Best of Atomistic Machine Learning ⚛️🧬💎

🏆  A ranked list of awesome atomistic machine learning (AML) projects. Updated quarterly.

This curated list contains 290 awesome open-source projects with a total of 120K stars grouped into 23 categories. All projects are ranked by a project-quality score, which is calculated based on various metrics automatically collected from GitHub and different package managers. If you like to add or update projects, feel free to open an issue, submit a pull request, or directly edit the projects.yaml.

The current focus of this list is more on simulation data rather than experimental data, and more on materials rather than drug design. Nevertheless, contributions from other fields are warmly welcome!

🧙‍♂️ Discover other best-of lists or create your own.

Contents

• Active learning 4 projects
• Biomolecules 2 projects
• Community resources 15 projects
• Datasets 24 projects
• Data Structures 3 projects
• Density functional theory (ML-DFT) 19 projects
• Educational Resources 18 projects
• Explainable Artificial intelligence (XAI) 4 projects
• Electronic structure methods (ML-ESM) 2 projects
• General Tools 22 projects
• Generative Models 10 projects
• Interatomic Potentials (ML-IAP) 51 projects
• Language Models 6 projects
• Materials Discovery 8 projects
• Mathematical tools 9 projects
• Molecular Dynamics 6 projects
• Probabilistic ML 0 projects
• Reinforcement Learning 2 projects
• Representation Engineering 22 projects
• Representation Learning 52 projects
• Unsupervised Learning 6 projects
• Visualization 1 projects
• Wavefunction methods (ML-WFT) 4 projects
• Others 1 projects

Explanation

• 🥇🥈🥉  Combined project-quality score
• ⭐️  Star count from GitHub
• 🐣  New project (less than 6 months old)
• 💤  Inactive project (6 months no activity)
• 💀  Dead project (12 months no activity)
• 📈📉  Project is trending up or down
• ➕  Project was recently added
• 👨‍💻  Contributors count from GitHub
• 🔀  Fork count from GitHub
• 📋  Issue count from GitHub
• ⏱️  Last update timestamp on package manager
• 📥  Download count from package manager
• 📦  Number of dependent projects

Active learning

Projects that focus on enabling active learning, iterative learning schemes for atomistic ML.

FLARE (🥇19 · ⭐ 250) - An open-source Python package for creating fast and accurate interatomic potentials. MIT C++ ML-IAP

• GitHub (👨‍💻 36 · 🔀 56 · 📥 1 · 📦 10 · 📋 190 - 12% open · ⏱️ 26.05.2023):

   git clone https://github.com/mir-group/flare
  

Finetuna (🥈11 · ⭐ 26 · 💤) - Active Learning for Machine Learning Potentials. MIT

• GitHub (👨‍💻 11 · 🔀 7 · 📋 18 - 22% open · ⏱️ 13.02.2023):

   git clone https://github.com/ulissigroup/finetuna
  

ACEHAL (🥉6 · ⭐ 7) - Hyperactive Learning (HAL) Python interface for building Atomic Cluster Expansion potentials. Unlicensed Julia

• GitHub (👨‍💻 3 · 🔀 2 · 📋 10 - 40% open · ⏱️ 21.09.2023):

   git clone https://github.com/ACEsuit/ACEHAL
  

Show 1 hidden projects...

• flare++ (🥉10 · ⭐ 34 · 💀) - A many-body extension of the FLARE code. MIT C++ ML-IAP

Biomolecules

Projects that focus on biomolecules, protein structure, protein folding, etc. using atomistic ML.

AlphaFold (🥇23 · ⭐ 11K) - Open source code for AlphaFold. Apache-2

• GitHub (👨‍💻 19 · 🔀 1.9K · 📦 6 · 📋 740 - 23% open · ⏱️ 10.08.2023):

   git clone https://github.com/deepmind/alphafold
  

Uni-Fold (🥉15 · ⭐ 290) - An open-source platform for developing protein models beyond AlphaFold. Apache-2

• GitHub (👨‍💻 7 · 🔀 51 · 📥 2.3K · 📋 58 - 18% open · ⏱️ 18.09.2023):

   git clone https://github.com/dptech-corp/Uni-Fold
  

Community resources

Projects that collect atomistic ML resources or foster communication within community.

🔗 AI for Science Map - Interactive mindmap of the AI4Science research field, including atomistic machine learning, including papers,..

🔗 Atomic Cluster Expansion - Atomic Cluster Expansion (ACE) community homepage.

🔗 CrystaLLM - Generate a crystal structure from a composition. LM generative pre-trained

🔗 matsci.org - A community forum for the discussion of anything materials science, with a focus on computational materials science..

🔗 Matter Modeling Stack Exchange - Machine Learning - Forum StackExchange, site Matter Modeling, ML-tagged questions.

Best-of Machine Learning with Python (🥇22 · ⭐ 14K) - A ranked list of awesome machine learning Python libraries. Updated weekly. CC-BY-4.0 general-ml Python

• GitHub (👨‍💻 44 · 🔀 2.1K · 📋 48 - 31% open · ⏱️ 28.09.2023):

   git clone https://github.com/ml-tooling/best-of-ml-python
  

Graph-based Deep Learning Literature (🥈19 · ⭐ 4.3K · 📈) - links to conference publications in graph-based deep learning. MIT general-ml rep-learn

• GitHub (👨‍💻 12 · 🔀 710 · ⏱️ 28.09.2023):

   git clone https://github.com/naganandy/graph-based-deep-learning-literature
  

MatBench (🥈17 · ⭐ 83) - Matbench: Benchmarks for materials science property prediction. MIT datasets benchmarking

• GitHub (👨‍💻 22 · 🔀 31 · 📦 10 · 📋 57 - 54% open · ⏱️ 07.08.2023):

   git clone https://github.com/materialsproject/matbench
  

• PyPi (📥 140 / month):

   pip install matbench
  

MatBench Discovery (🥉15 · ⭐ 36) - An evaluation framework for machine learning models simulating high-throughput materials discovery. MIT datasets benchmarking

• GitHub (👨‍💻 5 · 🔀 5 · 📋 24 - 25% open · ⏱️ 28.09.2023):

   git clone https://github.com/janosh/matbench-discovery
  

• PyPi (📥 83 / month):

   pip install matbench-discovery
  

AI for Science Resources (🥉14 · ⭐ 250) - List of resources for AI4Science research, including learning resources. GPL-3.0 license

• GitHub (👨‍💻 23 · 🔀 30 · ⏱️ 31.08.2023):

   git clone https://github.com/divelab/AIRS
  

Awesome Materials Informatics (🥉10 · ⭐ 300) - Curated list of known efforts in materials informatics = modern materials science. Custom

• GitHub (👨‍💻 18 · 🔀 72 · ⏱️ 21.08.2023):

   git clone https://github.com/tilde-lab/awesome-materials-informatics
  

The Collection of Database and Dataset Resources in Materials Science (🥉7 · ⭐ 160) - A list of databases, datasets and books/handbooks where you can find materials properties for machine learning.. Unlicensed datasets

• GitHub (👨‍💻 2 · 🔀 26 · ⏱️ 28.09.2023):

   git clone https://github.com/sedaoturak/data-resources-for-materials-science
  

Show 3 hidden projects...

• A Highly Opinionated List of Open-Source Materials Informatics Resources (🥉7 · ⭐ 94 · 💀) - A Highly Opinionated List of Open Source Materials Informatics Resources. MIT
• GitHub topic materials-informatics - Unlicensed
• MateriApps - Unlicensed

Datasets

Datasets, databases and trained models for atomistic ML.

🔗 Catalysis Hub - A web-platform for sharing data and software for computational catalysis research!.

🔗 Citrination Datasets - AI-Powered Materials Data Platform. Open Citrination has been decommissioned.

🔗 crystals.ai - Curated datasets for reproducible AI in materials science.

🔗 DeepChem Models - DeepChem models on HuggingFace. pre-trained LM

🔗 JARVIS-Leaderboard ( ⭐ 41) - This project provides benchmark-performances for materials science applications including Artificial Intelligence.. benchmarking

🔗 Materials Project - Charge Densities - Materials Project has started offering charge density information available for download via their public API.

🔗 matterverse.ai - Database of yet-to-be-sythesized materials predicted using state-of-the-art machine learning algorithms.

🔗 Quantum-Machine.org Datasets - Collection of datasets, including QM7, QM9, etc. MD, DFT. Small organic molecules, mostly.

🔗 sGDML Datasets - MD17, MD22, DFT datasets.

MPContribs (🥇23 · ⭐ 34) - Platform for materials scientists to contribute and disseminate their materials data through Materials Project. MIT

• GitHub (👨‍💻 25 · 🔀 20 · 📦 22 · 📋 98 - 20% open · ⏱️ 25.09.2023):

   git clone https://github.com/materialsproject/MPContribs
  

• PyPi (📥 2.6K / month):

   pip install mpcontribs-client
  

Open Catalyst datasets (🥇18 · ⭐ 470) - The datasets of the Open Catalyst project, OC20, OC22. CC-BY-4.0

• GitHub (👨‍💻 32 · 🔀 170 · 📋 130 - 11% open · ⏱️ 14.09.2023):

   git clone https://github.com/Open-Catalyst-Project/ocp
  

Open Databases Integration for Materials Design (OPTIMADE) (🥈15 · ⭐ 61) - Specification of a common REST API for access to materials databases. CC-BY-4.0

• GitHub (👨‍💻 19 · 🔀 35 · 📋 220 - 33% open · ⏱️ 22.06.2023):

   git clone https://github.com/Materials-Consortia/OPTIMADE
  

SPICE (🥈13 · ⭐ 93) - A collection of QM data for training potential functions. MIT ML-IAP MD

• GitHub (🔀 5 · 📥 220 · 📋 47 - 25% open · ⏱️ 18.08.2023):

   git clone https://github.com/openmm/spice-dataset
  

SciGlass (🥉7 · ⭐ 6) - The database contains a vast set of data on the properties of glass materials. MIT

• GitHub (👨‍💻 2 · 🔀 3 · ⏱️ 27.08.2023):

   git clone https://github.com/drcassar/SciGlass
  

3DSC Database (🥉5 · ⭐ 7) - Repo for the paper publishing the superconductor database with 3D crystal structures. Custom superconductors materials-discovery

• GitHub (🔀 2 · ⏱️ 21.07.2023):

   git clone https://github.com/aimat-lab/3DSC
  

Show 9 hidden projects...

