Awesome Materials Informatics tools and codes

A curated list of resources related to materials informatics, a field combining materials science, computer science, and data science.

Contents

• [Software and products](#software-and-products)
• [Cloud simulation platforms and AI startups](#cloud-simulation-platforms-and-ai-startups)
• [Machine-readable materials datasets](#machine-readable-materials-datasets)
• [Standardization initiatives](#standardization-initiatives)
• [Similar compilations](#similar-compilations)
• [License](#license)

Software and products

• [AFLOW](http://materials.duke.edu/AFLOW) - High-Throughput ab-initio Computing (**C++**).
• [AiiDA](http://aiida.net) - Automated Infrastructure and Database for Ab-initio design (**Python**). [](https://github.com/aiidateam/aiida-core)
• [ASE](https://wiki.fysik.dtu.dk/ase) - Atomic Simulation Environment (**Python**). [](https://gitlab.com/ase/ase)
• [ASR](https://gitlab.com/dtorel/asr) - Atomic Simulation Recipes, based on ASE (**Python**). [](https://gitlab.com/dtorel/asr)
• [atomate](https://hackingmaterials.github.io/atomate) - Materials science workflows based on FireWorks, developed at LBNL (**Python**). [](https://github.com/hackingmaterials/atomate)
• [aviary](https://github.com/CompRhys/aviary) - Predict materials properties using compositions and Wyckoff representations (**Python**). [](https://github.com/CompRhys/aviary)
• [BIOVIA Materials Studio](https://www.3ds.com/products-services/biovia/products/molecular-modeling-simulation/biovia-materials-studio/) - _Proprietary_ simulation infrastructure.
• [CAMD](https://github.com/tri-amdd/camd) - Agent-based sequential learning software for materials discovery (**Python**). [](https://github.com//tri-amdd/camd)
• [cclib](https://cclib.github.io) - Parse and interpret the results of computational chemistry packages (**Python**). [](https://github.com/cclib/cclib)
• [cctbx](https://cctbx.github.io) - Computational Crystallography Toolbox (**C++**). [](https://github.com/cctbx/cctbx_project)
• [CDVAE](https://github.com/txie-93/cdvae) - **Python** Crystal Diffusion Variational AutoEncoder (CDVAE) generates novel stable materials via inverse design. [](https://github.com/txie-93/cdvae)
• [CrabNet](https://github.com/anthony-wang/CrabNet) - Predict materials properties using only the composition information. (**Python**). 
• [Crystal Toolkit](https://docs.crystaltoolkit.org) - A framework for building web apps for materials science powering the new Materials Project website. [](https://github.com/materialsproject/crystaltoolkit)
• [Custodian](https://github.com/materialsproject/custodian) - Simple, robust and flexible just-in-time (JIT) job management framework (**Python**). [](https://github.com/materialsproject/custodian)
• [datamol](https://github.com/datamol-org/datamol) - Molecular Manipulation Made Easy. A light wrapper built on top of RDKit (**Python**). [](https://github.com/datamol-org/datamol)
• [ElMD](https://github.com/lrcfmd/ElMD) - Quantify the chemical similarity between two compositions using the Element Movers Distance. [](https://github.com/lrcfmd/ElMD/)
• [FireWorks](https://materialsproject.github.io/fireworks) - Workflow engine developed at LBNL (**Python**). [](https://github.com/materialsproject/fireworks)
• [Granta MI](https://www.grantadesign.com/products/mi) - _Proprietary_ enterprise infrastructure for the materials data.
• [Grobid superconductors](https://github.com/lfoppiano/grobid-superconductors) - Open source [Grobid](https://github.com/kermitt2/grobid) module for extracting superconductor material and related properties
• [httk](https://httk.openmaterialsdb.se) - High-throughput toolkit (**Python**). [](https://github.com/rartino/httk)
• [ICMD](https://www.questek.com/software) - A digital materials design platform in the cloud from QuesTek Innovations LLC (_proprietary_).
• [ioChem-BD](https://www.iochem-bd.org) - Solution to manage computational chemistry Big Data (**Java**).
• [MAST-ML](https://github.com/uw-cmg/MAST-ML) - An open-source Python package designed to broaden and accelerate the use of machine learning in materials science research (**Python**). [](https://github.com/uw-cmg/MAST-ML)
• [matador](https://github.com/ml-evs/matador) - A library for aggregation and analysis of high-throughput DFT (**Python**). [](https://github.com/ml-evs/matador)
• [matbench](https://github.com/materialsproject/matbench) - Matbench: Benchmarks for materials science property prediction (**Python**). [](https://github.com/materialsproject/matbench)
• [matbench-genmetrics](https://github.com/sparks-baird/matbench-genmetrics) - Generative materials benchmarking metrics, inspired by [guacamol](https://www.benevolent.com/guacamol) and [CDVAE](https://github.com/txie-93/cdvae) (**Python**). [](https://github.com/sparks-baird/matbench-genmetrics)
• [matminer](https://github.com/hackingmaterials/matminer) - A library for data mining in materials science (**Python**). [](https://github.com/hackingmaterials/matminer)
• [MatSciBERT](https://huggingface.co/m3rg-iitd/matscibert) - A Materials Domain Language Model for Text Mining and Information Extraction (**Python**).
• [mat_discover](https://sparks-baird.github.io/mat_discover/) - Find high-performance candidates in chemical spaces, composition-only (**Python**). 
• [MDCS](https://github.com/usnistgov/MDCS) - Materials Data Curation System (**Python**). [](https://github.com/usnistgov/MDCS)
• [MedeA](https://www.materialsdesign.com/medea-software) - _Proprietary_ computational **Tcl** environment by Materials Design, Inc.
• [MODNet](https://github.com/ppdebreuck/modnet) - Select optimal descriptions and build models for predicting materials properties (**Python**). [](https://github.com/ppdebreuck/modnet)
• [mp-time-split](https://github.com/sparks-baird/mp-time-split) - Use time-based cross-validation splits from Materials Project for genera

Acknowledgement: https://github.com/tilde-lab/awesome-materials-informatics/tree/master