/tools

This repository provides a simple X11 molecular viewer that allows users to visualize molecular structures and vibrations. It supports multiple file formats and offers various command-line options for displaying molecular properties.

MolEnc is a molecular encoder that uses RDKit and OCaml to create chemical fingerprints, specifically the Signature Molecular Descriptor. It allows for encoding databases of molecules and can reuse feature dictionaries, making it useful for various molecular property prediction and design tasks.

The RDKit Blog repository appears to be a collection of Jupyter Notebooks focused on cheminformatics and computational chemistry topics. It likely includes tutorials and examples related to molecular analysis and property prediction using the RDKit toolkit.

The 'tutorial-lmp' repository offers step-by-step instructions for setting up and running molecular dynamics simulations with polarizable force fields in LAMMPS. It covers the creation of simulation boxes, equilibration, and the addition of explicit polarization terms, making it a valuable resource for those interested in molecular simulations.

ParticlesMC is a Julia package designed for performing atomic and molecular Monte Carlo simulations. It provides a user-friendly interface and supports various interaction potentials, making it suitable for both research and educational purposes in the field of molecular simulations.

Coulomb Galore is a C++ library that calculates the potential, field, forces, and interactions from electric multipoles. It offers fast alternatives to traditional methods like Ewald summation, making it useful for molecular simulations and dynamics.

ProteomeLM is a transformer-based language model that predicts protein-protein interactions and gene essentiality across various taxa. It processes entire proteomes, capturing inter-protein dependencies and enabling fast interaction analysis.

PRODIGY-LIG is a tool designed for predicting the binding affinities of protein-small molecule complexes. It utilizes a structure-based approach to calculate binding energy, making it useful for drug discovery and molecular interactions.

CCMgen and CCMpredPy provide a Python toolkit for generating realistic synthetic protein sequences using second-order Markov Random Field models. The tools allow for the sampling of protein-like sequences while adhering to evolutionary pressures, making them useful for protein design and analysis.

DeepSP is a deep learning-based model that generates 30 spatial properties of antibodies from their sequences. It provides a method for predicting structural characteristics that are crucial for understanding antibody stability.

MetalDock is an open-source software tool that facilitates the docking of metal-organic complexes with proteins, DNA, and other biomolecules. It is designed to support research in molecular interactions involving transition metals.

Genos is a collection of foundation models designed for genomic sequence analysis, capable of handling long sequences and providing insights into gene elements and regulatory interactions. It supports various genomic tasks, including mutation prediction and cross-species classification, making it a valuable tool for researchers in molecular biology.

GS-Meta is an implementation of a meta-learning framework designed for predicting molecular properties using graph sampling techniques. It includes datasets and models specifically tailored for molecular property prediction tasks.

This repository provides a Docker image that integrates the RDKit cartridge with PostgreSQL, enabling users to perform cheminformatics tasks and molecular property calculations within a database environment.

fpocketR is a command-line tool designed to analyze RNA structures and visualize drug-like RNA-ligand binding pockets. It provides functionalities for characterizing these pockets and supports various analysis workflows for RNA-ligand interactions.

This repository offers a Docker image that integrates PostgreSQL with the RDKit cartridge, enabling users to perform cheminformatics operations within a database environment. It facilitates the storage and querying of molecular data, making it useful for various molecular property predictions and analyses.

EvalRetro is a repository designed for evaluating single-step retrosynthesis algorithms. It allows users to test their own retrosynthetic predictions against benchmark datasets, facilitating the development and assessment of molecular generation models.

Joint_Model_Stability is a toolkit for protein design that utilizes joint TrROS/TrMRF models for zero-shot stability prediction. It includes functionalities for designing protein sequences and structures, leveraging pre-trained models like ESMFold and ProteinMPNN.

The paccmann_sarscov2 repository provides a pipeline for automating the discovery and synthesis of targeted molecules using machine learning. It includes models for predicting protein-ligand interactions, toxicity, and generative models for both proteins and small molecules.

NonadditivityAnalysis is a tool designed to analyze SAR datasets by identifying complex patterns and computing matched pairs from molecular structures. It processes input data to derive insights about nonadditivity in molecular interactions, making it useful for researchers in computational chemistry and drug discovery.

JAMUN is a tool that bridges smoothed molecular dynamics and score-based learning to efficiently generate conformational ensembles of peptides. It enhances the sampling of molecular dynamics by operating in a smoothed space, allowing for faster and more transferable results in molecular simulations.

ABACUS-agent-tools is a Python package that connects large language models to ABACUS computational jobs, facilitating the generation of molecular input files and execution of simulations. It supports various functions including molecular dynamics calculations, Bader charge analysis, and density of states calculations.

STARLING is a tool for predicting coarse-grained ensembles of intrinsically disordered proteins from their sequences using a generative model. It allows for the generation of multiple conformations and provides functionalities for analyzing and converting ensemble data.