πΒ A ranked list of awesome atomistic machine learning (AML) projects. Updated quarterly.
This curated list contains 360 awesome open-source projects with a total of 170K stars grouped into 22 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!
π§ββοΈ Discover other best-of lists or create your own.
- Active learning 4 projects
- Biomolecules 2 projects
- Community resources 21 projects
- Datasets 34 projects
- Data Structures 4 projects
- Density functional theory (ML-DFT) 25 projects
- Educational Resources 24 projects
- Explainable Artificial intelligence (XAI) 4 projects
- Electronic structure methods (ML-ESM) 3 projects
- General Tools 22 projects
- Generative Models 11 projects
- Interatomic Potentials (ML-IAP) 61 projects
- Language Models 16 projects
- Materials Discovery 9 projects
- Mathematical tools 11 projects
- Molecular Dynamics 9 projects
- Reinforcement Learning 2 projects
- Representation Engineering 23 projects
- Representation Learning 55 projects
- Unsupervised Learning 7 projects
- Visualization 2 projects
- Wavefunction methods (ML-WFT) 4 projects
- Others 2 projects
- π₯π₯π₯Β Combined project-quality score
- βοΈΒ Star count from GitHub
- π£Β New project (less than 6 months old)
- π€Β Inactive project (6 months no activity)
- πΒ Dead project (12 months no activity)
- ππΒ Project is trending up or down
- βΒ Project was recently added
- π¨βπ»Β Contributors count from GitHub
- πΒ Fork count from GitHub
- πΒ Issue count from GitHub
- β±οΈΒ Last update timestamp on package manager
- π₯Β Download count from package manager
- π¦Β Number of dependent projects
Projects that focus on enabling active learning, iterative learning schemes for atomistic ML.
FLARE (π₯18 Β· β 260 Β· π€) - An open-source Python package for creating fast and accurate interatomic potentials. MIT
C++
ML-IAP
-
GitHub (π¨βπ» 37 Β· π 60 Β· π₯ 4 Β· π¦ 10 Β· π 190 - 14% open Β· β±οΈ 26.05.2023):
git clone https://github.com/mir-group/flare
Finetuna (π₯10 Β· β 38) - Active Learning for Machine Learning Potentials. MIT
-
GitHub (π¨βπ» 11 Β· π 10 Β· π 19 - 21% open Β· β±οΈ 03.10.2023):
git clone https://github.com/ulissigroup/finetuna
ACEHAL (π₯5 Β· β 9) - Hyperactive Learning (HAL) Python interface for building Atomic Cluster Expansion potentials. Unlicensed
Julia
-
GitHub (π¨βπ» 3 Β· π 3 Β· π 10 - 40% open Β· β±οΈ 21.09.2023):
git clone https://github.com/ACEsuit/ACEHAL
Show 1 hidden projects...
Projects that focus on biomolecules, protein structure, protein folding, etc. using atomistic ML.
AlphaFold (π₯21 Β· β 11K) - Open source code for AlphaFold. Apache-2
-
GitHub (π¨βπ» 19 Β· π 1.9K Β· π¦ 7 Β· π 780 - 25% open Β· β±οΈ 01.11.2023):
git clone https://github.com/deepmind/alphafold
Uni-Fold (π₯15 Β· β 320) - An open-source platform for developing protein models beyond AlphaFold. Apache-2
-
GitHub (π¨βπ» 7 Β· π 55 Β· π₯ 2.9K Β· π 66 - 22% open Β· β±οΈ 08.01.2024):
git clone https://github.com/dptech-corp/Uni-Fold
Projects that collect atomistic ML resources or foster communication within community.
πΒ AI for Science Map - Interactive mindmap of the AI4Science research field, including atomistic machine learning, including papers,..
πΒ Atomic Cluster Expansion - Atomic Cluster Expansion (ACE) community homepage.
πΒ CrystaLLM - Generate a crystal structure from a composition. language-models
generative
pre-trained
transformer
πΒ matsci.org - A community forum for the discussion of anything materials science, with a focus on computational materials science..
πΒ Matter Modeling Stack Exchange - Machine Learning - Forum StackExchange, site Matter Modeling, ML-tagged questions.
Best-of Machine Learning with Python (π₯22 Β· β 15K) - A ranked list of awesome machine learning Python libraries. Updated weekly. CC-BY-4.0
general-ml
Python
-
GitHub (π¨βπ» 44 Β· π 2.1K Β· π 51 - 35% open Β· β±οΈ 18.01.2024):
git clone https://github.com/ml-tooling/best-of-ml-python
MatBench (π₯19 Β· β 88) - Matbench: Benchmarks for materials science property prediction. MIT
datasets
benchmarking
Graph-based Deep Learning Literature (π₯16 Β· β 4.5K) - links to conference publications in graph-based deep learning. MIT
general-ml
rep-learn
-
GitHub (π¨βπ» 12 Β· π 730 Β· β±οΈ 19.11.2023):
git clone https://github.com/naganandy/graph-based-deep-learning-literature
MatBench Discovery (π₯16 Β· β 52) - An evaluation framework for machine learning models simulating high-throughput materials discovery. MIT
datasets
benchmarking
GT4SD - Generative Toolkit for Scientific Discovery (π₯15 Β· β 290) - Gradio apps of generative models in GT4SD. MIT
generative
pre-trained
drug-discovery
-
GitHub (π¨βπ» 19 Β· π 61 Β· π 94 - 2% open Β· β±οΈ 16.10.2023):
git clone https://github.com/GT4SD/gt4sd-core
AI for Science Resources (π₯14 Β· β 320) - List of resources for AI4Science research, including learning resources. GPL-3.0 license
-
GitHub (π¨βπ» 26 Β· π 41 Β· π 6 - 50% open Β· β±οΈ 19.01.2024):
git clone https://github.com/divelab/AIRS
Awesome Neural Geometry (π₯9 Β· β 810) - A curated collection of resources and research related to the geometry of representations in the brain, deep networks,.. Unlicensed
educational
rep-learn
-
GitHub (π¨βπ» 10 Β· π 53 Β· β±οΈ 21.09.2023):
git clone https://github.com/neurreps/awesome-neural-geometry
GNoME Explorer (π₯9 Β· β 700 Β· π£) - Graph Networks for Materials Exploration Database. Apache-2
datasets
materials-discovery
-
GitHub (π¨βπ» 2 Β· π 110 Β· π 14 - 71% open Β· β±οΈ 02.12.2023):
git clone https://github.com/google-deepmind/materials_discovery
MoLFormers UI (π₯9 Β· β 160) - A family of foundation models trained on chemicals. Apache-2
transformer
language-models
pre-trained
drug-discovery
-
GitHub (π¨βπ» 5 Β· π 31 Β· π 16 - 43% open Β· β±οΈ 16.10.2023):
git clone https://github.com/IBM/molformer
Awesome Materials Informatics (π₯8 Β· β 320) - Curated list of known efforts in materials informatics = modern materials science. Custom
-
GitHub (π¨βπ» 19 Β· π 73 Β· β±οΈ 30.10.2023):
git clone https://github.com/tilde-lab/awesome-materials-informatics
optimade.science (π₯8 Β· β 8) - A sky-scanner Optimade browser-only GUI. MIT
datasets
-
GitHub (π¨βπ» 8 Β· π 2 Β· π 25 - 28% open Β· β±οΈ 06.07.2023):
git clone https://github.com/tilde-lab/optimade.science
The Collection of Database and Dataset Resources in Materials Science (π₯6 Β· β 200) - A list of databases, datasets and books/handbooks where you can find materials properties for machine learning.. Unlicensed
datasets
-
GitHub (π¨βπ» 2 Β· π 29 Β· β±οΈ 03.11.2023):
git clone https://github.com/sedaoturak/data-resources-for-materials-science
Show 4 hidden projects...
- A Highly Opinionated List of Open-Source Materials Informatics Resources (π₯7 Β· β 100 Β· π) - A Highly Opinionated List of Open Source Materials Informatics Resources.
MIT
- Does this material exist? (π₯4 Β· β 5 Β· π£) - Vote on whether you think predicted crystal structures could be synthesised.
MIT
for-fun
materials-discovery
- MateriApps (π₯1) - A Portal Site of Materials Science Simulation.
Unlicensed
- GitHub topic materials-informatics -
Unlicensed
Datasets, databases and trained models for atomistic ML.
πΒ Catalysis Hub - A web-platform for sharing data and software for computational catalysis research!.
πΒ Citrination Datasets - AI-Powered Materials Data Platform. Open Citrination has been decommissioned.
πΒ crystals.ai - Curated datasets for reproducible AI in materials science.
πΒ DeepChem Models - DeepChem models on HuggingFace. pre-trained
language-models
πΒ JARVIS-Leaderboard ( β 43) - Explore State-of-the-Art Materials Design Methods: https://arxiv.org/abs/2306.11688. benchmarking
πΒ Materials Project - Charge Densities - Materials Project has started offering charge density information available for download via their public API.
πΒ matterverse.ai - Database of yet-to-be-sythesized materials predicted using state-of-the-art machine learning algorithms.
πΒ NRELMatDB - Computational materials database with the specific focus on materials for renewable energy applications including, but..
