eV | 0.063 | 0.066 | 0.0326 | 0.0381 |
ZPVE | eV | 0.0017 | 0.00143 | 0.00121 | 0.0031 |
µ | Debye | 0.033 | 0.05 | 0.0297 | 0.0146 |
α | Bohr3 | 0.235 | 0.081 | 0.0435 | 0.0561 |
R2 | Bohr2 | 0.073 | 0.302 | 0.331 | 0.5432 |
U0 | eV | 0.014 | 0.012 | 0.00632 | 0.0153 |
U | eV | 0.019 | 0.013 | 0.00628 | 0.0144 |
H | eV | 0.014 | 0.012 | 0.00653 | 0.0147 |
G | eV | 0.014 | 0.012 | 0.00756 | 0.0144 |
5) On hMOF dataset
Property | Unit | MAD | MAE | MAD:MAE | R2 | RMSE |
---|---|---|---|---|---|---|
Grav. surface area | m2 g-1 | 1430.82 | 91.15 | 15.70 | 0.99 | 180.89 |
Vol. surface area | m2 cm-3 | 561.44 | 107.81 | 5.21 | 0.91 | 229.24 |
Void fraction | No unit | 0.16 | 0.017 | 9.41 | 0.98 | 0.03 |
LCD | Å | 3.44 | 0.75 | 4.56 | 0.83 | 1.83 |
PLD | Å | 3.55 | 0.92 | 3.86 | 0.78 | 2.12 |
All adsp | mol kg-1 | 1.70 | 0.18 | 9.44 | 0.95 | 0.49 |
Adsp at 0.01bar | mol kg-1 | 0.12 | 0.04 | 3.00 | 0.77 | 0.11 |
Adsp at 2.5bar | mol kg-1 | 2.16 | 0.48 | 4.50 | 0.90 | 0.97 |
6) On qMOF dataset
MAE on electronic bandgap 0.20 eV
7) On OMDB dataset
coming soon!
8) On HOPV dataset
coming soon!
9) On QETB dataset
coming soon!
10) On OpenCatalyst dataset
DataSplit | CGCNN | DimeNet | SchNet | DimeNet++ | ALIGNN | MAD: MAE |
---|---|---|---|---|---|---|
10k | 0.988 | 1.0117 | 1.059 | 0.8837 | 0.61 | - |
Useful notes (based on some of the queries we received)
- If you are using GPUs, make sure you have a compatible dgl-cuda version installed, for example: dgl-cu101 or dgl-cu111, so e.g.
pip install dgl-cu111
. - While comnventional '.cif' and '.pdb' files can be read using jarvis-tools, for complex files you might have to install
cif2cell
andpytraj
respectively i.e.pip install cif2cell==2.0.0a3
andconda install -c ambermd pytraj
. - Make sure you use
batch_size
as 32 or 64 for large datasets, and not 2 as given in the example config file, else it will take much longer to train, and performnce might drop a lot. - Note that
train_alignn.py
andpretrained.py
in alignn folder are actually python executable scripts. So, even if you don't provide absolute path of these scripts, they should work. - Learn about the issue with QM9 results here: https://github.com/usnistgov/alignn/issues/54
- Make sure you have
pandas
version as >1.2.3. - Starting March 2024, pytroch-ignite dependency will be removed to enable conda-forge build.
References
- Atomistic Line Graph Neural Network for improved materials property predictions
- Prediction of the Electron Density of States for Crystalline Compounds with Atomistic Line Graph Neural Networks (ALIGNN)
- Recent advances and applications of deep learning methods in materials science
- Designing High-Tc Superconductors with BCS-inspired Screening, Density Functional Theory and Deep-learning
- A Deep-learning Model for Fast Prediction of Vacancy Formation in Diverse Materials
- Graph neural network predictions of metal organic framework CO2 adsorption properties
- Rapid Prediction of Phonon Structure and Properties using an Atomistic Line Graph Neural Network (ALIGNN)
- Unified graph neural network force-field for the periodic table
- Large Scale Benchmark of Materials Design Methods
Please see detailed publications list here.
How to contribute
For detailed instructions, please see Contribution instructions
Correspondence
Please report bugs as Github issues (https://github.com/usnistgov/alignn/issues) or email to kamal.choudhary@nist.gov.
Funding support
NIST-MGI (https://www.nist.gov/mgi).
Code of conduct
Please see Code of conduct
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Hashes for alignn-2024.8.27-py2.py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | b2090879f8e0df28559aff740be742a7ec93fe4800aecac353a4b32d7af21319 |
|
MD5 | 639834cd8a96b6b2cea8ecfcff81b460 |
|
BLAKE2b-256 | 0c8251a3b7ef1b19b471d1f9dcefbe369d2ad907e03b5a1da581b7d6dbdb5116 |