/tools

Ketcher is an open-source web-based chemical structure editor designed for chemists and laboratory scientists. It provides features for drawing, editing, and visualizing molecular structures in various formats, supporting both small molecules and macromolecules.

LightDock is a docking framework that utilizes the Glowworm Swarm Optimization algorithm to facilitate the docking of proteins, peptides, and DNA. It allows users to define custom scoring functions and apply residue restraints, making it a versatile tool for studying molecular interactions.

MHCflurry is a software package designed for predicting the binding affinity of peptides to MHC class I molecules. It provides a fast and accurate implementation for various MHC alleles, making it a valuable tool for researchers in immunology and drug development.

ATOMICA is a geometric AI model that learns universal representations of intermolecular interactions at an atomic scale. It is pretrained on a large dataset of molecular interaction interfaces and can be used for various downstream tasks, including binding site prediction and embedding biomolecular complexes.

Graph-ViT-MLPMixer is an implementation of a model that generalizes ViT and MLP-Mixer architectures to graph data, enabling tasks such as graph classification and regression on molecular datasets. It supports various datasets, including those related to peptides and small molecules, making it relevant for molecular property prediction.

ChatDrug is a tool for conversational drug editing that utilizes retrieval and domain feedback to assist in the design and modification of small molecules, peptides, and proteins. It includes datasets for training and evaluation, making it a comprehensive resource for drug discovery.

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.

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.

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.

PepINVENT is a generative reinforcement learning framework for designing peptides, including both natural and non-natural amino acids. It allows users to specify objectives for peptide generation and optimization, making it applicable for peptide-based drug design and development.

Grappa is a machine learned molecular mechanics force field that utilizes graph neural networks to predict bonded parameters for molecular simulations. It integrates with GROMACS and OpenMM, allowing users to parametrize systems and train custom models using various molecular datasets.

AutoDock CrankPep (ADCP) is a specialized docking engine for peptides that utilizes Monte-Carlo search methods to optimize peptide-receptor interactions. It allows for the docking of peptides provided as 3D structures or sequence strings, making it a valuable tool in molecular docking and protein design.

Wazy is a tool for Bayesian optimization of amino acid sequences, allowing users to design peptides that bind to specific proteins. It utilizes pretrained models to predict the properties of sequences and optimize their design through an interactive interface.

LLM4Mol is a repository that explores the application of large language models in molecular design and protein research. It serves as a hub for studies and techniques that leverage AI to advance understanding in molecular properties and material science.

π-PrimeNovo is a deep learning model designed for accurate and efficient de novo peptide sequencing. It addresses challenges in peptide identification from mass spectrometry data, making it a valuable tool in molecular biology and protein design.

AutoPeptideML is an AutoML system designed to help researchers build trustworthy models for predicting peptide bioactivity. It provides tools for model building, prediction, and benchmarking, making it accessible for users without prior machine learning expertise.

PeptideDesign is a codebase for full-atom d-peptide co-design utilizing flow matching methods. It includes functionalities for training models to generate peptides based on binding pockets, making it a valuable tool for peptide design in molecular biology.

HELM-GPT is a tool designed for the de novo generation of macrocyclic peptides using a generative pre-trained transformer model. It allows users to train models and generate new peptide structures, contributing to drug discovery efforts.

The Peptide Dashboard provides a web-based platform for predicting peptide properties using deep learning models. It includes a sequence-based solubility predictor that outperforms existing methods, making it a valuable tool for researchers in molecular biology and computational chemistry.

LightDock-Rust is a Rust implementation of the LightDock software designed for macromolecular docking. It utilizes scoring functions like DFIRE to optimize the binding of proteins and peptides, making it a valuable tool for molecular simulations in bioinformatics.

AF2_peptide_hallucination is a tool for generating high-affinity binders to flexible peptides using the AlphaFold2 Hallucination method. It allows users to design and optimize peptide binders by predicting their structures and properties based on input sequences.

p2smi is a Python toolkit designed for the generation and analysis of drug-like peptide SMILES strings. It allows users to create peptide sequences, convert them to SMILES representations, and evaluate various molecular properties, making it a valuable resource for computational peptide chemistry.

LaM-SLidE is a tool for latent space modeling of spatial dynamical systems, particularly in the context of molecular dynamics simulations. It provides a framework for training models that can handle various molecular types, including peptides, and facilitates the analysis of molecular properties through simulation.

DeepSeqPan is a deep convolutional neural network model designed for predicting the binding affinity of peptides to MHC I molecules. It includes datasets for training and evaluation, as well as trained models for use in further research.