/tools

TorchMMFF94 provides a PyTorch implementation of the MMFF94 force field, enabling molecular energy minimization both in isolation and in the context of protein pockets. It offers a simple interface for testing and running examples related to molecular optimization.

DockTGrid is a Python package designed to generate customized voxel representations of protein-ligand complexes, facilitating deep learning applications. It supports GPU acceleration and is compatible with various file formats, making it a useful tool for molecular docking and virtual screening tasks.

The SMIRNOFF Plugins repository offers a framework for using custom functional forms in SMIRNOFF-based force fields, enabling researchers to parameterize molecular interactions for simulations. It includes various parameter handlers for different potential types, facilitating the modeling of molecular systems.

DEL_analysis provides code to analyze data from DNA-encoded libraries, including data preparation, similarity calculations, and activity predictions for new compounds. It is designed to facilitate the analysis of experimental data from DEL screens.

The cryo_fit tool is designed for fitting atomic models into cryo-EM density maps, which is crucial for understanding protein structures. It provides functionalities that aid in the analysis and visualization of molecular structures derived from cryo-electron microscopy data.

The Tensor Contraction Engine (TCE) is a symbolic algebra code that derives equations for ab initio electron-correlated theories and generates corresponding Fortran code for use in quantum chemistry software like NWCHEM. It facilitates the execution of complex quantum chemical calculations in parallel.

The viewer3d tool enables the visualization of PackedPose and Pose objects, as well as PDB files, within Jupyter notebooks and Google Colab. It supports dynamic updates and various visualization modules, making it useful for analyzing macromolecular structures.

This tool predicts the binding affinity of protein-ligand complexes by utilizing Graph Neural Networks. It processes 3D structural data to enhance the accuracy of drug-target interaction predictions, aiding in drug design and discovery.

The xtbiff program is designed to implement a general intermolecular force field using tight-binding quantum chemical calculations. It can be utilized in molecular simulations and is compatible with other computational chemistry tools.

This repository contains scripts and methodologies for selecting features and performing Markov state modeling on protein folding data. It includes tools for analyzing molecular trajectories and clustering, which are essential for understanding protein dynamics.

CLIPS is a tool designed for the fast estimation of ion-pairing in electrolyte solutions. It utilizes molecular dynamics simulations to analyze interactions between cations and anions in various solvents, providing outputs that help in understanding electrolyte behavior.

Tinker-FFE is a Java-based graphical user interface designed for molecular engineering and modeling. It allows users to launch and control Tinker calculations and supports downloading molecular structures from various databases.

The 'topo-tools-scripts' repository provides scripts for preparing input files for molecular dynamics simulations of gases in MOF-74 analogues. It focuses on generating LAMMPS input files for simulating the adsorption of methane and carbon dioxide in metal-organic frameworks using a DFT-derived force field.

The Electron-Phonon Averaged (EPA) Approximation tool is designed to compute electron-phonon coupling and transport properties in materials. It utilizes a computational workflow involving Quantum ESPRESSO and BoltzTraP to analyze the electronic properties of materials like silicon and half-Heusler compounds.

This repository contains data and parsing scripts for a Graph Neural Network (GNN) model that predicts chemical shifts in molecules. It includes functionalities for loading, validating, and processing molecular data, making it a useful tool for molecular property prediction.

This repository contains materials for a workshop on AI in chemistry, covering topics such as molecular representations, data quality, and hands-on sessions for molecule generation. It aims to educate participants on the application of AI techniques in molecular design and analysis.

MolSim is a Julia package registry that facilitates the management and registration of packages related to molecular simulation. Although it is deprecated, it provides a platform for users to access and manage various molecular simulation tools.

NeighbourLists.jl is a Julia package designed for computing neighbour lists in molecular simulations. It supports both CPU and GPU implementations, making it efficient for handling large systems in molecular dynamics.

AMPTrans-lstm is a deep generative model application designed to discover novel and diverse functional peptides that can combat microbial resistance. It utilizes advanced machine learning techniques, specifically LSTM and transformer models, to generate and optimize peptide sequences.

OpenFF Pablo is a new implementation of the `Topology.from_pdb` function, which is part of the Open Force Field initiative. It is designed to facilitate the handling of molecular topologies, likely for use in simulations and other molecular modeling tasks.

PyFock-GUI is an interactive web application that enables users to perform density functional theory (DFT) calculations on molecules. It supports various exchange-correlation functionals and basis sets, allowing for the prediction of molecular properties and visualization of molecular orbitals in real-time.

molecular-python3 is a tool for virtual chemistry simulation in 2D, leveraging numpy and numba for efficient computation. It allows users to visualize and simulate molecular interactions in a virtual environment.

3D-PGT is a tool designed for automated 3D pre-training aimed at improving molecular property prediction tasks. It utilizes geometric information and includes both pre-training and fine-tuning stages to enhance the performance of models on molecular datasets.