πΒ Quantum-Machine.org Datasets - Collection of datasets, including QM7, QM9, etc. MD, DFT. Small organic molecules, mostly.
πΒ sGDML Datasets - MD17, MD22, DFT datasets.
πΒ MoleculeNet - A Benchmark for Molecular Machine Learning. benchmarking
πΒ ZINC15 - A free database of commercially-available compounds for virtual screening. ZINC contains over 230 million purchasable.. graph
biomolecules
πΒ ZINC20 - A free database of commercially-available compounds for virtual screening. ZINC contains over 230 million purchasable.. graph
biomolecules
OPTIMADE Python tools (π₯24 Β· β 56 Β· π) - Tools for implementing and consuming OPTIMADE APIs in Python. MIT
MPContribs (π₯23 Β· β 32) - Platform for materials scientists to contribute and disseminate their materials data through Materials Project. MIT
Open Catalyst datasets (π₯18 Β· β 550) - The datasets of the Open Catalyst project, OC20, OC22. CC-BY-4.0
-
GitHub (π¨βπ» 32 Β· π 190 Β· π 160 - 7% open Β· β±οΈ 12.01.2024):
git clone https://github.com/Open-Catalyst-Project/ocp
ATOM3D (π₯18 Β· β 280 Β· π€) - ATOM3D: tasks on molecules in three dimensions. MIT
biomolecules
benchmarking
Open Databases Integration for Materials Design (OPTIMADE) (π₯16 Β· β 62) - Specification of a common REST API for access to materials databases. CC-BY-4.0
-
GitHub (π¨βπ» 19 Β· π 35 Β· π 220 - 33% open Β· β±οΈ 17.01.2024):
git clone https://github.com/Materials-Consortia/OPTIMADE
QH9: A Quantum Hamiltonian Prediction Benchmark (π₯14 Β· β 320) - Artificial Intelligence Research for Science (AIRS). CC-BY-NC-SA 4.0
ML-DFT
-
GitHub (π¨βπ» 26 Β· π 41 Β· π 6 - 50% open Β· β±οΈ 19.01.2024):
git clone https://github.com/divelab/AIRS
SPICE (π₯12 Β· β 110) - A collection of QM data for training potential functions. MIT
ML-IAP
MD
-
GitHub (π 5 Β· π₯ 230 Β· π 50 - 26% open Β· β±οΈ 22.10.2023):
git clone https://github.com/openmm/spice-dataset
Materials Data Facility (MDF) (π₯9 Β· β 10 Β· π€) - A simple way to publish, discover, and access materials datasets. Publication of very large datasets supported (e.g.,.. Apache-2
-
GitHub (π¨βπ» 6 Β· π 1 Β· β±οΈ 19.04.2023):
git clone https://github.com/materials-data-facility/connect_client
SciGlass (π₯6 Β· β 8) - The database contains a vast set of data on the properties of glass materials. MIT
-
GitHub (π¨βπ» 2 Β· π 3 Β· π₯ 3 Β· β±οΈ 27.08.2023):
git clone https://github.com/drcassar/SciGlass
3DSC Database (π₯5 Β· β 11) - Repo for the paper publishing the superconductor database with 3D crystal structures. Custom
superconductors
materials-discovery
-
GitHub (π 3 Β· β±οΈ 08.01.2024):
git clone https://github.com/aimat-lab/3DSC
Show 11 hidden projects...
- OpenKIM (π₯10 Β· β 30 Β· π) - The Open Knowledgebase of Interatomic Models (OpenKIM) aims to be an online resource for standardized testing, long-..
LGPL-2.1
knowledge-base
pre-trained
- ANI-1 Dataset (π₯8 Β· β 92 Β· π) - A data set of 20 million calculated off-equilibrium conformations for organic molecules.
MIT
- MoleculeNet Leaderboard (π₯8 Β· β 79 Β· π) -
MIT
benchmarking
- GEOM (π₯7 Β· β 160 Β· π) - GEOM: Energy-annotated molecular conformations.
Unlicensed
drug-discovery
- 2DMD dataset (π₯7 Β· β 2) - 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-1x Datasets (π₯6 Β· β 48 Β· π) - The ANI-1ccx and ANI-1x data sets, coupled-cluster and density functional theory properties for organic molecules.
MIT
- COMP6 Benchmark dataset (π₯6 Β· β 36 Β· π) - COMP6 Benchmark dataset for ML potentials.
MIT
- paper-data-redundancy (π₯5 Β· β 3) - Codes and data for the paper On the redundancy in large material datasets: efficient and robust learning with less data.
BSD-3
small-data
single-paper
- Visual Graph Datasets (π₯5 Β· β 1) - Datasets for the training of graph neural networks (GNNs) and subsequent visualization of attributional explanations..
MIT
- linear-regression-benchmarks (π₯5 Β· β 1 Β· π) - Data sets used for linear regression benchmarks.
MIT
benchmarking
single-paper
- OPTIMADE providers dashboard (π₯4 Β· β 1) - A dashboard of known providers.
Unlicensed
Projects that focus on providing data structures used in atomistic machine learning.
dpdata (π₯22 Β· β 170) - Manipulating multiple atomic simulation data formats, including DeePMD-kit, VASP, LAMMPS, ABACUS, etc. LGPL-3.0
Metatensor (π₯19 Β· β 32) - Self-describing sparse tensor data format for atomistic machine learning and beyond. BSD-3
Rust
C-lang
C++
Python
-
GitHub (π¨βπ» 17 Β· π 12 Β· π₯ 4.1K Β· π¦ 6 Β· π 130 - 34% open Β· β±οΈ 25.01.2024):
git clone https://github.com/lab-cosmo/metatensor
dlpack (π₯14 Β· β 820) - common in-memory tensor structure. Apache-2
C++
-
GitHub (π¨βπ» 21 Β· π 130 Β· π 62 - 43% open Β· β±οΈ 13.12.2023):
git clone https://github.com/dmlc/dlpack
mp-pyrho (π₯14 Β· β 32 Β· π€) - Tools for re-griding volumetric quantum chemistry data for machine-learning purposes. Custom
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.
JAX-DFT (π₯25 Β· β 32K) - Google Research. Apache-2
-
GitHub (π¨βπ» 770 Β· π 7.5K Β· π 1.1K - 73% open Β· β±οΈ 25.01.2024):
git clone https://github.com/google-research/google-research
DM21 (π₯20 Β· β 12K Β· π€) - This package provides a PySCF interface to the DM21 (DeepMind 21) family of exchange-correlation functionals described.. Apache-2
-
GitHub (π¨βπ» 92 Β· π 2.5K Β· π 300 - 54% open Β· β±οΈ 02.06.2023):
git clone https://github.com/deepmind/deepmind-research
MALA (π₯18 Β· β 60) - Materials Learning Algorithms. A framework for machine learning materials properties from first-principles data. BSD-3
-
GitHub (π¨βπ» 41 Β· π 21 Β· π 240 - 11% open Β· β±οΈ 03.01.2024):
git clone https://github.com/mala-project/mala
QHNet (π₯14 Β· β 320) - Artificial Intelligence Research for Science (AIRS). GPL-3.0
rep-learn
-
GitHub (π¨βπ» 26 Β· π 41 Β· π 6 - 50% open Β· β±οΈ 19.01.2024):
git clone https://github.com/divelab/AIRS
DeepH-pack (π₯13 Β· β 170) - Deep neural networks for density functional theory Hamiltonian. LGPL-3.0
Julia
-
GitHub (π¨βπ» 8 Β· π 29 Β· π 37 - 2% open Β· β±οΈ 29.12.2023):
git clone https://github.com/mzjb/DeepH-pack
Grad DFT (π₯11 Β· β 54) - Grad-DFT is a JAX-based library enabling the differentiable design and experimentation of exchange-correlation.. Apache-2
-
GitHub (π¨βπ» 2 Β· π 2 Β· π 54 - 20% open Β· β±οΈ 12.12.2023):
git clone https://github.com/XanaduAI/GradDFT
DeePKS-kit (π₯10 Β· β 96 Β· π€) - a package for developing machine learning-based chemically accurate energy and density functional models. LGPL-3.0
-
GitHub (π¨βπ» 6 Β· π 31 Β· π 14 - 14% open Β· β±οΈ 01.04.2023):
git clone https://github.com/deepmodeling/deepks-kit
ACEhamiltonians (π₯7 Β· β 10 Β· π€) - Provides tools for constructing, fitting, and predicting self-consistent Hamiltonian and overlap matrices in solid-.. MIT
Julia
-
GitHub (π¨βπ» 4 Β· π 3 Β· π 4 - 25% open Β· β±οΈ 12.04.2023):
git clone https://github.com/ACEsuit/ACEhamiltonians.jl
DeepDFT (π₯6 Β· β 45 Β· π€) - Official implementation of DeepDFT model. MIT
-
GitHub (π¨βπ» 2 Β· π 8 Β· π 4 - 25% open Β· β±οΈ 28.02.2023):
git clone https://github.com/peterbjorgensen/DeepDFT
DeepH-E3 (π₯6 Β· β 45 Β· π€) - General framework for E(3)-equivariant neural network representation of density functional theory Hamiltonian. MIT
magnetism
-
GitHub (π¨βπ» 2 Β· π 11 Β· π 9 - 33% open Β· β±οΈ 04.04.2023):
git clone https://github.com/Xiaoxun-Gong/DeepH-E3
SALTED (π₯6 Β· β 16) - Symmetry-Adapted Learning of Three-dimensional Electron Densities. GPL-3.0
-
GitHub (π¨βπ» 13 Β· π 2 Β· β±οΈ 14.12.2023):
git clone https://github.com/andreagrisafi/SALTED
charge-density-models (π₯5 Β· β 9) - Tools to build charge density models using ocpmodels. MIT
-
GitHub (π 3 Β· β±οΈ 29.11.2023):
git clone https://github.com/ulissigroup/charge-density-models
Show 13 hidden projects...