• OpenKIM (🥈11 · ⭐ 29 · 💀) - The Open Knowledgebase of Interatomic Models (OpenKIM) aims to be an online resource for standardized testing, long-.. LGPL-2.1 knowledge-base pre-trained
• 2DMD dataset (🥈9 · ⭐ 1) - Code for Kazeev, N., Al-Maeeni, A.R., Romanov, I. et al. Sparse representation for machine learning the properties of.. Apache-2 material-defect
• ANI-1 Dataset (🥉8 · ⭐ 89 · 💀) - A data set of 20 million calculated off-equilibrium conformations for organic molecules. MIT
• MoleculeNet Leaderboard (🥉8 · ⭐ 73 · 💀) - MIT benchmarking
• ANI-1x Datasets (🥉6 · ⭐ 45 · 💀) - The ANI-1ccx and ANI-1x data sets, coupled-cluster and density functional theory properties for organic molecules. MIT
• COMP6 Benchmark dataset (🥉6 · ⭐ 36 · 💀) - COMP6 Benchmark dataset for ML potentials. MIT
• GEOM (🥉5 · ⭐ 140 · 💀) - GEOM: Energy-annotated molecular conformations. Unlicensed drug-discovery
• linear-regression-benchmarks (🥉5 · ⭐ 1 · 💀) - Data sets used for linear regression benchmarks. MIT benchmarking single-paper
• Visual Graph Datasets (🥉3 · ⭐ 1 · 🐣) - Datasets for the training of graph neural networks (GNNs) and subsequent visualization of attributional explanations.. MIT

Data Structures

Projects that focus on providing data structures used in atomistic machine learning.

dpdata (🥇22 · ⭐ 140) - Manipulating multiple atomic simulation data formats, including DeePMD-kit, VASP, LAMMPS, ABACUS, etc. LGPL-3.0

• GitHub (👨‍💻 51 · 🔀 100 · 📦 100 · 📋 71 - 23% open · ⏱️ 08.09.2023):

   git clone https://github.com/deepmodeling/dpdata
  

• PyPi (📥 6.4K / month):

   pip install dpdata
  

• Conda (📥 120 · ⏱️ 27.09.2023):

   conda install -c deepmodeling dpdata
  

mp-pyrho (🥉14 · ⭐ 28 · 📉) - Tools for re-griding volumetric quantum chemistry data for machine-learning purposes. Custom ML-DFT

• GitHub (👨‍💻 8 · 🔀 6 · 📦 18 · 📋 4 - 25% open · ⏱️ 21.03.2023):

   git clone https://github.com/materialsproject/pyrho
  

• PyPi (📥 89 / month):

   pip install mp-pyrho
  

Equistore (🥉14 · ⭐ 25) - Storage format for equivariant atomistic machine learning. BSD-3

• GitHub (👨‍💻 17 · 🔀 12 · 📦 3 · 📋 110 - 33% open · ⏱️ 27.09.2023):

   git clone https://github.com/lab-cosmo/equistore
  

Density functional theory (ML-DFT)

Projects and models that focus on quantities of DFT, such as density functional approximations (ML-DFA), the charge density, density of states, the Hamiltonian, etc.

DM21 (🥇20 · ⭐ 12K) - This package provides a PySCF interface to the DM21 (DeepMind 21) family of exchange-correlation functionals described.. Apache-2

• GitHub (👨‍💻 92 · 🔀 2.4K · 📋 290 - 53% open · ⏱️ 02.06.2023):

   git clone https://github.com/deepmind/deepmind-research
  

MALA (🥇19 · ⭐ 52 · 📈) - Materials Learning Algorithms. A framework for machine learning materials properties from first-principles data. BSD-3

• GitHub (👨‍💻 41 · 🔀 19 · 📋 240 - 11% open · ⏱️ 28.09.2023):

   git clone https://github.com/mala-project/mala
  

DeepH-pack (🥈12 · ⭐ 140) - Deep neural networks for density functional theory Hamiltonian. LGPL-3.0 Julia

• GitHub (👨‍💻 6 · 🔀 26 · 📋 35 - 11% open · ⏱️ 11.07.2023):

   git clone https://github.com/mzjb/DeepH-pack
  

DeePKS-kit (🥈10 · ⭐ 94) - a package for developing machine learning-based chemically accurate energy and density functional models. LGPL-3.0

• GitHub (👨‍💻 6 · 🔀 30 · 📋 10 - 10% open · ⏱️ 01.04.2023):

   git clone https://github.com/deepmodeling/deepks-kit
  

SALTED (🥈9 · ⭐ 13) - Symmetry-Adapted Learning of Three-dimensional Electron Densities. GPL-3.0

• GitHub (👨‍💻 10 · 🔀 2 · ⏱️ 25.09.2023):

   git clone https://github.com/andreagrisafi/SALTED
  

ACEhamiltonians (🥈7 · ⭐ 8) - Provides tools for constructing, fitting, and predicting self-consistent Hamiltonian and overlap matrices in solid-.. MIT Julia

• GitHub (👨‍💻 4 · 🔀 3 · 📋 4 - 25% open · ⏱️ 12.04.2023):

   git clone https://github.com/ACEsuit/ACEhamiltonians.jl
  

DeepDFT (🥉6 · ⭐ 36 · 💤) - Official implementation of DeepDFT model. MIT

• GitHub (👨‍💻 2 · 🔀 6 · ⏱️ 28.02.2023):

   git clone https://github.com/peterbjorgensen/DeepDFT
  

DeepH-E3 (🥉6 · ⭐ 29 · 🐣) - General framework for E(3)-equivariant neural network representation of density functional theory Hamiltonian. MIT magnetism

• GitHub (👨‍💻 2 · 🔀 8 · 📋 8 - 25% open · ⏱️ 04.04.2023):

   git clone https://github.com/Xiaoxun-Gong/DeepH-E3
  

Show 11 hidden projects...

• NeuralXC (🥈10 · ⭐ 28 · 💀) - Implementation of a machine learned density functional. BSD-3
• PROPhet (🥈9 · ⭐ 60 · 💀) - PROPhet is a code to integrate machine learning techniques with first-principles quantum chemistry approaches. GPL-3.0 ML-IAP MD single-paper C++
• Libnxc (🥈7 · ⭐ 14 · 💀) - A library for using machine-learned exchange-correlation functionals for density-functional theory. MPL-2.0 C++ Fortran
• gprep (🥉4 · 💀) - Fitting DFTB repulsive potentials with GPR. MIT single-paper
• ML-DFT (🥉3 · ⭐ 18 · 💀) - A package for density functional approximation using machine learning. MIT
• charge-density-models (🥉3 · ⭐ 2) - Tools to build charge density models using ocpmodels. MIT
• CSNN (🥉3 · ⭐ 1 · 💤) - Primary codebase of CSNN - Concentric Spherical Neural Network for 3D Representation Learning. BSD-3
• MALADA (🥉3) - MALA Data Acquisition: Helpful tools to build data for MALA. BSD-3
• xDeepH (🥉2 · ⭐ 18) - Extended DeepH (xDeepH) method for magnetic materials. LGPL-3.0 magnetism Julia
• DeepCDP (🥉2 · ⭐ 2) - DeepCDP: Deep learning Charge Density Prediction. Unlicensed
• kdft (🥉1 · ⭐ 2 · 💀) - The Kernel Density Functional (KDF) code allows generating ML based DFT functionals. Unlicensed

Educational Resources

Tutorials, guides, cookbooks, recipes, etc.

🔗 Quantum Chemistry in the Age of Machine Learning - Book, 2022.

Deep Learning for Molecules and Materials Book (🥇12 · ⭐ 530) - Deep learning for molecules and materials book. Custom

• GitHub (👨‍💻 19 · 🔀 96 · 📋 150 - 16% open · ⏱️ 02.07.2023):

   git clone https://github.com/whitead/dmol-book
  

jarvis-tools-notebooks (🥇12 · ⭐ 38) - A Google-Colab Notebook Collection for Materials Design: https://jarvis.nist.gov/. NIST

• GitHub (👨‍💻 5 · 🔀 21 · ⏱️ 19.08.2023):

   git clone https://github.com/JARVIS-Materials-Design/jarvis-tools-notebooks
  

RDKit Tutorials (🥈8 · ⭐ 210) - Tutorials to learn how to work with the RDKit. Custom

• GitHub (👨‍💻 5 · 🔀 65 · 📋 4 - 75% open · ⏱️ 19.03.2023):

   git clone https://github.com/rdkit/rdkit-tutorials
  

iam-notebooks (🥈8 · ⭐ 19) - Jupyter notebooks for the lectures of the Introduction to Atomistic Modeling. Apache-2

• GitHub (👨‍💻 6 · 🔀 4 · ⏱️ 07.08.2023):

   git clone https://github.com/ceriottm/iam-notebooks
  

AI4Science101 (🥉5 · ⭐ 73 · 💤) - AI for Science. Unlicensed

• GitHub (👨‍💻 5 · 🔀 11 · ⏱️ 04.09.2022):

   git clone https://github.com/deepmodeling/AI4Science101
  

Data Handling, DoE and Statistical Analysis for Material Chemists (🥉5 · 🐣) - Notebooks for workshops of DoE course, hosted by the Computational Materials Chemistry group at Uppsala University. GPL-3.0

• GitHub (👨‍💻 3 · 🔀 12 · ⏱️ 26.06.2023):

   git clone https://github.com/Teoroo-CMC/DoE_Course_Material
  

Show 11 hidden projects...

