/tools

DeepNeuralNet-QSAR is a Python tool developed for predicting molecular properties using deep neural networks. It allows users to train models on QSAR datasets and make predictions for various molecular tasks, facilitating drug discovery and molecular design.

Nequix is a framework for training foundation models for materials science, focusing on interatomic potentials and phonon fine-tuning. It allows users to perform molecular simulations and property predictions using pre-trained models and custom datasets.

PyCGTOOL is a software tool designed to generate coarse-grained molecular dynamics models from atomistic simulation trajectories. It aids in parametrizing coarse-grained molecular mechanics models, allowing for efficient testing of different mapping and bond topologies.

cG-SchNet is a conditional generative neural network that focuses on the inverse design of 3D molecular structures. It allows users to generate molecules based on specified conditions, leveraging a dataset of small molecules to train the model.

TREXIO is an open-source library that facilitates the storage and manipulation of quantum chemistry data, specifically wave function parameters and matrix elements. It supports various programming languages and is compatible with multiple quantum chemistry codes, making it a valuable resource for researchers in computational chemistry.

GNPS_Workflows provides a collection of public workflows for analyzing mass spectrometry data, focusing on molecular networking and metabolomics. It facilitates the exploration and interpretation of complex molecular data, making it a valuable resource for researchers in the field.

MOKIT is a software tool that facilitates the transfer of molecular orbitals between various quantum chemistry packages and automates multi-reference calculations. It provides utilities for users to perform complex quantum chemistry computations in a streamlined manner.

DeepChem GUI is a web-based interface that allows users to predict the docking of ligands to proteins using pretrained DeepChem models. It supports molecular visualization and editing, making it a useful tool for researchers in computational chemistry and drug discovery.

oxDNA is a simulation code designed for modeling DNA and RNA using a coarse-grained approach. It provides an extensible framework for simulating various molecular interactions and dynamics, supporting both single CPU and GPU computations.

PythonCompphys is a collection of Jupyter notebooks that cover various topics in computational physics, with a strong emphasis on computational chemistry methods like Hartree-Fock and Density Functional Theory. It serves as a tutorial resource for understanding molecular simulations and quantum mechanics.

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 Cheminformatics Microservice offers essential microservices for cheminformatics, including molecular property calculations, structure validation, and visualization through an API. It supports various chemical formats and provides tools for chemical analysis and natural product scoring.

The geo-gcn repository provides an implementation of Spatial Graph Convolutional Networks, which are used to learn from graph-structured data, particularly in the context of chemical compounds. It supports training on chemical datasets for tasks such as predicting molecular properties.

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.

This repository explores evolution-aware protein language models to predict protein functions. It provides datasets related to metal ion binding and antibiotic resistance, making it a valuable resource for researchers in molecular biology and protein analysis.

AIMNet2 is a machine-learned interatomic potential that enables fast and accurate atomistic simulations. It supports various molecular types and integrates with popular simulation packages, making it a versatile tool for molecular dynamics applications.

The CADD Vault is an open-source repository that offers a comprehensive collection of resources and tools for computer-aided drug design. It includes materials on virtual screening, molecular dynamics simulations, and machine learning applications, making it a valuable resource for researchers in the field.

DFTCXX is a C++ based program designed for educational purposes that calculates the electronic structure of simple molecules using Density Functional Theory (DFT) at the LDA level. It provides a documented source code to help students understand the underlying algorithms of electronic structure calculations.

Sire is a molecular modeling framework designed for biomolecular simulations, enabling users to prototype algorithms and exchange information between various molecular simulation programs. It supports functionalities such as molecular dynamics, parameterization, and trajectory analysis, making it a versatile tool for researchers in computational chemistry and molecular biology.

MolML is a Python library designed to interface molecules with machine learning by converting molecular structures into vector representations. It supports various molecular descriptors and is aimed at facilitating the application of machine learning techniques in predicting molecular properties.

HalluDesign is an all-atom framework that utilizes a structure prediction model to iteratively co-optimize and co-design protein sequences and structures. It allows for the design of new protein sequences based on structural hallucination, making it a valuable tool in molecular biology and protein engineering.

ISiCLE is an in silico chemical library engine that calculates high-accuracy chemical properties by generating 3D molecular conformations and optimizing them through simulations. It predicts properties such as collision cross sections and NMR chemical shifts, emphasizing results from probable conformations.

RNA3DB is a dataset of non-redundant RNA structures from the PDB, designed for training and benchmarking deep learning models focused on RNA structure prediction. It includes various RNA chains labeled with non-coding RNA families and provides tools for customizing and building the dataset.

protlearn is a Python package designed for extracting features from amino acid sequences. It includes preprocessing, feature computation, and dimensionality reduction stages, making it a valuable resource for analyzing protein data.