/tools

PAMmla is a set of machine learning models that predict SpCas9 PAM preferences based on amino acid sequences. It includes functionality for in silico directed evolution and provides a web tool for making predictions.

The 'rif' repository provides Python libraries for computational protein design, specifically utilizing Rotamer Interaction Fields. It aims to facilitate the design and optimization of protein structures, making it a valuable tool in molecular biology and computational chemistry.

ESMBind is a deep learning and physics-based workflow designed to predict metal-binding proteins and generate their 3D structures with bound metal ions. It integrates evolutionary scale modeling for residue-level predictions and physics-based modeling for detailed structural generation.

The alphascreen tool facilitates the screening of protein interactions by generating input files for AlphaFold predictions and analyzing the results. It automates the process of fetching sequences, fragmenting them, and interpreting the predictions to identify potential interactions between proteins.

SelfPAD is a framework designed to improve the prediction of antibody humanness by utilizing patent data. It includes functionalities for pre-training and fine-tuning models specifically for evaluating antibody sequences.

The CASP15 repository benchmarks various state-of-the-art protein structure prediction methods, including AlphaFold2 and RoseTTAFold. It provides generated protein structures and metrics for evaluating their predictive performance, making it a valuable resource for researchers in molecular biology and computational chemistry.

The nf-binder-design repository provides a Nextflow pipeline for designing protein binders using advanced molecular modeling techniques such as RFdiffusion and BindCraft. It automates the generation and optimization of protein structures, facilitating research in protein engineering and drug discovery.

The 'idp-design' repository provides tools for optimizing intrinsically disordered proteins by simulating their properties and designing sequences that meet specific functional criteria. It includes various optimization examples, such as targeting the radius of gyration and designing binders for specific substrates.

ProteinTuneRL is a framework designed for optimizing protein sequences using infilling language models and reinforcement learning. It specifically supports antibody design by modifying regions of protein sequences to enhance properties like stability and binding affinity.

The ProteinMPNN Wrapper enhances the usability of the ProteinMPNN model for protein design by allowing convenient sampling of protein sequences based on backbone structures. It simplifies the process of generating sequences for given protein backbones, making it a useful tool for researchers in molecular biology and computational chemistry.

SCALOP is a Python tool that annotates the canonical structure of antibodies based on their sequences. It supports input in various formats and utilizes dependencies like HMMER for its functionality.

MaskedProteinEnT provides code to sample protein sequences using a contextual Masked EnTransformer. It allows for the design and generation of protein sequences, making it a useful tool in the field of molecular biology and protein engineering.

SecretoGen is a conditional autoregressive model that generates signal peptides based on the mature protein sequence and the host organism. It also includes functionality for evaluating the efficiency of these peptides, making it a specialized tool for protein design.

Progen is a Python implementation of a language model for generating protein sequences, based on the ProGen paper. It utilizes various protein sequence datasets for training and evaluation, making it a valuable tool for protein design and generation.

RosettaAbinitio is a Bash script designed to automate the process of running Rosetta Abinitio folding simulations on high-performance computing systems. It facilitates the submission of jobs for generating and clustering protein decoys, making it a useful tool for protein structure prediction.

This tool provides a pipeline for designing and optimizing single chain variable fragment (scFv) antibodies targeting specific peptides and histone modifications. It automates the process of identifying CDR regions and optimizing antibody frameworks using AI models.

TopoteinWorkshop is a topological deep learning extension to the ProteinWorkshop framework, designed for protein structure representation learning. It incorporates novel geometric topological neural network architectures and provides benchmarking capabilities for evaluating these models against existing ones.

This repository provides scripts and data for conducting relative free energy calculations on terminally-blocked amino acids and the barnase-barstar complex. It utilizes the Perses framework for molecular simulations, enabling the analysis of molecular interactions and dynamics.

This repository contains implementations for protein structure prediction using various optimization techniques, including molecular dynamics simulations and genetic algorithms. It aims to explore different approaches to improve the accuracy and efficiency of predicting protein folding.

This repository contains source codes for a balance-evolution artificial bee colony algorithm aimed at optimizing protein structures. It utilizes a three-dimensional off-lattice model to enhance protein structure prediction and optimization processes.

ProteinWatermark is a tool designed to enhance privacy in protein design by injecting watermarks into protein sequences. It aims to protect intellectual property and ensure traceability in biosecurity applications.

sc-rs is an open-source Rust implementation of the Shape Complementarity (SC) algorithm, designed to evaluate the compatibility of protein interfaces. It provides a command-line interface and library API for quick analysis and integration into other tools.

RosettaSilentToolbox is a Python library designed for the analysis and management of large populations of protein or nucleotide decoys. It is particularly useful for protein designers and developers looking to benchmark their methods against existing protocols.

GPT_protein_design is a pipeline for de novo protein design that utilizes a GPT-based generator and a transfer learning-based discriminator. It aims to generate novel proteins, such as antimicrobial peptides, by leveraging advanced machine learning techniques.