• DeepLearningLifeSciences (🥈11 · ⭐ 300 · 💀) - Example code from the book Deep Learning for the Life Sciences. MIT
• MAChINE (🥈8 · ⭐ 1 · 🐣) - Client-Server Web App to introduce usage of ML in materials science to beginners. MIT
• BestPractices (🥈6 · ⭐ 140 · 💀) - Things that you should (and should not) do in your Materials Informatics research. MIT
• Applied AI for Materials (🥈6 · ⭐ 47 · 💀) - Course materials for Applied AI for Materials Science and Engineering. Unlicensed
• COSMO Software Cookbook (🥈6 · ⭐ 3 · 🐣) - The COSMO cookbook contains recipes for atomic-scale modelling for materials and molecules. BSD-3
• Machine Learning for Materials Hard and Soft (🥉5 · ⭐ 32 · 💀) - ESI-DCAFM-TACO-VDSP Summer School on Machine Learning for Materials Hard and Soft. Unlicensed
• ML-in-chemistry-101 (🥉4 · ⭐ 54 · 💀) - The course materials for Machine Learning in Chemistry 101. Unlicensed
• chemrev-gpr (🥉4 · ⭐ 5 · 💀) - Notebooks accompanying the paper on GPR in materials and molecules in Chemical Reviews 2020. Unlicensed
• MLDensity_tutorial (🥉2 · ⭐ 6 · 💤) - Tutorial files to work with ML for the charge density in molecules and solids. Unlicensed
• MALA Tutorial (🥉2 · ⭐ 2 · 🐣) - A full MALA hands-on tutorial. Unlicensed
• PiNN Lab (🥉1 · ⭐ 2) - GPL-3.0

Explainable Artificial intelligence (XAI)

Projects that focus on explainability and model interpretability in atomistic ML.

exmol (🥇19 · ⭐ 260) - Explainer for black box models that predict molecule properties. MIT

• GitHub (👨‍💻 7 · 🔀 39 · 📦 12 · 📋 67 - 14% open · ⏱️ 19.06.2023):

   git clone https://github.com/ur-whitelab/exmol
  

• PyPi (📥 470 / month):

   pip install exmol
  

Show 3 hidden projects...

• MEGAN: Multi Explanation Graph Attention Student (🥈7 · ⭐ 2) - Minimal implementation of graph attention student model architecture. MIT
• MEGAN (🥈7 · ⭐ 2) - Minimal implementation of graph attention student model architecture. MIT XAI rep-learn
• Linear vs blackbox (🥉3 · ⭐ 1 · 💤) - Code and data related to the publication: Interpretable models for extrapolation in scientific machine learning. MIT XAI single-paper rep-eng

Electronic structure methods (ML-ESM)

Projects and models that focus on quantities of electronic structure methods, which do not fit into either of the categories ML-WFT or ML-DFT.

Show 2 hidden projects...

• QDF for molecule (🥇9 · ⭐ 170 · 💀) - Quantum deep field: data-driven wave function, electron density generation, and energy prediction and extrapolation.. MIT
• e3psi (🥉3 · ⭐ 2) - Equivariant machine learning library for learning from electronic structures. LGPL-3.0

General Tools

General tools for atomistic machine learning.

DeepChem (🥇36 · ⭐ 4.6K · 📉) - Democratizing Deep-Learning for Drug Discovery, Quantum Chemistry, Materials Science and Biology. MIT

• GitHub (👨‍💻 230 · 🔀 1.5K · 📦 260 · 📋 1.6K - 25% open · ⏱️ 27.09.2023):

   git clone https://github.com/deepchem/deepchem
  

• PyPi (📥 13K / month):

   pip install deepchem
  

• Conda (📥 100K · ⏱️ 16.06.2023):

   conda install -c conda-forge deepchem
  

• Docker Hub (📥 7K · ⭐ 4 · ⏱️ 11.03.2022):

   docker pull deepchemio/deepchem
  

RDKit (🥇30 · ⭐ 2.2K) - BSD-3 C++

• GitHub (👨‍💻 200 · 🔀 760 · 📥 1.4K · 📦 2 · 📋 2.9K - 29% open · ⏱️ 28.09.2023):

   git clone https://github.com/rdkit/rdkit
  

• PyPi (📥 210K / month):

   pip install rdkit
  

• Conda (📥 2.5M · ⏱️ 16.06.2023):

   conda install -c rdkit rdkit
  

Matminer (🥇28 · ⭐ 410) - Data mining for materials science. Custom

• GitHub (👨‍💻 49 · 🔀 170 · 📦 230 · 📋 210 - 11% open · ⏱️ 11.09.2023):

   git clone https://github.com/hackingmaterials/matminer
  

• PyPi (📥 15K / month):

   pip install matminer
  

• Conda (📥 50K · ⏱️ 27.06.2023):

   conda install -c conda-forge matminer
  

QUIP (🥈25 · ⭐ 300) - libAtoms/QUIP molecular dynamics framework: https://libatoms.github.io. GPL-2.0

• GitHub (👨‍💻 80 · 🔀 120 · 📥 350 · 📦 24 · 📋 430 - 20% open · ⏱️ 29.08.2023):

   git clone https://github.com/libAtoms/QUIP
  

• PyPi (📥 1.5K / month):

   pip install quippy-ase
  

• Docker Hub (📥 9.9K · ⭐ 4 · ⏱️ 24.04.2023):

   docker pull libatomsquip/quip
  

MAML (🥈24 · ⭐ 270) - Python for Materials Machine Learning, Materials Descriptors, Machine Learning Force Fields, Deep Learning, etc. BSD-3

• GitHub (👨‍💻 29 · 🔀 58 · 📦 4 · 📋 64 - 6% open · ⏱️ 27.09.2023):

   git clone https://github.com/materialsvirtuallab/maml
  

• PyPi (📥 270 / month):

   pip install maml
  

JARVIS-Tools (🥈22 · ⭐ 250 · 📉) - JARVIS-Tools: an open-source software package for data-driven atomistic materials design. Publications:.. Custom

• GitHub (👨‍💻 15 · 🔀 110 · 📦 64 · 📋 81 - 46% open · ⏱️ 22.09.2023):

   git clone https://github.com/usnistgov/jarvis
  

• PyPi (📥 4.8K / month):

   pip install jarvis-tools
  

• Conda (📥 57K · ⏱️ 16.06.2023):

   conda install -c conda-forge jarvis-tools
  

Scikit-Matter (🥈18 · ⭐ 61) - A collection of scikit-learn compatible utilities that implement methods born out of the materials science and.. BSD-3 scikit-learn

• GitHub (👨‍💻 13 · 🔀 15 · 📦 6 · 📋 68 - 17% open · ⏱️ 22.09.2023):

   git clone https://github.com/scikit-learn-contrib/scikit-matter
  

• PyPi (📥 1K / month):

   pip install skmatter
  

• Conda (📥 510 · ⏱️ 24.08.2023):

   conda install -c conda-forge skmatter
  

MAST-ML (🥈17 · ⭐ 88) - MAterials Simulation Toolkit for Machine Learning (MAST-ML). MIT

• GitHub (👨‍💻 19 · 🔀 50 · 📥 81 · 📦 6 · 📋 210 - 10% open · ⏱️ 28.07.2023):

   git clone https://github.com/uw-cmg/MAST-ML
  

XenonPy (🥈16 · ⭐ 110) - XenonPy is a Python Software for Materials Informatics. BSD-3

• GitHub (👨‍💻 10 · 🔀 58 · 📥 1.2K · 📋 82 - 19% open · ⏱️ 21.05.2023):

   git clone https://github.com/yoshida-lab/XenonPy
  

• PyPi (📥 220 / month):

   pip install xenonpy
  

Artificial Intelligence for Science (AIRS) (🥉14 · ⭐ 250) - Artificial Intelligence for Science (AIRS). GPL-3.0 license rep-learn generative ML-IAP MD ML-DFT ML-WFT biomolecules

• GitHub (👨‍💻 23 · 🔀 30 · ⏱️ 31.08.2023):

   git clone https://github.com/divelab/AIRS
  

AMPtorch (🥉12 · ⭐ 55) - AMPtorch: Atomistic Machine Learning Package (AMP) - PyTorch. GPL-3.0

• GitHub (👨‍💻 14 · 🔀 31 · 📋 30 - 16% open · ⏱️ 16.07.2023):

   git clone https://github.com/ulissigroup/amptorch
  

Show 11 hidden projects...

• QML (🥈16 · ⭐ 180 · 💀) - QML: Quantum Machine Learning. MIT
• Automatminer (🥉14 · ⭐ 130 · 💀) - An automatic engine for predicting materials properties. Custom
• OpenChem (🥉10 · ⭐ 620 · 💀) - OpenChem: Deep Learning toolkit for Computational Chemistry and Drug Design Research. MIT
• Equisolve (🥉8 · ⭐ 4) - A package tasked with taking equistore objects and computing machine learning models using them. BSD-3 ML-IAP
• JAXChem (🥉7 · ⭐ 74 · 💀) - JAXChem is a JAX-based deep learning library for complex and versatile chemical modeling. MIT
• uncertainty_benchmarking (🥉7 · ⭐ 34 · 💀) - Various code/notebooks to benchmark different ways we could estimate uncertainty in ML predictions. Unlicensed benchmarking probabilistic
• torchchem (🥉7 · ⭐ 33 · 💀) - An experimental repo for experimenting with PyTorch models. MIT
• ACEatoms (🥉4 · ⭐ 2 · 💤) - Generic code for modelling atomic properties using ACE. Custom Julia
• MLatom (🥉4) - Machine learning for atomistic simulations. Custom
• Magpie (🥉3) - Materials Agnostic Platform for Informatics and Exploration (Magpie). MIT Java
• quantum-structure-ml (🥉2 · ⭐ 1 · 💤) - Multi-class classification model for predicting the magnetic order of magnetic structures and a binary classification.. Unlicensed magnetism benchmarking

Generative Models

Projects that implement generative models for atomistic ML.

