/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.

DyScore is an open-source tool that implements a scoring method for identifying true binders and non-binders in drug discovery. It utilizes molecular docking and dynamic feature generation to predict the binding likelihood of compounds to target proteins.

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.

The SMILES Featurizers repository offers a set of tools to extract molecular embeddings from SMILES strings using pre-trained language models like BERT and BART. This functionality is useful for applications in molecular property prediction and virtual screening.

Uni-Dock-Benchmarks is a repository that contains a curated collection of datasets and benchmarking tests for assessing the performance and accuracy of the Uni-Dock docking system. It includes prepared structures and input files for both molecular docking and virtual screening, making it a valuable resource for researchers in computational chemistry.

DeepLBVS is a tool for ligand-based virtual screening that utilizes deep learning techniques to predict molecular properties. It generates ECFP fingerprints and performs cross-validation using RandomForest models to assess assay results, making it useful for drug discovery applications.

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.

PDB-CAT is a Jupyter Notebook tool designed to automatically categorize PDB structures based on the type of interaction between proteins and ligands, while also checking for mutations in the protein sequence. It facilitates decision-making in drug discovery by providing clear classifications and outputs for protein-ligand interactions.

Zinc-Million is a tool that allows users to download millions of small molecules from the ZINC database in 3D SDF format. It is designed for large-scale virtual screening against specific protein targets, making it useful for drug discovery and molecular simulations.

ECIFGraph is a tool designed to predict protein-ligand binding affinities by utilizing a water network-augmented two-state model. It integrates deep learning techniques to enhance the accuracy of scoring functions in molecular docking and virtual screening applications.

The Tox21 dataset repository contains data used in the Tox21 Data Challenge for evaluating the toxicity of compounds. It includes lists of compounds, their activity, and descriptors, facilitating in silico toxicity prediction and compound prioritization.

OCEAN is a web-based tool that predicts the target activity of chemical structures using data from the ChEMBL database. It allows users to input molecular structures and receive predictions on their biological activity, making it a valuable resource in drug discovery.

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.

This repository contains computational models that identify potential drugs for repurposing against SARS-CoV-2 by utilizing QSAR models and virtual screening techniques. It specifically targets Mpro inhibitors and includes curated data and predictions for FDA approved and experimental drugs.

ConveyorLC is a parallel virtual screening pipeline designed for docking and MM/GBSA calculations. It facilitates the preparation of receptors and ligands, as well as the execution of docking simulations, making it a valuable tool for drug discovery and molecular modeling.

MUBDsyn is a computational tool designed to create synthetic Maximal Unbiased Benchmarking Datasets for virtual screening. It utilizes deep reinforcement learning to generate virtual molecules, enhancing the process of molecular design and evaluation.

RiFF is a tool for reaction-informed fusion of molecular fragments, allowing users to combine fragments based on specific criteria and perform docking simulations. It includes scripts for embedding pharmacophores and running virtual screening jobs, making it relevant for molecular design and drug discovery.

This repository provides course materials for a class on chemo-informatics and computational drug design at the University of Antwerp. It covers various topics related to drug discovery, molecular dynamics, and cheminformatics, making it a valuable resource for learning about molecular tools.

GGAP-CPI is a tool designed for predicting compound-protein interactions while addressing challenges such as activity cliffs in bioactivity data. It includes a comprehensive dataset and model for assessing binding affinities, making it useful for virtual drug screening applications.

The 'pria_lifechem' repository provides tools for virtual screening of compounds against specific molecular targets using neural networks. It includes datasets for high-throughput screening and scripts for model training and evaluation, making it a valuable resource for researchers in computational chemistry and drug discovery.

MolecularDockingTutorials offers scripts for performing molecular docking, focusing on virtual screening studies for drug discovery. It includes tools like AutoDock and AutoDock Vina, facilitating the analysis of ligand interactions with target proteins.

VSpipe is a software pipeline that facilitates virtual screenings, particularly focusing on protein docking. It is designed to help researchers in the field of drug discovery by enabling the selection of potential hits for further investigation.

This repository contains code for enhanced Thompson Sampling and Roulette Wheel Selection methods for screening large combinatorial libraries. It facilitates the evaluation of molecular properties through shape-based virtual screening, making it a useful tool in drug discovery.

This repository contains data and methods for predicting the binding of small molecule ligands to RNA using structural interaction fingerprints and machine learning techniques. It includes datasets for active and inactive ligands, docking poses, and results from various machine learning models, making it a valuable resource for virtual screening in drug discovery.