/tools

YetAnotherSimulationSuite.jl (YASS) is a modern atomic simulation suite written in Julia, providing tools for molecular dynamics simulations and analysis. It supports various molecular dynamics ensembles and includes built-in analysis tools for studying molecular systems.

This repository provides educational materials for the 2025 CCPBioSim Training Week, focusing on parameterizing small molecules and conducting molecular dynamics simulations for protein-ligand complexes. It includes Jupyter Notebooks that guide users through practical applications in molecular modeling.

This repository implements a deep learning approach to classify protein-ligand interactions as allosteric or orthosteric based on molecular dynamics data. It includes a full pipeline for data processing, model training, and evaluation, making it a useful tool for molecular simulations and drug discovery.

SPICE-Models provides models that are trained on the SPICE dataset, likely aimed at predicting molecular properties. This tool may be useful in various applications related to molecular design and analysis.

FAPEloss is a Python implementation of the FAPE loss function used in the AlphaFold algorithm for predicting protein structures. It provides a framework for testing and optimizing the loss function, which is crucial for accurate protein design.

The aizynthmodels repository provides tools for training and evaluating models that predict synthetic routes for molecules. It is designed to assist in the synthesis prediction process, making it a valuable resource in molecular design and cheminformatics.

molmetrics is a Python tool designed to assess 3D molecular structures by providing various metrics. It allows users to evaluate the validity and uniqueness of molecular structures and calculate bond length distributions, making it useful for molecular analysis and simulations.

Rxitect is a de-novo drug design library that utilizes deep reinforcement learning and generative flow networks to create molecules with a focus on synthetic accessibility. It aims to improve the practicality of generated molecules by incorporating retrosynthesis-aware models into the design process.

DrugDataResource is a repository that offers a variety of datasets aimed at facilitating drug discovery and development. It includes datasets for drug-target interactions, ADMET properties, and other molecular characteristics, which are essential for computational chemistry and molecular biology research.

Protify is an open-source platform that simplifies the process of predicting chemical properties, particularly for proteins, using deep learning models. It offers a low-code solution for users to benchmark models and utilize various datasets for protein property prediction.

ProteinF3S is an implementation of a model that enhances enzyme function prediction by combining various protein data types. It provides processed datasets and pre-trained weights for inference, making it a useful tool in the field of protein design and bioinformatics.

This repository contains code for evaluating reinforcement learning techniques applied to transformer-based molecular design. It includes predictive models and configurations for running experiments related to molecular generation and optimization.

PSP-GNM is a tool designed to predict changes in protein thermodynamic stability upon mutations using a Gaussian Network Model. It estimates free energy changes associated with point mutations, providing insights into protein stability and function.

proteinviz is an open-source tool that predicts the 3D structure of proteins based on their amino acid sequences. It utilizes a protein folding model to generate PDB files and visualize the protein structures in a user-friendly interface.

The addNewResidue.py script allows users to add custom-made amino acids to the GROMACS forcefield directory, supporting both AMBER and CHARMM forcefields. It facilitates the preparation of molecular simulations by enabling the incorporation of new residues into protein structures.

The AdKGromacsTutorial repository offers a comprehensive guide for performing molecular dynamics simulations of the adenylate kinase enzyme using Gromacs. It includes steps for system setup, energy minimization, equilibration, and trajectory visualization, making it a valuable resource for researchers in molecular dynamics.

gmx_clusterByFeatures is a tool designed for clustering the conformations of molecules in molecular dynamics trajectories based on various features. It supports GROMACS format and provides functionalities for distance matrix calculations and visualization of clustering results.

CPPCartoon is a tool designed to generate meshes of cartoon representations for the secondary structures of proteins. It can be utilized as a library or a standalone executable, processing PDB files to visualize protein structures effectively.

MDTools is a collection of Python scripts that facilitate the preparation and analysis of molecular dynamics simulations. It allows users to work with various trajectory and topology formats, making it a versatile tool for molecular simulation tasks.

The 'scalar_codes' repository contains Python codes designed to automate standard VASP calculations, focusing on molecular simulations and geometry optimization. It includes functionalities for analyzing molecular properties and performing various computational tasks related to atomistic systems.

mbGDML is a tool for creating, using, and analyzing machine learning potentials within the many-body expansion framework. It allows for accurate predictions of molecular properties and supports molecular dynamics simulations, making it a valuable resource in computational chemistry.

ADKF-IFT is a PyTorch implementation of a meta-learning method for predicting molecular properties using adaptive deep kernel Gaussian processes. It includes code for regression tasks on the FS-Mol dataset and provides model checkpoints for classification and regression, making it a useful tool for researchers in molecular property prediction.

USMPep is a tool designed for predicting the binding affinity of peptides to the Major Histocompatibility Complex (MHC) using a recurrent neural network. It demonstrates competitive performance against state-of-the-art methods and provides predictions on benchmark datasets.