- NeuralXC (π₯10 Β· β 30 Β· π) - Implementation of a machine learned density functional.
BSD-3
- PROPhet (π₯9 Β· β 62 Β· π) - 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 (π₯7 Β· β 15 Β· π) - A library for using machine-learned exchange-correlation functionals for density-functional theory.
MPL-2.0
C++
Fortran
- Mat2Spec (π₯6 Β· β 24 Β· π) -
MIT
spectroscopy
- ML-DFT (π₯4 Β· β 20 Β· π) - A package for density functional approximation using machine learning.
MIT
- gprep (π₯4 Β· π) - Fitting DFTB repulsive potentials with GPR.
MIT
single-paper
- xDeepH (π₯3 Β· β 25 Β· π€) - Extended DeepH (xDeepH) method for magnetic materials.
LGPL-3.0
magnetism
Julia
- DeepCDP (π₯3 Β· β 3 Β· π€) - DeepCDP: Deep learning Charge Density Prediction.
Unlicensed
- CSNN (π₯3 Β· β 1 Β· π) - Primary codebase of CSNN - Concentric Spherical Neural Network for 3D Representation Learning.
BSD-3
- A3MD (π₯2 Β· β 7 Β· π) - MPNN-like + Analytic Density Model = Accurate electron densities.
Unlicensed
representation-learning
single-paper
- APET (π₯2 Β· β 2) - Atomic Positional Embedding-based Transformer.
GPL-3.0
density-of-states
transformer
- MALADA (π₯2 Β· β 1 Β· π€) - MALA Data Acquisition: Helpful tools to build data for MALA.
BSD-3
- kdft (π₯1 Β· β 2 Β· π) - The Kernel Density Functional (KDF) code allows generating ML based DFT functionals.
Unlicensed
Tutorials, guides, cookbooks, recipes, etc.
πΒ Quantum Chemistry in the Age of Machine Learning - Book, 2022.
πΒ AL4MS 2023 workshop tutorials active-learning
Geometric GNN Dojo (π₯12 Β· β 380 Β· π€) - New to geometric GNNs: try our practical notebook, prepared for MPhil students at the University of Cambridge. MIT
rep-learn
-
GitHub (π¨βπ» 3 Β· π 37 Β· π 5 - 40% open Β· β±οΈ 18.06.2023):
git clone https://github.com/chaitjo/geometric-gnn-dojo
Deep Learning for Molecules and Materials Book (π₯11 Β· β 550) - Deep learning for molecules and materials book. Custom
-
GitHub (π¨βπ» 19 Β· π 100 Β· π 160 - 17% open Β· β±οΈ 02.07.2023):
git clone https://github.com/whitead/dmol-book
jarvis-tools-notebooks (π₯11 Β· β 48) - A Google-Colab Notebook Collection for Materials Design: https://jarvis.nist.gov/. NIST
-
GitHub (π¨βπ» 5 Β· π 21 Β· β±οΈ 08.01.2024):
git clone https://github.com/JARVIS-Materials-Design/jarvis-tools-notebooks
DSECOP (π₯11 Β· β 32) - This repository contains data science educational materials developed by DSECOP Fellows. CCO-1.0
-
GitHub (π¨βπ» 13 Β· π 23 Β· π 8 - 12% open Β· β±οΈ 19.01.2024):
git clone https://github.com/GDS-Education-Community-of-Practice/DSECOP
iam-notebooks (π₯9 Β· β 22) - Jupyter notebooks for the lectures of the Introduction to Atomistic Modeling. Apache-2
-
GitHub (π¨βπ» 6 Β· π 4 Β· β±οΈ 07.08.2023):
git clone https://github.com/ceriottm/iam-notebooks
OPTIMADE Tutorial Exercises (π₯9 Β· β 11) - Tutorial exercises for the OPTIMADE API. MIT
datasets
-
GitHub (π¨βπ» 6 Β· π 7 Β· β±οΈ 27.09.2023):
git clone https://github.com/Materials-Consortia/optimade-tutorial-exercises
RDKit Tutorials (π₯8 Β· β 220 Β· π€) - Tutorials to learn how to work with the RDKit. Custom
-
GitHub (π¨βπ» 5 Β· π 70 Β· π 4 - 75% open Β· β±οΈ 19.03.2023):
git clone https://github.com/rdkit/rdkit-tutorials
BestPractices (π₯7 Β· β 150) - Things that you should (and should not) do in your Materials Informatics research. MIT
-
GitHub (π¨βπ» 3 Β· π 66 Β· π 7 - 71% open Β· β±οΈ 17.11.2023):
git clone https://github.com/anthony-wang/BestPractices
Data Handling, DoE and Statistical Analysis for Material Chemists (π₯6 Β· π€) - Notebooks for workshops of DoE course, hosted by the Computational Materials Chemistry group at Uppsala University. GPL-3.0
-
GitHub (π¨βπ» 3 Β· π 13 Β· β±οΈ 26.06.2023):
git clone https://github.com/Teoroo-CMC/DoE_Course_Material
Show 13 hidden projects...
- DeepLearningLifeSciences (π₯11 Β· β 310 Β· π) - Example code from the book Deep Learning for the Life Sciences.
MIT
- MAChINE (π₯7 Β· β 1) - Client-Server Web App to introduce usage of ML in materials science to beginners.
MIT
- Applied AI for Materials (π₯6 Β· β 50 Β· π) - Course materials for Applied AI for Materials Science and Engineering.
Unlicensed
- COSMO Software Cookbook (π₯6 Β· β 3) - The COSMO cookbook contains recipes for atomic-scale modelling for materials and molecules.
BSD-3
- AI4Science101 (π₯5 Β· β 77 Β· π) - AI for Science.
Unlicensed
- Machine Learning for Materials Hard and Soft (π₯5 Β· β 33 Β· π) - ESI-DCAFM-TACO-VDSP Summer School on Machine Learning for Materials Hard and Soft.
Unlicensed
- ML-in-chemistry-101 (π₯4 Β· β 59 Β· π) - The course materials for Machine Learning in Chemistry 101.
Unlicensed
- MACE-tutorials (π₯4 Β· β 9 Β· π£) - Another set of tutorials for the MACE interatomic potential by one of the authors.
MIT
ML-IAP
rep-learn
MD
- chemrev-gpr (π₯4 Β· β 6 Β· π) - Notebooks accompanying the paper on GPR in materials and molecules in Chemical Reviews 2020.
Unlicensed
- MLDensity_tutorial (π₯2 Β· β 6 Β· π€) - Tutorial files to work with ML for the charge density in molecules and solids.
Unlicensed
- LAMMPS-style pair potentials with GAP (π₯2 Β· β 3 Β· π) - A tutorial on how to create LAMMPS-style pair potentials and use them in combination with GAP potentials to run MD..
Unlicensed
ML-IAP
MD
rep-eng
- MALA Tutorial (π₯2 Β· β 2) - A full MALA hands-on tutorial.
Unlicensed
- PiNN Lab (π₯2 Β· β 2 Β· π€) -
GPL-3.0
Projects that focus on explainability and model interpretability in atomistic ML.
Show 3 hidden projects...
- MEGAN: Multi Explanation Graph Attention Student (π₯7 Β· β 4) - Minimal implementation of graph attention student model architecture.
MIT
- MEGAN (π₯7 Β· β 4) - Minimal implementation of graph attention student model architecture.
MIT
XAI
rep-learn
- Linear vs blackbox (π₯3 Β· β 2 Β· π) - Code and data related to the publication: Interpretable models for extrapolation in scientific machine learning.
MIT
XAI
single-paper
rep-eng
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 3 hidden projects...
- QDF for molecule (π₯9 Β· β 180 Β· π) - Quantum deep field: data-driven wave function, electron density generation, and energy prediction and extrapolation..
MIT
- e3psi (π₯4 Β· β 3) - Equivariant machine learning library for learning from electronic structures.
LGPL-3.0
- halex (π₯4 Β· β 1 Β· π£) - Hamiltonian Learning for Excited States https://doi.org/10.48550/arXiv.2311.00844.
Unlicensed
excited-states
General tools for atomistic machine learning.
