/tools

GenAI4Drug is a survey repository that explores the use of generative AI techniques for de novo drug design, emphasizing the generation of molecules and proteins. It includes discussions on various models, datasets, and metrics relevant to molecular design and property prediction.

InstructPLM is a tool designed for generating protein sequences based on structural instructions using a large protein language model. It allows users to create and evaluate protein designs, achieving state-of-the-art performance on relevant benchmarks.

EvoProtGrad is a Python package designed for directed evolution of proteins using gradient-based discrete Markov chain Monte Carlo (MCMC). It allows users to create custom models that map protein sequences to functions, leveraging pretrained protein language models to optimize the search for beneficial mutations.

This repository provides educational materials for a course on Structural Bioinformatics, including practical exercises on molecular dynamics simulations, protein structure prediction, and molecular docking. It serves as a resource for understanding and applying computational methods in molecular biology and bioinformatics.

Dayhoff is a resource that combines extensive protein sequence data with generative language models to predict mutation effects and generate novel protein sequences. It includes datasets and models that facilitate the design and analysis of proteins, making it a valuable tool in molecular biology.

Denovo-Pinal is a tool for designing proteins from natural language descriptions, enabling users to generate novel protein sequences based on specified instructions. It utilizes advanced models to facilitate the design process, making it a valuable resource in the field of molecular biology and protein engineering.

DiffAbXL is a benchmarking tool for generative models aimed at antibody design, specifically evaluating log-likelihood scores for ranking antibody sequences based on their predicted binding affinities. It provides datasets and methodologies for assessing the performance of various models in the context of antibody optimization.

PoET is a generative model designed for protein families that enables the prediction of variant effects and the generation of protein sequences. It utilizes deep learning techniques to analyze and score protein variants based on their fitness, making it a valuable tool in protein engineering and bioinformatics.

The 'protein-design-skills' repository provides a set of 21 Claude Code skills aimed at facilitating computational protein design. It includes a standard pipeline for designing protein binders and utilizes various skills for optimizing and generating protein structures.

DiffPack is a torsional diffusion model that predicts the conformation of protein side-chains based on their backbone structures. It utilizes a diffusion process to improve the accuracy of side-chain packing, making it a valuable tool for protein design.

ProteinDJ is a protein design pipeline that integrates multiple software packages to facilitate the design and optimization of protein structures. It allows users to generate new protein sequences and structures through various design modes, leveraging advanced modeling techniques like RFdiffusion and AlphaFold2.

ProGen2-finetuning is a tool for finetuning a generative protein language model to generate sequences from selected protein families. It allows users to preprocess data, finetune the model, and sample new protein sequences, making it relevant for protein design and generation tasks.

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.

tr-rosetta-pytorch is a PyTorch implementation of trRosetta and trDesign, designed for predicting and designing protein structures. It provides a convenient package for users to perform structure predictions using deep learning techniques.

ProteinEBM is an open-source tool that utilizes denoising score matching to approximate the energy landscape of protein structures based on their sequences. It supports applications in structure prediction, stability assessment, and molecular simulations, making it a valuable resource in computational biology.

ManyFold is a library that facilitates the training and validation of protein folding models, including AlphaFold and pLMFold. It allows users to generate and optimize protein structures using advanced machine learning techniques.

Str2Str is a framework designed for zero-shot protein conformation sampling, utilizing a score-based approach to perturb protein structures and sample conformations. It integrates with existing tools for molecular dynamics simulations and protein folding, making it a valuable resource for computational biology.

ReQFlow is a generative model designed for efficient and high-quality protein backbone generation. It utilizes a rectified quaternion flow approach to enhance the designability and speed of protein structure generation, making it a valuable tool in protein design and molecular biology.

Caliby is a software tool for protein sequence design based on the Potts model, enabling users to condition designs on structural ensembles. It includes functionalities for sequence scoring and ensemble generation, making it a valuable resource for molecular design in computational biology.

The riff_diff_protflow repository provides an implementation of the RiffDiff pipeline, which is designed for generating and optimizing enzyme structures from theozymes. It utilizes various protein design tools and scripts to create fragment libraries and refine structures, facilitating the design of novel proteins.

DeepPBS is a tool that utilizes geometric deep learning techniques to predict the binding specificity between proteins and DNA. It allows for the processing and visualization of molecular interactions, making it relevant for studies in molecular biology and computational chemistry.

CA RFdiffusion is a repository that provides training and inference code for a protein structure diffusion model. It generates protein backbones through a two-step process involving diffusion and refinement, making it a valuable tool for computational protein design.

AiCE is a tool for predicting high-fitness mutations in proteins by utilizing inverse folding models that incorporate structural and evolutionary constraints. It allows for single and multi-mutation nominations, making it relevant for protein engineering and design applications.

LaMBO is a tool that accelerates Bayesian optimization for biological sequence design using denoising autoencoders. It allows for efficient exploration of protein sequences to optimize properties such as stability and surface area, outperforming traditional genetic algorithms in its evaluations.