/tools

GenAI4Drug is a survey repository that explores the use of generative AI techniques for de novo drug design, emphasizing the generation of molecules and proteins. It includes discussions on various models, datasets, and metrics relevant to molecular design and property prediction.

PandaDock is a next-generation molecular docking suite that combines advanced algorithms and GPU acceleration to achieve high-accuracy predictions of protein-ligand interactions. It is designed for applications in drug discovery and computational biology, offering various docking modes and scoring functions.

This repository implements a molecular generative model that utilizes randomized SMILES strings to create and train models for molecule generation. It provides scripts for model creation, training, sampling, and calculating log-likelihoods, facilitating de novo drug design.

DrugGEN is a generative system designed for the de novo creation of drug candidate molecules that are tailored to interact with specific protein targets. It utilizes graph transformer-based generative adversarial networks to generate and evaluate potential drug candidates.

The Benchmarking-Single-Cell-Perturbation repository provides a library of models for analyzing genetic and chemical perturbation data in single-cell contexts. It includes tools for predicting cellular responses to perturbations and offers datasets and benchmarks for evaluating model performance in drug discovery applications.

SumGNN is a tool designed for predicting multi-typed drug interactions by utilizing knowledge graph summarization techniques. It provides datasets and models for drug-drug interaction prediction, making it a valuable resource in the field of bioinformatics and drug discovery.

TypeDB Bio is an open-source biomedical knowledge graph designed to facilitate research in drug discovery, precision medicine, and drug repurposing. It allows researchers to query interconnected biomedical data, helping to identify potential drug targets and understand biological interactions.

This repository provides a codebase for designing molecules using structured state-space sequence models, enabling users to pre-train and fine-tune models for de novo drug design. It simplifies the process of generating new bioactive molecules with minimal code, making it a valuable tool for researchers in drug discovery.

PharmacoNet is an open-source tool for protein-based pharmacophore modeling that utilizes deep learning for ultra-large-scale virtual screening. It automates the evaluation of ligands and supports feature extraction for deep learning applications in drug discovery.

ShEPhERD is a diffusion generative model designed for bioisosteric drug design, capable of generating new molecules in their 3D conformations based on learned distributions of molecular structures. It includes functionalities for training and inference, making it a valuable tool for molecular design and optimization.

SECSE is a platform for systemic evolutionary chemical space exploration aimed at drug discovery. It utilizes deep learning and fragment-based design to generate novel small molecules, enhancing the hit-finding process in drug development.

QSPRpred is an open-source software library designed for creating QSPR/QSAR models, enabling researchers to predict molecular properties and activities. It provides a modular interface for building models using various descriptors and machine learning algorithms, facilitating drug discovery and cheminformatics research.

LigDream is a tool for generating novel molecules based on a reference shape using generative modeling techniques. It utilizes a dataset of drug-like compounds for training and allows for the generation of new compounds through a web interface or locally via Jupyter Notebooks.

PyAutoFEP is an automated workflow for Free Energy Perturbation (FEP) calculations using GROMACS, aimed at estimating the Relative Free Energies of Binding (RFEB) of small molecules to macromolecular targets. It integrates enhanced sampling methods and provides automation for various steps in the molecular dynamics setup and analysis.

MolDQN-pytorch is a PyTorch implementation of a deep reinforcement learning approach for optimizing molecular properties. It allows users to train models for property optimization tasks, making it a valuable tool in the field of molecular design and drug discovery.

The NVIDIA BioNeMo blueprint provides a framework for generative virtual screening in drug discovery, utilizing advanced AI models to design and optimize small molecules and predict protein-ligand interactions. It integrates various tools for protein structure prediction and molecular generation, facilitating efficient drug discovery workflows.

The 'AI in chemistry workshop' repository provides educational resources and hands-on sessions on applying AI and machine learning techniques in chemistry, particularly focusing on molecule generation and data exploration for drug discovery.

This tool implements a reinforced genetic algorithm for structure-based drug design, utilizing neural models to enhance the efficiency of molecular optimization. It aims to intelligently explore chemical space to identify potential drug candidates with improved binding affinity.

This repository provides an open-source solution for conducting computational studies in drug discovery using both quantum and classical computing resources. It includes sample code for various drug discovery problems, such as molecular docking and protein folding, facilitating research in these areas.

LitMatter is a template designed for rapid experimentation and scaling of deep learning models on molecular and crystal graphs. It supports various applications in drug discovery and molecular dynamics, allowing researchers to efficiently train models for predicting molecular properties and simulating molecular interactions.

The ChEMBL MCP Server is a comprehensive tool that facilitates drug discovery and cheminformatics analysis by providing access to the ChEMBL chemical database. It includes features for searching compounds, analyzing bioactivity data, and predicting molecular properties such as ADMET and solubility.

BALL is a Biochemical Algorithms Library that provides tools for molecular simulations, cheminformatics, and drug design. It supports various biochemical computations and is useful for researchers in computational biology and chemistry.

MXMNet is a molecular mechanics-driven graph neural network that utilizes multiplex graphs to analyze molecular structures. It is designed to predict various molecular properties and has applications in drug discovery.

gnina-torch is a PyTorch implementation of the GNINA scoring function, designed for molecular docking applications. It allows users to train and utilize deep learning models to predict protein-ligand interactions, enhancing the drug discovery process.