/tools

CodonMPNN is a tool for organism-specific and codon optimal inverse folding, producing codon sequences based on trained models from the AlphaFold database. It facilitates the design of codon-optimized sequences for proteins, making it relevant in the field of molecular biology.

DE-STRESS is a web application that provides tools for evaluating protein designs, making the process more reliable and accessible. It allows users to select promising protein designs for laboratory testing and includes functionalities for batch processing of protein structures.

Kanzi is a tool for modeling biological structures through discrete tokenization of proteins. It utilizes flow autoencoders to efficiently encode and decode protein structures, facilitating further applications in protein design and molecular representation.

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.

This repository provides a pipeline for evaluating protein structure diffusion models, assessing designability, diversity, and novelty of generated protein structures. It supports various evaluation metrics and models, making it a useful tool for protein design and analysis.

FvHallucinator is a tool that designs antibody sequences to achieve desired folding structures using a deep learning model. It employs a sequence-to-structure prediction approach to optimize the design of specific regions within antibodies, particularly the complementarity-determining regions (CDRs).

This repository provides a PyTorch implementation for generative protein design, allowing users to create and optimize protein structures. It includes scripts for dataset management and model training, making it a useful tool for researchers in molecular biology.

RAG-ESM is a framework that enhances pretrained protein language models by conditioning them on homologous sequences. It allows for the generation of novel protein sequences and improves predictive performance through a retrieval-augmented approach.

ProtProfileMD is a tool that leverages protein dynamics to enhance homology detection by predicting per-residue distributions over structural representations. It utilizes a sequence-to-3D-probability model to capture the flexibility of proteins, improving the sensitivity of remote homology detection.

GraphRelax is a drop-in replacement for Rosetta Relax that utilizes graph neural networks for residue repacking and design. It combines LigandMPNN for sequence design with OpenMM for energy minimization, enabling efficient protein structure optimization.

SES-Adapter is a framework designed to improve the representation learning of protein language models by utilizing structure-aware adapters. It enhances performance on tasks such as localization, function prediction, and solubility, while also providing datasets and configuration examples for training.

AbLang2 is an antibody-specific language model that addresses germline bias in antibody sequences to improve antibody design. It generates amino acid likelihoods and residue embeddings, facilitating the prediction of mutations that enhance binding properties.

PolyFold is an interactive visual simulator designed for distance-based protein folding. It allows users to visualize and manipulate the folding process in real-time, utilizing stochastic optimization algorithms to achieve protein structure predictions.

DiffPALM is a tool for pairing interacting protein sequences using masked language modeling. It employs a differentiable pairing method to optimize multiple sequence alignments, which is crucial for understanding protein interactions and structures.

CoCoPOD is a design platform for creating single-chain polyhedral cages from coiled-coil building modules. It allows users to specify polyhedral geometries, route polypeptide chains, and build 3D models, with capabilities for refining these models through folding simulations.

Pseudocycle_small_molecule_binder is a tool for the de novo design of diverse small molecule binders using shape complementary pseudocycles. It provides scripts and notebooks for generating and optimizing molecular structures, specifically targeting small molecules for binding applications.

Joltz is a translation of the boltz model from PyTorch to JAX, primarily aimed at protein design through a method called hallucination. It is compatible with JAX's features and is intended for use in molecular design applications.

ELASPIC2 is a tool designed to predict the effects of mutations on protein stability and binding affinity using pretrained neural networks. It provides various interfaces, including a web server, Python API, and command-line interface, making it accessible for users to analyze protein mutations effectively.

ADFLIP is a tool for all-atom inverse protein folding using discrete flow matching techniques. It allows users to sample protein sequences from input files, facilitating the design and prediction of protein structures.

This repository provides a method to run AlphaFold in batch mode using multiprocessing, allowing for efficient prediction of protein structures. It is designed to handle multiple structures simultaneously, enhancing the usability of AlphaFold for large-scale protein design tasks.

PyMissense is a tool that generates pathogenicity plots and modified PDB files for custom proteins based on the AlphaMissense paper. It helps identify critical regions in amino acid chains that affect protein function and visualizes pathogenicity predictions.

ProteinEnsembles.jl is a Julia package that implements the ExProSE algorithm to generate and perturb ensembles of protein structures. It allows for the prediction of allosteric sites and includes various functions for structural bioinformatics, making it a valuable tool for molecular biology research.

This repository implements a method that combines pre-trained protein language models with geometric deep learning networks to enhance the representation of macromolecules. It addresses tasks such as binding affinity prediction and protein-protein interface prediction, making it a valuable tool in molecular biology and computational chemistry.

ProCALM is a protein conditionally adapted language model designed for the generation of enzymes based on specific conditions such as EC number and taxonomy. It utilizes autoregressive transformers to create functional sequences, making it a valuable tool for protein design and molecular generation.