DeepChem (π₯36 Β· β 4.9K) - Democratizing Deep-Learning for Drug Discovery, Quantum Chemistry, Materials Science and Biology. MIT
-
GitHub (π¨βπ» 230 Β· π 1.5K Β· π¦ 310 Β· π 1.6K - 26% open Β· β±οΈ 24.01.2024):
git clone https://github.com/deepchem/deepchem
-
PyPi (π₯ 17K / month):
pip install deepchem
-
Conda (π₯ 100K Β· β±οΈ 16.06.2023):
conda install -c conda-forge deepchem
-
Docker Hub (π₯ 7.1K Β· β 4 Β· β±οΈ 11.03.2022):
docker pull deepchemio/deepchem
QUIP (π₯23 Β· β 310) - libAtoms/QUIP molecular dynamics framework: https://libatoms.github.io. GPL-2.0
MD
ML-IAP
rep-eng
Fortran
-
GitHub (π¨βπ» 81 Β· π 120 Β· π₯ 350 Β· π¦ 29 Β· π 440 - 21% open Β· β±οΈ 10.01.2024):
git clone https://github.com/libAtoms/QUIP
-
PyPi (π₯ 1.3K / month):
pip install quippy-ase
-
Docker Hub (π₯ 9.9K Β· β 4 Β· β±οΈ 24.04.2023):
docker pull libatomsquip/quip
MAML (π₯22 Β· β 310) - Python for Materials Machine Learning, Materials Descriptors, Machine Learning Force Fields, Deep Learning, etc. BSD-3
JARVIS-Tools (π₯21 Β· β 260) - JARVIS-Tools: an open-source software package for data-driven atomistic materials design. Publications:.. Custom
Scikit-Matter (π₯17 Β· β 68) - A collection of scikit-learn compatible utilities that implement methods born out of the materials science and.. BSD-3
scikit-learn
MAST-ML (π₯16 Β· β 89) - MAterials Simulation Toolkit for Machine Learning (MAST-ML). MIT
-
GitHub (π¨βπ» 19 Β· π 52 Β· π₯ 86 Β· π¦ 9 Β· π 210 - 10% open Β· β±οΈ 28.07.2023):
git clone https://github.com/uw-cmg/MAST-ML
Artificial Intelligence for Science (AIRS) (π₯14 Β· β 320) - Artificial Intelligence Research for Science (AIRS). GPL-3.0 license
rep-learn
generative
ML-IAP
MD
ML-DFT
ML-WFT
biomolecules
-
GitHub (π¨βπ» 26 Β· π 41 Β· π 6 - 50% open Β· β±οΈ 19.01.2024):
git clone https://github.com/divelab/AIRS
AMPtorch (π₯11 Β· β 59) - AMPtorch: Atomistic Machine Learning Package (AMP) - PyTorch. GPL-3.0
-
GitHub (π¨βπ» 14 Β· π 32 Β· π 31 - 16% open Β· β±οΈ 16.07.2023):
git clone https://github.com/ulissigroup/amptorch
Show 11 hidden projects...
- QML (π₯15 Β· β 190 Β· π) - QML: Quantum Machine Learning.
MIT
- Automatminer (π₯15 Β· β 130 Β· π) - An automatic engine for predicting materials properties.
Custom
- OpenChem (π₯11 Β· β 630 Β· π) - OpenChem: Deep Learning toolkit for Computational Chemistry and Drug Design Research.
MIT
- JAXChem (π₯7 Β· β 74 Β· π) - JAXChem is a JAX-based deep learning library for complex and versatile chemical modeling.
MIT
- uncertainty_benchmarking (π₯7 Β· β 36 Β· π) - Various code/notebooks to benchmark different ways we could estimate uncertainty in ML predictions.
Unlicensed
benchmarking
probabilistic
- torchchem (π₯7 Β· β 34 Β· π) - An experimental repo for experimenting with PyTorch models.
MIT
- Equisolve (π₯6 Β· β 4) - A ML toolkit package utilizing the metatensor data format to build models for the prediction of equivariant properties..
BSD-3
ML-IAP
- ACEatoms (π₯4 Β· β 2 Β· π€) - Generic code for modelling atomic properties using ACE.
Custom
Julia
- MLatom (π₯4) - Machine learning for atomistic simulations.
Custom
- Magpie (π₯3) - Materials Agnostic Platform for Informatics and Exploration (Magpie).
MIT
Java
- quantum-structure-ml (π₯2 Β· β 1 Β· π) - Multi-class classification model for predicting the magnetic order of magnetic structures and a binary classification..
Unlicensed
magnetism
benchmarking
Projects that implement generative models for atomistic ML.
GT4SD (π₯17 Β· β 290) - GT4SD, an open-source library to accelerate hypothesis generation in the scientific discovery process. MIT
pre-trained
drug-discovery
rep-learn
MoLeR (π₯17 Β· β 230) - Implementation of MoLeR: a generative model of molecular graphs which supports scaffold-constrained generation. MIT
SchNetPack G-SchNet (π₯10 Β· β 34) - G-SchNet extension for SchNetPack. MIT
-
GitHub (π¨βπ» 3 Β· π 6 Β· β±οΈ 07.11.2023):
git clone https://github.com/atomistic-machine-learning/schnetpack-gschnet
G-SchNet (π₯8 Β· β 120 Β· π€) - G-SchNet - a generative model for 3d molecular structures. MIT
-
GitHub (π¨βπ» 2 Β· π 23 Β· β±οΈ 24.03.2023):
git clone https://github.com/atomistic-machine-learning/G-SchNet
cG-SchNet (π₯8 Β· β 43 Β· π€) - cG-SchNet - a conditional generative neural network for 3d molecular structures. MIT
-
GitHub (π 14 Β· β±οΈ 24.03.2023):
git clone https://github.com/atomistic-machine-learning/cG-SchNet
bVAE-IM (π₯8 Β· β 10) - Implementation of Chemical Design with GPU-based Ising Machine. MIT
QML
single-paper
-
GitHub (π 3 Β· β±οΈ 11.07.2023):
git clone https://github.com/tsudalab/bVAE-IM
COATI (π₯5 Β· β 63 Β· π£) - COATI: multi-modal contrastive pre-training for representing and traversing chemical space. Apache-2
drug-discovery
pre-trained
rep-learn
-
GitHub (π¨βπ» 4 Β· π 5 Β· β±οΈ 27.10.2023):
git clone https://github.com/terraytherapeutics/COATI
MolSLEPA (π₯5 Β· β 5 Β· π€) - Interpretable Fragment-based Molecule Design with Self-learning Entropic Population Annealing. MIT
XAI
-
GitHub (π 1 Β· β±οΈ 13.04.2023):
git clone https://github.com/tsudalab/MolSLEPA
Show 2 hidden projects...
- EDM (π₯10 Β· β 340 Β· π) - E(3) Equivariant Diffusion Model for Molecule Generation in 3D.
MIT
- rxngenerator (π₯5 Β· β 12 Β· π) - A generative model for molecular generation via multi-step chemical reactions.
MIT
Machine learning interatomic potentials (aka ML-IAP, MLIAP, MLIP, MLP) and force fields (ML-FF) for molecular dynamics.
