/tools

NixOS-QChem is a repository that facilitates the integration of quantum chemistry software packages into the NixOS environment, enabling users to perform high-performance computing tasks related to molecular simulations and calculations. It supports various quantum chemistry tools, making it suitable for researchers in computational chemistry.

AlphaFold provides an implementation of a model for predicting protein structures based on their amino acid sequences. It utilizes advanced machine learning techniques to generate accurate structural predictions, which are essential for understanding protein function and interactions.

BAGEL is a customizable Python framework for programmable protein design that formalizes the design task as an optimization over an energy landscape. It includes components for defining energy terms, oracles for model integration, and algorithms for sequence sampling and optimization.

The 'protein-ebm' repository provides a PyTorch implementation of energy-based models aimed at predicting protein conformations at atomic resolution. It includes training code, datasets, and pre-trained model weights, making it a valuable resource for researchers in molecular biology and computational chemistry.

CatKit is a collection of computational tools aimed at facilitating research in catalysis. It includes modules for generating various catalytic structures and automating workflows, making it useful for researchers in the field of molecular catalysis.

PepFlow is a tool for full-atom peptide design utilizing multi-modal flow matching techniques. It allows for the generation and evaluation of peptides based on their interaction with receptor binding pockets, providing a framework for peptide optimization and design.

ProteinDT is a framework for text-guided protein design that allows for the generation and editing of protein sequences. It utilizes advanced machine learning techniques to optimize protein properties and facilitate design tasks.

ABCFold provides scripts to run AlphaFold3 and other related models for predicting protein structures using multiple sequence alignments and custom templates. It facilitates the generation of protein models and outputs useful visualizations for analysis.

DECIMER-Image-to-SMILES is a tool that utilizes an encoder-decoder neural network to recognize chemical structures from images and convert them into SMILES notation. This process aids in molecular representation and can facilitate further analysis in cheminformatics.

VSFlow is an open-source tool for ligand-based virtual screening of large compound libraries. It supports various screening methods, including substructure, fingerprint, and shape-based approaches, and allows for database preparation and result visualization.

NNPOps is a project aimed at enhancing the use of neural network potentials in molecular dynamics by offering highly optimized operations. It includes both CPU and CUDA implementations for efficient inference in simulations.

This repository provides code for predicting molecular properties using neural networks on raw molecular graphs. It includes implementations of various models designed for bioactivity and physical-chemical property prediction, making it a valuable resource for drug discovery applications.

CellListMap.jl is a Julia package designed for efficient computation of interactions and properties based on pairwise distances between particles in molecular dynamics simulations. It supports both parallel and serial implementations and can handle periodic boundary conditions.

Computational-ADME is a repository that provides code and data for building and validating machine learning models for predicting ADME (Absorption, Distribution, Metabolism, and Excretion) properties of drug candidates. It includes datasets of diverse compounds and various machine learning algorithms to enhance the accuracy of predictions in drug discovery.

DeePTB is a deep learning package that accelerates ab initio electronic structure simulations, providing accurate predictions for large systems. It features components for local environment dependent Slater-Koster tight-binding and equivariant neural networks for quantum operators, making it suitable for a variety of molecular simulations.

The ANI-1 dataset repository contains scripts for accessing a large dataset of 20 million calculated off-equilibrium conformations for organic molecules. This dataset is useful for training machine learning models in molecular property prediction and molecular simulations.

This repository provides an implementation of a pre-training method via denoising for predicting molecular properties using the TorchMD-NET architecture. It includes pre-training on the PCQM4Mv2 dataset and fine-tuning for specific molecular property predictions like HOMO/LUMO.

RITA is a family of autoregressive models designed for generating protein sequences. It leverages deep learning techniques to facilitate the design and optimization of proteins, making it a valuable tool in molecular biology and computational chemistry.

COCR is a tool designed to convert images of handwritten chemical structures into graphical representations of molecules. It utilizes Optical Character Recognition techniques to facilitate the recognition of chemical formulas, making it useful for cheminformatics applications.

AI4Science101 is an initiative aimed at educating researchers about the application of AI in scientific fields, with a specific focus on molecular dynamics. It offers a series of tutorials and a knowledge base to bridge the gap between AI and scientific discovery.

ProtST is a pretraining framework designed for understanding and predicting protein sequences by integrating protein functions with biomedical texts. It supports various downstream tasks such as protein localization prediction and zero-shot protein classification, enhancing the capabilities of protein language models.

PEER Benchmark is a comprehensive tool designed for evaluating various methods in protein sequence understanding. It includes multiple tasks such as protein function prediction and protein-ligand interaction prediction, facilitating advancements in molecular biology research.

The 'molecules.js' library is designed for chemical graph theory applications in JavaScript. It enables users to import molecules, compute graph matrices, and visualize molecular structures, making it a useful tool for cheminformatics and molecular property analysis.

MDANCE is a framework that enhances the analysis of molecular dynamics simulations through innovative clustering algorithms, enabling efficient processing of large datasets. It provides tools for identifying biologically relevant conformations and predicting native protein structures from simulation data.