Open Source

OpenMM is a molecular simulation toolkit. Its official OpenMM-ML extension connects machine learning potentials to simulations.

Computational Chemistry

e3nn provides mathematical components for E(3)-equivariant networks, including representations, tensor products and spherical harmonics.

PyTorch Geometric (PyG) is a general graph neural network library with an official QM9 example for molecular property learning.

Molecular Property Prediction

DGL-LifeSci is a DGL/PyTorch toolkit providing graph learning components and examples for chemistry and biology.

Molecular Property Prediction

ASE is a Python atomistic simulation library connecting conventional codes and external machine learning potentials through a common calculator interface.

Computational Chemistry

MatGL is a materials graph learning library for developing and using property predictors and machine learning potentials.

Computational Chemistry · Materials Discovery

molSimplify generates inorganic coordination and intermolecular complexes for computational screening, with bundled neural networks for selected properties of octahedral transition metal complexes.

Molecular Generation · Computational Chemistry

ChemML is a Python suite for chemical and materials data analysis, mining, and modeling, with a modular design and documented work on graph neural networks, AutoML, and explainability.

Molecular Property Prediction · Materials Discovery

DeepMol is a Python toolkit for molecular machine learning, connecting compound standardization and featurization with model training, evaluation, interpretation and reusable pipelines.

Molecular Property Prediction

AutoDock Vina is an open-source molecular docking and virtual screening program with Vina and AutoDock4.2 scoring, multi-ligand docking, macrocycle support and Python 3 bindings.

Drug Discovery

FEgrow supports interactive ligand-series construction for free-energy preparation, with documented active-learning examples and Dask-based acceleration for molecular design workflows.

Molecular Generation · Drug Discovery

Matchms is a Python toolkit for importing, cleaning and comparing tandem mass spectra, with configurable processing pipelines, multiple similarity measures and sparse score storage.

Spectroscopy

ChemDataExtractor v2 is a Python toolkit for extracting chemical entities, properties, spectra and tabulated data from scientific literature, with readers for HTML, XML and PDF.

Literature & Research

PySINDy is a Python package for inferring dynamical equations from measurement data using sparse system identification, with optional optimization methods for constrained and Bayesian regression.

Process Control · Digital Twins

SysIdentPy is a Python toolkit for identifying nonlinear dynamic systems with NARMAX-family models, combining structure selection, parameter estimation, simulation and forecasting.

Process Control · Predictive Maintenance

GEKKO is a Python modeling and optimization toolkit for differential algebraic systems, supporting process simulation, parameter estimation, mixed-integer optimization, and nonlinear predictive control.

Process Optimization · Process Control

do-mpc is a Python toolbox for nonlinear and robust model predictive control, moving horizon estimation, and simulation, with support for differential algebraic models and uncertainty.

Process Control · Digital Twins

IDAES is a Python process systems engineering toolkit for simulation-based design, analysis and optimization of advanced energy systems, with solver extensions and separately distributed examples.

Process Optimization · Chemical Manufacturing

Phoenics combines Bayesian optimization with Bayesian kernel density estimation to recommend experimental or computational parameters, supporting sequential, batch and multi-objective workflows.

Lab Automation · Process Optimization

Gryffin is a Python Bayesian optimization framework for categorical and mixed experimental design spaces, with batch recommendations and physicochemical descriptor support.

Lab Automation · Process Optimization