/tools

Datamol is a Python library that simplifies molecular processing by providing a user-friendly API built on RDKit. It allows users to manipulate molecular structures, generate conformers, and visualize molecules, making it a valuable tool for cheminformatics and drug discovery.

bert-loves-chemistry is a repository that contains BERT-like models specifically designed for chemical SMILES data, aimed at drug design and chemical modeling. It includes pre-trained models for property prediction and is intended for use by researchers and developers in the field of computational chemistry.

DiffSBDD is an implementation of an equivariant diffusion model aimed at structure-based drug design. It allows users to generate new ligands, optimize existing molecules, and benchmark performance using various datasets, making it a comprehensive tool for molecular design and analysis.

ProLIF (Protein-Ligand Interaction Fingerprints) is a tool that generates interaction fingerprints for complexes involving ligands, proteins, DNA, or RNA. It utilizes data from molecular dynamics trajectories and docking simulations, making it valuable for drug discovery and cheminformatics.

Allegro is an open-source code that implements an E(3)-equivariant deep learning interatomic potential, enabling highly scalable and accurate molecular simulations. It integrates with the NequIP framework and supports LAMMPS for efficient atomistic simulations.

The Open Drug Discovery Toolkit (ODDT) is a modular toolkit for cheminformatics and molecular modeling, enabling users to perform tasks such as scoring, docking, and screening of drug candidates. It is built in Python and leverages libraries like RDKit and OpenBabel for enhanced molecular analysis.

P2Rank is a command-line tool that predicts ligand-binding sites from protein structures using machine learning techniques. It provides high accuracy in identifying potential binding pockets without relying on external databases, making it useful for drug discovery and virtual screening applications.

Pocket2Mol is a tool designed for efficient molecular sampling based on the 3D structures of protein pockets. It employs equivariant graph neural networks to improve the quality and efficiency of molecular generation, making it useful for structure-based drug design.

Indigo is a universal cheminformatics toolkit that includes a variety of utilities for chemistry search, molecule visualization, and SMILES generation. It supports multiple programming languages and is designed for applications in drug discovery and molecular analysis.

ReLeaSE is a tool that utilizes deep reinforcement learning to facilitate the de-novo design of drug molecules. It includes functionalities for optimizing molecular properties and generating new molecular structures based on learned patterns.

The SMILES Transformer is a tool that extracts molecular fingerprints from SMILES representations of chemical molecules. It utilizes a transformer architecture to learn latent representations useful for various downstream tasks in drug discovery.

Meeko is an interface for AutoDock that prepares input files for molecular docking and processes the output. It parameterizes both small organic molecules and biological macromolecules, facilitating drug discovery and molecular modeling.

The SE3-Transformer-PyTorch repository provides an implementation of SE3-Transformers for equivariant self-attention, specifically aimed at applications in protein structure prediction and drug discovery. It allows for the modeling of molecular interactions and features, making it a valuable tool in computational chemistry and molecular biology.

CBGBench is a benchmark tool for generative target-aware molecule design, integrating multiple state-of-the-art methods for generating molecules. It supports tasks such as linker design, fragment growing, and scaffold hopping, making it a valuable resource for researchers in drug discovery.

EquiformerV2 is a PyTorch implementation of an improved equivariant transformer designed for scaling to higher-degree representations in molecular systems. It is utilized for training on datasets related to energy and force predictions, making it a valuable tool in drug discovery and molecular dynamics simulations.

Bio is an open-source AI assistant designed for biomedical research, allowing users to access academic literature, clinical trials, and drug information through natural language queries. It also supports advanced analytics and pharmacokinetic modeling, making it a valuable resource for drug discovery and molecular property analysis.

DeepDTA is a tool designed for predicting the binding affinity between drugs and their target proteins using deep learning techniques. It utilizes convolutional neural networks to model protein sequences and molecular representations, making it relevant for drug discovery and molecular property prediction.

The Ersilia Model Hub is a platform that hosts pre-trained AI/ML models aimed at drug discovery, particularly for infectious and neglected diseases. It includes models for predicting antibiotic activity, ADMET properties, and generative chemistry, facilitating research in molecular biology and computational chemistry.

Jupyter Dock is a collection of Jupyter Notebooks that facilitate interactive molecular docking protocols, allowing users to visualize, convert file formats, and analyze docking results. It supports various docking methods and provides comprehensive protocols for different docking scenarios.

HTMD is a programmable platform for simulation-based molecular discovery, focusing on increasing reproducibility and solving data generation and analysis challenges in molecular simulations.

GeoLDM is a tool for generating 3D molecular structures using geometric latent diffusion models. It supports conditional generation based on molecular properties and includes capabilities for evaluating the quality of generated molecules, making it useful for applications in drug discovery.

Equiformer is a PyTorch implementation of a graph attention transformer that processes 3D atomistic graphs, aimed at improving molecular simulations and property predictions. It supports training on established datasets like QM9 and MD17, making it a valuable tool for drug discovery and molecular dynamics research.

TxGNN is a graph neural network model that predicts therapeutic opportunities for diseases using a comprehensive knowledge graph. It enables zero-shot inference for new diseases and can be trained on drug repurposing datasets, making it a valuable tool in drug discovery.

EquiDock is a tool designed for fast rigid protein-protein docking using independent SE(3)-equivariant models. It includes preprocessing steps for datasets and allows for training and inference of docking models, making it relevant for molecular simulations and drug discovery.