GT4SD (🥇18 · ⭐ 250) - GT4SD, an open-source library to accelerate hypothesis generation in the scientific discovery process. MIT pre-trained drug-discovery rep-learn

• GitHub (👨‍💻 19 · 🔀 55 · 📋 92 - 2% open · ⏱️ 15.09.2023):

   git clone https://github.com/GT4SD/gt4sd-core
  

• PyPi (📥 780 / month):

   pip install gt4sd
  

MoLeR (🥈16 · ⭐ 210) - Implementation of MoLeR: a generative model of molecular graphs which supports scaffold-constrained generation. MIT

• GitHub (👨‍💻 5 · 🔀 31 · 📋 30 - 20% open · ⏱️ 09.08.2023):

   git clone https://github.com/microsoft/molecule-generation
  

• PyPi (📥 220 / month):

   pip install molecule-generation
  

synspace (🥈12 · ⭐ 30) - Synthesis generative model. MIT

• GitHub (👨‍💻 2 · 🔀 3 · 📦 5 · 📋 3 - 66% open · ⏱️ 15.04.2023):

   git clone https://github.com/whitead/synspace
  

• PyPi (📥 370 / month):

   pip install synspace
  

SchNetPack G-SchNet (🥈11 · ⭐ 27) - G-SchNet extension for SchNetPack. MIT

• GitHub (👨‍💻 3 · 🔀 4 · ⏱️ 01.06.2023):

   git clone https://github.com/atomistic-machine-learning/schnetpack-gschnet
  

G-SchNet (🥉8 · ⭐ 120) - G-SchNet - a generative model for 3d molecular structures. MIT

• GitHub (👨‍💻 2 · 🔀 22 · ⏱️ 24.03.2023):

   git clone https://github.com/atomistic-machine-learning/G-SchNet
  

cG-SchNet (🥉8 · ⭐ 43) - cG-SchNet - a conditional generative neural network for 3d molecular structures. MIT

• GitHub (🔀 13 · ⏱️ 24.03.2023):

   git clone https://github.com/atomistic-machine-learning/cG-SchNet
  

bVAE-IM (🥉8 · ⭐ 8 · 🐣) - Implementation of Chemical Design with GPU-based Ising Machine. MIT QML single-paper

• GitHub (🔀 2 · ⏱️ 11.07.2023):

   git clone https://github.com/tsudalab/bVAE-IM
  

Show 3 hidden projects...

• EDM (🥉9 · ⭐ 300 · 💀) - E(3) Equivariant Diffusion Model for Molecule Generation in 3D. MIT
• rxngenerator (🥉5 · ⭐ 12 · 💀) - A generative model for molecular generation via multi-step chemical reactions. MIT
• MolSLEPA (🥉4 · ⭐ 3 · 🐣) - Interpretable Fragment-based Molecule Design with Self-learning Entropic Population Annealing. MIT XAI

Interatomic Potentials (ML-IAP)

Machine learning interatomic potentials (aka ML-IAP, MLIAP, MLIP, MLP) and force fields (ML-FF) for molecular dynamics.

DeePMD-kit (🥇28 · ⭐ 1.2K) - A deep learning package for many-body potential energy representation and molecular dynamics. LGPL-3.0 C++

• GitHub (👨‍💻 62 · 🔀 430 · 📥 26K · 📦 11 · 📋 460 - 9% open · ⏱️ 27.09.2023):

   git clone https://github.com/deepmodeling/deepmd-kit
  

• PyPi (📥 1.3K / month):

   pip install deepmd-kit
  

• Conda (📥 1.1K · ⏱️ 27.09.2023):

   conda install -c deepmodeling deepmd-kit
  

• Docker Hub (📥 2K · ⭐ 1 · ⏱️ 01.09.2023):

   docker pull deepmodeling/deepmd-kit
  

MEGNet (🥇21 · ⭐ 460) - Graph Networks as a Universal Machine Learning Framework for Molecules and Crystals. BSD-3

• GitHub (👨‍💻 13 · 🔀 140 · 📦 69 · 📋 74 - 22% open · ⏱️ 27.04.2023):

   git clone https://github.com/materialsvirtuallab/megnet
  

• PyPi (📥 340 / month):

   pip install megnet
  

TorchANI (🥇21 · ⭐ 400) - Accurate Neural Network Potential on PyTorch. MIT

• GitHub (👨‍💻 16 · 🔀 110 · 📦 26 · 📋 160 - 11% open · ⏱️ 21.03.2023):

   git clone https://github.com/aiqm/torchani
  

• PyPi (📥 1.6K / month):

   pip install torchani
  

• Conda (📥 210K · ⏱️ 25.06.2023):

   conda install -c conda-forge torchani
  

DP-GEN (🥇21 · ⭐ 240) - The deep potential generator to generate a deep-learning based model of interatomic potential energy and force field. LGPL-3.0 workflows

• GitHub (👨‍💻 59 · 🔀 160 · 📥 1.5K · 📦 4 · 📋 240 - 16% open · ⏱️ 21.03.2023):

   git clone https://github.com/deepmodeling/dpgen
  

• PyPi (📥 280 / month):

   pip install dpgen
  

• Conda (📥 180 · ⏱️ 16.06.2023):

   conda install -c deepmodeling dpgen
  

NequIP (🥇20 · ⭐ 440) - NequIP is a code for building E(3)-equivariant interatomic potentials. MIT

• GitHub (👨‍💻 8 · 🔀 96 · 📦 15 · 📋 61 - 19% open · ⏱️ 26.03.2023):

   git clone https://github.com/mir-group/nequip
  

• PyPi (📥 510 / month):

   pip install nequip
  

• Conda (📥 3.4K · ⏱️ 18.06.2023):

   conda install -c conda-forge nequip
  

Pre-trained OCP models (🥇19 · ⭐ 470) - Pre-trained models released as part of the Open Catalyst Project. MIT pre-trained

• GitHub (👨‍💻 32 · 🔀 170 · 📋 130 - 11% open · ⏱️ 14.09.2023):

   git clone https://github.com/Open-Catalyst-Project/ocp
  

CHGNet (🥈18 · ⭐ 100) - Pretrained universal neural network potential for charge-informed atomistic modeling https://chgnet.lbl.gov. Custom MD pre-trained electrostatics magnetism structure-relaxation

• GitHub (👨‍💻 6 · 🔀 20 · 📦 7 · 📋 18 - 5% open · ⏱️ 28.09.2023):

   git clone https://github.com/CederGroupHub/chgnet
  

• PyPi (📥 5.9K / month):

   pip install chgnet
  

M3GNet (🥈17 · ⭐ 180) - Materials graph network with 3-body interactions featuring a DFT surrogate crystal relaxer and a state-of-the-art.. BSD-3

• GitHub (👨‍💻 14 · 🔀 51 · 📦 16 · 📋 35 - 42% open · ⏱️ 06.06.2023):

   git clone https://github.com/materialsvirtuallab/m3gnet
  

• PyPi (📥 390 / month):

   pip install m3gnet
  

sGDML (🥈17 · ⭐ 130) - sGDML - Reference implementation of the Symmetric Gradient Domain Machine Learning model. MIT

• GitHub (👨‍💻 8 · 🔀 34 · 📦 8 · 📋 16 - 31% open · ⏱️ 31.08.2023):

   git clone https://github.com/stefanch/sGDML
  

• PyPi (📥 180 / month):

   pip install sgdml
  

PyXtalFF (🥈15 · ⭐ 71) - Machine Learning Interatomic Potential Predictions. MIT

• GitHub (👨‍💻 8 · 🔀 19 · 📋 60 - 15% open · ⏱️ 17.08.2023):

   git clone https://github.com/MaterSim/PyXtal_FF
  

• PyPi (📥 22 / month):

   pip install pyxtal_ff
  

MACE (🥈14 · ⭐ 190) - MACE - Fast and accurate machine learning interatomic potentials with higher order equivariant message passing. MIT

• GitHub (👨‍💻 11 · 🔀 67 · 📋 72 - 31% open · ⏱️ 17.08.2023):

   git clone https://github.com/ACEsuit/mace
  

NNPOps (🥈14 · ⭐ 63) - High-performance operations for neural network potentials. MIT MD C++

• GitHub (👨‍💻 7 · 🔀 14 · 📋 52 - 38% open · ⏱️ 25.07.2023):

   git clone https://github.com/openmm/NNPOps
  

• Conda (📥 67K · ⏱️ 17.08.2023):

   conda install -c conda-forge nnpops
  

Ultra-Fast Force Fields (UF3) (🥈14 · ⭐ 42) - UF3: a python library for generating ultra-fast interatomic potentials. Apache-2

• GitHub (👨‍💻 8 · 🔀 15 · 📋 31 - 38% open · ⏱️ 26.09.2023):

   git clone https://github.com/uf3/uf3
  

• PyPi (📥 10 / month):

   pip install uf3
  

KLIFF (🥈14 · ⭐ 27) - KIM-based Learning-Integrated Fitting Framework (KLIFF). LGPL-2.1 probabilistic workflows

• GitHub (👨‍💻 10 · 🔀 17 · 📋 33 - 51% open · ⏱️ 28.08.2023):

   git clone https://github.com/openkim/kliff
  

• PyPi (📥 46 / month):

   pip install kliff
  

• Conda (📥 63K · ⏱️ 16.06.2023):

   conda install -c conda-forge kliff
  

n2p2 (🥈13 · ⭐ 190 · 💤) - n2p2 - A Neural Network Potential Package. GPL-3.0 C++

• GitHub (👨‍💻 9 · 🔀 67 · 📋 140 - 39% open · ⏱️ 05.09.2022):

   git clone https://github.com/CompPhysVienna/n2p2
  

So3krates (MLFF) (🥈13 · ⭐ 37) - Build neural networks for machine learning force fields with JAX. MIT

• GitHub (👨‍💻 3 · 🔀 6 · 📋 5 - 20% open · ⏱️ 06.09.2023):

   git clone https://github.com/thorben-frank/mlff
  

CCS_fit (🥈13 · ⭐ 5) - Curvature Constrained Splines. GPL-3.0

• GitHub (👨‍💻 8 · 🔀 9 · 📥 380 · 📋 14 - 57% open · ⏱️ 25.09.2023):

   git clone https://github.com/Teoroo-CMC/CCS
  

• PyPi (📥 240 / month):

   pip install ccs_fit
  

DMFF (🥈12 · ⭐ 110 · 💤) - DMFF (Differentiable Molecular Force Field) is a Jax-based python package that provides a full differentiable.. LGPL-3.0

• GitHub (👨‍💻 7 · 🔀 29 · 📋 17 - 64% open · ⏱️ 14.02.2023):

   git clone https://github.com/deepmodeling/DMFF
  

PiNN (🥈11 · ⭐ 96) - A Python library for building atomic neural networks. BSD-3

• GitHub (👨‍💻 2 · 🔀 26 · 📋 6 - 16% open · ⏱️ 28.09.2023):

   git clone https://github.com/Teoroo-CMC/PiNN
  

• Docker Hub (📥 220 · ⏱️ 28.09.2023):

   docker pull teoroo/pinn
  

Pacemaker (🥈11 · ⭐ 45 · 📉) - Python package for fitting atomic cluster expansion (ACE) potentials. Custom

