/tools

PaddleHelix is a bio-computing platform that leverages deep learning for drug discovery, vaccine design, and precision medicine. It offers various applications including molecular property prediction, drug-target interaction prediction, and molecular generation, along with advanced protein structure prediction capabilities.

This repository contains input files and datasets for the Folding@home efforts to understand and target the SARS-CoV-2 virus with small molecule and antibody therapeutics. It supports molecular dynamics simulations and provides resources for researchers working on COVID-19 related molecular studies.

CP2K is a quantum chemistry and solid state physics software package that enables atomistic simulations of various systems, including molecular and biological ones. It supports multiple modeling methods and can perform simulations such as molecular dynamics, energy minimization, and transition state optimization.

Uni-Mol is a universal 3D molecular representation learning framework that supports various tasks such as molecular property prediction, binding pose prediction, and quantum chemical property prediction. It includes tools for molecular representation and docking, demonstrating state-of-the-art performance in these areas.

BindCraft is a user-friendly pipeline for designing protein binders using advanced techniques like AlphaFold2 backpropagation and MPNN. It allows users to specify targets and generates multiple binder designs for experimental characterization.

OpenBioMed is a Python deep learning toolkit designed for AI-empowered biomedicine, offering flexible APIs and over 20 tools for various applications including molecular property prediction, protein folding, and docking. It supports a wide range of molecular types and provides a unified data processing pipeline for handling multi-modal biomedical data.

TeachOpenCADD is a teaching platform designed to educate users on computer-aided drug design (CADD) through interactive Jupyter Notebooks. It covers various topics in cheminformatics and structural bioinformatics, providing practical examples and resources for students and researchers in the field.

MOSES is a benchmarking platform for molecular generation models that facilitates research in drug discovery by providing datasets and metrics to evaluate the quality and diversity of generated molecules. It implements various generative models and standardizes the evaluation process for molecular generation.

3Dmol.js is a WebGL accelerated JavaScript library designed for online molecular visualization. It supports various molecular file formats and allows users to create interactive and visually appealing representations of molecular structures in web applications.

SimpleFold is a protein folding model that utilizes a generative flow-matching approach to predict protein structures from sequences. It is designed to be efficient and scalable, achieving competitive performance on standard folding benchmarks.

ToolUniverse is a platform that democratizes the creation of AI scientists by integrating a wide range of machine learning models, datasets, and scientific tools. It enables users to perform tasks related to molecular property prediction, molecular design, and scientific workflows, making it a versatile tool in computational chemistry and molecular biology.

The 'tf-gnn-samples' repository provides TensorFlow implementations of various Graph Neural Network architectures. It includes tasks related to molecular property prediction, such as protein-protein interactions and quantum chemistry, making it a useful resource for researchers in computational chemistry and molecular biology.

This repository provides a comprehensive list of papers and resources related to molecular and material design using generative AI and deep learning techniques. It covers various methodologies for drug design, molecular optimization, and includes datasets and benchmarks relevant to the field.

AutoDock Vina is a fast and widely used open-source docking program that facilitates the docking of ligands to macromolecules. It supports multiple ligands and batch mode for virtual screening, making it a valuable tool in computational drug discovery.

ProteinNet is a standardized dataset designed for machine learning of protein structures, offering sequences, structures, and multiple sequence alignments. It aims to facilitate research in protein structure prediction by providing a consistent framework for training and validation across various methods.

SchNetPack is a toolbox that facilitates the development and application of deep neural networks for predicting quantum-chemical properties and potential energy surfaces of molecules and materials. It includes features for training models on benchmark datasets and supports molecular dynamics simulations, making it a comprehensive tool for atomistic machine learning.

ColabDesign is a tool that makes protein design accessible through Google Colab, utilizing models like TrRosetta and AlphaFold for generating and optimizing protein structures based on sequences. It provides various functionalities for predicting protein structures and sequences, making it a valuable resource in the field of molecular biology.

ChemCrow is an open-source package that augments large language models with chemical tools to solve complex chemical tasks. It integrates various databases and APIs to assist in predicting molecular properties and generating chemical reactions.

GROMACS is a powerful molecular simulation toolkit that allows users to perform molecular dynamics simulations efficiently. It is widely used in the field of computational chemistry for studying the behavior of biomolecules and materials at the atomic level.

NequIP is an open-source framework for constructing E(3)-equivariant interatomic potentials, enabling accurate molecular simulations. It supports multi-GPU training and integrates with existing molecular dynamics software, making it a valuable tool for researchers in computational chemistry and materials science.

Gnina is a molecular docking program that utilizes deep learning techniques, particularly convolutional neural networks, to score and optimize ligand interactions with protein receptors. It is built on top of existing docking software and aims to enhance the accuracy and efficiency of molecular docking processes.

BoltzGen is a tool for designing and generating protein structures based on specified design criteria. It utilizes advanced algorithms to produce ranked sets of protein designs, facilitating the exploration of novel molecular architectures.

Open-AF3 is an open-source implementation of AlphaFold 3, a model that predicts the structures of biomolecules such as proteins. It utilizes advanced machine learning techniques to generate accurate structural predictions based on input sequences, making it a valuable tool for researchers in molecular biology.

DGL-LifeSci is a Python package designed for applying graph neural networks in chemistry and biology. It includes functionalities for molecular property prediction, reaction prediction, and various modeling tasks relevant to drug discovery.