/tools

MDeePred is a tool designed for predicting the binding affinity between bioactive small molecules and target proteins using a novel protein featurization approach. It employs deep learning techniques to enhance the accuracy of predictions, making it useful for drug discovery and repositioning efforts.

FRAME is a tool for fragment-based molecular expansion that utilizes geometric deep learning techniques to aid in structure-based ligand design. It allows for the addition of molecular fragments to a seed ligand, optimizing the design process for drug discovery.

This repository develops machine learning methods to predict adverse drug reactions (ADRs) using databases like SIDER and OFFSIDES. It provides tools and models that can be utilized in the drug discovery process to enhance safety and efficacy assessments.

NAMD-FEP is a tool designed for calculating the binding free energy difference between two small molecules interacting with the same protein target using free energy perturbation (FEP) methods. It provides a Jupyter Notebook tutorial for users to perform FEP simulations efficiently, leveraging cloud GPU resources.

LEADD is a tool that employs a Lamarckian evolutionary algorithm for the design and optimization of molecules in drug discovery. It utilizes a population-based approach to evolve molecular structures by combining fragments and optimizing them based on user-defined scoring functions.

ML-ensemble-docking is a tool designed to enhance structure-based virtual screening by utilizing ensemble docking methods combined with machine learning techniques. It evaluates the performance of various protein targets and improves ligand ranking through advanced predictive models.

DeepGS is a software tool designed for predicting drug-target binding affinity using deep representation learning techniques. It processes molecular and protein sequence data to generate predictions, making it a valuable resource in the field of drug discovery.

CASTER is a tool designed to predict drug interactions by utilizing chemical substructure representations. It provides a framework for understanding how different molecular structures can influence drug interactions, making it relevant for drug discovery efforts.

The Drug Design Data Resource (D3R) is a suite of software designed to facilitate the filtering and scoring of new molecular sequences. It supports participants in the CELPP challenge by providing necessary workflows and tools for molecular docking and analysis.

CAPLA is a deep learning tool designed to improve the prediction of protein-ligand binding affinity by utilizing a cross-attention mechanism. It aims to enhance the accuracy and speed of binding affinity predictions, which is crucial for drug development.

Screenlamp is a Python toolkit designed to facilitate ligand-based virtual screening workflows. It enables researchers to prioritize ligand candidates through hypothesis-driven filtering, contributing to drug discovery efforts.

MPEK is a multi-task learning tool that predicts enzyme turnover number (kcat) and Michaelis-Menten constant (Km) using enzyme sequences and substrate SMILES. It aims to enhance the evaluation of enzymatic efficiency and supports applications in biocatalysis and drug discovery.

Chem-Faiss is a tool that utilizes vector similarity search from Faiss combined with chemical fingerprinting to create a scalable architecture for searching compounds. It is particularly useful for drug design and finding structural matches within large datasets.

FEP-Minus is a free tool for performing free energy perturbation calculations, similar to the commercial FEP Plus software. It allows users to run these calculations on cloud platforms, making it accessible for academic research in drug design and molecular simulations.

The Computer_aided_drug_discovery_kit is a pipeline designed for virtual screening of pharmaceutical compounds using similarity-based and structure-based techniques. It includes modules for data extraction, descriptor calculation, and machine learning classification to predict the bioactivity of compounds.

The Automated QSAR Framework is designed for the curation of chemogenomics data and the development of predictive QSAR models using machine learning. It facilitates data preparation, chemical space analysis, and virtual screening, making it a valuable tool for drug discovery.

The 'vina_docking' repository contains Python scripts for performing molecular docking using AutoDock Vina. It allows users to preprocess receptor and ligand files, run docking simulations, and output results, making it a valuable tool for drug discovery and molecular interactions.

BiteNet is a computational tool that utilizes deep learning to identify druggable binding sites in proteins by analyzing their three-dimensional conformations. It offers functionalities for predicting binding sites and clustering predictions, making it valuable for drug discovery efforts.

CompassDock is a framework for deep learning-based molecular docking that evaluates binding affinities and protein-ligand interactions. It provides tools for assessing the physical and chemical properties of ligands and their bioactivity favorability.

The 'antibody-dl' repository is a collection of platforms, tools, and resources aimed at enhancing antibody engineering. It includes deep learning models for antibody design, structural prediction, and various databases that support antibody research and development.

This repository contains code for automatically extracting a dataset of interacting compound-target pairs from the ChEMBL database. It enables researchers to analyze drug-target interactions and supports future analyses in drug discovery.

DrugGen is a tool that enhances drug discovery by using large language models to generate drug-like SMILES structures from protein sequences. It employs reinforcement learning and supervised fine-tuning to ensure the generated structures are chemically valid and effective.

Drug_Design_Models is a reimplementation of various models for de novo drug design, utilizing techniques such as recurrent neural networks and graph convolutional networks. It aims to generate and optimize molecular structures based on established research in the field.

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.