/tools

BIND is a tool that leverages protein-language models for virtual screening of ligand-protein interactions without requiring 3D structural information. It utilizes graph neural networks to enhance the identification of true binders from non-binders, making it useful in computer-aided drug design.

The homebrew-cheminformatics repository offers a collection of cheminformatics formulae for the Homebrew package manager, allowing users to easily install various molecular modeling tools like RDKit and Open Babel. These tools are essential for tasks such as predicting molecular properties and performing simulations.

The DrugHunting repository provides Python scripts for automating drug discovery processes, including the design and optimization of drug-like molecules. It utilizes stochastic methods and cheminformatics to explore novel chemical spaces, making it suitable for applications like docking and virtual screening.

TTMD is a Python tool designed to automate the execution of Thermal Titration Molecular Dynamics simulations. It facilitates the analysis of protein-ligand complex stability and supports various molecular formats, making it useful for researchers in computational chemistry and molecular biology.

AnnapuRNA is a scoring function that evaluates RNA-ligand complex structures generated by computational docking methods. It provides a framework for predicting the interactions between RNA and small molecules, making it useful for drug discovery and molecular design.

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.

Syndirella is a tool designed for generating and scoring synthetically tractable elaborations of molecules derived from fragment screens. It utilizes retrosynthetic analysis and energy minimization to produce viable synthetic routes for small molecules.

The SMARTS-RX project provides tools for generating and managing molecular representations using SMARTS notation. It facilitates the classification and identification of various molecular types, making it useful for cheminformatics applications.

Dragonfly_gen is a tool for de novo drug design that utilizes deep interactome learning to generate novel molecules based on predefined properties. It allows users to preprocess data, sample from binding sites, and rank generated molecules based on pharmacophore similarity.

DiffIUPAC is a diffusion-based generative model that facilitates molecular editing by converting chemical natural language (IUPAC names) to SMILES strings. It aims to enhance molecular design and optimization, demonstrating applicability in drug design through various case studies.

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.

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.

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.

The 'mol-ellipsize' tool calculates the size of molecules by fitting an ellipsoid around their van der Waals cloud based on multiple conformers. It utilizes RDKit for generating conformer ensembles and provides functionality for molecular size analysis, making it useful in computational chemistry applications.

ChemBounce is a Python tool that facilitates scaffold hopping by generating new molecular structures based on input SMILES. It uses pre-computed fingerprints for efficient similarity searches and allows users to customize scaffold databases for enhanced performance.

DockCoV2 is a molecular docking pipeline that facilitates the prediction of binding affinities between FDA-approved drugs and SARS-CoV-2 proteins. It provides a comprehensive drug database and allows users to download docking data for further analysis.

The QED (Quantitative Estimation of Drug-likeness) module calculates a molecular descriptor that reflects the drug-likeness of compounds based on various molecular properties. It utilizes RDKit for cheminformatics and provides different weighting schemes for QED calculations.

This repository provides tools for exhaustive exploration of chemical space using a transformer model. It includes functionalities for generating molecular structures, preprocessing datasets, and computing molecular fingerprints, making it a valuable resource for molecular design and cheminformatics.

LAGNet is a neural network designed for better prediction of electron density, specifically optimized for drug-like small molecules. It includes implementations of various models for this purpose, contributing to the field of molecular property prediction.

LaplacianNB is a Python module for a Laplacian-modified Naive Bayes classifier optimized for binary/boolean molecular data. It integrates with RDKit for molecular fingerprint conversion and includes features for performance benchmarking and large-scale processing of molecular datasets.

AutoGrid is a software tool designed to precalculate grids used by docking programs like AutoDock. It helps predict the binding of small molecules to proteins, facilitating structure-based drug design and virtual screening.

Molecule-Generator is a Variational Autoencoder-based tool that generates synthetic SMILES strings for molecules composed of specific repeat units. It allows for the creation of a large dataset of molecular representations and facilitates the generation of new molecular structures through perturbation in the latent space.

ML Conformer Generator is a tool that utilizes Equivariant Diffusion Models and Graph Convolutional Networks to generate novel 3D molecular conformations that adhere to specific shape constraints. It supports workflows in molecular design by allowing the generation of molecules that are chemically valid and spatially similar to reference structures.

This repository contains code for generating molecular conformers using SO(3) Averaged Flow-Matching and Reflow techniques. It provides a framework for efficient conformer generation, which is essential in molecular design and optimization.