/tools

QSPRpred is an open-source software library designed for creating QSPR/QSAR models, enabling researchers to predict molecular properties and activities. It provides a modular interface for building models using various descriptors and machine learning algorithms, facilitating drug discovery and cheminformatics research.

GDyNet is a software package that utilizes Graph Dynamical Networks to learn atomic scale dynamics from molecular dynamics trajectories. It preprocesses MD data, constructs graphs, and trains models to analyze material behaviors at the atomic level.

Bacformer is a foundational model that processes whole bacterial genomes as sequences of proteins, leveraging protein embeddings to perform tasks like essential gene prediction and operon identification. It is designed for applications in molecular biology and bioinformatics.

PaRoutes is a framework that benchmarks multi-step retrosynthesis methods, providing curated datasets for building retrosynthesis models. It includes scripts for analyzing route quality and diversity, making it a valuable resource for researchers in molecular design.

McMurchie-Davidson is a Python tool that computes one and two electron integrals necessary for Hartree-Fock calculations using the McMurchie-Davidson algorithm. It currently supports closed shell molecules and provides functionalities for electronic structure calculations.

UniMoMo is a generative modeling tool designed for de novo binder design, enabling the creation of small molecules, peptides, and antibodies. It provides functionalities for training and evaluating models to generate molecular candidates based on specified configurations.

Arpeggio is a tool designed to calculate and visualize interatomic interactions in molecular structures, particularly proteins. It utilizes the CREDO rules to analyze contacts and interactions, providing valuable insights for molecular biology and cheminformatics.

OnionNet is a deep learning model designed to predict protein-ligand binding affinities based on inter-molecular contact features. It can also be used for re-scoring docking results, making it a valuable tool in drug discovery and molecular design.

tr-rosetta-pytorch is a PyTorch implementation of trRosetta and trDesign, designed for predicting and designing protein structures. It provides a convenient package for users to perform structure predictions using deep learning techniques.

The fastapi-redis project showcases the integration of Redis with the FastAPI framework to create an API for analyzing chemical compounds using RDKit. It allows users to manage and compare molecular data, particularly focusing on compounds related to COVID-19.

suanPan is an open-source finite element analysis framework designed for efficient simulations in solid mechanics and engineering applications. It supports parallel and heterogeneous computing, making it suitable for complex simulations, including those in molecular dynamics.

ProteinEBM is an open-source tool that utilizes denoising score matching to approximate the energy landscape of protein structures based on their sequences. It supports applications in structure prediction, stability assessment, and molecular simulations, making it a valuable resource in computational biology.

STORMM is a code base designed for structure and topology replica molecular mechanics, offering performant libraries for molecular dynamics simulations. It supports both CPU and GPU implementations, facilitating efficient energy evaluations and coordinate management.

PySMILESutils is a package designed for handling SMILES encodings of molecules, facilitating their use in deep learning applications with PyTorch. It includes features for data augmentation, dataset handling, and mini-batch creation, making it suitable for molecular machine learning tasks.

RetroExplainer is a deep-learning framework designed for predicting retrosynthesis pathways with a focus on molecular assembly reasoning and interpretability. It allows users to generate and analyze potential synthetic routes for chemical compounds, making it a useful tool in the field of molecular design.

GRASP is a Fortran-based software package designed for general relativistic atomic structure calculations. It allows researchers to perform detailed electron structure analyses, which are essential for understanding molecular properties and behaviors.

LigDream is a tool for generating novel molecules based on a reference shape using generative modeling techniques. It utilizes a dataset of drug-like compounds for training and allows for the generation of new compounds through a web interface or locally via Jupyter Notebooks.

The 'pyemma_tutorials' repository provides a comprehensive tutorial on using the PyEMMA software for analyzing molecular dynamics simulations. It includes various notebooks that cover topics such as data I/O, MSM estimation, and analysis, making it a valuable resource for those interested in molecular dynamics and Markov state modeling.

This repository provides a benchmark dataset of proteins and ligands for validating binding free energy prediction methods. It includes input structures for calculations, experimental binding data for reproducibility studies, and analysis scripts for generating results.

MiniFold is a fast model designed for single chain protein structure prediction, leveraging a protein language model for improved speed and efficiency. It allows users to predict protein structures from FASTA files and includes training capabilities for model optimization.

PaddleMaterials is an end-to-end toolkit based on the PaddlePaddle deep learning framework, aimed at facilitating the discovery and development of new materials. It supports various tasks such as property prediction and structure generation, making it a valuable resource for researchers in materials science.

PyAutoFEP is an automated workflow for Free Energy Perturbation (FEP) calculations using GROMACS, aimed at estimating the Relative Free Energies of Binding (RFEB) of small molecules to macromolecular targets. It integrates enhanced sampling methods and provides automation for various steps in the molecular dynamics setup and analysis.

RNAFlow is a tool for designing RNA sequences and structures using a flow matching model that incorporates inverse folding techniques. It allows users to generate RNA sequences conditioned on protein structures, facilitating the design of RNA molecules for various applications.

VortexDock is a Python-based distributed molecular docking system designed to improve the efficiency of virtual screening by utilizing parallel computation across multiple nodes. It supports AutoDock Vina and allows for task management and monitoring of docking processes.