DeePMD-kit (π₯28 Β· β 1.3K Β· π) - A deep learning package for many-body potential energy representation and molecular dynamics. LGPL-3.0
C++
-
GitHub (π¨βπ» 65 Β· π 440 Β· π₯ 31K Β· π¦ 12 Β· π 500 - 6% open Β· β±οΈ 23.01.2024):
git clone https://github.com/deepmodeling/deepmd-kit
-
PyPi (π₯ 1.2K / month):
pip install deepmd-kit
-
Conda (π₯ 590 Β· β±οΈ 23.01.2024):
conda install -c deepmodeling deepmd-kit
-
Docker Hub (π₯ 2.1K Β· β 1 Β· β±οΈ 29.10.2023):
docker pull deepmodeling/deepmd-kit
DP-GEN (π₯22 Β· β 260 Β· π) - The deep potential generator to generate a deep-learning based model of interatomic potential energy and force field. LGPL-3.0
workflows
MEGNet (π₯21 Β· β 470 Β· π€) - Graph Networks as a Universal Machine Learning Framework for Molecules and Crystals. BSD-3
TorchMD-NET (π₯21 Β· β 240) - Neural network potentials. MIT
MD
rep-learn
transformer
pre-trained
CHGNet (π₯21 Β· β 160) - Pretrained universal neural network potential for charge-informed atomistic modeling https://chgnet.lbl.gov. Custom
MD
pre-trained
electrostatics
magnetism
structure-relaxation
Pre-trained OCP models (π₯19 Β· β 550) - Pre-trained models released as part of the Open Catalyst Project. MIT
pre-trained
-
GitHub (π¨βπ» 32 Β· π 190 Β· π 160 - 7% open Β· β±οΈ 12.01.2024):
git clone https://github.com/Open-Catalyst-Project/ocp
NequIP (π₯19 Β· β 500) - NequIP is a code for building E(3)-equivariant interatomic potentials. MIT
MACE (π₯19 Β· β 290) - MACE - Fast and accurate machine learning interatomic potentials with higher order equivariant message passing. MIT
-
GitHub (π¨βπ» 17 Β· π 92 Β· π 120 - 21% open Β· β±οΈ 24.01.2024):
git clone https://github.com/ACEsuit/mace
M3GNet (π₯17 Β· β 200 Β· π€) - Materials graph network with 3-body interactions featuring a DFT surrogate crystal relaxer and a state-of-the-art.. BSD-3
KLIFF (π₯17 Β· β 30) - KIM-based Learning-Integrated Fitting Framework (KLIFF). LGPL-2.1
probabilistic
workflows
sGDML (π₯16 Β· β 130) - sGDML - Reference implementation of the Symmetric Gradient Domain Machine Learning model. MIT
Ultra-Fast Force Fields (UF3) (π₯15 Β· β 51) - UF3: a python library for generating ultra-fast interatomic potentials. Apache-2
DMFF (π₯13 Β· β 130) - DMFF (Differentiable Molecular Force Field) is a Jax-based python package that provides a full differentiable.. LGPL-3.0
-
GitHub (π¨βπ» 14 Β· π 37 Β· π 22 - 36% open Β· β±οΈ 12.01.2024):
git clone https://github.com/deepmodeling/DMFF
Pacemaker (π₯12 Β· β 53) - Python package for fitting atomic cluster expansion (ACE) potentials. Custom
Neural Force Field (π₯11 Β· β 200) - Neural Network Force Field based on PyTorch. MIT
pre-trained
-
GitHub (π¨βπ» 10 Β· π 46 Β· π 18 - 11% open Β· β±οΈ 25.07.2023):
git clone https://github.com/learningmatter-mit/NeuralForceField
PiNN (π₯11 Β· β 100) - A Python library for building atomic neural networks. BSD-3
-
GitHub (π¨βπ» 2 Β· π 27 Β· π 6 - 16% open Β· β±οΈ 18.01.2024):
git clone https://github.com/Teoroo-CMC/PiNN
-
Docker Hub (π₯ 230 Β· β±οΈ 18.01.2024):
docker pull teoroo/pinn
So3krates (MLFF) (π₯11 Β· β 42) - Build neural networks for machine learning force fields with JAX. MIT
-
GitHub (π¨βπ» 4 Β· π 9 Β· π 8 - 50% open Β· β±οΈ 16.01.2024):
git clone https://github.com/thorben-frank/mlff
ACEfit (π₯10 Β· β 5) - MIT
Julia
-
GitHub (π¨βπ» 6 Β· π 3 Β· π 54 - 40% open Β· β±οΈ 18.08.2023):
git clone https://github.com/ACEsuit/ACEfit.jl
DimeNet (π₯9 Β· β 260) - DimeNet and DimeNet++ models, as proposed in Directional Message Passing for Molecular Graphs (ICLR 2020) and Fast and.. Custom
-
GitHub (π¨βπ» 2 Β· π 57 Β· π¦ 1 Β· π 31 - 3% open Β· β±οΈ 03.10.2023):
git clone https://github.com/gasteigerjo/dimenet
Allegro (π₯9 Β· β 250 Β· π€) - Allegro is an open-source code for building highly scalable and accurate equivariant deep learning interatomic.. MIT
-
GitHub (π¨βπ» 2 Β· π 39 Β· π 27 - 48% open Β· β±οΈ 08.05.2023):
git clone https://github.com/mir-group/allegro
GemNet (π₯9 Β· β 160 Β· π€) - GemNet model in PyTorch, as proposed in GemNet: Universal Directional Graph Neural Networks for Molecules (NeurIPS.. Custom
-
GitHub (π¨βπ» 5 Β· π 25 Β· β±οΈ 26.04.2023):
git clone https://github.com/TUM-DAML/gemnet_pytorch
tinker-hp (π₯9 Β· β 71) - Tinker-HP: High-Performance Massively Parallel Evolution of Tinker on CPUs & GPUs. Custom
-
GitHub (π¨βπ» 10 Β· π 18 Β· π 18 - 16% open Β· β±οΈ 23.01.2024):
git clone https://github.com/TinkerTools/tinker-hp
ACE.jl (π₯9 Β· β 62 Β· π€) - Parameterisation of Equivariant Properties of Particle Systems. Custom
Julia
-
GitHub (π¨βπ» 12 Β· π 15 Β· π 82 - 29% open Β· β±οΈ 09.06.2023):
git clone https://github.com/ACEsuit/ACE.jl
wfl (π₯9 Β· β 20) - Workflow is a Python toolkit for building interatomic potential creation and atomistic simulation workflows. Unlicensed
workflows
HTC
-
GitHub (π¨βπ» 14 Β· π 15 Β· π 140 - 47% open Β· β±οΈ 20.01.2024):
git clone https://github.com/libAtoms/workflow
ACE1.jl (π₯9 Β· β 19) - Atomic Cluster Expansion for Modelling Invariant Atomic Properties. Custom
Julia
-
GitHub (π¨βπ» 7 Β· π 4 Β· π 46 - 47% open Β· β±οΈ 13.11.2023):
git clone https://github.com/ACEsuit/ACE1.jl
TurboGAP (π₯9 Β· β 14) - The TurboGAP code. Custom
Fortran
-
GitHub (π¨βπ» 8 Β· π 8 Β· π 7 - 57% open Β· β±οΈ 14.12.2023):
git clone https://github.com/mcaroba/turbogap
GAP (π₯8 Β· β 34) - Gaussian Approximation Potential (GAP). Custom
-
GitHub (π¨βπ» 12 Β· π 19 Β· β±οΈ 15.10.2023):
git clone https://github.com/libAtoms/GAP
ALF (π₯7 Β· β 19) - A framework for performing active learning for training machine-learned interatomic potentials. Custom
active-learning
-
GitHub (π¨βπ» 5 Β· π 9 Β· β±οΈ 08.01.2024):
git clone https://github.com/lanl/alf
MACE-Jax (π₯6 Β· β 40) - Equivariant machine learning interatomic potentials in JAX. MIT
-
GitHub (π¨βπ» 2 Β· π 1 Β· π 3 - 66% open Β· β±οΈ 04.10.2023):
git clone https://github.com/ACEsuit/mace-jax
MLIP-3 (π₯5 Β· β 18 Β· π€) - MLIP-3: Active learning on atomic environments with Moment Tensor Potentials (MTP). BSD-2
C++
-
GitLab (π 3 Β· π 24 - 75% open Β· β±οΈ 24.04.2023):
git clone https://gitlab.com/ashapeev/mlip-3
ACE1Pack.jl (π₯5 Β· π£) - Provides convenience functionality for the usage of ACE1.jl, ACEfit.jl, JuLIP.jl for fitting interatomic potentials.. MIT
Julia
-
GitHub (π¨βπ» 11 Β· β±οΈ 21.08.2023):
git clone https://github.com/ACEsuit/ACE1pack.jl
Show 26 hidden projects...
- n2p2 (π₯13 Β· β 190 Β· π) - n2p2 - A Neural Network Potential Package.
GPL-3.0
C++
- TensorMol (π₯12 Β· β 260 Β· π) - Tensorflow + Molecules = TensorMol.
GPL-3.0
single-paper
- ANI-1 (π₯12 Β· β 210 Β· π) - ANI-1 neural net potential with python interface (ASE).
MIT
- SIMPLE-NN (π₯11 Β· β 44 Β· π) - SIMPLE-NN(SNU Interatomic Machine-learning PotentiaL packagE version Neural Network).
GPL-3.0
- NNsforMD (π₯10 Β· β 10 Β· π) - Neural network class for molecular dynamics to predict potential energy, forces and non-adiabatic couplings.
MIT
- SchNet (π₯9 Β· β 200 Β· π) - SchNet - a deep learning architecture for quantum chemistry.
MIT
- AIMNet (π₯8 Β· β 79 Β· π) - Atoms In Molecules Neural Network Potential.
MIT
single-paper
- SNAP (π₯8 Β· β 33 Β· π) - Repository for spectral neighbor analysis potential (SNAP) model development.
BSD-3
- Atomistic Adversarial Attacks (π₯8 Β· β 26 Β· π) - Code for performing adversarial attacks on atomistic systems using NN potentials.
MIT
probabilistic
- PhysNet (π₯7 Β· β 86 Β· π) - Code for training PhysNet models.
MIT
electrostatics
- SIMPLE-NN v2 (π₯7 Β· β 34) -
GPL-3.0
- testing-framework (π₯6 Β· β 11 Β· π) - The purpose of this repository is to aid the testing of a large number of interatomic potentials for a variety of..
Unlicensed
benchmarking
- PANNA (π₯6 Β· β 7 Β· π) - A package to train and validate all-to-all connected network models for BP[1] and modified-BP[2] type local atomic..
MIT
benchmarking
- MLXDM (π₯6 Β· β 4) - A Neural Network Potential with Rigorous Treatment of Long-Range Dispersion https://doi.org/10.1039/D2DD00150K.
MIT
long-range
- Point Edge Transformer (PET) (π₯6 Β· β 2) - Point Edge Transformer.
Unlicensed
rep-learn
transformer
- Alchemical learning (π₯5 Β· β 2 Β· π€) - Code for the Modeling high-entropy transition metal alloys with alchemical compression article.
BSD-3
- glp (π₯4 Β· β 13) - tools for graph-based machine-learning potentials in jax.
MIT
- NequIP-JAX (π₯4 Β· β 12) - JAX implementation of the NequIP interatomic potential.
