/tools

LigParGen-CommandFiles provides the necessary command files to install LigParGen locally, a tool used for generating force fields for ligands in molecular dynamics simulations. This repository supports the computational chemistry community by facilitating the setup of simulations involving small molecules.

PHIEmbed is a tool designed for predicting phage-host interactions by utilizing protein language models to represent receptor-binding proteins. It improves upon traditional methods by automating feature extraction and enhancing prediction accuracy through the use of embeddings.

MetalloDock is an AI-powered molecular docking framework focused on metalloproteins. It excels in predicting binding affinities, reconstructing metal coordination geometries, and performing virtual screenings against metalloprotein targets.

PhyNEO is a hybrid force field development workflow that enhances traditional physics-based methods with neural networks to achieve accurate molecular simulations. It focuses on generating force fields for organic molecules and polymers, facilitating molecular dynamics simulations and analysis of properties like conductivity and diffusion coefficients.

XtalNet is an end-to-end tool for predicting crystal structures based on Powder X-Ray Diffraction data. It utilizes advanced deep learning techniques to generate and evaluate crystal structures, making it significant for materials science and molecular modeling.

Prospr is a toolbox designed for protein structure prediction using the HP-model. It includes various prediction algorithms, a protein data structure for simulating folding, and datasets for research in protein folding and structure analysis.

RELATION is a software tool that implements a deep generative model for structure-based de novo drug design. It allows users to prepare molecular datasets, train models, and sample new molecular structures, making it relevant for drug discovery and molecular design.

PROTON is a graph AI model designed to generate and validate neurological hypotheses across molecular, organoid, and clinical systems. It predicts drug candidates and toxicities related to neurological diseases, leveraging a heterogeneous graph transformer trained on a comprehensive biomedical knowledge graph.

CVPack is a Python package designed for use with OpenMM that offers pre-defined collective variables to enhance sampling in molecular dynamics simulations. It allows users to project molecular systems onto lower-dimensional spaces, facilitating the exploration of configuration spaces and the characterization of molecular states.

The 'koopmans' repository provides an implementation of Koopmans-compliant functionals for performing spectral functional calculations using Quantum ESPRESSO. It facilitates advanced electronic structure calculations relevant to molecular properties and simulations.

ADMET-PrInt is a tool designed to predict and interpret ADMET properties such as membrane permeability and solubility using multiple machine learning models. It provides a framework for evaluating these properties as part of the drug design process.

MasterMSM is a Python package designed for constructing Markov state models from molecular dynamics simulations. It allows users to analyze biomolecular trajectories, calculate rate matrices, and perform sensitivity analysis, making it a valuable tool in the field of molecular modeling.

ClayCode is a Python package designed to automate the setup of atomistic clay models for classical molecular dynamics simulations using GROMACS. It facilitates the modeling of clay systems, making it easier for researchers to conduct molecular simulations in this specific area.

SaLT&PepPr is a language model designed to create peptide-guided protein degraders for targeting undruggable proteins. It utilizes a sequence-based framework to select peptides for therapeutic intervention without requiring structural information.

GPCNDTA is a tool designed for predicting drug-target binding affinity using cross-attention networks enhanced with graph features and pharmacophores. It includes benchmark datasets for training and evaluation, making it suitable for drug discovery applications.

Sfcnn is a scoring function model that utilizes a 3D convolutional neural network to predict protein-ligand binding affinities. It is trained on various datasets and can be used for rescoring docking results, making it a valuable tool in drug discovery.

DRACO is an open-source framework that enhances solvation models by dynamically adjusting atomic radii based on precomputed charges and coordination numbers. It is compatible with various quantum chemistry programs, allowing for improved solute cavity performance in molecular simulations.

Mol.dev is a web application that utilizes deep ensemble and RNN models to predict the properties of small molecules, specifically solubility, directly on endpoint devices. It allows users to input molecular representations in SMILES or SELFIES format and provides predictions along with uncertainty estimates.

EnsembleFlex is a software tool designed for the flexibility analysis of protein structure ensembles. It allows users to analyze monomeric protein structures, perform binding site analysis, and predict flexibility using various methods, all through a user-friendly graphical interface.

This repository contains scripts for designing proteins by utilizing the TrRosetta neural network to generate scaffolds for functional motifs. It includes methods for folding design models and scoring the generated designs, making it a valuable tool for protein engineering.

CL&Pol is a tool designed for simulating polarisable force fields specifically for ionic liquids. It includes scripts for adding Drude induced dipoles, scaling Lennard-Jones interactions, and modifying force field parameters, making it useful for molecular dynamics simulations.

The MaxEnt repository provides a Keras implementation of maximum entropy simulation-based inference, allowing users to reweight outcomes from simulators to align with observed data. This method is particularly useful in scenarios with high complexity and limited data, making it applicable in molecular simulations and related fields.

DockBox is a Python wrapper library that simplifies the use of popular docking software for molecular docking tasks. It supports multiple docking programs and provides functionalities for rescoring and analyzing docking poses, making it a valuable tool for molecular modeling and drug discovery.