/tools

CatPred is a deep learning framework designed to predict in vitro enzyme kinetic parameters such as kcat, Km, and Ki. It provides tools for both training models and making predictions, facilitating research in enzyme kinetics and related molecular properties.

torch-pme is a library that enables efficient and auto-differentiable computation of long-range interactions in molecular systems using PyTorch. It supports various methods for calculating electrostatic interactions, making it suitable for applications in molecular dynamics and simulations.

Geometry-Deep-Learning-for-Drug-Discovery is a repository that explores the application of geometric deep learning methods in drug discovery and life sciences. It includes functionalities for predicting molecular properties, designing molecules, and provides datasets and benchmarks relevant to molecular machine learning.

PAMNet is a universal framework designed for accurate and efficient geometric deep learning of molecular systems. It excels in predicting molecular properties, such as binding affinities and RNA 3D structures, and utilizes graph neural networks to enhance performance in these tasks.

Faunus is a molecular simulation package designed for Metropolis Monte Carlo simulations of molecular systems. It supports various statistical mechanical ensembles and includes features for free energy sampling and parallel tempering.

TemStaPro is a program designed to predict the thermostability of proteins based on their sequences using embeddings from protein language models. It utilizes machine learning techniques to provide predictions that can aid in understanding protein stability across various temperatures.

FLAG is a framework for generating 3D molecules that bind to target proteins using a fragment-based approach. It employs deep generative models to create realistic molecular structures, enhancing the process of structure-based drug design.

FastMDAnalysis is a Python-based software tool that automates the analysis of molecular dynamics trajectories, allowing users to perform various analyses such as RMSD, RMSF, and clustering with simple commands. It is designed to streamline workflows and generate publication-quality figures, making it suitable for researchers in molecular dynamics.

TenCirChem is a quantum computational chemistry package designed for efficient calculations of molecular properties using advanced quantum algorithms. It supports various functionalities including UCC calculations and dynamics simulations, making it a versatile tool for researchers in the field.

CalcUS is a user-friendly web platform that provides tools for performing quantum chemistry calculations. It aims to facilitate the study of molecular properties and dynamics through a cloud service and a comprehensive interface for quantum chemical analysis.

RxDock is an open-source docking program that facilitates the docking of small molecules to proteins and nucleic acids. It is optimized for high-throughput virtual screening and binding mode prediction, allowing researchers to efficiently explore ligand interactions.

MatterTune is a machine learning library that allows computational chemists and materials scientists to fine-tune pre-trained models for various molecular properties such as energy and forces. It supports multiple dataset formats and provides tools for training and optimizing atomistic models.

GearBind is a pretrainable geometric graph neural network that predicts changes in protein-protein binding affinity. It is pretrained on CATH and fine-tuned on SKEMPI, providing tools for inference and dataset processing related to antibody affinity maturation.

SurfGen is a tool designed for generating 3D molecular structures by learning from topological surfaces and geometric features. It utilizes a dataset for training and provides functionalities for generating molecules, particularly targeting pharmaceutical applications.

The forest-openfermion repository provides a plugin for the OpenFermion package, enabling the construction and simulation of quantum algorithms for fermionic systems. It facilitates the integration of quantum computing techniques with quantum chemistry, which is essential for molecular simulations.

Atomify enables real-time molecular dynamics simulations in the browser using LAMMPS, providing users with the ability to visualize simulations and analyze physical quantities in real-time. It simplifies the workflow for molecular dynamics by integrating simulation and visualization into a single platform accessible via a web interface.

DeepFMPO is a tool designed for optimizing drug design through deep reinforcement learning. It allows users to generate and modify molecules based on lead compounds, facilitating the exploration of new drug candidates.

This repository implements a hierarchical statistical mechanical model for predicting protein-peptide interactions and signaling networks using machine learning. It provides tools for training models, making predictions, and analyzing results related to molecular interactions.

Watvina is a docking tool that facilitates drug design by supporting both explicit and implicit water models in protein-ligand interactions. It allows for pharmacophore and position-constrained docking, optimizing ligand interactions with receptors using the Autodock Vina engine.

Meta Flow Matching is a tool designed for integrating vector fields on the Wasserstein manifold, particularly useful in predicting individual treatment responses in personalized medicine. It includes datasets and models for training on biological experiments, specifically targeting drug-screen datasets.

Pizza.py is a collection of Python tools designed to facilitate pre- and post-processing for the LAMMPS molecular dynamics package. It includes functionalities for creating input files, converting file formats, processing simulation data, and visualizing results.

Delete is a tool for deep lead optimization that generates new molecular structures by utilizing a structure-aware network and deleting specific fragments from lead compounds. It is designed to assist in drug discovery by suggesting new ligands that fit within protein pockets.

Molecule3d is a React component that wraps 3Dmol.js to visualize molecular structures in three dimensions. It allows users to input molecular data and customize the visualization, making it a useful tool for molecular representation.

Frame2seq is a tool for generating and scoring protein sequences using a structured-conditioned masked language model. It allows users to design sequences based on PDB structures and provides functionality for scoring these sequences based on their likelihood.