Software Resources

Materials ScienceFor ML packages specific to materials science, refer to the following list. Most of the examples below are pulled directly from this resource.
﻿
GitHub - JuDFTteam/best-of-atomistic-machine-learning: 🏆 A ranked list of awesome atomistic machine learning projects ⚛️🧬💎.
https://github.com/JuDFTteam/best-of-atomistic-machine-learning
Add a caption...
ML FrameworksThe following are useful frameworks for training machine learning models:
﻿﻿  scikit-learn : The go-to standard for "conventional" (i.e. not graph-related) classification, regression, and clustering machine learning algorithms. This is the package you should start with when getting familiar with machine learning.
﻿﻿  PyTorch : A Python library for training and running neural networks. This is the deep learning framework we use in the group.
﻿ PyTorch Geometric : PyTorch-based library for graph neural networks.
﻿ PyTorch Lightning : Helps to remove boilerplate in PyTorch codes 
﻿ PySR : Symbolic regression, for when having an equation is desirable.
﻿ Optuna : Hyperparameter tuning
ML Interatomic PotentialsTo find the top pre-trained ML interatomic potentials for materials science, refer to  Matbench Discovery. ﻿
For some pre-made calculation tasks for ML interatomic potentials, check out  matcalc .
To train your own ML interatomic potentials, here are some general-purpose libraries:
﻿ Graph PES ﻿
﻿ Autoplex ﻿
﻿