/tools

The schnetpack-gschnet repository provides an extension for generating 3D molecular structures using a conditional generative neural network. It allows for targeted molecule generation by conditioning on chemical and structural properties, making it a valuable tool for molecular design.

The 'timed-design' repository provides a library for protein sequence design using deep learning models. It includes functionalities for predicting protein sequences based on 3D structures and sampling sequences using Monte Carlo methods, making it a valuable tool for molecular biology and computational chemistry.

pyCOFBuilder is a Python package designed for the automated assembly of Covalent Organic Framework structures using a reticular approach. It allows users to generate a variety of COF structures based on specified building blocks and functional groups, facilitating high-throughput molecular design.

DiffCSP-PP is an implementation for generating crystal structures constrained by space groups. It includes functionalities for training models on datasets and evaluating crystal structure predictions, making it a useful tool for molecular design and generation in materials science.

Evolla is a generative model designed to decode the molecular language of proteins, facilitating the generation and understanding of protein sequences. It provides tools for protein design and can be utilized for various applications in molecular biology.

ProteinSolver is a deep neural network tool designed to generate amino acid sequences that can fold into specific protein structures. It utilizes graph neural networks to tackle protein design challenges, making it a valuable resource in the field of bioinformatics.

MOFDiff is a diffusion model designed for generating coarse-grained structures of metal-organic frameworks (MOFs). It includes functionalities for optimizing these structures based on specific properties and simulating their behavior in gas adsorption scenarios.

PepINVENT is a generative reinforcement learning framework for designing peptides, including both natural and non-natural amino acids. It allows users to specify objectives for peptide generation and optimization, making it applicable for peptide-based drug design and development.

The 'salad' repository provides a framework for generating protein structures using sparse all-atom denoising models. It allows for various protein design tasks, including unconditional generation and motif scaffolding, leveraging advanced machine learning techniques.

The 'walk-jump' repository provides an implementation of discrete Walk-Jump Sampling (dWJS) for training and sampling in protein design. It includes functionalities for evaluating large molecule descriptors and assessing sample quality, making it a valuable tool in molecular design and optimization.

OMTRA is a multi-task generative model that facilitates structure-based drug design by generating novel molecules and performing protein-ligand docking. It supports various tasks including unconditional and conditioned generation of ligands, making it a valuable tool in computational chemistry and drug discovery.

GraphRetro is a tool designed for predicting retrosynthesis pathways using graph models. It employs a two-stage process to transform product molecules back to their reactants, making it useful for molecular design and synthesis planning.

FrameDiPT is a tool that utilizes an SE(3) diffusion model for protein structure inpainting and de novo design. It allows for the generation of protein backbones and evaluates their structural properties, making it a valuable resource in molecular biology and computational chemistry.

FASMIFRA is a tool for generating molecules quickly from a training set of molecular fragments using a method that matches the distribution of the training set. It also includes functionality for fragmenting molecules and has been evaluated in the GuacaMol benchmark for molecular generation methods.

Equiformer Diffusion is an implementation of denoising diffusion specifically aimed at protein design, utilizing the Equiformer architecture. It incorporates advanced techniques for generating and optimizing protein structures, making it a valuable tool in molecular design.

Lo-Hi Splitter is a tool designed for partitioning molecular datasets to facilitate drug discovery tasks such as lead optimization and hit identification. It employs methods to ensure that training and test sets are distinct, improving the predictive performance of models in drug discovery applications.

AaronTools.py is a Python library designed to automate routine tasks in quantum chemistry computations. It offers features for generating molecular structures, calculating steric parameters, and setting up quantum computation processes, making it a valuable tool for computational chemists.

LifeBrush is a VR toolkit that allows users to create and simulate biomolecular environments using a generative brush for painting molecular structures. It employs an agent-based modeling framework to visualize and interact with molecular dynamics in a 3D space.

This tool utilizes neural machine translation techniques to predict the outcomes of organic chemistry reactions based on known reactants. It employs an attention mechanism to enhance the prediction accuracy and provides a graphical user interface for user interaction.

MolSnapper is a software tool that utilizes a conditioned diffusion model to generate 3D drug-like molecules. It is built on the MolDiff framework and is aimed at aiding in structure-based drug design.

Metis is a Python-based GUI designed to collect expert feedback on small molecules, facilitating the training of generative models for drug discovery. It supports de novo design and integrates with existing generative chemistry frameworks to enhance molecular design processes.

LDM-3DG implements a pipeline for latent 3D graph diffusion, enabling the generation and evaluation of molecular structures. It includes functionalities for training models on molecular data and generating embeddings for small molecules, making it a valuable tool for molecular design and docking applications.

RamaNet is a tool that utilizes machine learning and PyRosetta to autonomously generate novel helical protein structures. It performs de novo design by creating a topology and optimizing the sequence to fit, while also providing datasets for training the neural network.

RiboDiffusion is a tool for tertiary structure-based RNA inverse folding utilizing generative diffusion models. It allows users to generate RNA sequences from given PDB structures, facilitating molecular design and exploration in RNA biology.