Unlicensed
- TensorPotential (π₯4 Β· β 5) - Tensorpotential is a TensorFlow based tool for development, fitting ML interatomic potentials from electronic..
Custom
- ACE Workflows (π₯4) - Workflow Examples for ACE Models.
Unlicensed
Julia
workflows
- PeriodicPotentials (π₯4 Β· π) - A Periodic table app that displays potentials based on the selected elements.
MIT
community-resource
viz
JavaScript
- MEGNetSparse (π₯3 Β· β 1 Β· π£) - A library imlementing a graph neural network with sparse representation from Code for Kazeev, N., Al-Maeeni, A.R.,..
MIT
material-defect
- Allegro-JAX (π₯2 Β· β 12 Β· π£) - JAX implementation of the Allegro interatomic potential.
Unlicensed
- SingleNN (π₯2 Β· β 7 Β· π) - An efficient package for training and executing neural-network interatomic potentials.
Unlicensed
C++
- RuNNer (π₯2) - The RuNNer Neural Network Energy Representation is a Fortran-based framework for the construction of Behler-..
GPL-3.0
Fortran
- mlp (π₯1 Β· β 1 Β· π) - Proper orthogonal descriptors for efficient and accurate interatomic potentials...
Unlicensed
Julia
Projects that use (large) language models (LMs, LLMs) or natural language procesing (NLP) techniques for atomistic ML.
paper-qa (π₯25 Β· β 3.4K) - LLM Chain for answering questions from documents with citations. Apache-2
ChemNLP project (π₯16 Β· β 120) - ChemNLP project. MIT
datasets
mat2vec (π₯12 Β· β 600 Β· π€) - Supplementary Materials for Tshitoyan et al. Unsupervised word embeddings capture latent knowledge from materials.. MIT
rep-learn
-
GitHub (π¨βπ» 5 Β· π 170 Β· π 24 - 29% open Β· β±οΈ 06.05.2023):
git clone https://github.com/materialsintelligence/mat2vec
nlcc (π₯11 Β· β 43 Β· π€) - Natural language computational chemistry command line interface. MIT
single-paper
MoLFormer (π₯9 Β· β 160) - Repository for MolFormer. Apache-2
transformer
pre-trained
drug-discovery
-
GitHub (π¨βπ» 5 Β· π 31 Β· π 16 - 43% open Β· β±οΈ 16.10.2023):
git clone https://github.com/IBM/molformer
MolSkill (π₯9 Β· β 94) - Extracting medicinal chemistry intuition via preference machine learning. MIT
drug-discovery
recommender
chemlift (π₯7 Β· β 11 Β· π£) - Language-interfaced fine-tuning for chemistry. MIT
-
GitHub (π¨βπ» 2 Β· π 1 Β· π 17 - 58% open Β· β±οΈ 14.10.2023):
git clone https://github.com/lamalab-org/chemlift
SciBot (π₯6 Β· β 25 Β· π) - SciBot is a simple demo of building a domain-specific chatbot for science. Unlicensed
-
GitHub (π 3 Β· β±οΈ 24.01.2024):
git clone https://github.com/CFN-softbio/SciBot
BERT-PSIE-TC (π₯5 Β· β 6) - A dataset of Curie temperatures automatically extracted from scientific literature with the use of the BERT-PSIE.. MIT
magnetism
-
GitHub (π¨βπ» 2 Β· π 3 Β· β±οΈ 18.08.2023):
git clone https://github.com/StefanoSanvitoGroup/BERT-PSIE-TC
Show 5 hidden projects...
- ChemDataExtractor (π₯16 Β· β 270 Β· π) - Automatically extract chemical information from scientific documents.
MIT
literature-data
- MAPI_LLM (π₯5 Β· β 4 Β· π€) - A LLM application developed during the LLM March MADNESS Hackathon https://doi.org/10.1039/D3DD00113J.
MIT
dataset
- LLM-Prop (π₯5 Β· β 4) - A repository for the LLM-Prop implementation.
Unlicensed
- CatBERTa (π₯3 Β· β 15) - Large Language Model for Catalyst Property Prediction.
Unlicensed
transformer
catalysis
- ChemDataWriter (π₯3 Β· β 10 Β· π£) - ChemDataWriter is a transformer-based library for automatically generating research books in the chemistry area.
MIT
literature-data
Projects that implement materials discovery methods using atomistic ML.
aviary (π₯12 Β· β 36) - The Wren sits on its Roost in the Aviary. MIT
-
GitHub (π¨βπ» 4 Β· π 9 Β· π 26 - 15% open Β· β±οΈ 02.01.2024):
git clone https://github.com/CompRhys/aviary
Materials Discovery: GNoME (π₯9 Β· β 700 Β· π£) - Graph Networks for Materials Science (GNoME) and dataset of 381,000 novel stable materials. Apache-2
rep-learn
datasets
-
GitHub (π¨βπ» 2 Β· π 110 Β· π 14 - 71% open Β· β±οΈ 02.12.2023):
git clone https://github.com/google-deepmind/materials_discovery
Show 7 hidden projects...
- BOSS (π₯7 Β· β 19 Β· π) - Bayesian Optimization Structure Search (BOSS).
Unlicensed
probabilistic
- AGOX (π₯6 Β· β 12 Β· π) - 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) (π₯6 Β· β 1 Β· π€) - Agent-based sequential learning software for materials discovery.
Apache-2
- closed-loop-acceleration-benchmarks (π₯4 Β· π€) - Data and scripts in support of the publication By how much can closed-loop frameworks accelerate computational..
MIT
materials-discovery
active-learning
single-paper
- SPINNER (π₯3 Β· β 9 Β· π) - SPINNER (Structure Prediction of Inorganic crystals using Neural Network potentials with Evolutionary and Random..
GPL-3.0
C++
structure-prediction
- sl_discovery (π₯3 Β· β 5 Β· π) - Data processing and models related to Quantifying the performance of machine learning models in materials discovery.
Apache-2
materials-discovery
single-paper
- CSPML (crystal structure prediction with machine learning-based element substitution) (π₯2 Β· β 14 Β· π) - Original implementation of CSPML.
Unlicensed
structure-prediction
Projects that implement mathematical objects used in atomistic machine learning.
gpax (π₯18 Β· β 160 Β· π) - Gaussian Processes for Experimental Sciences. MIT
probabilistic
active-learning
KFAC-JAX (π₯17 Β· β 180) - Second Order Optimization and Curvature Estimation with K-FAC in JAX. Apache-2
SpheriCart (π₯15 Β· β 48) - Multi-language library for the calculation of spherical harmonics in Cartesian coordinates. Apache-2
Polynomials4ML.jl (π₯14 Β· β 12) - Polynomials for ML: fast evaluation, batching, differentiation. MIT
Julia
-
GitHub (π¨βπ» 10 Β· π 5 Β· π 44 - 34% open Β· β±οΈ 16.01.2024):
git clone https://github.com/ACEsuit/Polynomials4ML.jl
lie-nn (π₯9 Β· β 24 Β· π€) - Tools for building equivariant polynomials on reductive Lie groups. MIT
rep-learn
-
GitHub (π¨βπ» 3 Β· π 1 Β· β±οΈ 20.06.2023):
git clone https://github.com/lie-nn/lie-nn
GElib (π₯9 Β· β 16) - C++/CUDA library for SO(3) equivariant operations. MPL-2.0
C++
-
GitHub (π¨βπ» 3 Β· π 3 Β· π 5 - 40% open Β· β±οΈ 25.10.2023):
git clone https://github.com/risi-kondor/GElib
COSMO Toolbox (π₯6 Β· β 6 Β· π€) - Assorted libraries and utilities for atomistic simulation analysis. Unlicensed
C++
-
GitHub (π¨βπ» 9 Β· π 5 Β· β±οΈ 23.06.2023):
git clone https://github.com/lab-cosmo/toolbox
Show 4 hidden projects...
- EquivariantOperators.jl (π₯5 Β· β 17) -
MIT
Julia
- cnine (π₯4 Β· β 2) - Cnine tensor library.
Unlicensed
C++
- torch_spex (π₯3 Β· β 2) - Spherical expansions in PyTorch.
Unlicensed
- Wigner Kernels (π₯2 Β· β 1) - Collection of programs to benchmark Wigner kernels.
Unlicensed
benchmarking
Projects that simplify the integration of molecular dynamics and atomistic machine learning.
FitSNAP (π₯17 Β· β 130) - Software for generating SNAP machine-learning interatomic potentials. GPL-2.0
mlcolvar (π₯17 Β· β 70 Β· π) - A unified framework for machine learning collective variables for enhanced sampling simulations. MIT
enhanced-sampling
openmm-torch (π₯15 Β· β 150) - OpenMM plugin to define forces with neural networks. Custom
ML-IAP
C++
OpenMM-ML (π₯12 Β· β 57) - High level API for using machine learning models in OpenMM simulations. MIT
ML-IAP
PACE (π₯10 Β· β 21) - The LAMMPS ML-IAP `pair_style pace`, aka Atomic Cluster Expansion (ACE), aka ML-PACE,.. Custom
-
GitHub (π¨βπ» 6 Β· π 10 Β· π 6 - 16% open Β· β±οΈ 27.11.2023):
git clone https://github.com/ICAMS/lammps-user-pace
pair_allegro (π₯7 Β· β 29 Β· π€) - LAMMPS pair style for Allegro deep learning interatomic potentials with parallelization support. MIT
ML-IAP
rep-learn
-
GitHub (π¨βπ» 2 Β· π 6 Β· π 20 - 15% open Β· β±οΈ 27.06.2023):
git clone https://github.com/mir-group/pair_allegro
Show 2 hidden projects...
