/tools

MOFid is a system designed for the rapid identification and analysis of metal-organic frameworks. It provides tools for researchers to analyze these materials, which are significant in various applications including catalysis and gas storage.

Gaussium is a quantum chemistry program written in Python that implements several electronic structure methods, including DFT and CCSD. It allows users to perform calculations on molecular systems, making it a valuable tool for computational chemistry.

GraDe_IF implements a graph denoising diffusion model for inverse protein folding, allowing for the generation of protein sequences based on structural information. It utilizes advanced machine learning techniques to optimize the design of proteins, making it a valuable tool in molecular biology.

Maize is a graph-based workflow manager that allows users to define and execute complex computational chemistry pipelines. It supports arbitrary graph topologies and task dependencies, making it suitable for various molecular applications.

PocketVina is a GPU-accelerated software for protein-ligand docking that automates the detection of binding pockets and evaluates interactions between proteins and ligands. It aims to enhance the accuracy and efficiency of docking processes in drug discovery.

SchNOrb is a tool that integrates machine learning with quantum chemistry to develop deep neural networks for accurately representing molecular wavefunctions. This approach can enhance the prediction of molecular properties and facilitate simulations in computational chemistry.

This repository provides a PyTorch implementation of a variational autoencoder designed for automatic chemical design. It focuses on generating continuous representations of molecules, which can be utilized for drug discovery and molecular optimization.

OpenFermion-FQE is a fermionic circuit simulator designed for quantum simulations, specifically emulating fermion dynamics. It provides tools for researchers in quantum chemistry to simulate state evolutions under fermionic generators.

HartreeFock is a program that implements the Hartree-Fock self-consistent field method along with other quantum chemistry techniques. It allows users to compute molecular properties and perform simulations for various molecular systems using Gaussian orbitals.

PatentChem is a tool that downloads USPTO patents and extracts molecules related to specified keyword queries. It processes patent claims to find and output SMILES strings of relevant molecules, making it useful for cheminformatics and molecular data extraction.

Kallisto is a tool designed for the efficient calculation of atomic features from molecular geometries, aiding in quantitative structure-activity relationship modeling. It includes various modeling tools for molecular geometry analysis and is developed in Python.

PGMG is a PyTorch implementation that utilizes a pharmacophore-guided deep learning model to generate bioactive molecules with structural diversity. It allows users to input pharmacophore hypotheses and generates a large number of candidate molecules that meet specified conditions.

Optimas is a framework designed for the end-to-end optimization of compound AI systems, utilizing Globally Aligned Local Reward Functions to enhance the performance of various components. It supports the generation of preference data, training of reward models, and optimization of system variables, making it applicable to molecular design and optimization tasks.

rDock is a fast and versatile open-source docking program that facilitates the docking of small molecules to proteins and nucleic acids. It is particularly useful for high-throughput virtual screening campaigns and binding mode prediction studies.

This repository contains code for a deep generative model aimed at generating molecular fragments, as presented in the AISTATS 2020 paper. It includes functionalities for data preprocessing, model training, sampling, and postprocessing, making it a useful tool for molecular design.

This repository serves as a companion to the book 'Machine Learning for Drug Discovery', providing code and data for various machine learning techniques applied to drug discovery. It covers topics such as ligand-based screening, generative models for de novo design, and structure-based drug design, making it a valuable resource for researchers in the field.

PROPhet is a software that combines neural networks with first-principles quantum chemistry methods to predict material properties. It allows for the mapping of atomic configurations to various properties and can be used for molecular dynamics simulations with LAMMPS.

py2Dmol is a Python library designed for visualizing protein, DNA, and RNA structures in 2D, suitable for use in Google Colab and Jupyter notebooks. It allows users to load and display molecular structures interactively, making it a useful tool for molecular representation.

Matcher is a web application that facilitates the exploration of structure/activity relationships derived from large datasets, enabling users to optimize chemical structures for drug design. It is built on the mmpdb platform and provides a user-friendly interface for querying and analyzing molecular data.

GeminiMol is a molecular representation model that enhances molecular feature extraction by incorporating conformational space profiles. It is designed for applications in drug discovery, including virtual screening, target identification, and quantitative structure-activity relationship (QSAR) modeling.

PrismNet is a deep learning framework designed to predict dynamic cellular protein-RNA interactions by utilizing in vivo RNA structure. It includes scripts for training models, evaluating performance, and preparing datasets for research in molecular biology.

Surfaxe is a Python package designed to automate the generation of surface slabs and facilitate density functional theory (DFT) calculations for surface properties. It provides tools for data processing, analysis, and visualization of results related to surface and bulk calculations in computational chemistry.

μProtein is a framework that accelerates protein engineering by integrating a deep learning model for predicting mutational effects with a reinforcement learning algorithm for navigating the protein fitness landscape. It aims to enhance the design and optimization of proteins through advanced computational techniques.

SkipGNN is a tool designed to predict molecular interactions by leveraging skip-graph networks, which consider both direct and second-order interactions in molecular networks. It provides datasets for drug-target and drug-drug interactions, making it useful for applications in drug discovery and molecular property prediction.