• GitHub (👨‍💻 5 · 🔀 11 · 📋 35 - 22% open · ⏱️ 17.09.2023):

   git clone https://github.com/ICAMS/python-ace
  

• PyPi (📥 1 / month):

   pip install python-ace
  

ACEfit (🥈11 · ⭐ 5) - MIT Julia

• GitHub (👨‍💻 6 · 🔀 3 · 📋 54 - 40% open · ⏱️ 18.08.2023):

   git clone https://github.com/ACEsuit/ACEfit.jl
  

Neural Force Field (🥉10 · ⭐ 190 · 📉) - Neural Network Force Field based on PyTorch. MIT pre-trained

• GitHub (👨‍💻 10 · 🔀 41 · ⏱️ 25.07.2023):

   git clone https://github.com/learningmatter-mit/NeuralForceField
  

DimeNet (🥉9 · ⭐ 250) - DimeNet and DimeNet++ models, as proposed in Directional Message Passing for Molecular Graphs (ICLR 2020) and Fast and.. Custom

• GitHub (👨‍💻 2 · 🔀 53 · 📋 30 - 3% open · ⏱️ 01.08.2023):

   git clone https://github.com/gasteigerjo/dimenet
  

Allegro (🥉9 · ⭐ 230) - Allegro is an open-source code for building highly scalable and accurate equivariant deep learning interatomic.. MIT

• GitHub (👨‍💻 2 · 🔀 33 · 📋 18 - 33% open · ⏱️ 08.05.2023):

   git clone https://github.com/mir-group/allegro
  

ACE.jl (🥉9 · ⭐ 62) - Parameterisation of Equivariant Properties of Particle Systems. Custom Julia

• GitHub (👨‍💻 12 · 🔀 14 · 📋 81 - 28% open · ⏱️ 09.06.2023):

   git clone https://github.com/ACEsuit/ACE.jl
  

ACE1.jl (🥉9 · ⭐ 19) - Atomic Cluster Expansion for Modelling Invariant Atomic Properties. Custom Julia

• GitHub (👨‍💻 7 · 🔀 4 · 📋 45 - 46% open · ⏱️ 19.09.2023):

   git clone https://github.com/ACEsuit/ACE1.jl
  

wfl (🥉9 · ⭐ 14) - Workflow is a Python toolkit for building interatomic potential creation and atomistic simulation workflows. Unlicensed workflows HTC

• GitHub (👨‍💻 13 · 🔀 13 · 📋 130 - 46% open · ⏱️ 22.09.2023):

   git clone https://github.com/libAtoms/workflow
  

NNsforMD (🥉9 · ⭐ 10 · 💤) - Neural network class for molecular dynamics to predict potential energy, forces and non-adiabatic couplings. MIT

• GitHub (👨‍💻 2 · 🔀 4 · ⏱️ 10.11.2022):

   git clone https://github.com/aimat-lab/NNsForMD
  

• PyPi (📥 16 / month):

   pip install pyNNsMD
  

GemNet (🥉8 · ⭐ 150) - GemNet model in PyTorch, as proposed in GemNet: Universal Directional Graph Neural Networks for Molecules (NeurIPS.. Custom

• GitHub (👨‍💻 5 · 🔀 25 · ⏱️ 26.04.2023):

   git clone https://github.com/TUM-DAML/gemnet_pytorch
  

GAP (🥉8 · ⭐ 32) - Gaussian Approximation Potential (GAP). Custom

• GitHub (👨‍💻 12 · 🔀 20 · ⏱️ 08.06.2023):

   git clone https://github.com/libAtoms/GAP
  

Atomistic Adversarial Attacks (🥉8 · ⭐ 24 · 💤) - Code for performing adversarial attacks on atomistic systems using NN potentials. MIT probabilistic

• GitHub (👨‍💻 6 · 🔀 6 · ⏱️ 03.10.2022):

   git clone https://github.com/learningmatter-mit/Atomistic-Adversarial-Attacks
  

ACE1Pack.jl (🥉8 · 🐣) - Provides convenience functionality for the usage of ACE1.jl, ACEfit.jl, JuLIP.jl for fitting interatomic potentials.. MIT Julia

• GitHub (👨‍💻 11 · ⏱️ 21.08.2023):

   git clone https://github.com/ACEsuit/ACE1pack.jl
  

MACE-Jax (🥉7 · ⭐ 35) - Equivariant machine learning interatomic potentials in JAX. MIT

• GitHub (👨‍💻 2 · 🔀 1 · ⏱️ 20.07.2023):

   git clone https://github.com/ACEsuit/mace-jax
  

ALF (🥉7 · ⭐ 19) - A framework for performing active learning for training machine-learned interatomic potentials. Custom active-learning

• GitHub (👨‍💻 5 · 🔀 7 · ⏱️ 04.08.2023):

   git clone https://github.com/lanl/alf
  

Show 17 hidden projects...

• TensorMol (🥈12 · ⭐ 260 · 💀) - Tensorflow + Molecules = TensorMol. GPL-3.0 single-paper
• ANI-1 (🥈12 · ⭐ 200 · 💀) - ANI-1 neural net potential with python interface (ASE). MIT
• SIMPLE-NN (🥈11 · ⭐ 43 · 💀) - SIMPLE-NN(SNU Interatomic Machine-learning PotentiaL packagE version Neural Network). GPL-3.0
• SchNet (🥉9 · ⭐ 180 · 💀) - SchNet - a deep learning architecture for quantum chemistry. MIT
• SNAP (🥉8 · ⭐ 33 · 💀) - Repository for spectral neighbor analysis potential (SNAP) model development. BSD-3
• SIMPLE-NN v2 (🥉8 · ⭐ 28) - GPL-3.0
• PhysNet (🥉7 · ⭐ 78 · 💀) - Code for training PhysNet models. MIT electrostatics
• AIMNet (🥉7 · ⭐ 76 · 💀) - Atoms In Molecules Neural Network Potential. MIT single-paper
• testing-framework (🥉6 · ⭐ 11 · 💀) - The purpose of this repository is to aid the testing of a large number of interatomic potentials for a variety of.. Unlicensed benchmarking
• PANNA (🥉6 · ⭐ 6 · 💀) - A package to train and validate all-to-all connected network models for BP[1] and modified-BP[2] type local atomic.. MIT benchmarking
• Alchemical learning (🥉5 · ⭐ 2) - Code for the Modeling high-entropy transition metal alloys with alchemical compression article. BSD-3
• glp (🥉4 · ⭐ 12 · 🐣) - tools for graph-based machine-learning potentials in jax. MIT
• TensorPotential (🥉4 · ⭐ 5) - Tensorpotential is a TensorFlow based tool for development, fitting ML interatomic potentials from electronic.. Custom
• MLIP-3 (🥉2 · ⭐ 12 · 🐣) - MLIP-3: Active learning on atomic environments with Moment Tensor Potentials (MTP). BSD-2 C++
• SingleNN (🥉2 · ⭐ 6 · 💀) - An efficient package for training and executing neural-network interatomic potentials. Unlicensed C++
• ACE Workflows (🥉2 · 🐣) - Workflow Examples for ACE Models. Unlicensed Julia workflows
• RuNNer (🥉2) - The RuNNer Neural Network Energy Representation is a Fortran-based framework for the construction of Behler-.. GPL-3.0 Fortran

Language Models

Projects that use (large) language models (LMs, LLMs) or natural language procesing (NLP) techniques for atomistic ML.

paper-qa (🥇25 · ⭐ 3.1K) - LLM Chain for answering questions from documents with citations. Apache-2

• GitHub (👨‍💻 12 · 🔀 290 · 📦 32 · 📋 100 - 39% open · ⏱️ 19.09.2023):

   git clone https://github.com/whitead/paper-qa
  

• PyPi (📥 4.4K / month):

   pip install paper-qa
  

mat2vec (🥈12 · ⭐ 600) - Supplementary Materials for Tshitoyan et al. Unsupervised word embeddings capture latent knowledge from materials.. MIT rep-learn

• GitHub (👨‍💻 5 · 🔀 170 · 📋 23 - 26% open · ⏱️ 06.05.2023):

   git clone https://github.com/materialsintelligence/mat2vec
  

gptchem (🥈12 · ⭐ 160) - Use GPT-3 to solve chemistry problems. MIT

• GitHub (👨‍💻 2 · 🔀 30 · 📋 8 - 75% open · ⏱️ 22.06.2023):

   git clone https://github.com/kjappelbaum/gptchem
  

• PyPi (📥 80 / month):

   pip install gptchem
  

MolSkill (🥉11 · ⭐ 81) - Learning chemical intuition from humans in the loop. Supporting code. MIT drug-discovery recommender

• GitHub (👨‍💻 4 · 🔀 5 · 📋 5 - 40% open · ⏱️ 13.06.2023):

   git clone https://github.com/microsoft/molskill
  

• Conda (📥 120 · ⏱️ 18.06.2023):

   conda install -c msr-ai4science molskill
  

nlcc (🥉10 · ⭐ 41 · 💤) - Natural language computational chemistry command line interface. MIT single-paper

• GitHub (👨‍💻 3 · 🔀 6 · ⏱️ 04.02.2023):

   git clone https://github.com/whitead/nlcc
  

• PyPi (📥 9 / month):

   pip install nlcc
  

Show 1 hidden projects...

• BERT-PSIE-TC (🥉4 · ⭐ 2) - A dataset of Curie temperatures automatically extracted from scientific literature with the use of the BERT-PSIE.. MIT magnetism

Materials Discovery

Projects that implement materials discovery methods using atomistic ML.

aviary (🥇13 · ⭐ 29) - The Wren sits on its Roost in the Aviary. MIT

• GitHub (👨‍💻 7 · 🔀 7 · 📋 26 - 15% open · ⏱️ 10.08.2023):

   git clone https://github.com/CompRhys/aviary
  

closed-loop-acceleration-benchmarks (🥉5) - Data and scripts in support of the publication By how much can closed-loop frameworks accelerate computational.. MIT materials-discovery active-learning single-paper

• GitHub (👨‍💻 2 · 🔀 1 · ⏱️ 02.05.2023):

   git clone https://github.com/aced-differentiate/closed-loop-acceleration-benchmarks
  

Show 6 hidden projects...