- pair_nequip (π₯10 Β· β 33 Β· π) - LAMMPS pair style for NequIP.
MIT
ML-IAP
rep-learn
- interface-lammps-mlip-3 (π₯3 Β· β 5 Β· π€) - An interface between LAMMPS and MLIP (version 3).
GPL-2.0
Projects that focus on reinforcement learning for atomistic ML.
Show 2 hidden projects...
- ReLeaSE (π₯11 Β· β 330 Β· π) - Deep Reinforcement Learning for de-novo Drug Design.
MIT
drug-discovery
- CatGym (π₯6 Β· β 10 Β· π) - Surface segregation using Deep Reinforcement Learning.
GPL
Projects that offer implementations of representations aka descriptors, fingerprints of atomistic systems, and models built with them, aka feature engineering.
cdk (π₯23 Β· β 450 Β· π) - The Chemistry Development Kit. LGPL-2.1
cheminformatics
Java
DScribe (π₯22 Β· β 360) - DScribe is a python package for creating machine learning descriptors for atomistic systems. Apache-2
CatLearn (π₯16 Β· β 95 Β· π€) - GPL-3.0
surface-science
MODNet (π₯14 Β· β 63) - MODNet: a framework for machine learning materials properties. MIT
pre-trained
small-data
transfer-learning
-
GitHub (π¨βπ» 7 Β· π 29 Β· π¦ 5 Β· π 37 - 37% open Β· β±οΈ 13.11.2023):
git clone https://github.com/ppdebreuck/modnet
GlassPy (π₯14 Β· β 21 Β· π) - Python module for scientists working with glass materials. GPL-3.0
SISSO (π₯12 Β· β 200) - A data-driven method combining symbolic regression and compressed sensing for accurate & interpretable models. Apache-2
Fortran
-
GitHub (π¨βπ» 3 Β· π 68 Β· π 53 - 3% open Β· β±οΈ 12.09.2023):
git clone https://github.com/rouyang2017/SISSO
Librascal (π₯12 Β· β 77) - A scalable and versatile library to generate representations for atomic-scale learning. LGPL-2.1
-
GitHub (π¨βπ» 29 Β· π 19 Β· π 230 - 42% open Β· β±οΈ 30.11.2023):
git clone https://github.com/lab-cosmo/librascal
Rascaline (π₯12 Β· β 37) - Computing representations for atomistic machine learning. BSD-3
Rust
C++
-
GitHub (π¨βπ» 14 Β· π 11 Β· π 51 - 50% open Β· β±οΈ 25.01.2024):
git clone https://github.com/Luthaf/rascaline
NICE (π₯6 Β· β 12 Β· π€) - NICE (N-body Iteratively Contracted Equivariants) is a set of tools designed for the calculation of invariant and.. MIT
-
GitHub (π¨βπ» 4 Β· π 2 Β· π 3 - 66% open Β· β±οΈ 01.05.2023):
git clone https://github.com/lab-cosmo/nice
Show 13 hidden projects...
- cmlkit (π₯10 Β· β 33 Β· π) - tools for machine learning in condensed matter physics and quantum chemistry.
MIT
benchmarking
- SkipAtom (π₯7 Β· β 23 Β· π) - Distributed representations of atoms, inspired by the Skip-gram model.
MIT
- CBFV (π₯7 Β· β 16 Β· π) - Tool to quickly create a composition-based feature vector.
Unlicensed
- pyLODE (π₯7 Β· β 3) - Pythonic implementation of LOng Distance Equivariants.
Apache-2
electrostatics
- milad (π₯6 Β· β 28 Β· π) - Moment Invariants Local Atomic Descriptor.
GPL-3.0
generative
- SA-GPR (π₯6 Β· β 14 Β· π) - Public repository for symmetry-adapted Gaussian Process Regression (SA-GPR).
LGPL-3.0
C-lang
- fplib (π₯6 Β· β 7 Β· π) - a fingerprint library.
MIT
C-lang
single-paper
- SOAPxx (π₯6 Β· β 7 Β· π) - A SOAP implementation.
GPL-2.0
C++
- soap_turbo (π₯5 Β· β 4 Β· π€) - soap_turbo comprises a series of libraries to be used in combination with QUIP/GAP and TurboGAP.
Custom
Fortran
- SISSO++ (π₯4 Β· β 2 Β· π) - C++ Implementation of SISSO with python bindings.
Apache-2
C++
- magnetism-prediction (π₯4 Β· β 1) - DFT-aided Machine Learning Search for Magnetism in Fe-based Bimetallic Chalcogenides.
Apache-2
magnetism
single-paper
- ML-for-CurieTemp-Predictions (π₯4 Β· π€) - Machine Learning Predictions of High-Curie-Temperature Materials.
MIT
single-paper
magnetism
- AMP (π₯2) - Amp is an open-source package designed to easily bring machine-learning to atomistic calculations.
Unlicensed
General models that learn a representations aka embeddings of atomistic systems, such as message-passing neural networks (MPNN).
Deep Graph Library (DGL) (π₯38 Β· β 13K) - Python package built to ease deep learning on graph, on top of existing DL frameworks. Apache-2
PyG Models (π₯30 Β· β 19K) - Representation learning models implemented in PyTorch Geometric. MIT
general-ml
-
GitHub (π¨βπ» 480 Β· π 3.4K Β· π 3.3K - 23% open Β· β±οΈ 25.01.2024):
git clone https://github.com/pyg-team/pytorch_geometric
SchNetPack (π₯27 Β· β 690 Β· π) - SchNetPack - Deep Neural Networks for Atomistic Systems. MIT
dgl-lifesci (π₯23 Β· β 660 Β· π€) - Python package for graph neural networks in chemistry and biology. Apache-2
NVIDIA Deep Learning Examples for Tensor Cores (π₯21 Β· β 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 (π¨βπ» 120 Β· π 2.9K Β· π 790 - 29% open Β· β±οΈ 08.12.2023):
git clone https://github.com/NVIDIA/DeepLearningExamples
DIG: Dive into Graphs (π₯21 Β· β 1.7K) - A library for graph deep learning research. GPL-3.0
MatGL (Materials Graph Library) (π₯21 Β· β 170) - Graph deep learning library for materials. BSD-3
ocp (π₯19 Β· β 550) - ocp is the Open Catalyst Projects library of state-of-the-art machine learning algorithms for catalysis. MIT
-
GitHub (π¨βπ» 32 Β· π 190 Β· π 160 - 7% open Β· β±οΈ 12.01.2024):
git clone https://github.com/Open-Catalyst-Project/ocp
matsciml (π₯17 Β· β 94) - Open MatSci ML Toolkit is a framework for prototyping and scaling out deep learning models for materials discovery.. MIT
workflows
benchmarking
-
GitHub (π¨βπ» 10 Β· π 14 Β· π 28 - 28% open Β· β±οΈ 24.01.2024):
git clone https://github.com/IntelLabs/matsciml
Uni-Mol (π₯16 Β· β 500) - Official Repository for the Uni-Mol Series Methods. MIT
pre-trained
-
GitHub (π¨βπ» 13 Β· π 93 Β· π₯ 9.3K Β· π 120 - 36% open Β· β±οΈ 18.01.2024):
git clone https://github.com/dptech-corp/Uni-Mol
escnn (π₯14 Β· β 280) - Equivariant Steerable CNNs Library for Pytorch https://quva-lab.github.io/escnn/. Custom
Compositionally-Restricted Attention-Based Network (CrabNet) (π₯12 Β· β 11 Β· π€) - Predict materials properties using only the composition information!. MIT
GDC (π₯10 Β· β 240 Β· π€) - Graph Diffusion Convolution, as proposed in Diffusion Improves Graph Learning (NeurIPS 2019). MIT
generative
-
GitHub (π¨βπ» 3 Β· π 40 Β· π¦ 1 Β· β±οΈ 26.04.2023):
git clone https://github.com/gasteigerjo/gdc
hippynn (π₯9 Β· β 51) - python library for atomistic machine learning. Custom
workflows
-
GitHub (π¨βπ» 12 Β· π 20 Β· π 8 - 37% open Β· β±οΈ 23.01.2024):
git clone https://github.com/lanl/hippynn
Equiformer (π₯8 Β· β 150 Β· π€) - [ICLR23 Spotlight] Equiformer: Equivariant Graph Attention Transformer for 3D Atomistic Graphs. MIT
transformer
-
GitHub (π¨βπ» 2 Β· π 30 Β· π 12 - 41% open Β· β±οΈ 21.06.2023):
git clone https://github.com/atomicarchitects/equiformer
DeeperGATGNN (π₯8 Β· β 37) - Scalable graph neural networks for materials property prediction. MIT
-
GitHub (π¨βπ» 3 Β· π 7 Β· β±οΈ 19.01.2024):
git clone https://github.com/usccolumbia/deeperGATGNN
CGAT (π₯8 Β· β 21 Β· π€) - Crystal graph attention neural networks for materials prediction. MIT
-
GitHub (π¨βπ» 4 Β· π 7 Β· β±οΈ 10.01.2023):
git clone https://github.com/hyllios/CGAT
