/tools

This repository offers educational materials for a course on drug discovery computing techniques, covering various topics such as molecular dynamics, docking, and solubility. It aims to provide both course-specific resources and broader educational content for the community.

ChatDrug is a tool for conversational drug editing that utilizes retrieval and domain feedback to assist in the design and modification of small molecules, peptides, and proteins. It includes datasets for training and evaluation, making it a comprehensive resource for drug discovery.

NoLabs is an open-source biolab that facilitates experiments in bioinformatics and drug discovery. It includes features for protein design, molecular simulations, and a workflow engine to manage various bioinformatics tasks.

DeepAffinity is a deep learning model that predicts the affinity between proteins and compounds by integrating recurrent and convolutional neural networks. It utilizes both labeled and unlabeled data to enhance prediction accuracy and interpretability in drug discovery.

TransformerCPI is a tool designed to improve the prediction of compound-protein interactions through a sequence-based deep learning approach utilizing self-attention mechanisms. It includes datasets and trained models to facilitate drug-target identification and virtual screening.

MolMapNet is a deep learning framework that utilizes knowledge-based molecular representations to predict molecular properties. It provides tools for feature extraction, distance calculation, and visualization, making it suitable for tasks in drug discovery and molecular property prediction.

ConPLex is a tool that utilizes deep learning and protein language models to predict interactions between drugs and protein targets. It aims to enhance drug discovery by providing accurate predictions at scale, leveraging contrastive learning techniques.

BindFlow is a snakemake-based workflow that facilitates the calculation of absolute and relative binding free energies using GROMACS. It is particularly useful for researchers in drug design and molecular simulations, providing a structured approach to perform complex calculations efficiently.

The ATOM Modeling PipeLine (AMPL) is an open-source software pipeline that facilitates data curation, model building, and molecular property prediction to enhance in silico drug discovery efforts. It supports various machine learning techniques and has been benchmarked on extensive pharmaceutical datasets.

chemCPA is a tool designed to predict cellular responses to novel drug perturbations at a single-cell resolution. It includes code for model training, data processing, and utilizes various molecular embedding models to enhance drug discovery efforts.

MolCRAFT is a series of projects aimed at developing deep learning models for structure-based drug design and molecule optimization. It introduces novel methodologies for generating molecules with high binding affinity and stable 3D conformations, addressing critical challenges in the field.

Summit is a set of tools designed for optimizing chemical processes, particularly reactions, using machine learning techniques. It includes various optimization strategies and benchmarks to enhance the efficiency of reaction optimization in the fine chemicals industry.

DrugFlow is a generative model designed for structure-based drug design, integrating advanced techniques to learn chemical and physical properties from protein-ligand data. It allows for the generation of novel molecules tailored to specific protein targets, enhancing the drug discovery process.

DrugAssist is a large language model aimed at optimizing molecules, making it a valuable tool in drug discovery. It includes a dataset for training and facilitates the generation and optimization of molecular structures.

This repository provides a conditional graph-based molecule generator designed for multi-objective de novo drug design. It allows users to generate molecules with controlled properties using a generative model, making it a valuable tool for drug discovery.

PANDORA is a research platform designed for high-dimensional data analysis in biomedical research, facilitating predictive modeling and biomarker discovery. It leverages advanced statistical methodologies to provide insights into systems biology and drug discovery.

BFEE2 is a Python-based software designed for automating absolute binding free energy calculations using molecular dynamics simulations. It supports both alchemical and geometric routes for evaluating binding affinities in protein-ligand and protein-protein systems.

Tangelo is an open-source Python package that facilitates end-to-end chemistry workflows on quantum computers. It supports the design of quantum experiments and integrates with various quantum chemistry packages, making it suitable for molecular simulations and drug discovery applications.

KarmaDock is a deep learning tool for ligand docking that enhances the speed and accuracy of predicting binding poses and affinities. It integrates advanced graph neural networks to model protein-ligand interactions and has been validated on benchmark datasets for drug discovery applications.

Chemprop is a tool designed for guided molecular property prediction and discovery using evidential deep learning techniques. It enables uncertainty quantification in predictions, facilitating better optimization and virtual screening in drug discovery.

Uni-GBSA is an automatic workflow designed to perform MM/GB(PB)SA calculations for evaluating ligand binding free energies in virtual screening. It includes functionalities for topology preparation, structure optimization, and batch processing of multiple ligands against a protein target.

PSICHIC is a physicochemical graph neural network designed to learn protein-ligand interaction fingerprints from sequence data. It enables quick virtual screening and deep analysis of molecular interactions, making it a valuable tool for drug discovery.

The Deep Docking protocol is a deep learning-based tool that accelerates docking-based virtual screening, allowing researchers to screen extensive chemical libraries significantly faster than traditional methods. It integrates various stages of molecular preparation, docking, and model training to identify potential drug candidates effectively.

dyMEAN is a tool for end-to-end full-atom antibody design, enabling the generation and optimization of antibody structures based on specific epitope definitions. It includes functionalities for complex structure prediction and affinity optimization, making it a valuable resource in drug discovery and protein design.