• BOSS (🥈7 · ⭐ 18 · 💀) - Bayesian Optimization Structure Search (BOSS). Unlicensed probabilistic
• AGOX (🥈6 · ⭐ 10 · 💀) - AGOX is a package for global optimization of atomic system using e.g. the energy calculated from density functional.. GPL-3.0 structure-optimization
• Computational Autonomy for Materials Discovery (CAMD) (🥈6 · ⭐ 1 · 💤) - Agent-based sequential learning software for materials discovery. Apache-2
• CSPML (crystal structure prediction with machine learning-based element substitution) (🥉3 · ⭐ 12 · 💀) - Original implementation of CSPML. Unlicensed structure-prediction
• SPINNER (🥉3 · ⭐ 9 · 💀) - SPINNER (Structure Prediction of Inorganic crystals using Neural Network potentials with Evolutionary and Random.. GPL-3.0 C++ structure-prediction
• sl_discovery (🥉3 · ⭐ 5 · 💤) - Data processing and models related to Quantifying the performance of machine learning models in materials discovery. Apache-2 materials-discovery single-paper

Mathematical tools

Projects that implement mathematical objects used in atomistic machine learning.

KFAC-JAX (🥇18 · ⭐ 160) - Second Order Optimization and Curvature Estimation with K-FAC in JAX. Apache-2

• GitHub (👨‍💻 11 · 🔀 13 · 📦 6 · 📋 9 - 22% open · ⏱️ 26.09.2023):

   git clone https://github.com/deepmind/kfac-jax
  

• PyPi (📥 950 / month):

   pip install kfac-jax
  

gpax (🥈17 · ⭐ 120) - Gaussian Processes for Experimental Sciences. MIT probabilistic active-learning

• GitHub (🔀 15 · 📋 8 - 37% open · ⏱️ 04.09.2023):

   git clone https://github.com/ziatdinovmax/gpax
  

• PyPi (📥 350 / month):

   pip install gpax
  

Polynomials4ML.jl (🥈15 · ⭐ 10) - Polynomials for ML: fast evaluation, batching, differentiation. MIT Julia

• GitHub (👨‍💻 8 · 🔀 4 · 📋 42 - 35% open · ⏱️ 24.09.2023):

   git clone https://github.com/ACEsuit/Polynomials4ML.jl
  

SpheriCart (🥈13 · ⭐ 41) - Multi-language library for the calculation of spherical harmonics in Cartesian coordinates. Apache-2

• GitHub (👨‍💻 6 · 🔀 3 · 📥 1 · 📦 1 · 📋 14 - 57% open · ⏱️ 18.08.2023):

   git clone https://github.com/lab-cosmo/sphericart
  

• PyPi (📥 93 / month):

   pip install sphericart
  

GElib (🥉6 · ⭐ 16) - C++/CUDA library for SO(3) equivariant operations. MPL-2.0 C++

• GitHub (👨‍💻 3 · 🔀 2 · 📋 5 - 80% open · ⏱️ 23.07.2023):

   git clone https://github.com/risi-kondor/GElib
  

COSMO Toolbox (🥉6 · ⭐ 6) - Assorted libraries and utilities for atomistic simulation analysis. Unlicensed C++

• GitHub (👨‍💻 9 · 🔀 5 · ⏱️ 23.06.2023):

   git clone https://github.com/lab-cosmo/toolbox
  

Show 3 hidden projects...

• EquivariantOperators.jl (🥉6 · ⭐ 17) - MIT Julia
• cnine (🥉4 · ⭐ 2) - Cnine tensor library. Unlicensed C++
• Wigner Kernels (🥉3 · ⭐ 1) - Collection of programs to benchmark Wigner kernels. Unlicensed benchmarking

Molecular Dynamics

Projects that simplify the integration of molecular dynamics and atomistic machine learning.

JAX-MD (🥇23 · ⭐ 990) - Differentiable, Hardware Accelerated, Molecular Dynamics. Apache-2

• GitHub (👨‍💻 28 · 🔀 160 · 📦 33 · 📋 130 - 45% open · ⏱️ 29.08.2023):

   git clone https://github.com/jax-md/jax-md
  

• PyPi (📥 1.6K / month):

   pip install jax-md
  

FitSNAP (🥈19 · ⭐ 120) - Software for generating SNAP machine-learning interatomic potentials. GPL-2.0

• GitHub (👨‍💻 24 · 🔀 43 · 📥 7 · 📋 62 - 12% open · ⏱️ 15.09.2023):

   git clone https://github.com/FitSNAP/FitSNAP
  

• Conda (📥 4.6K · ⏱️ 16.06.2023):

   conda install -c conda-forge fitsnap3
  

openmm-torch (🥈15 · ⭐ 130) - OpenMM plugin to define forces with neural networks. Custom ML-IAP C++

• GitHub (👨‍💻 7 · 🔀 24 · 📋 68 - 25% open · ⏱️ 27.09.2023):

   git clone https://github.com/openmm/openmm-torch
  

• Conda (📥 210K · ⏱️ 27.09.2023):

   conda install -c conda-forge openmm-torch
  

OpenMM-ML (🥉10 · ⭐ 52) - High level API for using machine learning models in OpenMM simulations. MIT ML-IAP

• GitHub (👨‍💻 2 · 🔀 15 · 📋 39 - 53% open · ⏱️ 21.08.2023):

   git clone https://github.com/openmm/openmm-ml
  

• Conda (📥 1.9K · ⏱️ 21.08.2023):

   conda install -c conda-forge openmm-ml
  

PACE (🥉9 · ⭐ 21 · 💤) - The LAMMPS ML-IAP `pair_style pace`, aka Atomic Cluster Expansion (ACE), aka ML-PACE,.. Custom

• GitHub (👨‍💻 6 · 🔀 10 · 📋 6 - 16% open · ⏱️ 31.01.2023):

   git clone https://github.com/ICAMS/lammps-user-pace
  

Show 1 hidden projects...

• interface-lammps-mlip-3 (🥉2 · ⭐ 5 · 🐣) - An interface between LAMMPS and MLIP (version 3). GPL-2.0

Probabilistic ML

Projects that focus on probabilistic, Bayesian, Gaussian process and adversarial methods for atomistic ML, for optimization, uncertainty quantification (UQ), etc.

Reinforcement Learning

Projects that focus on reinforcement learning for atomistic ML.

Show 2 hidden projects...

• ReLeaSE (🥇11 · ⭐ 310 · 💀) - Deep Reinforcement Learning for de-novo Drug Design. MIT drug-discovery
• CatGym (🥉6 · ⭐ 10 · 💀) - Surface segregation using Deep Reinforcement Learning. GPL

Representation Engineering

Projects that offer implementations of representations aka descriptors, fingerprints of atomistic systems, and models built with them, aka feature engineering.

cdk (🥇25 · ⭐ 430) - The Chemistry Development Kit. LGPL-2.1 cheminformatics Java

• GitHub (👨‍💻 160 · 🔀 150 · 📥 16K · 📦 18 · 📋 260 - 8% open · ⏱️ 11.09.2023):

   git clone https://github.com/cdk/cdk
  

• Maven:

   <dependency>
   	<groupId>org.openscience.cdk</groupId>
   	<artifactId>cdk-bundle</artifactId>
   	<version>[VERSION]</version>
   </dependency>
  

DScribe (🥇23 · ⭐ 340) - DScribe is a python package for creating machine learning descriptors for atomistic systems. Apache-2

• GitHub (👨‍💻 18 · 🔀 79 · 📦 150 · 📋 85 - 9% open · ⏱️ 05.09.2023):

   git clone https://github.com/SINGROUP/dscribe
  

• PyPi (📥 25K / month):

   pip install dscribe
  

• Conda (📥 78K · ⏱️ 06.09.2023):

   conda install -c conda-forge dscribe
  

CatLearn (🥇16 · ⭐ 93 · 💤) - GPL-3.0 surface-science

• GitHub (👨‍💻 22 · 🔀 51 · 📦 4 · 📋 25 - 36% open · ⏱️ 07.02.2023):

   git clone https://github.com/SUNCAT-Center/CatLearn
  

• PyPi (📥 100 / month):

   pip install catlearn
  

MODNet (🥇16 · ⭐ 58) - MODNet: a framework for machine learning materials properties. MIT pre-trained small-data transfer-learning

• GitHub (👨‍💻 7 · 🔀 26 · 📦 3 · 📋 35 - 37% open · ⏱️ 29.07.2023):

   git clone https://github.com/ppdebreuck/modnet
  

SISSO (🥈14 · ⭐ 180) - A data-driven method combining symbolic regression and compressed sensing for accurate & interpretable models. Apache-2 Fortran

• GitHub (👨‍💻 3 · 🔀 61 · 📋 51 - 1% open · ⏱️ 12.09.2023):

   git clone https://github.com/rouyang2017/SISSO
  

GlassPy (🥈14 · ⭐ 16) - Python module for scientists working with glass materials. GPL-3.0

• GitHub (🔀 6 · 📦 2 · 📋 4 - 25% open · ⏱️ 27.08.2023):

   git clone https://github.com/drcassar/glasspy
  

• PyPi (📥 260 / month):

   pip install glasspy
  

Librascal (🥈13 · ⭐ 71) - A scalable and versatile library to generate representations for atomic-scale learning. LGPL-2.1

• GitHub (👨‍💻 29 · 🔀 18 · 📋 230 - 43% open · ⏱️ 06.06.2023):

   git clone https://github.com/lab-cosmo/librascal
  

Rascaline (🥈12 · ⭐ 20) - Computing representations for atomistic machine learning. BSD-3 Rust C++

• GitHub (👨‍💻 11 · 🔀 11 · 📋 40 - 47% open · ⏱️ 21.09.2023):

   git clone https://github.com/Luthaf/rascaline
  

BenchML (🥉7 · ⭐ 13) - ML benchmarking and pipeling framework. Apache-2 benchmarking

• GitHub (👨‍💻 9 · 🔀 2 · 📋 13 - 23% open · ⏱️ 24.05.2023):

   git clone https://github.com/capoe/benchml
  

• PyPi (📥 17 / month):

   pip install benchml
  

milad (🥉6 · ⭐ 27 · 💤) - Moment Invariants Local Atomic Descriptor. GPL-3.0 generative

• GitHub (🔀 1 · 📦 1 · ⏱️ 03.12.2022):

   git clone https://github.com/muhrin/milad
  

SA-GPR (🥉6 · ⭐ 14 · 💤) - Public repository for symmetry-adapted Gaussian Process Regression (SA-GPR). LGPL-3.0 C-lang

• GitHub (👨‍💻 5 · 🔀 9 · 📋 7 - 28% open · ⏱️ 29.09.2022):

   git clone https://github.com/dilkins/TENSOAP
  

NICE (🥉6 · ⭐ 10) - NICE (N-body Iteratively Contracted Equivariants) is a set of tools designed for the calculation of invariant and.. MIT

• GitHub (👨‍💻 4 · 🔀 2 · 📋 3 - 66% open · ⏱️ 01.05.2023):

   git clone https://github.com/lab-cosmo/nice
  

Show 10 hidden projects...

