/tools

The openmmforcefields repository offers CHARMM and AMBER force fields for use with OpenMM, enabling the parameterization of biomolecular systems and small molecules. It supports various force fields and provides tools for generating parameters for small molecules, making it a valuable resource for molecular simulations.

The `exmol` package is designed to explain black-box predictions of molecular properties using model agnostic methods. It includes functionalities for generating counterfactuals and descriptor attributions, helping users understand the influence of molecular structures on predicted properties.

ChemDataExtractor is a toolkit designed to automatically extract chemical information from scientific documents. It utilizes natural language processing techniques to identify and parse chemical entities and data from various document formats.

Packmol is a tool that generates initial configurations for molecular dynamics simulations by packing molecules in defined regions of space. It ensures that short-range repulsive interactions do not disrupt the simulations, making it suitable for various types of molecular systems.

This repository contains Fortran and Python examples for molecular dynamics and Monte Carlo simulations, designed to accompany the book 'Computer Simulation of Liquids'. It serves as a practical resource for understanding and implementing these simulation techniques in computational chemistry.

PyEMMA is an open-source Python package that provides algorithms for the estimation, validation, and analysis of Markov models in the context of molecular dynamics simulations. It supports clustering, featurization, and various Markov modeling techniques, making it useful for researchers in computational chemistry.

REINVENT is a tool for molecular de novo design that employs recurrent neural networks and reinforcement learning techniques. It allows users to explore chemical space and generate novel molecular structures based on learned representations.

PyPDB is a Python toolkit designed for performing searches and fetching data from the RCSB Protein Data Bank (PDB). It allows users to access information about protein structures, sequences, and related data programmatically, facilitating research in molecular biology.

Meeko is an interface for AutoDock that prepares input files for molecular docking and processes the output. It parameterizes both small organic molecules and biological macromolecules, facilitating drug discovery and molecular modeling.

ProteinGenerator is a tool that generates sequence-structure pairs using a diffusion model based on RoseTTAFold. It allows users to explore and create new protein sequences conditioned on structural motifs, facilitating advancements in protein design.

The 'rgn' repository provides a TensorFlow implementation of recurrent geometric networks for end-to-end differentiable learning of protein structures. It allows users to train models and predict protein structures from sequences, making it a valuable tool in the field of molecular biology and computational chemistry.

The SE3-Transformer-PyTorch repository provides an implementation of SE3-Transformers for equivariant self-attention, specifically aimed at applications in protein structure prediction and drug discovery. It allows for the modeling of molecular interactions and features, making it a valuable tool in computational chemistry and molecular biology.

Scikit-fingerprints is a Python library designed for efficient computation of molecular fingerprints, which are crucial in drug discovery and chemical analysis. It provides a scikit-learn compatible interface, allowing users to integrate molecular fingerprints into machine learning workflows and access popular benchmark datasets.

CBGBench is a benchmark tool for generative target-aware molecule design, integrating multiple state-of-the-art methods for generating molecules. It supports tasks such as linker design, fragment growing, and scaffold hopping, making it a valuable resource for researchers in drug discovery.

EquiformerV2 is a PyTorch implementation of an improved equivariant transformer designed for scaling to higher-degree representations in molecular systems. It is utilized for training on datasets related to energy and force predictions, making it a valuable tool in drug discovery and molecular dynamics simulations.

VIAMD is an interactive analysis tool designed for molecular dynamics simulations. It allows users to perform operations on trajectory frames and visualize the results, making it a valuable resource for researchers in computational chemistry.

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.

MolCLR is an implementation of a contrastive learning framework for molecular representation learning using graph neural networks. It enhances the performance of models on various molecular property prediction tasks and provides datasets for pre-training and fine-tuning.

GearNet is a geometry-aware relational graph neural network designed for protein structure representation learning. It employs various self-supervised learning methods to enhance the encoding of protein spatial information, making it suitable for downstream tasks in molecular biology.

gReLU is a Python library designed for training, interpreting, and applying deep learning models to DNA sequences. It provides functionalities for genome annotation and processing, making it a useful tool in the field of molecular biology.

OpenMMTools is a Python library that enhances the OpenMM molecular simulation engine by providing tools for various molecular dynamics tasks, including free energy calculations and Markov chain Monte Carlo methods. It is designed to facilitate the development of comprehensive molecular simulation packages.

Moltemplate is a cross-platform text-based molecule builder that prepares simulations for LAMMPS, supporting both coarse-grained and all-atom models. It facilitates the creation of molecular models using various force fields and integrates with other molecular modeling tools.

torch-molecule is a deep learning package designed for molecular discovery, featuring an sklearn-style interface for property prediction, inverse design, and representation learning. It supports various molecular tasks and includes datasets for training models on molecular properties.

This repository provides an implementation for visualizing and analyzing attention in protein language models, specifically designed to interpret how these models interact with protein structures. It includes tools for generating visualizations and conducting attention analysis on various protein datasets.