UVVisML (π₯8 Β· β 14 Β· π€) - Predict optical properties of molecules with machine learning. MIT
optical-properties
single-paper
probabilistic
-
GitHub (π 5 Β· β±οΈ 26.05.2023):
git clone https://github.com/learningmatter-mit/uvvisml
T-e3nn (π₯8 Β· β 8 Β· π€) - Time-reversal Euclidean neural networks based on e3nn. MIT
magnetism
-
GitHub (π¨βπ» 26 Β· β±οΈ 21.02.2023):
git clone https://github.com/Hongyu-yu/T-e3nn
graphite (π₯7 Β· β 43) - A repository for implementing graph network models based on atomic structures. MIT
-
GitHub (π¨βπ» 2 Β· π 8 Β· π¦ 9 Β· π 3 - 66% open Β· β±οΈ 12.12.2023):
git clone https://github.com/llnl/graphite
AdsorbML (π₯7 Β· β 28) - MIT
surface-science
single-paper
-
GitHub (π¨βπ» 5 Β· π 5 Β· π 2 - 50% open Β· β±οΈ 31.07.2023):
git clone https://github.com/Open-Catalyst-Project/AdsorbML
escnn_jax (π₯7 Β· β 23 Β· π€) - Equivariant Steerable CNNs Library for Pytorch https://quva-lab.github.io/escnn/. Custom
ML4pXRDs (π₯7) - Contains code to train neural networks based on simulated powder XRDs from synthetic crystals. MIT
XRD
single-paper
-
GitHub (π₯ 2 Β· β±οΈ 14.07.2023):
git clone https://github.com/aimat-lab/ML4pXRDs
EquiformerV2 (π₯6 Β· β 110) - [ICLR24] EquiformerV2: Improved Equivariant Transformer for Scaling to Higher-Degree Representations. MIT
-
GitHub (π¨βπ» 2 Β· π 14 Β· β±οΈ 02.12.2023):
git clone https://github.com/atomicarchitects/equiformer_v2
MACE-Layer (π₯6 Β· β 28 Β· π€) - Higher order equivariant graph neural networks for 3D point clouds. MIT
-
GitHub (π¨βπ» 2 Β· π 4 Β· β±οΈ 06.06.2023):
git clone https://github.com/ACEsuit/mace-layer
CraTENet (π₯5 Β· β 8 Β· π€) - An attention-based deep neural network for thermoelectric transport properties. MIT
transport-phenomena
-
GitHub (π 1 Β· β±οΈ 05.04.2023):
git clone https://github.com/lantunes/CraTENet
Show 25 hidden projects...
- benchmarking-gnns (π₯14 Β· β 2.4K Β· π) - Repository for benchmarking graph neural networks.
MIT
single-paper
benchmarking
- Crystal Graph Convolutional Neural Networks (CGCNN) (π₯12 Β· β 560 Β· π) - Crystal graph convolutional neural networks for predicting material properties.
MIT
- Neural fingerprint (nfp) (π₯12 Β· β 56 Β· π) - Keras layers for end-to-end learning with rdkit and pymatgen.
Custom
- SE(3)-Transformers (π₯9 Β· β 440 Β· π) - code for the SE3 Transformers paper: https://arxiv.org/abs/2006.10503.
MIT
single-paper
transformer
- molecularGNN_smiles (π₯9 Β· β 260 Β· π) - The code of a graph neural network (GNN) for molecules, which is based on learning representations of r-radius..
Apache-2
- GATGNN: Global Attention Graph Neural Network (π₯9 Β· β 61 Β· π) - Pytorch Repository for our work: Graph convolutional neural networks with global attention for improved materials..
MIT
- FAENet (π₯8 Β· β 24) -
MIT
- DTNN (π₯7 Β· β 76 Β· π) - Deep Tensor Neural Network.
MIT
- Cormorant (π₯7 Β· β 57 Β· π) - Codebase for Cormorant Neural Networks.
Custom
- ai4material_design (π₯7 Β· β 2) - 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
- charge_transfer_nnp (π₯6 Β· β 25 Β· π) - Graph neural network potential with charge transfer.
MIT
electrostatics
- GLAMOUR (π₯6 Β· β 18 Β· π) - Graph Learning over Macromolecule Representations.
MIT
single-paper
- tensorfieldnetworks (π₯5 Β· β 140 Β· π) -
MIT
- Autobahn (π₯5 Β· β 29 Β· π) - Repository for Autobahn: Automorphism Based Graph Neural Networks.
MIT
- SCFNN (π₯5 Β· β 15 Β· π) - Self-consistent determination of long-range electrostatics in neural network potentials.
MIT
C++
electrostatics
single-paper
- FieldSchNet (π₯5 Β· β 11 Β· π) -
MIT
- Per-Site CGCNN (π₯5 Β· β 1 Β· π€) - Crystal graph convolutional neural networks for predicting material properties.
MIT
pre-trained
single-paper
- Per-site PAiNN (π₯5 Β· β 1 Β· π€) - Fork of PaiNN for PerovskiteOrderingGCNNs.
MIT
probabilistic
pre-trained
single-paper
- Atom2Vec (π₯4 Β· β 26 Β· π) - Atom2Vec: a simple way to describe atoms for machine learning.
Unlicensed
- Graph Transport Network (π₯4 Β· β 15 Β· π€) - Graph transport network (GTN), as proposed in Scalable Optimal Transport in High Dimensions for Graph Distances,..
Custom
transport-phenomena
- Element encoder (π₯3 Β· β 5 Β· π) - Autoencoder neural network to compress properties of atomic species into a vector representation.
GPL-3.0
single-paper
- gkx: Green-Kubo Method in JAX (π₯2 Β· β 2 Β· π€) - Green-Kubo + JAX + MLPs = Anharmonic Thermal Conductivities Done Fast.
MIT
transport-phenomena
- atom_by_atom (π₯2 Β· β 2) - Atom-by-atom design of metal oxide catalysts for the oxygen evolution reaction with Machine Learning.
Unlicensed
surface-science
single-paper
- Point Edge Transformer (π₯2) - Smooth, exact rotational symmetrization for deep learning on point clouds.
CC-BY-4.0
- SphericalNet (π₯1 Β· β 3 Β· π) - Implementation of Clebsch-Gordan Networks (CGnet: https://arxiv.org/pdf/1806.09231.pdf) by GElib & cnine libraries in..
Unlicensed
Projects that focus on unsupervised learning (USL) for atomistic ML, such as dimensionality reduction, clustering and visualization.
ASAP (π₯12 Β· β 120) - ASAP is a package that can quickly analyze and visualize datasets of crystal or molecular structures. MIT
-
GitHub (π¨βπ» 6 Β· π 27 Β· π¦ 5 Β· π 24 - 25% open Β· β±οΈ 30.08.2023):
git clone https://github.com/BingqingCheng/ASAP
Sketchmap (π₯8 Β· β 42 Β· π€) - Suite of programs to perform non-linear dimensionality reduction -- sketch-map in particular. GPL-3.0
C++
-
GitHub (π¨βπ» 8 Β· π 10 Β· π 8 - 37% open Β· β±οΈ 24.05.2023):
git clone https://github.com/lab-cosmo/sketchmap
Show 4 hidden projects...
- paper-ml-robustness-material-property (π₯4 Β· β 3 Β· π€) -
BSD-3
datasets
single-paper
- Coarse-Graining-Auto-encoders (π₯3 Β· β 20 Β· π) -
Unlicensed
single-paper
- KmdPlus (π₯2 Β· β 3) - 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) ( β 2) - Provides a workflow to obtain clustering of local environments in dataset of structures.
Unlicensed
Projects that focus on visualization (viz.) for atomistic ML.
Chemiscope (π₯18 Β· β 98) - An interactive structure/property explorer for materials and molecules. BSD-3
JavaScript
pymatviz (π₯18 Β· β 98) - A toolkit for visualizations in materials informatics. MIT
general-tool
probabilistic
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.
FermiNet (π₯15 Β· β 630) - An implementation of the Fermionic Neural Network for ab-initio electronic structure calculations. Apache-2
transformer
-
GitHub (π¨βπ» 18 Β· π 110 Β· β±οΈ 20.12.2023):
git clone https://github.com/deepmind/ferminet
DeepErwin (π₯8 Β· β 36) - DeepErwin is a python 3.8+ package that implements and optimizes JAX 2.x wave function models for numerical solutions.. Custom
Show 1 hidden projects...
pretrained-gnns (π₯10 Β· β 890) - Strategies for Pre-training Graph Neural Networks. MIT
pre-trained
-
GitHub (π¨βπ» 2 Β· π 160 Β· π 59 - 50% open Β· β±οΈ 29.07.2023):
git clone https://github.com/snap-stanford/pretrain-gnns
Show 1 hidden projects...
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.