/tools

FAIR Chemistry's `fairchem` library offers a centralized repository of machine learning models and methods tailored for chemistry and materials science. It supports various tasks such as predicting molecular properties, running molecular dynamics simulations, and optimizing molecular structures.

The Materials Discovery: GNoME repository provides a dataset of over 520,000 novel stable materials and includes models for discovering new materials using graph networks. It aims to facilitate research in materials science by offering tools for exploring chemical systems and computing material properties.

DFTK.jl is a density-functional toolkit designed for plane-wave density-functional theory (DFT) calculations. It provides routines for electronic structure calculations, enabling researchers to predict molecular properties and perform simulations in solid-state research.

Pyiron is an integrated development environment designed for computational materials science, facilitating the management and execution of complex simulation protocols. It supports various atomistic simulation codes and provides tools for visualization and data management, making it suitable for molecular dynamics and related tasks.

JARVIS-Tools is an open-source software package designed for data-driven atomistic materials design. It provides capabilities for setting up calculations, analysis, and informatics, as well as database and web-page development.

CHGNet is a universal neural network potential that enables charge-informed atomistic modeling with high accuracy. It can predict molecular properties such as energy and forces, and is capable of running molecular dynamics simulations, making it a valuable tool in computational chemistry and materials science.

PyXtal is an open-source Python library that facilitates the generation of atomic and molecular structures while adhering to symmetry constraints. It includes features for geometry optimization and supports various structural formats for further analysis.

freud is a Python library that provides powerful tools for analyzing particle trajectories from molecular dynamics and Monte Carlo simulations. It includes features for computing various analysis metrics such as radial distribution functions and potentials of mean force, facilitating research in materials science and computational chemistry.

VASPy is a Python library that facilitates the manipulation and visualization of VASP files, which are used in computational chemistry. It allows users to process various types of VASP data, including electronic structure and molecular dynamics simulations.

The All-atom Diffusion Transformers repository provides an implementation of a generative model that can create new molecular and material structures using a unified latent diffusion framework. It supports the generation of both small molecules and periodic materials, making it a valuable tool for molecular design and materials science.

IBM's FM4M is a multi-modal foundation model designed to support research in materials science and chemistry. It includes various pre-trained models for predicting molecular properties and generating molecular representations, making it a versatile tool for computational chemistry applications.

The 'stk' library is designed for the construction and manipulation of complex molecules, facilitating automatic molecular design and the creation of molecular databases. It serves as a framework for researchers in computational chemistry and materials science to explore molecular structures and properties.

quacc is a flexible platform designed for computational materials science and quantum chemistry, enabling users to run various workflows for molecular simulations and property predictions efficiently. It integrates with existing resources and provides a unified interface for managing computational tasks.

RadonPy is an open-source Python library that automates the calculation of various physical properties for polymers through all-atom classical molecular dynamics simulations. It supports the generation of polymer structures, force field assignments, and the calculation of numerous polymer properties, making it a comprehensive tool for polymer informatics.

Sumo is a Python toolkit designed for plotting and analyzing data from ab initio solid-state calculations. It offers features for generating k-point paths and creating publication-ready plots of electronic and phonon band structures, density of states, and optical absorption diagrams.

Atomsk is a command-line tool that allows users to manipulate and convert atomic data files, facilitating the construction of crystals and polycrystals, as well as the introduction of defects in atomic systems. It supports various file formats and is useful in the context of materials science and atomic simulations.

Doped is a Python software designed for the generation, pre-/post-processing, and analysis of defect supercell calculations in materials. It implements a defect simulation workflow that allows users to efficiently analyze defect formation energies, charge states, and thermodynamic properties in semiconductors.

Matbench Discovery is an evaluation framework that ranks machine learning models on tasks related to high-throughput discovery of stable inorganic crystals. It predicts material properties such as thermodynamic stability and thermal conductivity, providing insights for building large-scale materials databases.

The MACE foundation models provide pre-trained machine learning models for materials chemistry, covering a wide range of chemical elements. These models are designed to predict molecular properties and improve stability during molecular dynamics simulations.

SLICES is an innovative tool for encoding and decoding crystal structures, enabling the inverse design of solid-state materials with specific properties. It utilizes generative deep learning techniques to facilitate the creation of new materials, making it a valuable resource in computational chemistry and materials science.

DynaPhoPy is a software tool designed to calculate crystal microscopic anharmonic properties from molecular dynamics simulations. It utilizes normal-mode-decomposition techniques to analyze phonon frequency shifts and thermal properties, making it useful for researchers in materials science and molecular dynamics.

CrystalFormer is a transformer-based autoregressive model that generates crystalline materials while considering space group symmetries. It utilizes reinforcement learning for fine-tuning and can produce stable crystal structures based on specified prototypes.

SMACT is a Python package designed for materials design and informatics, focusing on rapid screening of hypothetical materials and predicting their properties. It utilizes data about chemical elements to facilitate the generation and optimization of compositions, making it a valuable resource in computational chemistry.

UPET is a tool for advanced atomistic simulations that utilizes machine-learned interatomic potentials to predict energies, forces, and other properties of materials and molecules. It supports various simulation engines and is designed for efficiency in high-performance computing environments.