• cmlkit (🥈10 · ⭐ 31 · 💀) - tools for machine learning in condensed matter physics and quantum chemistry. MIT benchmarking
• SkipAtom (🥉8 · ⭐ 22 · 💀) - Distributed representations of atoms, inspired by the Skip-gram model. MIT
• CBFV (🥉7 · ⭐ 14 · 💀) - Tool to quickly create a composition-based feature vector. Unlicensed
• pyLODE (🥉7 · ⭐ 2) - Pythonic implementation of LOng Distance Equivariants. Apache-2 electrostatics
• fplib (🥉6 · ⭐ 7 · 💀) - a fingerprint library. MIT C-lang single-paper
• SOAPxx (🥉6 · ⭐ 7 · 💀) - A SOAP implementation. GPL-2.0 C++
• magnetism-prediction (🥉4 · ⭐ 1) - DFT-aided Machine Learning Search for Magnetism in Fe-based Bimetallic Chalcogenides. Apache-2 magnetism single-paper
• SISSO++ (🥉3 · ⭐ 1 · 💀) - C++ Implementation of SISSO with python bindings. Apache-2 C++
• ML-for-CurieTemp-Predictions (🥉3 · 🐣) - Machine Learning Predictions of High-Curie-Temperature Materials. MIT single-paper magnetism
• AMP (🥉2) - Amp is an open-source package designed to easily bring machine-learning to atomistic calculations. Unlicensed

Representation Learning

General models that learn a representations aka embeddings of atomistic systems, such as message-passing neural networks (MPNN).

Deep Graph Library (DGL) (🥇38 · ⭐ 12K) - Python package built to ease deep learning on graph, on top of existing DL frameworks. Apache-2

• GitHub (👨‍💻 280 · 🔀 2.8K · 📦 150 · 📋 2.4K - 13% open · ⏱️ 28.09.2023):

   git clone https://github.com/dmlc/dgl
  

• PyPi (📥 83K / month):

   pip install dgl
  

• Conda (📥 290K · ⏱️ 14.09.2023):

   conda install -c dglteam dgl
  

PyG Models (🥇29 · ⭐ 19K) - Representation learning models implemented in PyTorch Geometric. MIT general-ml

• GitHub (👨‍💻 450 · 🔀 3.3K · 📋 3.2K - 23% open · ⏱️ 28.09.2023):

   git clone https://github.com/pyg-team/pytorch_geometric
  

SchNetPack (🥇27 · ⭐ 640) - SchNetPack - Deep Neural Networks for Atomistic Systems. MIT

• GitHub (👨‍💻 31 · 🔀 180 · 📦 59 · 📋 210 - 1% open · ⏱️ 13.09.2023):

   git clone https://github.com/atomistic-machine-learning/schnetpack
  

• PyPi (📥 420 / month):

   pip install schnetpack
  

e3nn (🥇24 · ⭐ 750) - A modular framework for neural networks with Euclidean symmetry. MIT

• GitHub (👨‍💻 29 · 🔀 110 · 📦 110 · 📋 150 - 10% open · ⏱️ 02.09.2023):

   git clone https://github.com/e3nn/e3nn
  

• PyPi (📥 49K / month):

   pip install e3nn
  

• Conda (📥 9.2K · ⏱️ 18.06.2023):

   conda install -c conda-forge e3nn
  

kgcnn (🥇23 · ⭐ 85 · 📈) - Graph convolutions in Keras with TensorFlow, PyTorch or Jax. MIT

• GitHub (👨‍💻 7 · 🔀 25 · 📦 15 · 📋 77 - 6% open · ⏱️ 28.09.2023):

   git clone https://github.com/aimat-lab/gcnn_keras
  

• PyPi (📥 170 / month):

   pip install kgcnn
  

NVIDIA Deep Learning Examples for Tensor Cores (🥇21 · ⭐ 12K) - State-of-the-Art Deep Learning scripts organized by models - easy to train and deploy with reproducible accuracy and.. Custom educational drug-discovery

• GitHub (👨‍💻 120 · 🔀 2.8K · 📋 780 - 28% open · ⏱️ 05.09.2023):

   git clone https://github.com/NVIDIA/DeepLearningExamples
  

dgl-lifesci (🥇21 · ⭐ 620) - Python package for graph neural networks in chemistry and biology. Apache-2

• GitHub (👨‍💻 22 · 🔀 130 · 📦 120 · 📋 80 - 30% open · ⏱️ 16.04.2023):

   git clone https://github.com/awslabs/dgl-lifesci
  

• PyPi (📥 6.7K / month):

   pip install dgllife
  

MatGL (Materials Graph Library) (🥇21 · ⭐ 120) - Graph deep learning library for materials. BSD-3

• GitHub (👨‍💻 12 · 🔀 26 · 📦 6 · 📋 39 - 7% open · ⏱️ 26.09.2023):

   git clone https://github.com/materialsvirtuallab/matgl
  

• PyPi (📥 390 / month):

   pip install m3gnet
  

ocp (🥈19 · ⭐ 470) - ocp is the Open Catalyst Projects library of state-of-the-art machine learning algorithms for catalysis. MIT

• GitHub (👨‍💻 32 · 🔀 170 · 📋 130 - 11% open · ⏱️ 14.09.2023):

   git clone https://github.com/Open-Catalyst-Project/ocp
  

ALIGNN (🥈19 · ⭐ 150 · 📈) - Atomistic Line Graph Neural Network. Custom

• GitHub (👨‍💻 7 · 🔀 63 · 📦 7 · 📋 46 - 50% open · ⏱️ 11.08.2023):

   git clone https://github.com/usnistgov/alignn
  

• PyPi (📥 490 / month):

   pip install alignn
  

e3nn-jax (🥈18 · ⭐ 120) - jax library for E3 Equivariant Neural Networks. Apache-2

• GitHub (👨‍💻 4 · 🔀 13 · 📋 9 - 11% open · ⏱️ 28.09.2023):

   git clone https://github.com/e3nn/e3nn-jax
  

• PyPi (📥 2.5K / month):

   pip install e3nn-jax
  

Uni-Mol (🥈17 · ⭐ 420) - Official Repository for the Uni-Mol Series Methods. MIT pre-trained

• GitHub (👨‍💻 10 · 🔀 76 · 📥 6K · 📋 100 - 28% open · ⏱️ 26.09.2023):

   git clone https://github.com/dptech-corp/Uni-Mol
  

matsciml (🥈17 · ⭐ 65) - Open MatSci ML Toolkit is a single framework for prototyping and scaling out deep learning models for materials.. MIT workflows

• GitHub (👨‍💻 8 · 🔀 8 · 📋 10 - 50% open · ⏱️ 27.09.2023):

   git clone https://github.com/IntelLabs/matsciml
  

escnn (🥈15 · ⭐ 220) - Equivariant Steerable CNNs Library for Pytorch https://quva-lab.github.io/escnn/. Custom

• GitHub (👨‍💻 9 · 🔀 33 · 📋 55 - 34% open · ⏱️ 11.09.2023):

   git clone https://github.com/QUVA-Lab/escnn
  

• PyPi (📥 1.1K / month):

   pip install escnn
  

Compositionally-Restricted Attention-Based Network (CrabNet) (🥈12 · ⭐ 10) - Predict materials properties using only the composition information!. MIT

• GitHub (👨‍💻 5 · 🔀 3 · 📦 10 · 📋 16 - 87% open · ⏱️ 19.06.2023):

   git clone https://github.com/sparks-baird/CrabNet
  

• PyPi (📥 89 / month):

   pip install crabnet
  

GDC (🥈10 · ⭐ 220) - Graph Diffusion Convolution, as proposed in Diffusion Improves Graph Learning (NeurIPS 2019). MIT generative

• GitHub (👨‍💻 3 · 🔀 38 · ⏱️ 26.04.2023):

   git clone https://github.com/gasteigerjo/gdc
  

graphite (🥈10 · ⭐ 25) - A repository for implementing graph network models based on atomic structures. MIT

• GitHub (👨‍💻 2 · 🔀 6 · 📦 6 · ⏱️ 16.08.2023):

   git clone https://github.com/llnl/graphite
  

GATGNN: Global Attention Graph Neural Network (🥉9 · ⭐ 60 · 💤) - Pytorch Repository for our work: Graph convolutional neural networks with global attention for improved materials.. MIT

• GitHub (👨‍💻 3 · 🔀 18 · 📋 6 - 50% open · ⏱️ 03.10.2022):

   git clone https://github.com/superlouis/GATGNN
  

CGAT (🥉9 · ⭐ 15 · 💤) - Crystal graph attention neural networks for materials prediction. MIT

• GitHub (👨‍💻 4 · 🔀 7 · ⏱️ 10.01.2023):

   git clone https://github.com/hyllios/CGAT
  

hippynn (🥉8 · ⭐ 42) - python library for atomistic machine learning. Custom workflows

• GitHub (👨‍💻 11 · 🔀 18 · 📋 4 - 75% open · ⏱️ 05.08.2023):

   git clone https://github.com/lanl/hippynn
  

DeeperGATGNN (🥉8 · ⭐ 32) - Scalable graph neural networks for materials property prediction. MIT

• GitHub (👨‍💻 3 · 🔀 7 · ⏱️ 19.04.2023):

   git clone https://github.com/usccolumbia/deeperGATGNN
  

UVVisML (🥉8 · ⭐ 14) - Predict optical properties of molecules with machine learning. MIT optical-properties single-paper probabilistic

• GitHub (🔀 4 · ⏱️ 26.05.2023):

   git clone https://github.com/learningmatter-mit/uvvisml
  

Equiformer (🥉7 · ⭐ 120) - [ICLR23 Spotlight] Equiformer: Equivariant Graph Attention Transformer for 3D Atomistic Graphs. MIT

