/tools

The lammps-packages repository contains scripts and tools for building pre-compiled LAMMPS packages, which are essential for conducting molecular dynamics simulations. It includes documentation and supporting libraries to facilitate the use of LAMMPS in computational chemistry applications.

AWS RoseTTAFold is a tool that facilitates the prediction of protein structures using the RoseTTAFold algorithm on AWS Batch. It includes Jupyter notebooks for submitting protein sequences for analysis, leveraging high-performance computing resources to optimize the prediction process.

PIGNet2 is a deep learning-based model that predicts protein-ligand interactions and binding affinities, facilitating virtual screening in drug discovery. It includes training and benchmarking scripts, making it a comprehensive tool for evaluating molecular interactions.

GenUI is a frontend application that offers a graphical user interface for interacting with the GenUI REST API web services. It is designed to facilitate molecular generation and cheminformatics tasks through a user-friendly dashboard.

This repository implements a method for aggregating residue-level embeddings from protein language models using optimal transport. It aims to improve the representation of protein sequences for various prediction tasks, such as drug-target interactions and protein-protein interactions.

EquiPNAS is a tool designed for predicting binding sites between proteins and nucleic acids (DNA/RNA) using equivariant deep graph neural networks. It provides methods for training and testing models specifically tailored for protein-DNA and protein-RNA interactions.

This repository contains a tool for optimizing crystal structures using machine learning models. It allows users to perform structure optimization and single point evaluations, making it useful for researchers in materials science and computational chemistry.

AEV-PLIG is a tool that utilizes a graph neural network to predict the binding affinity of protein-ligand complexes based on their 3D structures. It benchmarks its performance against established datasets and demonstrates how to train and use the model for predictions.

HimGNN is a PyTorch implementation of a novel hierarchical molecular representation learning framework aimed at predicting molecular properties. It utilizes a combination of Atom-MPNN and Motif-MPNN to enhance the performance of molecular property prediction tasks through advanced graph-based techniques.

This repository explores QSAR models for predicting activity cliffs in small-molecule inhibitors, providing datasets and methodologies for molecular property prediction. It includes clean data for various targets and allows for the reproduction of experiments related to binding affinity and activity classification.

BiteNet is a computational tool that utilizes deep learning to identify druggable binding sites in proteins by analyzing their three-dimensional conformations. It offers functionalities for predicting binding sites and clustering predictions, making it valuable for drug discovery efforts.

PaCS-Toolkit enables the execution of Parallel Cascade Selection Molecular Dynamics (PaCS-MD) simulations and offers tools for result analysis and visualization. It is designed to facilitate molecular dynamics simulations across various environments, making it a valuable resource for researchers in computational chemistry.

This repository provides Jupyter notebooks and simulation inputs for a mini course on enhanced sampling methods using GROMACS. It covers techniques such as umbrella sampling and metadynamics, which are crucial for molecular simulations and dynamics.

MolPROP is a tool designed for molecular property prediction that integrates molecular language and graph representations. It includes models for training and hyperparameter tuning to enhance the accuracy of predictions related to molecular properties.

GeomGCL is an implementation of a method for predicting molecular properties using geometric graph contrastive learning. It includes preprocessing steps for molecular datasets and provides a framework for training models on these datasets.

TCM-Network-Pharmacology is a tool for traditional Chinese medicine network pharmacology that includes processes like prognostic gene screening, molecular docking verification, and various diagram mappings. It provides functionalities for analyzing and validating molecular interactions and properties.

LC-PLM is a long-context protein language model designed to extract embeddings for protein sequences and predict properties at the residue or protein level. It utilizes a unique architecture based on structured state-space models and is pretrained on extensive protein sequence data.

Venus-MAXWELL is a tool that efficiently learns the stability landscapes of protein mutations using advanced protein language models. It allows users to generate predictions for the effects of single mutations on protein stability, making it relevant for applications in protein design and stability analysis.

AMix-1 is a protein foundation model that employs a test-time scalable approach to generate and evaluate protein sequences. It allows for the iterative evolution of protein designs through a systematic evaluation of various metrics, making it a valuable tool for protein engineering.

EMBER2 is a tool for predicting protein structures without the need for sequence alignment, utilizing protein language models. It allows users to generate PDB structures from predicted distograms and provides predictions for human proteins.

The 'protein-uq' repository provides tools for benchmarking uncertainty quantification methods in protein engineering. It includes functionalities for training models that predict protein fitness and function, utilizing active learning and Bayesian optimization techniques.

PPI-Miner is a pipeline for searching protein-protein interactions based on specific structural and sequence motifs. It allows users to mine potential PPI partners and optimize protein structures, facilitating protein design and interaction studies.

CompassDock is a framework for deep learning-based molecular docking that evaluates binding affinities and protein-ligand interactions. It provides tools for assessing the physical and chemical properties of ligands and their bioactivity favorability.