/tools

Torchchem is an experimental repository that offers high-quality tools for molecular machine learning with PyTorch. It focuses on various aspects of molecular modeling, including property prediction and molecular generation.

ANARCII is a generalized language model designed for numbering antigen receptor sequences. It provides a web tool and installation options for users interested in protein design and analysis.

This repository provides an implementation of AlphaFold 3 using PyTorch Lightning and Hydra, focusing on predicting protein structures from amino acid sequences. It includes functionalities for training and evaluating models that predict molecular structures, making it a valuable resource in the field of molecular biology.

The RDKit Tutorials repository offers a collection of Jupyter notebooks that guide users through various cheminformatics tasks using RDKit. It covers fundamental and advanced topics such as property calculations, QSAR modeling, and molecular structure manipulation, making it a valuable resource for those interested in molecular design and analysis.

ProtFlow is a Python package that facilitates the management of protein design workflows on computing clusters and local machines. It provides tools for configuring and running various protein design tools, making it a valuable resource for researchers in molecular biology.

GCP-VQVAE is a model that converts protein tertiary structures into discrete tokens using vector-quantized variational autoencoders. It enables the generation and evaluation of protein structures, achieving state-of-the-art performance on various benchmarks.

I-ReaxFF is a differentiable framework for the Reactive Force Field (ReaxFF) based on TensorFlow, allowing for the optimization of ReaxFF parameters using machine learning techniques. It facilitates molecular simulations by providing first and higher-order derivatives of energies, which are essential for various computational chemistry applications.

LatentDE is a tool for protein sequence design that utilizes a latent-based directed evolution approach. It employs a variational autoencoder to optimize biological functionalities by exploring high-fitness mutants in the latent space, making it suitable for protein engineering tasks.

Build Your Agent is an open-source initiative that provides a collection of intelligent agents designed for scientific research, focusing on materials property prediction and drug discovery. It aims to facilitate the development and deployment of AI-powered tools for various research workflows.

Ambertools-OpenMM-MD is a repository designed to facilitate molecular dynamics simulations of protein-ligand complexes, particularly for beginners. It utilizes Ambertools and OpenMM to streamline the simulation process and includes resources for analyzing protein-ligand interactions.

AA-Score is a tool that predicts protein-ligand binding affinity using an empirical scoring function based on various interaction components. It is utilized in virtual screening and lead optimization within the field of computer-aided drug discovery.

This repository provides tools for predicting binding affinity and generating kinase inhibitors using active site sequence representations. It includes scripts for training models and optimizing molecular structures based on predicted affinities.

The af_backprop repository contains modifications to AlphaFold that enable backpropagation through the model, facilitating advancements in protein design. It is associated with projects that enhance protein design accessibility and improve sequence alignment methods.

TFTraj is a tool for analyzing molecular dynamics trajectories using TensorFlow, specifically implementing routines for calculating root-mean-square deviation (RMSD). It includes benchmarks for performance comparison with other methods, making it useful for researchers in molecular simulations.

OPLSAA-DB is a database containing hand-built OPLS-AA parameters and topologies for 464 molecules, facilitating molecular simulations across various platforms such as OpenMM, Gromacs, and NAMD. It serves as a resource for researchers working on molecular dynamics and simulations in computational chemistry.

ABT-MPNN is a software tool that implements an atom-bond transformer-based message passing neural network for predicting molecular properties. It provides functionalities for training models, making predictions, and visualizing attention weights, making it a valuable resource for molecular property prediction tasks.

pNeRF is a parallelized implementation of the NeRF method designed to convert polymer parameterizations from internal coordinates to Cartesian coordinates, specifically for proteins. It enhances computational efficiency for machine learning applications in molecular dynamics and simulations.

PyMOL Remote is a Python package that allows users to send commands and data to and from PyMOL, a molecular visualization tool. It enables remote procedure calls between a client and a PyMOL server, facilitating molecular design and analysis workflows.

OpenPharmaco is an open-source software designed for fully-automated protein-based pharmacophore modeling and high-throughput virtual screening. It utilizes deep learning techniques to enhance the pharmacophore modeling process, making it suitable for drug discovery applications.

AutoPeptideML is an AutoML system designed to help researchers build trustworthy models for predicting peptide bioactivity. It provides tools for model building, prediction, and benchmarking, making it accessible for users without prior machine learning expertise.

This repository contains modular components designed for cheminformatics and computational chemistry, allowing users to create data processing pipelines. It leverages RDKit for various cheminformatics functionalities, making it suitable for tasks related to molecular property prediction and simulations.

This repository contains Dockerfiles for building lightweight RDKit images, which are used for cheminformatics tasks such as molecular property prediction and manipulation. It facilitates the use of RDKit in cloud environments, making it easier to deploy molecular modeling applications.

MSAGPT is a protein language model designed for predicting protein structures through multiple sequence alignment (MSA) generation. It achieves state-of-the-art performance in scenarios where natural MSAs are scarce, making it a valuable tool for protein design and analysis.