• GitHub (👨‍💻 2 · 🔀 25 · 📋 12 - 41% open · ⏱️ 21.06.2023):

   git clone https://github.com/atomicarchitects/equiformer
  

AdsorbML (🥉7 · ⭐ 20) - MIT surface-science single-paper

• GitHub (👨‍💻 5 · 🔀 5 · ⏱️ 31.07.2023):

   git clone https://github.com/Open-Catalyst-Project/AdsorbML
  

ML4pXRDs (🥉7) - Contains code to train neural networks based on simulated powder XRDs from synthetic crystals. MIT XRD single-paper

• GitHub (🔀 1 · 📥 2 · ⏱️ 14.07.2023):

   git clone https://github.com/aimat-lab/ML4pXRDs
  

MACE-Layer (🥉6 · ⭐ 25) - Higher order equivariant graph neural networks for 3D point clouds. MIT

• GitHub (👨‍💻 2 · 🔀 3 · ⏱️ 06.06.2023):

   git clone https://github.com/ACEsuit/mace-layer
  

escnn_jax (🥉6 · ⭐ 22 · 🐣) - Equivariant Steerable CNNs Library for Pytorch https://quva-lab.github.io/escnn/. Custom

• GitHub (👨‍💻 8 · 🔀 2 · ⏱️ 28.06.2023):

   git clone https://github.com/emilemathieu/escnn_jax
  

• PyPi:

   pip install escnn_jax
  

GLAMOUR (🥉6 · ⭐ 18 · 💤) - Graph Learning over Macromolecule Representations. MIT single-paper

• GitHub (🔀 6 · ⏱️ 31.12.2022):

   git clone https://github.com/learningmatter-mit/GLAMOUR
  

EquiformerV2 (🥉5 · ⭐ 82 · 🐣) - [arXiv23] EquiformerV2: Improved Equivariant Transformer for Scaling to Higher-Degree Representations. MIT

• GitHub (👨‍💻 2 · 🔀 9 · ⏱️ 28.07.2023):

   git clone https://github.com/atomicarchitects/equiformer_v2
  

CraTENet (🥉5 · ⭐ 6) - An attention-based deep neural network for thermoelectric transport properties. MIT transport-phenomena

• GitHub (🔀 1 · ⏱️ 05.04.2023):

   git clone https://github.com/lantunes/CraTENet
  

Per-site PAiNN (🥉5 · 🐣) - Fork of PaiNN for PerovskiteOrderingGCNNs. MIT probabilistic pre-trained single-paper

• GitHub (👨‍💻 10 · ⏱️ 05.06.2023):

   git clone https://github.com/learningmatter-mit/per-site_painn
  

Show 21 hidden projects...

• benchmarking-gnns (🥈14 · ⭐ 2.3K · 💀) - Repository for benchmarking graph neural networks. MIT single-paper benchmarking
• Crystal Graph Convolutional Neural Networks (CGCNN) (🥈12 · ⭐ 510 · 💀) - Crystal graph convolutional neural networks for predicting material properties. MIT
• Neural fingerprint (nfp) (🥈12 · ⭐ 54 · 💀) - Keras layers for end-to-end learning with rdkit and pymatgen. Custom
• SE(3)-Transformers (🥈10 · ⭐ 410 · 💀) - code for the SE3 Transformers paper: https://arxiv.org/abs/2006.10503. MIT single-paper
• molecularGNN_smiles (🥉9 · ⭐ 250 · 💀) - The code of a graph neural network (GNN) for molecules, which is based on learning representations of r-radius.. Apache-2
• ai4material_design (🥉9 · ⭐ 1) - Code for Kazeev, N., Al-Maeeni, A.R., Romanov, I. et al. Sparse representation for machine learning the properties of.. Apache-2 pre-trained material-defect
• DTNN (🥉7 · ⭐ 77 · 💀) - Deep Tensor Neural Network. MIT
• Cormorant (🥉7 · ⭐ 54 · 💀) - Codebase for Cormorant Neural Networks. Custom
• charge_transfer_nnp (🥉6 · ⭐ 21 · 💀) - Graph neural network potential with charge transfer. MIT electrostatics
• tensorfieldnetworks (🥉5 · ⭐ 140 · 💀) - MIT
• Autobahn (🥉5 · ⭐ 27 · 💀) - Repository for Autobahn: Automorphism Based Graph Neural Networks. MIT
• SCFNN (🥉5 · ⭐ 14 · 💀) - Self-consistent determination of long-range electrostatics in neural network potentials. MIT C++ electrostatics single-paper
• FieldSchNet (🥉5 · ⭐ 9 · 💀) - MIT
• Graph Transport Network (🥉4 · ⭐ 14) - Graph transport network (GTN), as proposed in Scalable Optimal Transport in High Dimensions for Graph Distances,.. Custom transport-phenomena
• Per-Site CGCNN (🥉4 · ⭐ 1 · 🐣) - Crystal graph convolutional neural networks for predicting material properties. MIT pre-trained single-paper
• Atom2Vec (🥉3 · ⭐ 25 · 💀) - Atom2Vec: a simple way to describe atoms for machine learning. Unlicensed
• Element encoder (🥉3 · ⭐ 5 · 💀) - Autoencoder neural network to compress properties of atomic species into a vector representation. GPL-3.0 single-paper
• Point Edge Transformer (🥉2) - Smooth, exact rotational symmetrization for deep learning on point clouds. CC-BY-4.0
• SphericalNet (🥉1 · ⭐ 3 · 💀) - Implementation of Clebsch-Gordan Networks (CGnet: https://arxiv.org/pdf/1806.09231.pdf) by GElib & cnine libraries in.. Unlicensed
• gkx: Green-Kubo Method in JAX (🥉1 · ⭐ 2 · 🐣) - Green-Kubo + JAX + MLPs = Anharmonic Thermal Conductivities Done Fast. MIT transport-phenomena
• atom_by_atom ( ⭐ 2 · 🐣) - Atom-by-atom design of metal oxide catalysts for the oxygen evolution reaction with Machine Learning. Unlicensed surface-science single-paper

Unsupervised Learning

Projects that focus on unsupervised learning (USL) for atomistic ML, such as dimensionality reduction, clustering and visualization.

DADApy (🥇15 · ⭐ 72) - Distance-based Analysis of DAta-manifolds in python. Apache-2

• GitHub (👨‍💻 15 · 🔀 8 · 📦 2 · 📋 25 - 40% open · ⏱️ 14.09.2023):

   git clone https://github.com/sissa-data-science/DADApy
  

• PyPi (📥 55 / month):

   pip install dadapy
  

ASAP (🥈13 · ⭐ 110) - ASAP is a package that can quickly analyze and visualize datasets of crystal or molecular structures. MIT

• GitHub (👨‍💻 6 · 🔀 25 · 📦 4 · 📋 24 - 25% open · ⏱️ 30.08.2023):

   git clone https://github.com/BingqingCheng/ASAP
  

Sketchmap (🥉8 · ⭐ 39) - Suite of programs to perform non-linear dimensionality reduction -- sketch-map in particular. GPL-3.0 C++

• GitHub (👨‍💻 8 · 🔀 10 · 📋 8 - 37% open · ⏱️ 24.05.2023):

   git clone https://github.com/lab-cosmo/sketchmap
  

Show 3 hidden projects...

• Coarse-Graining-Auto-encoders (🥉3 · ⭐ 19 · 💀) - Unlicensed single-paper
• KmdPlus (🥉1 · ⭐ 1 · 🐣) - This module contains a class for treating kernel mean descriptor (KMD), and a function for generating descriptors with.. Unlicensed
• Descriptor Embedding and Clustering for Atomisitic-environment Framework (DECAF) ( ⭐ 2) - Provides a workflow to obtain clustering of local environments in dataset of structures. Unlicensed

Visualization

Projects that focus on visualization (viz.) for atomistic ML.

Chemiscope (🥇15 · ⭐ 87) - An interactive structure/property explorer for materials and molecules. BSD-3 JavaScript

• GitHub (👨‍💻 17 · 🔀 27 · 📥 140 · 📦 5 · 📋 110 - 38% open · ⏱️ 14.09.2023):

   git clone https://github.com/lab-cosmo/chemiscope
  

• npm (📥 14 / month):

   npm install chemiscope
  

Wavefunction methods (ML-WFT)

Projects and models that focus on quantities of wavefunction theory methods, such as Monte Carlo techniques like deep learning variational Monte Carlo (DL-VMC), quantum chemistry methods, etc.

DeepQMC (🥇21 · ⭐ 300 · 📈) - Deep learning quantum Monte Carlo for electrons in real space. MIT

• GitHub (👨‍💻 13 · 🔀 56 · 📦 1 · 📋 36 - 5% open · ⏱️ 27.09.2023):

   git clone https://github.com/deepqmc/deepqmc
  

• PyPi (📥 140 / month):

   pip install deepqmc
  

FermiNet (🥈14 · ⭐ 580) - An implementation of the Fermionic Neural Network for ab-initio electronic structure calculations. Apache-2

• GitHub (👨‍💻 18 · 🔀 100 · ⏱️ 14.08.2023):

   git clone https://github.com/deepmind/ferminet
  

DeepErwin (🥉9 · ⭐ 35) - DeepErwin is a python 3.8+ package that implements and optimizes JAX 2.x wave function models for numerical solutions.. Custom

• GitHub (👨‍💻 6 · 🔀 6 · 📋 10 - 10% open · ⏱️ 21.09.2023):

   git clone https://github.com/mdsunivie/deeperwin
  

• PyPi (📥 20 / month):

   pip install deeperwin
  

Show 1 hidden projects...

• SchNOrb (🥉5 · ⭐ 54 · 💀) - Unifying machine learning and quantum chemistry with a deep neural network for molecular wavefunctions. MIT

Others

Show 1 hidden projects...

---

Contribution

Contributions are encouraged and always welcome! If you like to add or update projects, choose one of the following ways:

• Open an issue by selecting one of the provided categories from the issue page and fill in the requested information.
• Modify the projects.yaml with your additions or changes, and submit a pull request. This can also be done directly via the Github UI.

If you like to contribute to or share suggestions regarding the project metadata collection or markdown generation, please refer to the best-of-generator repository. If you like to create your own best-of list, we recommend to follow this guide.

For more information on how to add or update projects, please read the contribution guidelines. By participating in this project, you agree to abide by its Code of Conduct.

License